Chicken nutrition modeling and visual analysis system

Abstract

The invention relates to the technical field of animal nutrition information modeling, in particular to a chicken nutrition modeling and visual analysis system which comprises a nutrition requirement evaluation module, a proportion optimization calculation module, a nutrition trend analysis module, a proportion adjustment module and a nutrition diagnosis decision module. According to the method, accurate description of a nutritional demand structure is realized through the weight growth rate and the change trend of the ingestion behavior, efficient matching of feed energy and protein content is assisted by extracting a comparison result of absorption fluctuation and demand intensity, a high-frequency demand stage is identified according to the time sequence characteristics of the weight fluctuation, and dynamic tracking of a nutritional demand period is realized. According to the method, the feed matching value is revised in a segmented mode according to the ingestion time delay and the absorption difference, so that the matching response is close to the growth rhythm, the nutrition attribution path is recognized through the absorption difference and the fluctuation rule, the nutrition supply adaptability and the ingredient pertinence are improved, the feed waste rate and the nutrition imbalance probability are reduced, and the feeding benefit and the management intelligent level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of animal nutrition information modeling, and in particular to a chicken nutrition modeling and visualization analysis system. Background Art

[0002] The field of animal nutrition information modeling technology involves collecting and analyzing multi-dimensional data such as growth stages, feed composition, and physiological needs of poultry and livestock, constructing nutritional requirement models and feed ratio relationship models, and achieving precise nutritional regulation and feeding efficiency optimization. The core issues in this technical field mainly include the acquisition of animal physiological parameters, feed nutrient composition analysis, modeling algorithm construction and adjustment, structured expression of nutritional data, and visualization of modeling results. It is a cross-disciplinary area integrating agricultural informatization, livestock and poultry breeding management, and nutritional science, focusing on establishing data-supported models that can be used to assess changes in nutritional needs of animals at different growth stages.

[0003] The traditional chicken nutrition modeling and visualization analysis system uses laying hens or broilers as research subjects. By collecting raw data such as weight, age, feed intake, and feed nutrient composition across different growth cycles, and combining it with existing chicken nutrition requirement standards for energy levels, protein content, and amino acid requirements, it constructs a nutrient requirement expression formula using mathematical regression models and statistical analysis. The analysis results are then output as two-dimensional charts. Traditional techniques involve manually recording the age and weight of chickens, manually estimating feed intake, manually adjusting feed ratios by consulting standard nutrition recommendation tables, and relying on spreadsheet tools for data statistics and charting.

[0004] The existing technology relies on manual recording for age and weight collection, with limited data granularity and delayed update cycles, making it difficult to grasp the weight growth rate and feed intake changes in real time. Feed intake estimation lacks dynamic precision support, and feed adjustments are manually revised based on standard recommended values. There is a lack of a mechanism to judge nutritional responses based on individual differences. Spreadsheets are relied upon for static data organization and chart output, making it difficult to reflect the temporal evolution characteristics of nutritional needs. During the feeding cycle, nutritional regulation decisions lag behind the actual pace of change, resulting in delayed or oversupply in the high-demand stage, which in turn leads to adverse effects such as decreased feed utilization, mismatched nutritional structure, and uneven growth efficiency. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a chicken nutrition modeling and visualization analysis system.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: A chicken nutrition modeling and visualization analysis system includes: The nutritional demand assessment module obtains data on the age distribution, weight growth curve, feed intake fluctuations, and feed component absorption rate of the chicken flock, analyzes the relationship between nutritional needs, and determines the direction of nutritional needs and the length of the supply chain based on the changing trends of weight growth rate and feeding behavior. It also maps the ratio of nutrient utilization rate to absorption delay to generate a nutritional demand composition map. The ratio optimization calculation module selects the energy level and protein content of key feed ingredients based on the nutritional requirement composition map, matches and compares the absorption fluctuation frequency with the demand level, identifies the optimization key level, and obtains the feed ratio priority scale; The nutritional trend analysis module extracts the time interval and duration of chicken weight fluctuations based on the feed ratio priority scale, determines the high-frequency fluctuation distribution stage, classifies the periodic trends of similar fluctuation events, and generates a nutritional demand evolution cycle sequence; The ratio adjustment module calls the nutritional demand evolution cycle sequence, combines the absorption fluctuation value and feeding time delay in the section under its jurisdiction, screens the target feed components in the high trend section, revises the ratio value in sections, and obtains the feed optimization ratio adjustment table.

[0007] As a further solution of the present invention, the nutritional demand composition map includes nutritional demand direction classification, supply chain path structure, and absorption delay ratio distribution; the feed ratio priority scale includes optimization level label, component risk coefficient, and priority score interval; the nutritional demand evolution cycle sequence includes fluctuation interval distribution, fluctuation duration frequency, and cycle classification results; the feed optimization ratio adjustment table includes target ingredient list, ratio revision parameters, and delay correlation factors.

[0008] As a further embodiment of the present invention, the nutritional needs assessment module includes: The weight and feed intake identification submodule obtains data on the age distribution of chickens, weight growth curve, feed intake fluctuations, and feed component absorption rate. It aligns the three signals by timestamp, extracts weight mutation points, locates changes in feed intake and absorption rate, identifies response differences, and generates nutritional requirement response deviations. The absorption hysteresis analysis submodule extracts the absorption signal delay segment and the feeding signal response sequence based on the nutritional demand response deviation, calculates the delay length and response sequence, determines the signal demand direction, measures the number of supply chain trigger sequences within the hysteresis segment, and generates the supply signal hysteresis structure quantity; The nutrient supply structure generation submodule extracts the feed composition change points and the supply chain signal linkage period based on the supply signal hysteresis structure, compares the signal response frequency and delay, identifies the linkage times and the average delay ratio, analyzes the demand relationship and supply frequency mapping, and generates a nutrient demand composition map.

[0009] As a further solution of the present invention, the ratio optimization calculation module includes: The energy fluctuation extraction submodule extracts the energy level values ​​of key feed ingredients based on the nutritional requirement composition map, screens sequences whose fluctuations exceed the energy fluctuation benchmark value, analyzes the proportion of abnormal fluctuations, and generates an abnormal energy fluctuation frequency ratio; The frequency demand matching submodule calls the abnormal energy fluctuation frequency ratio, combines the component operation frequency and the number of supply paths, identifies the frequency demand comparison item, adjusts the component abnormal offset according to the proportion of tasks on the supply path, and calculates the fluctuation coupling priority index; The priority level determination submodule extracts the numerical interval corresponding to the component based on the fluctuation coupling priority index, sets the component level to divide the interval group, assigns the level identifier according to the index value falling into the interval, sorts and determines the optimization level, and obtains the feed ratio priority scale.

