A livestock vaccine data management system

Abstract

The present invention relates to the technical field of vaccine data processing, and specifically to a livestock vaccine data management system, the system comprising: a vaccine data acquisition and stratification module collects livestock vaccine data, and divides it into multiple levels, obtains a vaccine data stratification set, performs weighted sampling operations on the data in the vaccine data stratification set according to their respective weight ratios, obtains weighted stratified vaccine samples, compares and analyzes the statistical characteristics of the variables in the weighted stratified vaccine samples with the overall livestock vaccine data, and generates a vaccine representative sample set. In the present invention, systematic sampling and dynamic monitoring of vaccine data are achieved through multi-level data acquisition and stratified set processing. At the data processing level, key variables such as vaccines and animal species, vaccination time, vaccination location, and effects are weighted sampled and stratified statistics are performed according to weights, so that the sampling reflects the actual data structure more comprehensively and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of vaccine data processing, and in particular to a livestock vaccine data management system. Background Art

[0002] Vaccine data processing technology helps realize the traceability and information sharing of the entire life cycle of vaccines through data collection, transmission, storage and processing processes, and improves the production quality management and effective supply of vaccines. Vaccine data processing not only includes the recording of key data such as vaccine ingredients, production batches, storage environment, etc., but also involves intelligent data analysis and decision support, providing data support for the effectiveness and safety of vaccines.

[0003] Among them, the livestock vaccine data management system is a vaccine data processing application used in the livestock industry. The purpose of the system is to ensure that livestock animals receive effective vaccine protection at different growth stages through real-time management of data in the production, storage, circulation and use of livestock vaccines.

[0004] Existing technologies have difficulty in fully presenting the distribution characteristics of vaccine efficacy in vaccine data management, which makes it difficult to accurately reflect the representativeness of samples in large-scale data analysis. For example, when it is necessary to evaluate the distribution of the effects of a certain vaccine in multiple animal types, it is impossible to present the actual proportion of each type in the total, resulting in deviations in the analysis of the effect. At the same time, when evaluating the effectiveness of vaccination, it is difficult to identify and correct the deviations caused by batch differences and environmental fluctuations, resulting in the effectiveness evaluation results being susceptible to interference from external factors. For example, different batches of vaccines may affect their efficacy due to differences in storage conditions, resulting in greater volatility in the evaluation results. In addition, existing technologies have difficulty in responding effectively to changes in the types of diseases and environmental factors, resulting in the inability to flexibly adjust vaccination strategies for different disease types. For example, in the context of multiple disease outbreaks, the protective effect of vaccines is relatively limited. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a livestock vaccine data management system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A livestock vaccine data management system comprises:

[0007] The vaccine data collection and stratification module collects animal husbandry vaccine data and divides it into multiple levels to obtain a stratified set of vaccine data. The data in the stratified set of vaccine data are weighted sampled according to their respective weight ratios to obtain weighted stratified vaccine samples. The statistical characteristics of the variables in the weighted stratified vaccine samples are compared and analyzed with the overall animal husbandry vaccine data to generate a representative vaccine sample set.

[0008] The vaccine efficacy evaluation and adjustment module performs residual analysis on the representative sample set of the vaccine, identifies potential deviation factors, performs probability distribution adjustment operations according to the potential deviation factors, obtains deviation-adjusted efficacy distribution data, calculates the confidence interval of the adjusted vaccination effect according to the deviation-adjusted efficacy distribution data, and obtains the confidence interval of efficacy evaluation;

[0009] The vaccination sequence optimization module evaluates the protective effect of the vaccination sequence under each disease type and environmental condition based on the confidence interval of the efficacy evaluation, extracts the multi-frequency vaccination sequence and calculates the protection effect score, selects the efficient vaccination sequence with the highest efficacy score, analyzes the vaccination interval time according to the efficient vaccination sequence, and obtains the optimization results of the vaccination sequence and time interval;

[0010] The vaccine efficacy trend analysis module calls the observed data and adjusted efficacy data, analyzes the dynamic changes of the stratified set of vaccine data, and performs step-by-step fitting of the efficacy data to form the vaccine efficacy trend analysis results. Based on the vaccine efficacy trend analysis results and the efficient vaccination sequence based on the vaccination sequence and time interval optimization results, a simulation prediction of the efficacy is performed to obtain the livestock vaccine data processing results.

[0011] As a further solution of the present invention, the steps of obtaining the weighted stratified vaccine samples are specifically as follows:

[0012] Based on livestock vaccine data, including key variables such as vaccine and animal species, vaccination time, vaccination location, and vaccination effect, each type of variable is labeled and divided into multiple levels to generate a hierarchical set of vaccine data;

[0013] Based on the stratified set of vaccine data, the formula is used:

[0014] ;

[0015] Calculate the weighted average of the sample values , perform weighted sampling operation according to the weight ratio to obtain weighted stratified vaccine samples;

[0016] in, Indicates the index position of the current level. represents the total number of layers, Indicates The data weight value of the layer, Indicates The variable value of the layer.

[0017] As a further embodiment of the present invention, the steps for obtaining the vaccine representative sample set are specifically as follows:

[0018] Based on the weighted stratified vaccine sample, the formula is used:

[0019] ;

[0020] Calculate the Frequency distribution value of the layer ,Through stratified proportion analysis, the frequency distribution results of weighted samples were obtained;

[0021] Based on the frequency distribution results of the weighted samples, the representativeness of the samples in each level is checked, and if there are deviations, adjustments are made to generate a representative vaccine sample set.

