CN117786543B - Digital broiler raising information storage management method and system - Google Patents
Digital broiler raising information storage management method and system Download PDFInfo
- Publication number
- CN117786543B CN117786543B CN202410216870.6A CN202410216870A CN117786543B CN 117786543 B CN117786543 B CN 117786543B CN 202410216870 A CN202410216870 A CN 202410216870A CN 117786543 B CN117786543 B CN 117786543B
- Authority
- CN
- China
- Prior art keywords
- information
- tree
- isolated
- cultivation
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000287828 Gallus gallus Species 0.000 title claims abstract description 52
- 238000007726 management method Methods 0.000 title claims description 18
- 238000003860 storage Methods 0.000 title claims description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 56
- 238000009395 breeding Methods 0.000 claims abstract description 36
- 230000001488 breeding effect Effects 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000003066 decision tree Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims description 14
- 238000002955 isolation Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 12
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002123 temporal effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009313 farming Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 229910021529 ammonia Inorganic materials 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for storing and managing digital broiler raising information, wherein the method comprises the following steps: collecting breeding information of all collection time in the broiler breeding process; constructing a cultivation information isolated forest model for broiler cultivation; obtaining the dividing characteristics of the isolated tree according to all the monitoring categories in the isolated tree, and further obtaining the decision tree height of each cultivation information; acquiring time sequence confidence of each cultivation information; correcting the decision tree height according to the time sequence confidence of each cultivation information to obtain the actual tree height of each cultivation information; and obtaining target information and common information according to the actual tree heights of the cultivation information in all the isolated trees, and respectively storing the target information and the common information. The method aims to solve the problem that the decision result of the isolated forest is error caused by the change of monitoring data of broiler chicken breeding along with the time, and achieve the purpose of improving the decision accuracy of the isolated forest.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for storing and managing digital broiler raising information.
Background
The digital broiler chicken breeding information management system is a system for comprehensively recording and analyzing the breeding process, aims at improving the breeding efficiency, reducing the management cost, ensuring the traceability and controllability in the breeding process, and carrying out statistic analysis and data mining by monitoring breeding data of multiple aspects such as feed management, environment monitoring, growth conditions, health conditions and the like of broilers and combining cloud storage and analysis tools based on big data, so that the production performance is improved by coordinated management, and the breeding is more intelligent and efficient.
When the breeding data are stored and analyzed, as the monitoring items to be monitored are more, the generated breeding information data are large in data quantity, and a large load is generated for cloud storage and analysis, so that the breeding information which is different from and outstanding from the normal breeding information is required to be selected from all the breeding information as the target information for large data storage and analysis, and in order to select the target information from the breeding information formed by the monitoring items with multi-dimensional characteristics, the method is realized by using an isolated forest algorithm considering the multi-dimensional characteristics; however, the monitoring data of a part of the monitoring items in the cultivation information may change with time, resulting in an error in the decision result of the isolated tree when the cultivation information in the sub-sample set of the isolated tree is mainly distributed over a period of time.
Disclosure of Invention
The invention provides a method and a system for storing and managing digital broiler breeding information, which are used for solving the problem that the decision result of an isolated tree is error when the breeding information in a sub-sample set of the isolated tree is mainly distributed in a time period because the monitoring data of part of monitoring items in the existing breeding information is changed along with the time.
The invention relates to a method and a system for storing and managing digital broiler raising information, which adopts the following technical scheme:
In a first aspect, an embodiment of the present invention provides a method for managing storage of digitized broiler raising information, the method comprising the steps of:
collecting all monitoring data of the broiler chicken raising process, and obtaining raising information of all collecting time;
Obtaining a sub-sample set of a plurality of isolated trees according to preset isolated forest model parameters, wherein the plurality of isolated trees form a cultivation information isolated forest model for broiler cultivation; obtaining the dividing characteristics of each isolated tree according to the monitoring data trend of each monitored class in the sub-sample set of each isolated tree; making a decision on a sub-sample set of each isolated tree according to the dividing characteristics of each isolated tree to obtain the decision tree height of each cultivation information; acquiring time sequence confidence coefficient of each cultivation information in the sub-sample set of each isolated tree according to the collection time distribution of the cultivation information in the sub-sample set of each isolated tree; correcting the decision tree height according to the time sequence confidence of each cultivation information to obtain the actual tree height of each cultivation information in each isolated tree;
obtaining a target score of each cultivation information according to the actual tree height of each cultivation information in all the isolated trees; and obtaining target information and common information according to the target score of each cultivation information, and respectively storing the target information and the common information.