[0010] As a further embodiment of the present invention, the nutritional trend analysis module includes: The fluctuation record screening submodule collects the time points of triggering and ending of chicken group weight fluctuations according to the feed ratio priority scale, identifies the time intervals between adjacent fluctuations, screens records that exceed the fluctuation interval benchmark value, and generates a fluctuation time interval sequence; The fluctuation period division submodule calls the fluctuation time interval sequence, counts the number of consecutive fluctuations of the same type of fluctuation events, calculates the fluctuation period distribution trend value according to the fluctuation duration, interval time and feeding behavior index, and establishes the fluctuation period distribution stage; The periodic trend classification submodule calls the fluctuation period distribution stage, identifies fluctuation events of the same periodic trend, analyzes the trend fluctuation differences, classifies and archives them according to the difference threshold, and generates a nutritional demand evolution period sequence.

[0011] As a further solution of the present invention, the ratio adjustment module includes: The trend sequence identification submodule calls the nutritional demand evolution cycle sequence, extracts the incremental change value, determines the trend rising interval based on the cumulative increase and fluctuation amplitude, marks the key feed components, and generates a feed optimization trend anomaly identification list; The absorption characteristic extraction submodule calls the component number in the feed optimization trend anomaly identification list, identifies the abnormal fluctuation value and absorption delay in the segment, combines the delay distribution and fluctuation frequency, analyzes the component absorption difference, and obtains the feed optimization absorption characteristic difference value; The ratio revision submodule identifies the ratio revision item structure according to the difference value of the feed optimized absorption characteristics and the corresponding period of the trend segment, analyzes the ratio deviation degree and the frequency distribution amplitude, calculates the ratio deviation degree characteristic value, and adjusts the feed component ratio and time distribution in combination with the original ratio structure difference to obtain the feed optimized ratio adjustment table.

[0012] As a further solution of the present invention, the system also includes a nutrition diagnosis decision module: The nutrition diagnosis and decision module collects the absorption difference and utilization fluctuation characteristics of high-frequency feed components based on the feed optimization ratio adjustment table, determines whether the fluctuation characteristics have homology, and identifies the nutrition attribution nodes to form a nutrition imbalance traceability path diagram; The nutritional imbalance traceability path diagram includes a fluctuation homology feature group, nutritional node positioning results, and a traceability path structure diagram.

[0013] As a further solution of the present invention, the nutrition diagnosis decision module includes: The absorption difference extraction submodule checks the absorption time and utilization rate change sequence of high-frequency feed components based on the feed optimization ratio adjustment table, identifies the synchronization deviation between the absorption time difference and the utilization rate change rate, selects the time points and component numbers where the deviation exceeds the stable range, and generates a feed optimization absorption deviation list; The fluctuation homology discrimination submodule calls the utilization fluctuation sequence according to the feed optimization absorption offset list, compares the fluctuation amplitude and direction at the offset time point, identifies the continuous and consistent fluctuation segments and records the intervals overlapping with the offset time point, and generates an absorption fluctuation homology segment table; The nutrient attribution identification submodule extracts the node path of the component number according to the absorption fluctuation homologous segment table, tracks the absorption order and signal transmission of the nodes in the overlapping segments, identifies the abnormal absorption frequency of the signal source node, and forms a nutritional imbalance traceability path diagram.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, a mapping relationship is constructed based on the changing trend of weight growth rate and feeding behavior, combined with the relationship between nutrient utilization efficiency and absorption delay, to achieve accurate characterization of the nutritional demand structure. By extracting the comparison results of absorption fluctuations and demand intensity, a feed ingredient optimization priority logic is established to assist in achieving efficient matching of feed energy and protein content. At the same time, the high-frequency demand stage is identified based on the time series characteristics of weight fluctuations, and dynamic tracking of the nutritional demand cycle is achieved. The feed ratio value is revised in sections based on feeding delay and absorption difference, so that the ratio response can be closer to the individual growth rhythm. The nutritional attribution path is identified through the absorption difference and utilization fluctuation law, and the structural adaptability and component specificity of the nutritional supply are improved, which effectively reduces the feed waste rate and the probability of nutritional imbalance, and improves the overall feeding efficiency and management intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system flow chart of the present invention; Figure 2 This is a flow chart of the nutritional needs assessment module in the present invention; Figure 3 This is a flow chart of the ratio optimization calculation module in the present invention; Figure 4 This is a flow chart of the nutrition trend analysis module in the present invention; Figure 5 This is a flow chart of the ratio adjustment module in the present invention; Figure 6 This is a flow chart of the nutritional diagnosis decision module in the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0018] See also Figure 1 , a chicken nutrition modeling and visualization analysis system includes: The nutritional demand assessment module obtains data on the age distribution, weight growth curve, feed intake fluctuations, and feed component absorption rate of the chicken flock, analyzes the relationship between nutritional needs, and determines the direction of nutritional needs and the length of the supply chain based on the changing trends of weight growth rate and feeding behavior. It also maps the ratio of nutrient utilization rate to absorption delay to generate a nutritional demand composition map. The feed ratio optimization calculation module selects the energy level and protein content of key feed ingredients based on the nutritional requirement composition map, matches the absorption fluctuation frequency with the demand level, identifies the key optimization levels, and obtains the feed ratio priority scale; The nutritional trend analysis module extracts the time intervals and durations of chicken weight fluctuations based on the feed ratio priority scale, determines the distribution phase of high-frequency fluctuations, classifies the periodic trends of similar fluctuation events, and generates a cyclical sequence of nutritional demand evolution; The ratio adjustment module calls the nutrient demand evolution cycle sequence, combines the absorption fluctuation value and feeding time delay in the section under its jurisdiction, selects the target feed ingredients in the high-trend section, and revises the ratio value in sections to obtain the feed optimization ratio adjustment table; The nutritional diagnosis and decision-making module is based on the feed optimization ratio adjustment table, collects the absorption difference and utilization fluctuation characteristics of high-frequency feed ingredients, determines whether the fluctuation characteristics are homologous, and identifies the nutritional attribution nodes to form a nutritional imbalance traceability path map.