[0022] As a further solution of the present invention, the step of obtaining the bias-adjusted performance distribution data is specifically as follows:

[0023] Based on the representative sample set of vaccines, the vaccination effects of different batches of vaccines were compared with the standard effects item by item, and the residuals between each batch were calculated. By analyzing each variable, the potential deviation factors were identified and a list of deviation factors was obtained.

[0024] Based on the deviation factor list, the vaccination effect data is redistributed according to the influence of the deviation factors, and the distribution density of the vaccination effect data is adjusted according to each factor to generate deviation-adjusted efficacy distribution data.

[0025] As a further solution of the present invention, the steps for obtaining the confidence interval of the efficacy evaluation are specifically as follows:

[0026] Based on the bias-adjusted potency distribution data, the formula is used:

[0027] ;

[0028] Calculating confidence intervals , and obtain the confidence interval of the vaccination effect;

[0029] in, is the sample mean, is the standard score, is the sample standard deviation, is the sample mean, is the sample size;

[0030] Based on the confidence interval of the vaccination effect, the efficacy evaluation is confirmed, and the adjusted effect data is analyzed to see whether they are in line with the expected effect range to obtain the confidence interval of the efficacy evaluation.

[0031] As a further solution of the present invention, the steps for obtaining the optimization results of the vaccination sequence and time interval are specifically as follows:

[0032] Based on the confidence interval of the efficacy evaluation, the vaccination effect data that meets the confidence interval under each disease condition is extracted, the vaccination scheme with the smallest deviation is selected through deviation analysis, and the vaccination schemes that appear at multiple frequencies are compared to establish a multi-frequency vaccination sequence;

[0033] Based on the multi-frequency vaccination sequence, the formula is used:

[0034] ;

[0035] Calculating the standardized protection effectiveness score , obtain effect score data of multiple vaccination sequences;

[0036] in, It is The protective effect of the vaccination sequence is the reference value of the protection effect. It is The weight of the vaccination order, is the maximum value of the weight, It is The time required for each vaccination sequence, It is the reference value of the time required for vaccination;

[0037] Based on the effect score data of multiple vaccination sequences, the vaccination sequence with the highest score was screened and determined as the efficient vaccination sequence. The relationship between the vaccination intervals with different disease types was analyzed to obtain the optimization results of vaccination sequence and time interval.

[0038] As a further embodiment of the present invention, the steps for obtaining the vaccine efficacy trend analysis results are specifically as follows:

[0039] Based on the observed data and adjusted performance data, extract the key variable data in the stratified set, record the dynamic changes of each variable step by step according to the time period, analyze the change amplitude and direction of the variable within the time period, mark the trend, and generate the dynamic change analysis results of the variable;

[0040] Based on the analysis results of the dynamic changes of the variables, the dynamic data are segmented in chronological order for trend fitting, and the fitting residuals of the key variables are evaluated during the fitting process to obtain the vaccine efficacy trend analysis results.

[0041] As a further solution of the present invention, the steps for obtaining the livestock vaccine data processing results are specifically as follows:

[0042] Based on the vaccine efficacy trend analysis results, the current efficacy is set as the starting value, efficacy trend parameters are extracted according to time periods, a prediction model for simulation is constructed, future efficacy changes are simulated section by section, parameters within the time period are adjusted, and a prediction curve for vaccine efficacy is generated;

[0043] Based on the prediction curve of the vaccine efficacy, the efficient vaccination sequence and vaccination interval data of the vaccination sequence and time interval optimization results are compared with the efficacy prediction, and the vaccination time point is adjusted to align with the peak of efficacy to obtain the livestock vaccine data processing results.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, systematic sampling and dynamic monitoring of vaccine data are achieved through multi-level data collection and hierarchical set processing. At the data processing level, key variables such as vaccines and animal species, vaccination time, vaccination location, and effects are weighted and sampled and hierarchically counted according to weights, so that the sampling reflects the actual data structure more comprehensively and accurately. The comparison of weighted samples with the frequency distribution of overall data verifies the representativeness of the samples, making the samples for vaccine effect evaluation more reasonable. In the process of vaccine effect evaluation, potential batch deviations and environmental factors are identified through residual analysis, and corrections are made through the adjustment operation of probability distribution, which effectively reduces the volatility of vaccination effects affected by environmental and batch differences, and ensures the credibility and consistency of efficacy evaluation data. Based on the actual efficacy evaluation of disease types and environmental conditions, efficient vaccination schemes are screened to ensure the scientific nature of vaccination timing and frequency under different disease types, thereby improving the vaccination effect. By analyzing the trend of vaccine efficacy and combining efficient vaccination sequence and interval optimization, future changes in vaccination effects are predicted, and dynamic optimization and trend warning of vaccination schemes are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a system flow chart of the present invention;

[0047] Figure 2 Flow chart for obtaining weighted stratified vaccine samples for the present invention;

[0048] Figure 3 A flow chart for obtaining a representative sample set of vaccines for the present invention;

[0049] Figure 4 A flow chart for obtaining bias-adjusted performance distribution data for the present invention;

[0050] Figure 5 A flow chart for obtaining confidence intervals for efficacy estimates of the present invention;

[0051] Figure 6 A flow chart of the present invention for obtaining optimization results of vaccination sequence and time interval;

[0052] Figure 7 A flow chart for obtaining vaccine efficacy trend analysis results for the present invention;

[0053] Figure 8The present invention is a flow chart for obtaining livestock vaccine data processing results. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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.