Further, the obtaining the classification feature of each isolated tree according to the monitoring data trend of each monitored class in the sub-sample set of each isolated tree includes:
And calculating the corrected information gain rate of each monitored class in each isolated tree, and selecting the monitored class with the maximum corrected information gain rate value in each isolated tree as the dividing characteristic of each isolated tree.
Further, the specific method for obtaining the gain ratio of the correction information includes:
For the isolated tree in the culture information isolated forest model Will/>Individual monitor categories are in the isolation tree/>The test statistic in (a) is recorded as/>Will isolate the tree/>Middle/>The information gain ratio of each monitored class is recorded as/>Isolation tree/>Middle/>Corrected information gain Rate of individual monitoring items/>The calculation mode of (a) is as follows:
Wherein, Is an isolated tree/>Number of middle time level intervals,/>Representing taking an absolute function.
Further, the specific obtaining mode of the test statistic includes:
Will isolate the tree The monitoring data of all monitoring items in the sub-sample set of (1) are ordered according to the collection time of the culture information to obtain an isolated tree/>The monitoring data sequence of each monitoring class of (3) will be an isolated tree/>The monitoring data sequence of each monitoring class is input into a Mann-Kendall trend test model to obtain an isolated tree/>Test statistics for each monitored category of (3).
Further, the specific acquisition mode of the time level interval includes:
all acquisition time of the breeding information is divided into Time-level, statistics of isolated tree/>Acquisition time of each cultivation information in the sub-sample set of (1) and mapping to/>In the individual time levels, an orphan tree/>, is generatedThe horizontal axis of the time level histogram is the time level, and the vertical axis is the number of cultivation information of the isolated tree in each time level; according to the isolation tree/>The dip of the temporal level histogram in the sub-sample set divides the temporal level histogram into several temporal level bins.
Further, the obtaining the decision tree height of each cultivation information includes:
And using the dividing characteristics of each isolated tree to make a decision on each cultivation information in the sub-sample set of each isolated tree, and ending the decision when the tree height of each isolated tree reaches the maximum height of each tree to obtain the decision tree height of each cultivation information in each isolated tree.
Further, the decision tree height making the decision for each sub-sample set of each isolated tree according to the partition characteristics of each isolated tree to obtain each cultivation information includes:
For the isolated tree in the culture information isolated forest model Will isolate the tree/>Is recorded as the first/>Individual time level intervals/>First/>Individual time level intervals/>Middle/>Time sequence confidence of individual cultivation information/>The calculation mode of (a) is as follows:
Wherein, For/>Individual time level intervals/>Middle/>Acquisition time of individual cultivation information,/>For/>Average value of acquisition time in each time level interval,/>For/>Standard deviation of acquisition time in each time class interval,/>The representation is to take the absolute value,Representing a minimum function,/>An exponential function based on a natural constant is represented.
Further, the step of correcting the decision tree height according to the time sequence confidence coefficient of each cultivation information to obtain the actual tree height of each cultivation information in each isolated tree includes:
For the isolated tree in the culture information isolated forest model Will/>The individual cultivation information is in isolated tree/>The timing confidence in (1) is noted as/>Will/>The individual cultivation information is in isolated tree/>The decision tree height in (1) is denoted/>First/>The individual cultivation information is in isolated tree/>Actual tree height in/>The calculation mode of (a) is as follows:
Wherein, For/>The individual cultivation information is in isolated tree/>In decision tree high,/>For/>The individual cultivation information is in isolated tree/>Timing confidence in (c).
Further, the obtaining the target information and the common information according to the target score of each cultivation information includes:
Presetting a target threshold When the target score of the cultivation information is greater than or equal to the target threshold/>When the information is recorded as target information;
When the target score of the cultivation information is smaller than the target threshold value At this time, the cultivation information is recorded as the general information.
In a second aspect, another embodiment of the present invention provides a storage management system for digitized broiler raising information, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the storage management method for digitized broiler raising information are implemented by the processor when the computer program is executed.