[0019] The nutritional demand composition map includes the nutritional demand direction classification, supply chain path structure, and absorption delay ratio distribution; the feed ratio priority scale includes the optimization grade label, ingredient risk coefficient, and priority score interval; the nutritional demand evolution cycle sequence includes the fluctuation interval distribution, fluctuation duration frequency, and cycle classification results; the feed optimization ratio adjustment table includes the target ingredient list, ratio revision parameters, and delay correlation factors; the nutritional imbalance traceability path diagram includes the fluctuation homologous feature group, nutritional node positioning results, and traceability path structure diagram.

[0020] See also Figure 2 , the nutritional needs assessment module includes: The weight and feed intake identification submodule obtains data on the age distribution of chickens, weight growth curve, feed intake fluctuations, and feed component absorption rate. It aligns the three signals by timestamp, extracts weight mutation points, locates changes in feed intake and absorption rate, identifies response differences, and generates nutritional requirement response deviations. Obtain the age distribution data of the chicken flock. Taking 5,000 broilers as an example, their age is recorded daily from the first day of hatching to the 42nd day. The weight growth curve data is obtained by daily random sampling and weighing of the chicken flock. For example, 0.5% of the total number of chickens in the flock, that is, 25 broilers, are randomly selected for weighing, and their daily weight is continuously recorded to form a weight time series. The feed intake fluctuation data is monitored in real time by sensors installed on the feed trough. The hourly feed intake is then aggregated into the total daily feed intake. For example, the average daily feed intake data of a batch of broilers is recorded from the 7th day of age. The feed component absorption rate data is obtained by regularly analyzing the composition of feces and combining the feed component content to calculate the apparent digestibility of major nutrients (such as crude protein, crude fat, and energy). As the absorption rate, for example, digestibility is measured at key growth nodes such as the 7th day, the 14th day, and the 21st day of age, and the three signals of weight growth curve, feed intake fluctuation and feed component absorption rate are aligned according to the timestamp. For example, 00:00:00 every day is used as the timestamp, and the weight, feed intake and absorption rate data of the day are uniformly attributed to the timestamp. The weight mutation point is extracted and identified by calculating the deviation between the daily weight growth rate and the historical average growth rate. When the daily weight growth rate for three consecutive days is lower than the historical average growth rate by 10%, it is determined to be a weight mutation point. For example, if the historical average daily weight gain of a broiler flock is 60 grams, and the daily weight gain for three consecutive days is 50 grams, 52 grams, and 53 grams respectively, the growth rate deviations are 、 、 , all exceed the 10% threshold, then these 3 days are marked as weight mutation points, and the changes in feed intake and absorption rate are determined by analyzing the degree of deviation between their daily average values ​​and the historical average values. When the feed intake or absorption rate deviates from the historical average value by more than 2 times its standard deviation for 2 consecutive days, it is considered to have changed. For example, if the historical average feed intake is 120 grams / day and the standard deviation is 5 grams, when the feed intake on certain two days is 108 grams and 107 grams respectively, the deviation degrees are |108-120| / 5=2.4 and |107-120| / 5=2.6 respectively, both exceeding 2 times. The threshold of the standard deviation is marked as the feed intake change point. The identification response difference is obtained by calculating the difference between the average change in feed intake and absorption rate within 7 days before the weight mutation and the average change in feed intake and absorption rate within 7 days after the weight mutation. For example, if the average feed intake decreases by 5 grams / day before the weight mutation and decreases by 15 grams / day after the mutation, the feed intake response difference is 15-5=10 grams / day. If the average absorption rate decreases by 1% before the mutation and decreases by 3% after the mutation, the absorption rate response difference is 3%-1%=2%, generating the nutritional demand response deviation.

[0021] The absorption lag analysis submodule extracts the absorption signal delay segment and the feeding signal response sequence based on the nutritional demand response deviation, calculates the delay length and response sequence, determines the signal demand direction, measures the number of supply chain trigger sequences within the lag segment, and generates the supply signal lag structure. According to the deviation of the nutritional demand response, the correlation coefficient between the change in absorption rate and the change in feed intake is calculated. For example, the absorption rate response difference sequence and the feed intake response difference sequence are cross-correlated with each other in a sliding window. The window size is 7 days and the step size is 1 day. The lag days where the peak of the cross-correlation coefficient is located are determined as the signal delay segment. A positive value indicates that absorption lags behind feed intake, and a negative value indicates that feed intake lags behind absorption. The statistical delay length and response sequence are determined by recording the lag days when the cross-correlation coefficient reaches the peak. For example, if the peak of the cross-correlation coefficient appears at a lag of 2 days, the delay length is 2 days, and the absorption signal lags behind the feed intake signal. The signal demand direction is judged based on the characteristics of the absorption signal delay segment and the response difference. When the absorption signal lags behind the feed intake signal and the absorption rate response difference is negative (absorption decreases), it is judged to be caused by insufficient absorption capacity. Demand direction: If the feeding signal lags behind the absorption signal and the feed intake response difference is negative (feed intake decreases), it is judged that the demand direction is caused by feed palatability or energy density problems. For example, if the absorption signal delay period is 3 days between the 15th and 22nd days of age, the absorption rate response difference is -1.8%, the feed intake response difference is -5 g / day, and the cross-correlation peak shows that absorption lags behind feeding, then the demand direction is judged to be insufficient absorption capacity. The number of supply chain trigger sequences in the lag period is determined by checking whether there are supply chain operation records such as feed formula adjustment, feeding method change, and ambient temperature change in the lag period (for example, 3 days), and recording their occurrence order. For example, in the 3-day lag period, if the lysine content in the feed is adjusted first and then the ambient temperature is increased, the number of supply chain trigger sequences is 2, and the supply signal lag structure quantity is generated.