[0055] 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 indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0056] See also Figure 1 , a livestock vaccine data management system comprises:

[0057] The vaccine data collection and stratification module collects animal husbandry vaccine data, including key variables such as vaccine and animal species, vaccination time, vaccination location and vaccination effect, marks the variables and divides them into multiple levels, obtains the vaccine data stratification set, calls the variable information of each level in the vaccine data stratification set, performs weighted sampling operations on the vaccine and animal species, vaccination time and vaccination effect according to their respective weight ratios, obtains weighted stratified vaccine samples, compares and analyzes the statistical characteristics of the variables in the weighted stratified vaccine samples, and the statistical characteristics are frequency distribution data with the overall animal husbandry vaccine data, verifies the integrity of the sample, and generates a representative vaccine sample set;

[0058] The vaccine efficacy evaluation and adjustment module performs residual analysis on the representative sample set of the vaccine. By comparing the residuals between different vaccine batches, potential deviation factors are identified, including batch differences, environmental conditions (such as fluctuations in temperature and humidity), changes in vaccination time, and animal health conditions. Probability distribution adjustment operations are performed based on potential deviation factors. By adjusting the data distribution of vaccination effects, deviation-adjusted efficacy distribution data is obtained. Based on the deviation-adjusted efficacy distribution data, the confidence interval of the adjusted vaccination effect is calculated to obtain the confidence interval of efficacy evaluation.

[0059] The vaccination sequence optimization module evaluates the protective effect of the vaccination sequence under each disease type and environmental condition based on the confidence interval of the efficacy evaluation, selects the vaccination scheme that can provide higher protection effect and has smaller deviation within the confidence interval, extracts the multi-frequency vaccination sequence, calculates the protective effect score of each vaccination sequence in the multi-frequency vaccination sequence, selects the vaccination sequence with the highest efficacy score, and obtains the efficient vaccination sequence. According to the efficient vaccination sequence, the vaccination interval between different disease types is analyzed to determine the best vaccination time and obtain the optimization results of the vaccination sequence and time interval;

[0060] The vaccine efficacy trend analysis module calls the observed data and adjusted efficacy data. The observed data refers to the vaccine effect data actually observed during the livestock vaccination process. The adjusted efficacy data is the data after adjusting and correcting the potential deviation factors. It analyzes the dynamic changes of the variables in the vaccine data stratification set in different time periods, and performs step-by-step fitting of the efficacy data to form the vaccine efficacy trend analysis results. According to the vaccine efficacy trend analysis results, the efficacy simulation prediction is performed, and the efficient vaccination sequence based on the vaccination sequence and time interval optimization results is combined to integrate information and obtain the livestock vaccine data processing results.

[0061] The representative vaccine sample set includes representative animal breed samples, vaccine batch samples, vaccination effect samples and vaccination time samples. The confidence interval of efficacy evaluation includes the confidence interval range for different batches of vaccines, efficacy confidence intervals under different environmental conditions and confidence interval evaluation values ​​for animal health conditions. The vaccination sequence and time interval optimization results include the recommended vaccination intervals between different disease types, vaccination time adjustment recommendations for different environmental conditions and vaccination sequence optimization plans. The livestock vaccine data processing results include long-term vaccine efficacy prediction values, adaptability analysis results of different vaccination strategies and recommendations on the impact of environmental conditions on vaccine efficacy.

[0062] See also Figure 2 , the specific steps for obtaining weighted stratified vaccine samples are:

[0063] Based on livestock vaccine data, including key variables such as vaccine and animal species, vaccination time, vaccination location, and vaccination effect, each type of variable is labeled and divided into multiple levels to generate a hierarchical set of vaccine data;

[0064] In the process of stratifying livestock vaccine data, it is assumed that the following types of data are to be stratified: vaccine type, animal type, vaccination time and vaccination effect. The specific stratification steps and examples are as follows: Vaccine type level: Vaccine data are stratified by different types and batches. Assume that there are "rinderpest vaccine", "swine fever vaccine" and "avian influenza vaccine" in the data, and each vaccine may have different batches. Therefore, this layer can be further subdivided into a "vaccine type-batch" structure. For example, "rinderpest vaccine-batch A", "rinderpest vaccine-batch B", etc. are used as data stratification tags for this layer. Animal type level: Stratify according to the livestock breeds vaccinated, and record the application of vaccines in different animals. Assume that there are different animal breeds in the records, such as "dairy cows", "beef cattle", "goats", "sheep", etc., and each animal breed represents a layer. The vaccination effect may vary depending on the animal breed, so after data collection, it is hierarchical by "animal breed" to ensure that the vaccine reactions of different animals can be classified and processed separately. Vaccination time level: Vaccination time is an important factor affecting vaccine efficacy, so vaccination data needs to be stratified by time. Suppose the data records the vaccination of each batch of vaccines in different seasons, such as "Spring", "Summer", "Autumn" and "Winter". At this time, the data can be stratified by the season or month of vaccination to observe the performance of the vaccine under different seasonal conditions, thus forming a data set for the "vaccination time" layer. Vaccination effect level: This level is divided based on the vaccination effect, recording the effects of different vaccines after vaccination, including indicators such as "antibody level" and "reduction rate of disease incidence". For example, assuming that the proportion of animals with antibody levels reaching a certain standard after vaccination is recorded, the data can be divided into sub-layers such as "antibody level reaching standard group" and "non-standard group" according to different effect indicators in this layer.