The technical scheme of the application has the beneficial effects that: according to the method, the cultivation information in the broiler cultivation process is collected, an isolated forest model is constructed, the cultivation information which has obvious difference with other cultivation information in the cultivation information is extracted to serve as target information, and the method is used for optimizing storage management of the broiler cultivation information; in the process of extracting target information, according to the monitoring item trend of the cultivation information in the sub-sample set of each isolated tree of the cultivation information isolated forest model, the dividing feature of each isolated tree is obtained by combining the information gain rate of each monitoring item, so that the selected dividing feature is prevented from generating larger change along with time change, partial normal cultivation information is early decided due to large time difference of the cultivation information in the sub-sample set, and the decision accuracy of the isolated forest model is improved; obtaining time sequence confidence coefficient of each cultivation information according to time distribution of each cultivation information in a sub-sample set of each isolation tree, obtaining actual tree height of each cultivation information in each isolation tree by combining the decision tree height of each cultivation information obtained by dividing feature decisions, correcting the decision tree height by using the time sequence distribution of each cultivation information as a punishment item, avoiding decision result distortion caused by unbalanced distribution of selected acquisition time of the cultivation information selected by the sub-sample set of the isolation tree, and achieving the purpose of reducing decision errors of an isolated forest model; and further, calculating the target score of each cultivation information according to the actual tree height to obtain target information and common information in the cultivation information of the broiler cultivation, so that classified storage and management of the broiler cultivation information are realized, and the efficiency of digitally analyzing important target information is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of a method for managing storage of information of digital broiler raising.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to specific implementation, structure, characteristics and effects of a method and a system for storing and managing digital broiler raising information according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for storing and managing digital broiler chicken raising information.
Referring to fig. 1, a flowchart of steps of a method for managing storage of information of digital broiler raising according to an embodiment of the invention is shown, the method comprises the following steps:
S001, collecting all monitoring data of the broiler chicken raising process in the collection time period, and obtaining raising information of broiler chicken raising in the collection time period.
It should be noted that, in the conventional isolated forest algorithm, the raising information of broiler raising is taken as a data set, a plurality of sub-sample sets are randomly selected from the data set, each sub-sample set is used to construct an isolated tree, each sample of the sub-sample set is decided by selecting the dividing feature of each isolated tree from the sub-sample set, the decision result of each isolated tree on each sample is the tree height of the sample in the isolated tree, so that the difference between the sample which is decided out faster in the isolated tree, i.e. the higher the tree height value in the tree, and other samples in the sub-sample set where the sample is located is represented, and the target information in all raising information is extracted; however, conditions required for raising at different time stages are different due to time variation in the broiler raising process, and the conditions required for partial raising may change in trend with time variation, so that when the collection time of the raising information selected in the sub-sample set approaches to a time period, the raising information not in the time period generates errors due to larger interval of the collection time, and the decision result of the isolated tree constructed by using the sub-sample set is generated. Therefore, in order to solve the above-mentioned problems, the present embodiment provides a method for storing and managing digitized broiler raising information.
It should be further noted that, when the isolated forest model is constructed to screen the target information in the cultivation information, the objective of the embodiment is to eliminate the influence of the time characteristics of the cultivation information according to the time analysis of the cultivation information in the sub-sample set of each isolated tree, so as to solve the error problem caused by the time characteristics; therefore, firstly, the breeding information of broiler breeding needs to be collected; specifically, the period of collection of the cultivation information in this embodiment is the last year from the current collection time, every hour is an collection time, the environmental data is collected at each collection time by using a sensor based on the internet of things, the growth data and the feed management data of the broiler chickens at each collection time are obtained by manually sampling and recording the broiler chickens, the collected cultivation information comprises a plurality of monitoring categories, specifically, the quantity and proportion of each feed in the mixed feed, the feeding time, the feeding amount, the weight, the body temperature, the environmental temperature, the humidity, the ammonia concentration and the like of the broiler chickens, all the cultivation information is quantized and standardized, and the monitoring data of all the monitoring categories collected at each collection time are recorded as the cultivation information of each collection time, so as to obtain all the cultivation information of broiler chickens cultivated in the collection period.
Thus, the breeding information of broiler breeding is obtained.
S002, presetting isolated forest model parameters, obtaining a plurality of sub-sample sets according to the isolated forest model parameters, and constructing a broiler cultivation information isolated forest model according to the sub-sample sets.