[0022] The nutrient supply structure generation submodule extracts the feed composition change points and the supply chain signal linkage period based on the supply signal hysteresis structure, compares the signal response frequency and delay, identifies the linkage number and average delay ratio, analyzes the demand relationship and supply frequency mapping, and generates a nutrient demand structure map; Based on the supply signal hysteresis structure, by comparing the delay segments identified in the supply signal hysteresis structure with historical feed formula adjustment records and feeding management plan change records, the specific date and time of the feed ingredient adjustment and the time period during which it affected the feed intake and absorption rate signals are accurately marked. For example, on day 25 of age, the crude protein content in the feed increases from 20% to 22%. If it is subsequently observed that the absorption rate increases by 1.5% between days 27 and 30, the crude protein change point is extracted and the linkage period between days 27 and 30 is compared. The signal response frequency and delay are compared by calculating the number of feed intake and absorption rate responses after a specific feed ingredient change and the delay time of each response. For example, after crude protein content adjustment, 8 of the past 10 adjustments resulted in significant changes in feed intake or absorption rate, with an average delay time of 2.5 days. The linkage number and average delay ratio are identified by counting the total number of feed intake or absorption rate fluctuations caused by each feed ingredient or supply chain operation under a specific hysteresis structure, and Each linkage is the average delay in the response of the feed intake or absorption rate signal relative to the change in feed composition. For example, if the calcium-phosphorus ratio in the feed is adjusted 15 times, and 12 of them result in significant fluctuations in absorption rate, the number of linkages is 12. If the average delay time of these 12 fluctuations is 3.2 days, the average delay ratio is obtained by dividing this delay time by the preset benchmark response time (for example, 5 days): 3.2 / 5 = 0.64. Analysis of demand relationship and supply frequency mapping By constructing a multidimensional matrix, the demand direction of different nutrients (such as insufficient energy demand and excessive protein demand) is associated with the corresponding feed adjustment frequency, adjustment amount, and the resulting feed intake and absorption response. For example, if broilers show insufficient energy demand at day 35 of age, and the frequency of adjustment of high-energy feed components (such as fat) in the past 30 days is twice per week, with each adjustment amount being 0.5%, a mapping relationship is established between this insufficient energy demand and the frequency of high-energy feed adjustment to generate a nutrient demand composition map, which is displayed in graphical or tabular form.

[0023] See also Figure 3 , the ratio optimization calculation module includes: The energy fluctuation extraction submodule extracts the energy level values ​​of key feed ingredients based on the nutritional requirement composition map, screens sequences with fluctuations exceeding the energy fluctuation benchmark value, analyzes the proportion of abnormal fluctuations, and generates the abnormal energy fluctuation frequency ratio; Based on the nutritional requirement composition map, for example, the real-time energy level values ​​of the main energy contribution components such as crude protein, crude fat, and carbohydrates are obtained from the map. Assuming that they are 2500kcal / kg, 3500kcal / kg, and 2000kcal / kg respectively, the sequences with fluctuations exceeding the energy fluctuation reference value are screened out. The relative deviation between the actual energy level of the key feed ingredients and their reference energy level (for example, the energy level set based on the standard nutritional guide for the chickens of that age) is calculated, and the energy fluctuation reference value is set to 5%. When the relative deviation exceeds 5% for three consecutive days, it is considered that an abnormal fluctuation has occurred. For example, if the crude protein energy level on a certain day is 230 0kcal / kg, and its baseline energy level is 2450kcal / kg, then the relative deviation is |(2300-2450) / 2450|≈6.12. If the deviation exceeds 5% for three consecutive days, it will be marked as an abnormal fluctuation sequence. The proportion of abnormal fluctuation times is analyzed by counting the total number of abnormal fluctuation sequences of each key feed component within the set monitoring period (for example, 30 days), and dividing it by the total number of monitoring days to obtain its abnormal fluctuation frequency ratio. For example, within the 30-day monitoring period, the energy level of crude protein has an abnormal fluctuation sequence for a total of 5 times, then the abnormal fluctuation frequency ratio is 5 / 30≈16.7, generating the abnormal energy fluctuation frequency ratio.

[0024] The frequency demand matching submodule calls the abnormal energy fluctuation frequency ratio, combines the component operation frequency and the number of supply paths, identifies the frequency demand comparison item, adjusts the component abnormal offset according to the proportion of tasks on the supply path, and calculates the fluctuation coupling priority index; Call the abnormal energy fluctuation frequency ratio. For example, if the abnormal energy fluctuation frequency ratio of crude protein is 0.167, its component operation frequency (the frequency of adjustment or use in the past 30 days) is 2 times a week, and the number of supply paths (the number of ways to supplement the component through different raw material sources or additives) is 3, then use these three data as the frequency demand comparison items of crude protein, and adjust the abnormal component offset according to the task proportion on the supply path. For example, if crude protein has three supply paths, namely soybean meal, fish meal and synthetic amino acids, and their task proportions in the current feed formula are 40%, 30% and 30% respectively, if the overall abnormal offset of crude protein is 50kcal / kg, then its abnormal offset is distributed to each path in proportion, with the soybean meal path bearing 50×40%=20kcal / kg of offset, and the fish meal path bearing 50 ×30%=15kcal / kg offset, the amino acid synthesis pathway bears 50×30%=15kcal / kg offset. The fluctuation coupling priority index is calculated by weighted summing the abnormal energy fluctuation frequency ratio with the component operation frequency, the number of supply pathways, and the component abnormal offset adjusted by the task proportion. For example, the fluctuation coupling priority index I=W1×(abnormal frequency ratio)+W2×(component operation frequency)+W3×(adjusted abnormal offset mean), where weights W1=0.4, W2=0.3, and W3=0.3. If the abnormal frequency ratio of a component is 0.15, the component operation frequency is 1.5 times per week, and the adjusted abnormal offset mean is 10kcal / kg, then its fluctuation coupling priority index is .4×0.15+0.3×1.5+0.3×10=3.51.

[0025] The priority level determination submodule extracts the numerical interval corresponding to the component based on the fluctuation coupling priority index, sets the component level to divide the interval group, assigns the level identifier according to the index value falling into the interval, sorts and determines the optimization level, and obtains the feed ratio priority scale; Based on the fluctuation coupling priority index, for crude protein, the value range of its fluctuation coupling priority index is 0 to 10. The component level division interval group is set, and the fluctuation coupling priority index is divided into three levels: the low priority interval is [0, 3.5), the medium priority interval is [3.5, 6.5), and the high priority interval is [6.5, 10]. For example, the calculated value of the fluctuation coupling priority index of a certain component is 3.2, which falls into the low priority interval. The level identifier is assigned according to the interval in which the index value falls. For example, if the fluctuation coupling priority index of a feed component is 3.2, the assigned level identifier is "low priority". If it is 5.8, the assigned level is marked as "medium priority"; if it is 7.1, the assigned level is marked as "high priority". Sorting is performed to determine the optimization level. For example, all feed ingredients are arranged in descending order according to their assigned priority levels, with high priority at the front. For example, crude fat (high priority, indicator 7.2), lysine (medium priority, indicator 5.5), and crude protein (low priority, indicator 3.2) are sorted to form an optimization order of high, medium, and low levels, and a feed ratio priority scale is obtained. The scale contains all key feed ingredients and their corresponding optimization priority levels.