[0065] Based on the stratified set of vaccine data, the formula is used:

[0066] ;

[0067] Calculate the weighted average of the sample values , perform weighted sampling operation according to the weight ratio to obtain weighted stratified vaccine samples;

[0068] in, Indicates the index position of the current level. Represents the total number of stratifications, that is, the number of strata participating in the weighted average, such as vaccine type stratum, animal type stratum, vaccination time stratum, and vaccination effect stratum. Indicates The weight of each layer is set based on actual monitoring and analysis of factors such as vaccine type and animal type. The basis for weight setting is the contribution ratio of each layer to the representativeness of the overall data. Indicates The variable values ​​of the layers reflect the representative data in each layer, such as the number of specific vaccines in the vaccine type layer or the value of vaccination effect.

[0069] For example, the variable values ​​of the vaccine type layer in the sample data , the variable values ​​at the animal species level , the variable value of the vaccination time layer , the variable value of the inoculation effect layer . According to the set weight value , , , , put it into the formula:

[0070] Calculate the weight numerator:

[0071] ;

[0072] Then calculate the weight denominator part:

[0073] ;

[0074] ;

[0075] The result shows that the weighted stratified vaccine sample value is 121. The role of the sample value is that it provides a target number for stratified sampling, so that the data extracted from each layer is proportional to the structural characteristics of the population, ensuring that the sample is representative. For example, in the stratified sampling operation, the total sample size of 121 is distributed to different levels according to the weight ratio of each layer, and samples are extracted from each layer according to the set weight ratio. The specific operation is as follows: Vaccine type layer (weight 0.4): The weight of this layer is 0.4, which accounts for 40% of the total sample. Therefore, the number of samples drawn from the vaccine type layer is: , so 48 samples are drawn from the vaccine type layer. Animal type layer (weight 0.3): The weight of this layer is 0.3, accounting for 30% of the total samples. The number of samples drawn from the animal type layer is: , therefore, 36 samples were drawn from the animal species layer. Vaccination time layer (weight 0.2): The weight of this layer is 0.2, accounting for 20% of the total samples. The number of samples drawn from the vaccination time layer is: , therefore, 24 samples are drawn from the inoculation time layer. Inoculation effect layer (weight 0.1): The weight of this layer is 0.1, accounting for 10% of the total samples. The number of samples drawn from the inoculation effect layer is: Therefore, 12 samples were drawn from the vaccination effect layer. The calculated 121 sets a clear sampling target for the sample distribution of each layer, so that the data of each layer can participate in the sampling according to the set weight, avoiding too little or too much data in some layers, thus ensuring that the samples of each layer are structurally consistent with the distribution of the overall data. This weighted sample value helps to more accurately reflect the characteristics of the overall vaccine data in statistical analysis and ensure that the sampled samples can represent the actual situation of different layers.

[0076] See also Figure 3 , the steps for obtaining the vaccine representative sample set are as follows:

[0077] Based on a weighted stratified vaccine sample, the formula is:

[0078] ;

[0079] Calculate the Frequency distribution value of the layer ,Through stratified proportion analysis, the frequency distribution results of weighted samples were obtained;

[0080] Assume that the weighted sample value obtained by sampling , bringing in the vaccine type layer , Animal species layer , vaccination time layer , inoculation effect layer , calculate the frequency distribution of each layer as follows:

[0081] Vaccine type stratification frequency :

[0082] ;

[0083] Animal species layer frequency :

[0084] ;

[0085] Vaccination time layer frequency :

[0086] ;

[0087] Vaccination effect layer frequency :

[0088] ;

[0089] The calculation results show that the proportion of each level in the weighted stratified sample is 39.7% for vaccine type level, 29.8% for animal type level, 19.8% for vaccination time level, and 9.9% for vaccination effect level.

[0090] Based on the frequency distribution results of the weighted samples, the representativeness of the samples in each level is checked, and if there is any deviation, adjustments are made to generate a representative sample set of vaccines;

[0091] In the process of verifying the integrity of the sample, the frequency distribution of the weighted stratified vaccine sample is compared with the overall livestock vaccine data to confirm whether the proportion of each layer of data conforms to the characteristics of the overall sample. The specific operation includes comparing the frequency distribution values ​​of each layer in the weighted sample set with the distribution proportion of each layer in the original data, and evaluating the representativeness of the sample at each level by comparing item by item. Assume that the frequency distribution calculated by the weighted stratified sample is as follows: vaccine type layer 39.7%, animal type layer 29.8%, vaccination time layer 19.8%, vaccination effect layer 9.9%. Compare these proportions with the corresponding distributions in the historical benchmark data, for example, in the historical data, the vaccine type layer accounts for 40%, the animal type layer accounts for 30%, the vaccination time layer accounts for 20%, and the vaccination effect layer accounts for 10%. If the stratification proportions of the current weighted sample are close to these benchmark values ​​(for example, the error of each layer is controlled within ±1%), it can be considered that the stratification structure of the sample is reasonable and representative. If the proportion of a certain layer is very different (for example, the vaccination effect layer currently accounts for 9.9%, but the historical benchmark is 15%), it may be necessary to resample or adjust the sampling strategy to increase the proportion of this layer in the sample. Through this comparison and adjustment, a representative vaccine sample set is ultimately generated that matches the overall structure in frequency distribution, ensuring that the sample integrity meets the analysis requirements.