It should be noted that, all the breeding information of the broiler chicken breeding forms a sample set which needs to extract target data, parameters of the isolated forest model are preset, the parameters comprise the number of the isolated trees and the number of the breeding information in the sub-sample set of each isolated tree, the breeding information of the number of the breeding information in the sub-sample set is selected in a random selection mode to form a breeding information sub-sample set of each isolated tree, and the isolated forest model is constructed according to the preset isolated forest model parameters and the sub-sample set.
Specifically, parameters of the isolated forest model preset in this embodiment are specifically: number of isolated treesNumber of culture information in sub-sample set of isolated tree/>According to the number/>, of the culture information in the sub-sample set of each isolated treeObtaining maximum height per tree/>：/>Random selection/>, which is put back in all breeding information of broiler breedingThe culture information is selected randomly/>Secondary, per selection/>The individual cultivation information forms a sub-sample set of each isolated tree, and the sub-sample sets of all the isolated trees and the maximum tree height are used as inputs of the isolated forest model to construct a cultivation information isolated forest model for broiler cultivation.
Thus, the isolated forest model of the cultivation information of the broiler cultivation is obtained.
S003, according to the trend change of the monitoring data of each monitoring class in the sub-sample set of each isolated tree, the dividing characteristic of each isolated tree is obtained.
It should be noted that, when each isolated tree of the traditional isolated forest algorithm makes a decision on each cultivation information in its sub-sample set, one monitored class needs to be selected from all the monitored classes as the dividing feature of the isolated tree, and the existing method mainly calculates the information gain rate of each monitored class in the sub-sample set of the isolated tree, and selects the monitored class with the largest information gain rate in all the monitored classes as the dividing feature; however, when the monitoring data of the monitoring item has a trend change along with the change of the collection time, the more the monitoring item is affected by the change of the collection time, the less need to be selected when selecting as the division feature. Therefore, the embodiment obtains the dividing characteristics of each isolated tree of the culture information isolated forest model according to the influence degree of the collection time change of each monitored item in the sub-sample set of each isolated tree.
Specifically, for the isolated tree in the isolated forest model of the cultivation informationAll acquisition times of the breeding information are divided into/>Time level, the present embodiment provides/>To describe, statistics of isolated tree/>Acquisition time of each cultivation information in the sub-sample set of (1) and mapping to/>In the individual time levels, an orphan tree/>, is generatedThe horizontal axis of the time level histogram is the time level, and the vertical axis is the number of cultivation information of the isolated tree in each time level; according to the isolation tree/>The troughs of the temporal level histogram of the sub-sample set of (a) divide the temporal level histogram into several temporal level bins.
Further, an isolated tree is to be usedObtaining the isolated tree/>, by sequencing the monitoring data of all monitoring items in the sub-sample set of the culture information according to the collection time of the culture informationThe monitoring data sequence of each monitoring class of (3) will be an isolated tree/>The monitoring data sequence of each monitoring class is input into a Mann-Kendall trend test model to obtain an isolated tree/>The larger the absolute value of the test statistic is, the more the monitored data of the monitored class shows a significant trend; it should be noted that, the Mann-Kendall trend test model is a prior art, and this embodiment will not be repeated.
Further, the first step isIndividual monitor categories are in the isolation tree/>The test statistic in (a) is recorded as/>Will isolate the tree/>Middle/>The information gain ratio of each monitored class is recorded as/>It should be noted that, the calculation mode of the information gain rate is the existing known technology, and this embodiment is not repeated. Then isolate tree/>Middle/>The calculation mode of the correction information gain rate of each monitoring class is as follows:
Wherein, Is an isolated tree/>Middle/>Correction information gain ratio of each monitored class,/>Is an isolated treeMiddle/>Information gain ratio of individual monitoring items,/>For/>Individual monitor categories are in the isolation tree/>Test statistic in/>Is an isolated tree/>Number of middle time level intervals,/>Representing taking an absolute function. When/>Individual monitor categories are in the isolation tree/>Absolute value of test statistic in/>The greater the value, the description of the/>The monitoring data of each monitoring class show obvious trend change along with time in the sub-sample set, and when the culture information time span of the sub-sample set is the isolated tree/>Number of middle time level intervals/>When larger, the first/>The monitoring data of each monitored category will change greatly, so the confidence as a classification feature will be reduced, then the/>And the gain value of the correction information of each monitored class is reduced.