[0026] See also Figure 4 , Nutrition Trend Analysis Module includes: The fluctuation record screening submodule collects the trigger and end time points of the chicken group weight fluctuation according to the feed ratio priority scale, identifies the time interval between adjacent fluctuations, filters out records that exceed the fluctuation interval benchmark value, and generates a fluctuation time interval sequence; According to the feed ratio priority scale, by monitoring daily body weight data, when the body weight drops by more than 5% of the average body weight growth rate for three consecutive days, it is marked as a fluctuation trigger point. When the body weight returns to normal growth rate for three consecutive days and the growth rate deviation is less than 2%, it is marked as a fluctuation end point. The time interval between adjacent fluctuations is identified by calculating the number of days between the previous fluctuation end time point and the next fluctuation trigger time point. For example, if the previous weight fluctuation ends at the 20th day of age and the next fluctuation is triggered at the 25th day of age, the time interval is 5 days. Records that exceed the fluctuation interval benchmark value are filtered out by setting the fluctuation interval benchmark value to 4 days. When the time interval between adjacent fluctuations is greater than 4 days, the record is included in the screening results. For example, if the interval calculated above is 5 days, which exceeds the benchmark value of 4 days, this record is filtered out to generate a fluctuation time interval sequence, for example, [5, 6, 4, 7, 5, 8] days.

[0027] The fluctuation period division submodule calls the fluctuation time interval sequence to count the number of consecutive fluctuations of the same type of fluctuation events. According to the fluctuation duration, interval time and feeding behavior index, the formula is used: ; Calculate the trend value of the period distribution of fluctuations and establish the period distribution stage of fluctuations; in, represents the trend value of the periodic distribution of fluctuations, Representative The duration of the same type of fluctuation events, Represents the average duration of all fluctuation events of the same type, Representative The interval between the first and next fluctuation of the same type, represents the average time interval between all fluctuation events, represents the standard deviation of the duration of all volatility events, Represents the total number of fluctuation events of the same type; Call the fluctuation time interval sequence, assuming that "weight loss" is a type of fluctuation. If three consecutive weight loss fluctuations are monitored, the number of consecutive fluctuations is counted as three. According to the duration of the fluctuation, the interval time and the feeding behavior index, the periodic distribution trend value of the fluctuation is calculated. The feeding behavior index is defined as the percentage deviation of the average daily feed intake during the fluctuation period relative to the historical average feed intake. For example, if the average daily feed intake during the fluctuation period decreases by 10%, the feeding behavior index is , using the formula Calculate the period distribution trend value, where Represents the periodic distribution trend value of the fluctuation. The larger the value, the more irregular the fluctuation periodicity, and the smaller the value, the more obvious the periodicity. Representative The duration of the same type of fluctuation events, for example, the first fluctuation lasted 3 days, and the second lasted 4 days, Represents the average duration of all fluctuation events of the same type, Representative The interval between the first and second fluctuation events of the same type, for example, the interval between the first fluctuation and the triggering of the second fluctuation is 5 days. represents the average time interval between all fluctuation events, represents the standard deviation of the duration of all volatility events, Represents the total number of fluctuation events of the same type; Assume that three fluctuation events of the same type are counted, and their durations are sky, sky, Heaven, then Days, and the intervals after these three fluctuation events are Days (from the end of the first time to the second trigger), Days (from the end of the second time to the third trigger), then sky, For duration The standard deviation of The calculation process is: first calculate the variance ;so , substitute into the formula to calculate value, (because Only for intervals); Take the first two fluctuation data for calculation: ; Periodic distribution trend value This shows that this type of fluctuation has a certain periodicity, but there is a certain degree of irregularity. The benefit of the formula is that by comprehensively considering the discrete degree of the fluctuation duration and the fluctuation interval time, as well as taking the standard deviation of the fluctuation duration into consideration, it can more comprehensively evaluate the regularity of the fluctuation period distribution, help to distinguish random fluctuations from potential periodic changes in nutritional demand, and establish the fluctuation period distribution stage. For example, Fluctuations with values ​​below 0.5 are classified as the "stable cycle stage", those between 0.5 and 1.5 are classified as the "irregular cycle stage", and those above 1.5 are classified as the "random fluctuation stage".

[0028] The periodic trend classification submodule calls the fluctuation period distribution stage, identifies fluctuation events of the same periodic trend, analyzes the trend fluctuation differences, classifies and archives them according to the difference threshold, and generates a nutrient demand evolution period sequence; The fluctuation cycle distribution stage is called, and all fluctuation events are classified into the preset cycle distribution stage (such as "stable cycle stage", "irregular cycle stage", "random fluctuation stage") according to their calculated G values. For example, all fluctuation events with G values ​​between 0.5 and 1.5 are identified as similar events in the "irregular cycle stage". The trend fluctuation difference is analyzed by calculating the standard deviation of the G values ​​of each fluctuation event in the same cycle trend stage and the average difference of the G values ​​between different stages. For example, the standard deviation of the G values ​​of all fluctuation events in the "irregular cycle stage" is calculated to be 0.25. If it is significantly different from the average G value of the stage, it is classified and archived according to the difference threshold. The threshold of the G value standard deviation difference is set to 0.3. If the G value standard deviation in the same stage is less than 0.3, it is further subdivided into smaller subcategories. If it is greater than 0.3, the stage division needs to be re-evaluated. For example, if the G value standard deviation in the "irregular cycle stage" is 0.25, which is less than the threshold of 0.3, the fluctuation events in this stage are further divided into two subcategories: "tends to be stable" and "tends to be random", and a nutritional demand evolution cycle sequence is generated. The sequence includes the classification of different types of fluctuation events, the cycle stage to which they belong, and the key characteristic values. For example, the sequence includes "the Xth weight loss fluctuation belongs to the irregular cycle stage, and the G value is 1.155".