[0092] See also Figure 4 , the specific steps for obtaining the bias-adjusted performance distribution data are:

[0093] Based on the representative sample set of vaccines, the vaccination effects of different batches of vaccines were compared with the standard effects item by item, and the residuals between each batch were calculated. By analyzing each variable, the potential deviation factors were identified and a list of deviation factors was obtained.

[0094] Residual analysis is performed on the representative sample set of vaccines. By comparing the actual vaccination effect of each batch of vaccines with the standard effect, the residuals are calculated item by item and the potential deviation factors are identified. The specific steps are as follows: First, the vaccination effect data of each vaccine batch is compared with the expected effect. For example, if the vaccination effect of a batch is 85% and the standard effect is 90%, the residual is -5%. Based on this residual data, analyze whether there are systematic differences between batches. On this basis, further refine the analysis of the impact of environmental conditions, extract variables such as temperature, humidity and vaccination time, and examine their changes in each batch. For example, in a batch, the temperature during vaccination is higher than that of other batches, and the residual of this batch is low, then "higher temperature" may be identified as a deviation factor. Compare the animal health records (such as health scores) of different batches. If it is found that the residuals of batches with low health scores are generally high, the animal health status can be included in the deviation factor range.

[0095] Based on the list of deviation factors, the vaccination effect data are redistributed according to the influence of the deviation factors, and the distribution density of the vaccination effect data is adjusted according to each factor to generate deviation-adjusted efficacy distribution data;

[0096] According to the identified potential deviation factors, the probability distribution adjustment operation is performed to adjust the data distribution of the inoculation effect. The specific steps are: based on the degree of influence of each deviation factor on the inoculation effect, the data of each batch is redistributed according to the direction of the deviation factor. For example, assuming that temperature fluctuation is a major deviation factor, all inoculation effect data are reclassified according to temperature conditions, and the data with low effects under high temperature conditions are adjusted to make them conform to the overall efficacy distribution. At the same time, for the influence of different humidity environments, the corresponding adjustment coefficients are applied to redistribute the probability density of the effect data. For example, the inoculation effect of the batch with low humidity is 80%, and the effect is 88% when the humidity is high. The humidity factor is included in the distribution adjustment, and the data is readjusted to be close to the expected effect under this condition.

[0097] See also Figure 5 , the specific steps for obtaining the confidence interval of performance evaluation are:

[0098] Based on the bias-adjusted efficacy distribution data, the formula is used:

[0099] ;

[0100] Calculating confidence intervals , and obtain the confidence interval of the vaccination effect;

[0101] in, It indicates the statistical range of the vaccination effect, and the reliable interval of the efficacy data is expressed through a specific confidence level. Through this value, a statistical judgment can be made on the accuracy and consistency of the adjusted efficacy data. is the sample mean, which represents the average vaccination effect of the bias-adjusted efficacy data. The vaccination effect value of each sample is obtained from the bias-adjusted efficacy data set and is calculated by summing and dividing by the total number of samples. is a standard score, which represents the standard normal distribution coefficient at a specific confidence level. It is obtained by looking up the table according to the required confidence level. Common confidence levels are 95% (corresponding to ) and 99% (corresponding to ), is the sample standard deviation, which indicates the degree of dispersion of the vaccination effect data and reflects the degree of deviation of the sample data from the mean. The larger the sample standard deviation, the greater the volatility of the sample value. The calculation formula is: ,in For the Sample values, is the sample mean, is the sample size, that is, the total number of samples of bias-adjusted performance data.

[0102] For example, in bias-adjusted performance data, the sample mean , with a confidence level of 95% , sample standard deviation , sample size .

[0103] Calculate the standard error:

[0104] ;

[0105] Compute the confidence interval range:

[0106] ;

[0107] This yields a confidence interval:

[0108] ;

[0109] The results showed that at a 95% confidence level, the confidence interval of the adjusted vaccination effect was 81.18 to 93.82.

[0110] Based on the confidence interval of the vaccination effect, the efficacy evaluation is confirmed, and the adjusted effect data is analyzed to see whether they meet the expected effect range, and the confidence interval of the efficacy evaluation is obtained;

[0111] Based on the confidence interval results obtained, the adjusted confidence interval of the vaccination effect was used for the final confirmation of the efficacy evaluation. Specifically, the confidence interval As a statistical evaluation range of vaccination effectiveness, it is used to assess the credibility of sample data and the reliability of the vaccination program. Assuming that the vaccination effect of the historical benchmark data is 85, the adjusted confidence interval The inclusion of this benchmark value indicates that the adjusted data is statistically closer to the expected range of historical efficacy, so it can be considered that the current sample data can better reflect the reliability of vaccination effects after bias adjustment. Through this confirmation process, the final confidence interval for efficacy evaluation is generated for the reliability verification of vaccine effects and the subsequent formulation of vaccination strategies.