And similarly, calculating the corrected information gain rate of each monitored class in each isolated tree, and selecting the monitored class with the maximum corrected information gain rate value in each isolated tree as the dividing characteristic of each isolated tree.
So far, the dividing characteristics of each isolated tree in the culture information isolated forest model are obtained.
S004, making a decision according to the dividing characteristics of each isolated tree in the isolated forest model of the cultivation information to obtain the decision tree height of each cultivation information in each isolated tree, obtaining the time sequence confidence coefficient of each cultivation information in each isolated tree according to the collection time distribution of the cultivation information of the sub-sample set of each isolated tree, and correcting the decision tree height by using the time sequence confidence coefficient of each cultivation information in each isolated tree to obtain the actual tree height of each cultivation information in each isolated tree.
It should be noted that, using the partition feature of each isolated tree to make a decision on each cultivation information in the sub-sample set of each isolated tree, when the tree height of the isolated tree reaches the maximum height of each treeWhen the decision is finished, obtaining the decision tree height of each cultivation information in each isolated tree; the variation of part of the monitoring items of the cultivation information along with time can generate larger covariant effect, the variation can be influenced by the trend of the monitoring items corresponding to the dividing characteristics, the non-uniform selection effect can be also caused when the sub-sample sets of the isolated trees are randomly selected, the situation that when most of the cultivation information in the sub-sample sets of the isolated trees is gathered in the main time period, other cultivation information which is not in the main time period is caused to have larger difference from the cultivation information in the main time period is caused, further, the other cultivation information which is not in the main time period is caused to be prematurely decided, the tree height of the other cultivation information in the isolated forest is caused to have error with the tree height which is supposed to be decided, and the target score obtained by calculating the tree height of each cultivation information is caused to be larger than the target score which is supposed to be decided, namely the target information extraction has error.
It should be further noted that, in the sub-sample set of each isolated tree, the more closely the time distribution of the cultivation information, the more the cultivation information selected in the isolated tree belongs to a main time period, so that a confidence level needs to be given to the cultivation information in the sub-sample set, which is not in the main time period, as a penalty item, so that the effect of weakening the cultivation information tree heights determined as early as possible is achieved.
Specifically, an isolated tree is to be usedIs recorded as the first/>Individual time level intervals/>Then/>Individual time level intervals/>Middle/>The time sequence confidence of the individual cultivation information is calculated in the following way:
Wherein, For/>Individual time level intervals/>Middle/>Time sequence confidence of individual cultivation information,/>For/>Individual time level intervals/>Middle/>Acquisition time of individual cultivation information,/>For/>Average value of acquisition time in each time level interval,/>For/>Standard deviation of acquisition time in each time class interval,/>Representing a minimum function,/>An exponential function based on a natural constant is represented. When/>Individual time level intervals/>Middle/>The acquisition time of the individual cultivation information belongs to the/>Individual time level intervals/>When the main range of (2) is then considered to be/>Individual time level intervals/>Middle/>The individual cultivation information is in isolated tree/>The culture information belonging to the main body time period, namely more other culture information belonging to the same main body time period in decision making, does not cause the/>Individual farming information is determined prematurely because of the large time interval from other farming information. In this embodiment, the acquisition time distribution state of each time-level interval is fitted to a normal distribution, so that the mean and standard deviation are used to construct the main time period of each time-level interval, and the main time period is the/>Individual time level intervals/>Middle/>The individual cultivation information is in the main body time periodInner time, thenIndividual time level intervals/>Middle/>The time sequence confidence of the individual cultivation information is recorded as 1; when/>Individual time level intervals/>Middle/>When the individual cultivation information is outside the main body time period, the larger the time difference from the main body time period is, the description of the/>Individual time level intervals/>Middle/>The individual breeding information may be decided prematurely, so the smaller the value of its time series confidence.
And similarly, calculating the time sequence confidence coefficient of each cultivation information in each isolated tree in the cultivation information isolated forest model.
And correcting the decision tree height of each cultivation information in each isolated tree by using the time sequence confidence of each cultivation information in each isolated tree to obtain the actual tree height of each cultivation information in each isolated tree.