[0029] See also Figure 5 , the ratio adjustment module includes: The trend sequence identification submodule calls the nutrient demand evolution cycle sequence, extracts the incremental change value, determines the trend rising interval based on the cumulative increase and fluctuation amplitude, marks the key feed components, and generates a feed optimization trend anomaly identification list; Call the nutrient requirement evolution cycle sequence and obtain the change in the daily weight gain of the chicken group in a specific cycle from the sequence. For example, in a certain "irregular cycle stage", the daily weight gain drops from an average of 60 grams in the previous week to an average of 55 grams this week, and the incremental change value is -5 grams / day. The trend upward interval is judged based on the cumulative increase and fluctuation range and the key feed ingredients are marked. The cumulative increase is accumulated by accumulating the daily weight gain change values ​​for multiple consecutive days, and the fluctuation range is calculated by calculating the difference between the maximum and minimum daily weight gain change values ​​in the cycle. When the cumulative increase is positive for 7 consecutive days and the fluctuation range is less than 30% of the historical average fluctuation range, it is judged to be a trend upward interval, and according to the range, the key feed ingredients are marked. The specific nutritional requirement type exhibited by the animal (such as increased energy requirement) and the feed component with the strongest correlation with this requirement type in historical data are marked as key feed components. For example, if the cumulative weight gain of the chicken group increases from 1.5kg to 2.0kg between days 28 and 35 of age, and the daily weight gain fluctuation is controlled within 3 grams, it is judged to be in the rising trend range. At the same time, the feed intake is observed to increase, and historical data shows that the demand for lysine increases significantly during the rapid weight gain period. Therefore, lysine is marked as a key feed component, and a feed optimization trend anomaly identification list is generated. This list contains all marked key feed components and their corresponding rising trend ranges.

[0030] The absorption characteristics extraction submodule calls the component number in the feed optimization trend anomaly identification list, identifies the abnormal fluctuation value and absorption delay within the segment, combines the delay distribution and fluctuation frequency, analyzes the component absorption difference, and obtains the feed optimization absorption characteristics difference value; Call the ingredient number in the feed optimization trend anomaly identification list, for example, obtain the lysine number marked as "key feed ingredient" in the list, identify the abnormal fluctuation value and absorption delay in the segment by analyzing the deviation between the actual absorption rate and the target absorption rate of the ingredient in the corresponding trend segment, and the absorption delay time of the deviation relative to the change in feed intake. For example, if the actual absorption rate of lysine in the rising trend interval is 75%, and the target absorption rate is 80%, then the abnormal fluctuation value is -5. If its absorption rate change lags behind the feed intake change by 1.5 days, the absorption delay is 1.5 days. Combined with the delay distribution and fluctuation frequency, the absorption difference of the ingredient is analyzed. The delay distribution is statistically analyzed by the historical records of the ingredient. The distribution pattern of absorption delay time and the fluctuation frequency are calculated by counting the number of abnormal fluctuations in its absorption rate. For example, if the absorption delay time of lysine is mainly distributed in 1-2 days, and its absorption rate has fluctuated abnormally 10 times in the past 60 days, the analysis shows that the absorption of lysine has a certain hysteresis and a high frequency of abnormal fluctuations, indicating that there are differences in its absorption and utilization. The feed optimization absorption characteristic difference value is obtained. This difference value is calculated by multiplying the average absorption delay and the frequency of abnormal fluctuations in the absorption rate. For example, if the average absorption delay of lysine is 1.5 days and the frequency of abnormal fluctuations is 0.1 (10 times / 100 days), the absorption characteristic difference value is 1.5x0.1=0.15.

[0031] The ratio revision submodule identifies the ratio revision item structure based on the difference value of feed optimization absorption characteristics and the corresponding period of trend segment, analyzes the ratio deviation degree and frequency distribution amplitude, and uses the formula: ; Calculate the ratio deviation characteristic value, combine the original ratio structure difference, adjust the feed component ratio and time distribution, and obtain the feed optimization ratio adjustment table; in, Represents the characteristic value of the ratio deviation, Represents the total number of feed ingredient types, Representative The actual proportion of the components in the current period, Representative The target ratio of the components in the benchmark period, Representative The frequency distribution value of the item component in the current period, Represents the arithmetic mean of the ratio of all feed ingredients in the current cycle; According to the difference value of feed optimization absorption characteristics and the corresponding period of trend segment, the ratio revision item structure is identified. For example, if the difference value of lysine absorption characteristics is 0.15 and its corresponding trend segment is the rapid weight gain period, then based on this information, it is identified that the lysine ratio and feeding stage need to be revised, and the ratio deviation degree and frequency distribution amplitude are analyzed. The ratio deviation degree is determined by calculating the absolute difference between the current actual ratio and the benchmark target ratio. For example, if the actual lysine ratio is 1.1% and the target ratio is 1.2%, the deviation degree is The frequency distribution amplitude is calculated by calculating the range of changes in the ratio adjustment of the component in different feeding stages. For example, if the ratio adjustment range of lysine in the rapid weight gain period is 0.1%-0.3%, the formula is used. Calculate the ratio deviation characteristic value, where Represents the ratio deviation characteristic value. The larger the value, the greater the deviation between the current ratio and the target ratio and the more urgent the adjustment need. Represents the total number of feed ingredient types. For example, considering the four key ingredients of crude protein, crude fat, lysine and methionine, , Representative The actual ratio of the component in the current cycle, for example, the current actual ratio of lysine is 1.1%. Representative The target ratio of each component in the benchmark period, for example, the benchmark target ratio of lysine is 1.2%. Representative The frequency distribution value of the component in the current cycle, that is, the actual frequency of adjustment of the component or the frequency of change of its ratio during the monitoring period. For example, the frequency of adjustment of the ratio of lysine during the monitoring period is 2 times per week, which is quantified as 0.25 using 0-1 (if the maximum adjustment frequency per week is 8 times). Represents the arithmetic mean of the ratio of all feed ingredients in the current cycle. For example, in the current cycle, crude protein is 18%, crude fat is 6%, lysine is 1.1%, and methionine is 0.5%. , The calculation example is as follows: Assuming that only lysine is considered for calculation, , ; The benefit of this formula is that it not only takes into account the degree of deviation between the actual ratio of the ingredients and the target ratio, but also introduces the frequency distribution value of the ingredient (adjustment frequency) and weights the degree of deviation, so that it can more accurately reflect the urgency of the ratio adjustment, especially through This makes the component that deviates more from the average level have a larger calculated deviation characteristic value, thus gaining higher attention in the ratio optimization. Combined with the original ratio structure difference, the feed component ratio and time distribution are adjusted, and the calculated ratio deviation characteristic value is used. , combined with historical recipe data, for example, if If the value is higher, the lysine ratio will be adjusted from the current 1.1% to 1.2%, and by analyzing the difference in its absorption characteristics, the specific feeding time of the day will be determined. For example, it will be provided during the peak feed intake in the morning, and the feed optimization ratio adjustment table will be obtained. The table contains the revised proportions of each feed ingredient and its recommended feeding time at different growth stages and daily.