[0112] See also Figure 6 The specific steps for obtaining the optimization results of vaccination sequence and time interval are as follows:

[0113] Based on the confidence interval of efficacy evaluation, extract the vaccination effect data that meets the confidence interval under each disease condition, select the vaccination scheme with the smallest deviation through deviation analysis, and compare the vaccination schemes that appear at multiple frequencies to establish a multi-frequency vaccination sequence;

[0114] Based on the calculated confidence interval (the adjusted confidence interval of vaccination effect is 81.18 to 93.82 at the 95% confidence level), the protective effect of vaccination sequence under different disease types and environmental conditions was evaluated. First, the vaccination effect data under each disease condition were extracted, and these data were compared with the confidence interval of efficacy evaluation to screen out the vaccination sequence with a protective effect ranging from 81.18 to 93.82. For the vaccination sequence that meets the confidence interval conditions, the mean of the protective effect of each vaccination scheme is calculated item by item to reflect its average protection level. Then, based on these means, the deviation value of each vaccination scheme is calculated to identify which vaccination schemes have the smallest fluctuation in protective effect. Suppose there are three vaccination sequences A, B and C. The protective effect data of sequence A are 82, 85, 88, with a mean of 85 and a deviation of 3; the data of sequence B are 84, 90, 86, with a mean of 86.67 and a deviation of 3.06; the data of sequence C are 89, 87, 91, with a mean of 89 and a deviation of 2. After comparison, sequence C has the smallest deviation, so sequence C is selected as the preferred vaccination scheme. Then, by analyzing the vaccination schemes with higher frequencies under various diseases and environmental conditions, a multi-frequency vaccination sequence is constructed. For example, if sequence C appears frequently in multiple environments, a multi-frequency vaccination sequence with sequence C as the main one is constructed.

[0115] Based on a multi-frequency vaccination sequence, the formula is used:

[0116] ;

[0117] Calculating the standardized protection effectiveness score , obtain effect score data of multiple vaccination sequences;

[0118] in, It is the protective effect of the vaccination sequence, which refers to the protective effect achieved by the vaccination sequence under specific epidemic conditions. It is usually obtained through historical vaccination data or experimental analysis, and can reflect the protective efficacy of the vaccine under the current vaccination plan. It is a reference value for the protection effect and is used for standardization The score can be selected from the historical average protection effect, the theoretical maximum protection effect, or the effect of a reference vaccine, which is usually determined based on the long-term statistical mean or expected efficacy of the sample. It is the weight of the vaccination order, which indicates the influence of the current vaccination environment or specific disease conditions on the vaccination order. It is used to incorporate the influence of environmental conditions on the effect into the score calculation. It is usually set according to the environmental characteristics, disease severity or vaccination condition priority. is the maximum value of the weight, used for normalization , which is usually the maximum possible value of the weight under a specific condition and is used to keep the score weights consistent under different conditions. It is the time required for vaccination, which indicates the actual number of days (or hours or other time units) required to complete the vaccination sequence. It is used to measure the time efficiency of the vaccination sequence under different conditions. It is obtained through actual vaccination records, or the average completion time is used as a representative value. It is the reference value of the time required for inoculation and is used for standardization , which is usually set as the theoretical optimal time or the historical average vaccination time as the benchmark time for vaccination efficiency.

[0119] For example, the protective effect of a certain vaccination sequence , reference protection effect , weight , the maximum weight , time required for vaccination Day, reference time sky.

[0120] Calculate the dimensionless protection effect score of this vaccination sequence:

[0121] ;

[0122] The results show that the dimensionless protection effect score of the current inoculation sequence under specific environmental and disease conditions is 0.3168. This standardized score can be used for direct comparison with other inoculation sequences to screen out inoculation sequences with higher comprehensive effects and efficiency.

[0123] Based on the effect score data of multiple vaccination sequences, the vaccination sequence with the highest score is screened and determined as the efficient vaccination sequence. The relationship between the vaccination intervals of different disease types is analyzed to obtain the optimization results of the vaccination sequence and time interval.

[0124] The protection effect score calculated for each vaccination sequence , select the vaccination sequence with the highest score as the efficient vaccination sequence. First, obtain the protection effect score of each vaccination sequence. For example, assuming that the scores of vaccination sequences A, B, and C are , and , then the sequence C with the highest score is selected as the efficient vaccination sequence. On this basis, for the efficient vaccination sequence C, its vaccination interval with other disease types is gradually analyzed. The specific operation is: first read the vaccination interval data of different disease types, such as the interval data of sequence C, which is 3 days for disease X and 5 days for disease Y. By gradually adjusting and comparing the vaccination intervals between different disease types, ensure that the vaccination plan obtains the best vaccination time while maximizing the effect score. Finally, based on the analysis, the vaccination sequence C and the optimal vaccination interval (such as vaccination 3 days after disease X and vaccination 5 days after disease Y) are obtained.

[0125] See also Figure 7 , the specific steps for obtaining the results of vaccine efficacy trend analysis are as follows:

[0126] Based on the observed data and adjusted performance data, extract the key variable data in the stratified set, record the dynamic changes of each variable step by step according to the time period, analyze the change amplitude and direction of the variable within the time period, mark the trend, and generate the dynamic change analysis results of the variable;

[0127] Call the observed data and adjusted efficacy data. The observed data is the actual observed vaccine effect data, and the adjusted efficacy data is the data obtained after correcting the potential bias factors. First, extract the key variables of vaccine effect, such as vaccination success rate, duration of immune effect, disease control rate, etc., based on the existing stratified set, and track these variables dynamically by time period. Then, use the time series analysis method to record the changes of each variable in different time periods, including the magnitude and direction of changes. For example, for the vaccination success rate variable, assuming that the data in different time periods are the following groups: 92% in the first time period, 89% in the second time period, and 85% in the third time period, then record the dynamic changes of the variable as a downward trend in stages, with a change of 3% and 4% respectively. This process further observes the volatility of the vaccination success rate through rolling time window analysis, and identifies mutation points or trend changes (such as a significant change of 4% in the third time period).