[0032] See also Figure 6 , the nutrition diagnosis and decision-making module includes: The absorption difference extraction submodule checks the absorption time and utilization rate change sequence of high-frequency feed ingredients based on the feed optimization ratio adjustment table, identifies the synchronization deviation between the absorption time difference and the utilization rate change rate, selects the time points and ingredient numbers where the deviation exceeds the stable range, and generates a feed optimization absorption deviation list; Based on the feed optimization ratio adjustment table, for lysine and methionine marked as requiring high-frequency adjustment in the ratio adjustment table, their absorption time (through blood sample testing) and utilization rate (through metabolic balance test) in the chicken body are continuously monitored. The synchronization deviation between the absorption time difference and the utilization rate change rate is identified by calculating the Pearson correlation coefficient of the two series and setting a threshold for judgment. When the absolute value of the correlation coefficient is less than 0.3 or greater than 0.7, it is determined to be a synchronization deviation. For example, if the correlation coefficient between the lysine absorption time series and the utilization rate change series is 0.25, which is lower than the threshold of 0.3, it is considered that there is a synchronization deviation. The time points and component numbers where the deviations exceed the stable range are screened by setting the absorption time difference stable range to ±0.5 hours and the utilization rate change rate stable range to ±2. When the absorption time difference exceeds ±0.5 hours or the utilization rate change rate exceeds ±2, the time point and the corresponding component number are marked. For example, if the absorption time of lysine is extended by 1.0 hours compared with the average value and the utilization rate decreases by 3% at the 40th day of age, the lysine at the 40th day of age is marked as a record of deviation outside the stable range, and a feed optimization absorption deviation list is generated, which contains all identified absorption deviation events, including time points and components.

[0033] The fluctuation homology discrimination submodule calls the utilization fluctuation sequence based on the feed optimization absorption offset list, compares the fluctuation amplitude and direction at the offset time point, identifies the continuous and consistent fluctuation segments and records the intervals overlapping with the offset time point, and generates the absorption fluctuation homology segment table; According to the feed optimization absorption deviation list, obtain the absorption deviation event of lysine at the 40th day of age in the list, and retrieve its historical utilization fluctuation series data to compare the fluctuation amplitude and direction of the deviation time point. By analyzing the numerical changes and trends of the utilization series before and after the deviation time point, for example, at the 40th day of age, the lysine utilization rate dropped from 85% on the previous day to 82%, with a fluctuation amplitude of 3% and a downward direction, identify the continuous and consistent fluctuation segments and record the intervals overlapping with the deviation time point. Smooth the utilization series by using the sliding average method, and then identify the utilization series with 5 consecutive days. The sections with consistent declining trends in utilization (for example, daily declines of 1% to 3%) were selected, and the sections were checked for overlap with time points in the absorption excursion list. For example, if it was found that the utilization of lysine and methionine showed a continuous declining trend from day 38 to day 42 of age, and overlapped with the lysine absorption excursion event at day 40 of age, this 5-day interval was marked as a continuous consistent fluctuation section, and an absorption fluctuation homologous section table was generated, which recorded the continuous fluctuation sections with the same fluctuation amplitude and direction, as well as the overlap with the absorption excursion time points.

[0034] The nutrient attribution identification submodule extracts the node path of the component number based on the absorption fluctuation homologous segment table, tracks the absorption order and signal transmission of the nodes in the overlapping segments, identifies the abnormal absorption frequency of the signal source node, and forms a nutrient imbalance traceability path diagram; According to the absorption fluctuation homologous segment table, the node path of the component number is extracted. For example, for the record of "continuous decline and fluctuation of lysine and methionine at 38-42 days of age" in the table, it is decomposed into "lysine" node and "methionine" node, and the order of absorption, metabolism and utilization of the two in the body is extracted from the metabolic pathway database to form a node path, for example, "lysine absorption" → "protein synthesis" → "methionine conversion", and the node absorption order and signal transmission in the overlapping segments are tracked by performing time series analysis on the node path. For example, if a decrease in lysine absorption rate is first observed at 38 days of age, and then a decrease in methionine utilization rate is observed at 39 days of age, it indicates that the absorption problem of lysine may be caused by affecting protein. The synthesis of methionine affects the utilization of methionine. The frequency of abnormal absorption of the signal source node is identified by counting the frequency of each component node as the starting point of the chain (that is, the first to have abnormal absorption) in all overlapping segments. For example, if lysine is used as the starting node of the absorption abnormality 3 times in 10 overlapping segments, and methionine is used as the starting node of the absorption abnormality 0 times in 10 overlapping segments, then the frequency of abnormal absorption of lysine is 3 times, and that of methionine is 0 times, forming a nutritional imbalance traceability path diagram, which graphically shows the starting component of nutritional imbalance, its impact path on the component, and the frequency of abnormalities of each starting component. For example, the direction of signal transmission is represented by an arrow, and the number next to the arrow represents the abnormal frequency, thereby intuitively revealing the root cause of nutritional imbalance.

[0035] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A chicken nutrition modeling and visualization analysis system, characterized in that: The system comprises: The nutritional demand assessment module obtains data on the age distribution, weight growth curve, feed intake fluctuations, and feed component absorption rate of the chicken flock, analyzes the relationship between nutritional needs, and determines the direction of nutritional needs and the length of the supply chain based on the changing trends of weight growth rate and feeding behavior. It also maps the ratio of nutrient utilization rate to absorption delay to generate a nutritional demand composition map. The ratio optimization calculation module selects the energy level and protein content of key feed ingredients based on the nutritional requirement composition map, matches and compares the absorption fluctuation frequency with the demand level, identifies the optimization key level, and obtains the feed ratio priority scale; The nutritional trend analysis module extracts the time interval and duration of chicken weight fluctuations based on the feed ratio priority scale, determines the high-frequency fluctuation distribution stage, classifies the periodic trends of similar fluctuation events, and generates a nutritional demand evolution cycle sequence; The ratio adjustment module calls the nutritional demand evolution cycle sequence, combines the absorption fluctuation value and feeding time delay in the section under its jurisdiction, screens the target feed components in the high trend section, revises the ratio value in sections, and obtains the feed optimization ratio adjustment table.

2. The chicken nutrition modeling and visualization analysis system according to claim 1, characterized in that: The nutritional demand composition map includes nutritional demand direction classification, supply chain path structure, and absorption delay ratio distribution; the feed ratio priority scale includes optimization level label, component risk coefficient, and priority score interval; the nutritional demand evolution cycle sequence includes fluctuation interval distribution, fluctuation duration frequency, and cycle classification results; the feed optimization ratio adjustment table includes target ingredient list, ratio revision parameters, and delay correlation factors.

3. The chicken nutrition modeling and visualization analysis system according to claim 1, characterized in that: The nutritional needs assessment module includes: The weight and feed intake identification submodule obtains data on the age distribution of chickens, weight growth curve, feed intake fluctuations, and feed component absorption rate. It aligns the three signals by timestamp, extracts weight mutation points, locates changes in feed intake and absorption rate, identifies response differences, and generates nutritional requirement response deviations. The absorption hysteresis analysis submodule extracts the absorption signal delay segment and the feeding signal response sequence based on the nutritional demand response deviation, calculates the delay length and response sequence, determines the signal demand direction, measures the number of supply chain trigger sequences within the hysteresis segment, and generates the supply signal hysteresis structure quantity; The nutrient supply structure generation submodule extracts the feed composition change points and the supply chain signal linkage period based on the supply signal hysteresis structure, compares the signal response frequency and delay, identifies the linkage times and the average delay ratio, analyzes the demand relationship and supply frequency mapping, and generates a nutrient demand composition map.

4. The chicken nutrition modeling and visualization analysis system according to claim 3, characterized in that: The ratio optimization calculation module includes: The energy fluctuation extraction submodule extracts the energy level values ​​of key feed ingredients based on the nutritional requirement composition map, screens sequences whose fluctuations exceed the energy fluctuation benchmark value, analyzes the proportion of abnormal fluctuations, and generates an abnormal energy fluctuation frequency ratio; The frequency demand matching submodule calls the abnormal energy fluctuation frequency ratio, combines the component operation frequency and the number of supply paths, identifies the frequency demand comparison item, adjusts the component abnormal offset according to the proportion of tasks on the supply path, and calculates the fluctuation coupling priority index; The priority level determination submodule extracts the numerical interval corresponding to the component based on the fluctuation coupling priority index, sets the component level to divide the interval group, assigns the level identifier according to the index value falling into the interval, sorts and determines the optimization level, and obtains the feed ratio priority scale.

5. The chicken nutrition modeling and visualization analysis system according to claim 4, characterized in that: The nutrition trend analysis module includes: The fluctuation record screening submodule collects the time points of triggering and ending of chicken group weight fluctuations according to the feed ratio priority scale, identifies the time intervals between adjacent fluctuations, screens records that exceed the fluctuation interval benchmark value, and generates a fluctuation time interval sequence; The fluctuation period division submodule calls the fluctuation time interval sequence, counts the number of consecutive fluctuations of the same type of fluctuation events, calculates the fluctuation period distribution trend value according to the fluctuation duration, interval time and feeding behavior index, and establishes the fluctuation period distribution stage; The periodic trend classification submodule calls the fluctuation period distribution stage, identifies fluctuation events of the same periodic trend, analyzes the trend fluctuation differences, classifies and archives them according to the difference threshold, and generates a nutritional demand evolution period sequence.

6. The chicken nutrition modeling and visualization analysis system according to claim 5, characterized in that: The ratio adjustment module includes: The trend sequence identification submodule calls the nutritional demand evolution cycle sequence, extracts the incremental change value, determines the trend rising interval based on the cumulative increase and fluctuation amplitude, marks the key feed components, and generates a feed optimization trend anomaly identification list; The absorption characteristic extraction submodule calls the component number in the feed optimization trend anomaly identification list, identifies the abnormal fluctuation value and absorption delay in the segment, combines the delay distribution and fluctuation frequency, analyzes the component absorption difference, and obtains the feed optimization absorption characteristic difference value; The ratio revision submodule identifies the ratio revision item structure according to the difference value of the feed optimized absorption characteristics and the corresponding period of the trend segment, analyzes the ratio deviation degree and the frequency distribution amplitude, calculates the ratio deviation degree characteristic value, and adjusts the feed component ratio and time distribution in combination with the original ratio structure difference to obtain the feed optimized ratio adjustment table.

7. The chicken nutrition modeling and visualization analysis system according to claim 1, characterized in that: The system also includes a nutrition diagnosis and decision-making module: The nutrition diagnosis and decision module collects the absorption difference and utilization fluctuation characteristics of high-frequency feed components based on the feed optimization ratio adjustment table, determines whether the fluctuation characteristics have homology, and identifies the nutrition attribution nodes to form a nutrition imbalance traceability path diagram; The nutritional imbalance traceability path diagram includes a fluctuation homology feature group, nutritional node positioning results, and a traceability path structure diagram.

8. The chicken nutrition modeling and visualization analysis system according to claim 7, characterized in that: The nutrition diagnosis decision module includes: The absorption difference extraction submodule checks the absorption time and utilization rate change sequence of high-frequency feed components based on the feed optimization ratio adjustment table, identifies the synchronization deviation between the absorption time difference and the utilization rate change rate, selects the time points and component numbers where the deviation exceeds the stable range, and generates a feed optimization absorption deviation list; The fluctuation homology discrimination submodule calls the utilization fluctuation sequence according to the feed optimization absorption offset list, compares the fluctuation amplitude and direction at the offset time point, identifies the continuous and consistent fluctuation segments and records the intervals overlapping with the offset time point, and generates an absorption fluctuation homology segment table; The nutrient attribution identification submodule extracts the node path of the component number according to the absorption fluctuation homologous segment table, tracks the absorption order and signal transmission of the nodes in the overlapping segments, identifies the abnormal absorption frequency of the signal source node, and forms a nutritional imbalance traceability path diagram.

Images