[0128] Based on the results of the dynamic change analysis of variables, the dynamic data is segmented and trend fitted in chronological order, and the fitting residuals of key variables are evaluated during the fitting process to obtain the trend analysis results of vaccine efficacy;

[0129] On the basis of the obtained results of the dynamic change analysis of the variables, the efficacy data is gradually fitted to form the trend analysis results of the vaccine efficacy. First, the dynamic data divided by time is imported into the fitting system, and the variable data (such as vaccination success rate, disease control rate, etc.) is fitted segment by segment. For example, a polynomial fitting model is selected, with time as the independent variable and vaccination effect as the dependent variable, and the data points in each time period are fitted to obtain a fitting curve. Then, in the fitting process, the residual of each fitting segment (that is, the difference between the actual value and the fitted value of each data point) is calculated, and the residual value is evaluated to ensure the accuracy of the fitting. Assuming that the time period data of the vaccination success rate variable are 92%, 89%, and 85%, the fitting value of the fitted curve after fitting in the second time period is 90%, and the actual observed value is 89%, then the residual is -1. If the residual is large (such as exceeding the preset threshold), it is necessary to adjust the parameters of the fitting model, such as increasing the order of the polynomial or switching to a more suitable fitting method (such as exponential fitting) until the residual is within a reasonable range. By adjusting and evaluating the residual segment by segment, the fitted curve will gradually reflect the trend of efficacy over time. For example, when the residual is reduced to the ideal range, the fitting curve shows the attenuation or improvement of the vaccine effect in different time periods, and finally forms a complete vaccine efficacy trend analysis curve. This curve is used to predict the future performance of vaccine efficacy and provide data support for determining the best time for vaccination.

[0130] See also Figure 8 , the specific steps for obtaining the results of livestock vaccine data processing are:

[0131] Based on the results of the vaccine efficacy trend analysis, the current efficacy is set as the starting value, the efficacy trend parameters are extracted by time period, a prediction model for simulation is constructed, the changes in future efficacy are simulated section by section, the parameters within the time period are adjusted, and a prediction curve for vaccine efficacy is generated;

[0132] First, the efficacy change curve obtained from the analysis results is used as the basic data, and the efficacy trend parameters (such as change rate, growth or decay rate, etc.) are extracted according to the time period to construct a prediction model for simulation. In the model, the current value of the vaccine efficacy is used as the starting value. By simulating the efficacy performance at different future time points, the model parameters in the prediction time period are gradually adjusted. For example, a decreasing coefficient is set for the trend of declining efficacy, so that the simulation results of each time period are closer to the actual changes. The specific simulation process can be progressive according to a certain time step, for example, the efficacy value is updated every month until the set final time point. Assuming that the current vaccine efficacy is 90%, according to the results of the efficacy change trend analysis, the model sets the efficacy to decrease by 5% every month in the future. In the first simulation time period (i.e., one month later), the efficacy value simulation result is 85%; in the second month, the efficacy decreases to 80%; and in the third month, the efficacy decreases to 75%. In this way, the efficacy changes in the next few months are gradually simulated to form an efficacy prediction curve, which shows the possible changes in the protective effect of the vaccine in the future, which is used to determine the best time for vaccination or remind when additional vaccination may be needed.

[0133] Based on the prediction curve of vaccine efficacy, the efficient vaccination sequence and vaccination interval data of the optimization results of vaccination sequence and time interval are compared with the efficacy prediction, and the vaccination time point is adjusted to align with the peak period of efficacy to obtain the livestock vaccine data processing results;

[0134] First, the optimal vaccination sequence and corresponding vaccination interval data for different disease types are obtained, and compared with the simulated vaccine efficacy change curve to ensure that each vaccination time matches the corresponding vaccine efficacy. During the integration process, the optimal vaccination time point is appropriately adjusted according to the high efficiency and low efficiency periods of the vaccine efficacy curve, such as arranging vaccination in advance before the efficacy decreases, or delaying the vaccination time during the peak efficacy period, to ensure that each vaccination time coincides with the optimal efficacy of the vaccine. Assuming that the simulation prediction shows that the vaccine efficacy drops below 70% in the third month after vaccination, and the vaccination sequence of disease type X is arranged in the second month when the vaccine efficacy is higher, the vaccination time can remain unchanged to ensure that the vaccination of disease X is completed during the period of higher efficacy. For another disease type Y, if the efficacy is predicted to drop to 60% in the sixth month, the vaccination of Y should be arranged before the sixth month to avoid vaccination after the vaccine efficacy decreases, thereby improving the protective effect of the vaccine. Finally, these integrated vaccination sequences, intervals and timings form the livestock vaccine data processing results for subsequent actual vaccination planning.

[0135] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A livestock vaccine data management system, characterized in that: The system comprises: The vaccine data collection and stratification module collects animal husbandry vaccine data and divides it into multiple levels to obtain a stratified set of vaccine data. The data in the stratified set of vaccine data are weighted sampled according to their respective weight ratios to obtain weighted stratified vaccine samples. The statistical characteristics of the variables in the weighted stratified vaccine samples are compared and analyzed with the overall animal husbandry vaccine data to generate a representative vaccine sample set. The vaccine efficacy evaluation and adjustment module performs residual analysis on the representative sample set of the vaccine, identifies potential deviation factors, performs probability distribution adjustment operations according to the potential deviation factors, obtains deviation-adjusted efficacy distribution data, calculates the confidence interval of the adjusted vaccination effect according to the deviation-adjusted efficacy distribution data, and obtains the confidence interval of efficacy evaluation; The vaccination sequence optimization module evaluates the protective effect of the vaccination sequence under each disease type and environmental condition based on the confidence interval of the efficacy evaluation, extracts the multi-frequency vaccination sequence and calculates the protection effect score, selects the efficient vaccination sequence with the highest efficacy score, analyzes the vaccination interval time according to the efficient vaccination sequence, and obtains the optimization results of the vaccination sequence and time interval; The vaccine efficacy trend analysis module calls the observed data and adjusted efficacy data, analyzes the dynamic changes of the stratified set of vaccine data, and performs step-by-step fitting of the efficacy data to form the vaccine efficacy trend analysis results. Based on the vaccine efficacy trend analysis results and the efficient vaccination sequence based on the vaccination sequence and time interval optimization results, a simulation prediction of the efficacy is performed to obtain the livestock vaccine data processing results.

2. The livestock vaccine data management system according to claim 1, characterized in that: The steps for obtaining the weighted stratified vaccine sample are specifically as follows: Based on livestock vaccine data, including key variables such as vaccine and animal species, vaccination time, vaccination location, and vaccination effect, each type of variable is labeled and divided into multiple levels to generate a hierarchical set of vaccine data; Based on the stratified set of vaccine data, the formula is used: ； Calculate the weighted average of the sample values , perform weighted sampling operation according to the weight ratio to obtain weighted stratified vaccine samples; in, Indicates the index position of the current level. represents the total number of layers, Indicates The data weight value of the layer, Indicates The variable value of the layer.

3. The livestock vaccine data management system according to claim 2, characterized in that: The steps for obtaining the vaccine representative sample set are specifically as follows: Based on the weighted stratified vaccine sample, the formula is used: ； Calculate the Frequency distribution value of the layer ,Through stratified proportion analysis, the frequency distribution results of weighted samples were obtained; Based on the frequency distribution results of the weighted samples, the representativeness of the samples in each level is checked, and if there are deviations, adjustments are made to generate a representative vaccine sample set.

4. The livestock vaccine data management system according to claim 3, characterized in that: The steps for obtaining the bias-adjusted performance distribution data are specifically as follows: Based on the representative sample set of vaccines, the vaccination effects of different batches of vaccines were compared with the standard effects item by item, and the residuals between each batch were calculated. By analyzing each variable, the potential deviation factors were identified and a list of deviation factors was obtained. Based on the deviation factor list, the vaccination effect data is redistributed according to the influence of the deviation factors, and the distribution density of the vaccination effect data is adjusted according to each factor to generate deviation-adjusted efficacy distribution data.

5. The livestock vaccine data management system according to claim 4, characterized in that: The steps for obtaining the confidence interval of the efficacy evaluation are specifically as follows: Based on the bias-adjusted potency distribution data, the formula is used: ； Calculating confidence intervals , and obtain the confidence interval of the vaccination effect; in, is the sample mean, is the standard score, is the sample standard deviation, is the sample mean, is the sample size; Based on the confidence interval of the vaccination effect, the efficacy evaluation is confirmed, and the adjusted effect data is analyzed to see whether they are in line with the expected effect range to obtain the confidence interval of the efficacy evaluation.

6. The livestock vaccine data management system according to claim 5, characterized in that: The steps for obtaining the optimization results of the vaccination sequence and time interval are specifically as follows: Based on the confidence interval of the efficacy evaluation, the vaccination effect data that meets the confidence interval under each disease condition is extracted, the vaccination scheme with the smallest deviation is selected through deviation analysis, and the vaccination schemes that appear at multiple frequencies are compared to establish a multi-frequency vaccination sequence; Based on the multi-frequency vaccination sequence, the formula is used: ； Calculating the standardized protection effectiveness score , obtain effect score data of multiple vaccination sequences; in, It is The protective effect of the vaccination sequence is the reference value of the protection effect. It is The weight of the vaccination order, is the maximum value of the weight, It is The time required for each vaccination sequence, It is the reference value of the time required for vaccination; Based on the effect score data of multiple vaccination sequences, the vaccination sequence with the highest score was screened and determined as the efficient vaccination sequence. The relationship between the vaccination intervals with different disease types was analyzed to obtain the optimization results of vaccination sequence and time interval.

7. The livestock vaccine data management system according to claim 1, characterized in that: The steps for obtaining the vaccine efficacy trend analysis results are specifically as follows: Based on the observed data and adjusted performance data, extract the key variable data in the stratified set, record the dynamic changes of each variable step by step according to the time period, analyze the change amplitude and direction of the variable within the time period, mark the trend, and generate the dynamic change analysis results of the variable; Based on the analysis results of the dynamic changes of the variables, the dynamic data are segmented in chronological order for trend fitting, and the fitting residuals of the key variables are evaluated during the fitting process to obtain the vaccine efficacy trend analysis results.

8. The livestock vaccine data management system according to claim 7, characterized in that: The steps for obtaining the animal husbandry vaccine data processing results are specifically as follows: Based on the vaccine efficacy trend analysis results, the current efficacy is set as the starting value, efficacy trend parameters are extracted according to time periods, a prediction model for simulation is constructed, future efficacy changes are simulated section by section, parameters within the time period are adjusted, and a prediction curve for vaccine efficacy is generated; Based on the prediction curve of the vaccine efficacy, the efficient vaccination sequence and vaccination interval data of the vaccination sequence and time interval optimization results are compared with the efficacy prediction, and the vaccination time point is adjusted to align with the peak of efficacy to obtain the livestock vaccine data processing results.

Images