Specifically, will beThe individual cultivation information is in isolated tree/>The timing confidence in (1) is noted as/>Will/>The individual cultivation information is in isolated tree/>The decision tree height in (1) is denoted/>Then/>The individual cultivation information is in isolated tree/>The actual tree height is calculated by the following steps:
Wherein, For/>The individual cultivation information is in isolated tree/>In actual tree height,/>For/>The individual cultivation information is in isolated tree/>In decision tree high,/>For/>The individual cultivation information is in isolated tree/>Timing confidence in (c).
And similarly, correcting the decision tree height of each cultivation information in each isolated tree by using the time sequence confidence of each cultivation information in each isolated tree to obtain the actual tree height of each cultivation information in each isolated tree.
S005, obtaining the target score of each cultivation information according to the actual tree height of each cultivation information in all the isolated trees of the cultivation information isolated forest model, and further obtaining the target information in all the cultivation information.
Counting the actual tree height of each cultivation information in each isolated tree in the cultivation information isolated forest model, calculating the average actual tree height of each cultivation information, and calculating the target score of each cultivation information according to the average actual tree height; it should be noted that, calculating the target score by using the isolated forest model is a known technique, and the embodiment will not be repeated in detail; constructing a common data memory and a target data memory in a digital broiler raising information management system, and presetting a target threshold valueThis example shows/>To describe, when the target score of the cultivation information is greater than or equal to the target threshold/>When the breeding information is marked as target information, the detection data of all monitoring items in the target information are stored in a target data storage, and when the target score of the breeding information is smaller than a target threshold/>And when the cultivation information is recorded as common information, the detection data of all monitoring categories in the common information is stored in a common data memory, so that classified storage of the broiler cultivation information is realized, only the cultivation information in a target data memory is analyzed when the cultivation information is analyzed to coordinate cultivation management, and the running load of the digital broiler cultivation information management based on big data is reduced.
The following examples were usedThe model only represents that the result output by the negative correlation and constraint model is in/>Within the interval, wherein/>For the input of the model, the implementation can be replaced by other models with the same purpose, and the embodiment is only to/>The model is described as an example, and is not particularly limited.
Another embodiment of the present invention provides a digitized broiler raising information storage management system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the above method steps S001 to S005 when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (5)
1. The digital broiler raising information storage management method is characterized by comprising the following steps of:
collecting all monitoring data of the broiler chicken raising process, and obtaining raising information of all collecting time;
Obtaining a sub-sample set of a plurality of isolated trees according to preset isolated forest model parameters, wherein the plurality of isolated trees form a cultivation information isolated forest model for broiler cultivation; obtaining the dividing characteristics of each isolated tree according to the monitoring data trend of each monitored class in the sub-sample set of each isolated tree; making a decision on a sub-sample set of each isolated tree according to the dividing characteristics of each isolated tree to obtain the decision tree height of each cultivation information; acquiring time sequence confidence coefficient of each cultivation information in the sub-sample set of each isolated tree according to the collection time distribution of the cultivation information in the sub-sample set of each isolated tree; correcting the decision tree height according to the time sequence confidence of each cultivation information to obtain the actual tree height of each cultivation information in each isolated tree;
Obtaining a target score of each cultivation information according to the actual tree height of each cultivation information in all the isolated trees; obtaining target information and common information according to the target score of each cultivation information, and respectively storing the target information and the common information;
The obtaining the dividing feature of each isolated tree according to the monitoring data trend of each monitored class in the sub-sample set of each isolated tree comprises the following steps:
Calculating the corrected information gain rate of each monitored class in each isolated tree, and selecting the monitored class with the maximum corrected information gain rate value in each isolated tree as the dividing characteristic of each isolated tree;
the specific acquisition mode of the corrected information gain rate comprises the following steps:
For the isolated tree in the culture information isolated forest model Will/>Individual monitor categories are in the isolation tree/>The test statistic in (a) is recorded as/>Will isolate the tree/>Middle/>The information gain ratio of each monitored class is recorded as/>Isolation tree/>Middle/>Corrected information gain Rate of individual monitoring items/>The calculation mode of (a) is as follows:
Wherein, Is an isolated tree/>Number of middle time level intervals,/>Representing an absolute value function;
The specific acquisition mode of the time level interval comprises the following steps:
all acquisition time of the breeding information is divided into Time-level, statistics of isolated tree/>Acquisition time of each cultivation information in the sub-sample set of (1) and mapping to/>In the individual time levels, an orphan tree/>, is generatedThe horizontal axis of the time level histogram is the time level, and the vertical axis is the number of cultivation information of the isolated tree in each time level; according to the isolation tree/>Dividing the time-level histogram into a plurality of time-level bins by the valley value of the time-level histogram in the sub-sample set;
The step of obtaining the decision tree height of each cultivation information by deciding the sub-sample set of each isolated tree according to the dividing characteristics of each isolated tree comprises the following steps:
For the isolated tree in the culture information isolated forest model Will isolate the tree/>Is recorded as the first/>Individual time level intervals/>First/>Individual time level intervals/>Middle/>Time sequence confidence of individual cultivation information/>The calculation mode of (a) is as follows:
Wherein, For/>Individual time level intervals/>Middle/>Acquisition time of individual cultivation information,/>For/>Average value of acquisition time in each time level interval,/>For/>Standard deviation of acquisition time in each time class interval,/>Representing absolute value,/>Representing a minimum function,/>An exponential function that is based on a natural constant;
the step of correcting the decision tree height according to the time sequence confidence of each cultivation information to obtain the actual tree height of each cultivation information in each isolated tree comprises the following steps:
For the isolated tree in the culture information isolated forest model Will/>The individual cultivation information is in isolated tree/>The timing confidence in (1) is noted as/>Will/>The individual cultivation information is in isolated tree/>The decision tree height in (1) is denoted/>First/>The individual cultivation information is in isolated tree/>Actual tree height in/>The calculation mode of (a) is as follows:
Wherein, For/>The individual cultivation information is in isolated tree/>In decision tree high,/>For/>The individual cultivation information is in an isolated treeTiming confidence in (c).
2. The method for storing and managing digitized broiler raising information according to claim 1, wherein the specific obtaining mode of the test statistic comprises:
Will isolate the tree The monitoring data of all monitoring items in the sub-sample set of (1) are ordered according to the collection time of the culture information to obtain an isolated tree/>The monitoring data sequence of each monitoring class of (3) will be an isolated tree/>The monitoring data sequence of each monitoring class is input into a Mann-Kendall trend test model to obtain an isolated tree/>Test statistics for each monitored category of (3).
3. The method for managing storage of digitized broiler raising information as set forth in claim 1, wherein said obtaining decision tree height for each raising information comprises:
And using the dividing characteristics of each isolated tree to make a decision on each cultivation information in the sub-sample set of each isolated tree, and ending the decision when the tree height of each isolated tree reaches the maximum height of each tree to obtain the decision tree height of each cultivation information in each isolated tree.
4. The method for managing storage of digitized broiler raising information of claim 1, wherein said obtaining target information and general information according to the target score of each raising information comprises:
Presetting a target threshold When the target score of the cultivation information is greater than or equal to the target threshold/>When the information is recorded as target information;
When the target score of the cultivation information is smaller than the target threshold value At this time, the cultivation information is recorded as the general information.
5. A digitized broiler raising information storage management system comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the steps of a digitized broiler raising information storage management method according to any one of claims 1 to 4 are implemented when the processor executes the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410216870.6A CN117786543B (en) | 2024-02-28 | 2024-02-28 | Digital broiler raising information storage management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410216870.6A CN117786543B (en) | 2024-02-28 | 2024-02-28 | Digital broiler raising information storage management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117786543A CN117786543A (en) | 2024-03-29 |
| CN117786543B true CN117786543B (en) | 2024-05-10 |
Family
ID=90396670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410216870.6A Active CN117786543B (en) | 2024-02-28 | 2024-02-28 | Digital broiler raising information storage management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786543B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118114164B (en) * | 2024-04-30 | 2024-06-25 | 济宁市金桥煤矿 | Real-time monitoring system for coal mine electromechanical operation fault |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109669030A (en) * | 2018-12-28 | 2019-04-23 | 佛山科学技术学院 | A kind of industrial injecting products defect diagnostic method based on decision tree |
| CN109859029A (en) * | 2019-01-04 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Abnormal application detection method, device, computer equipment and storage medium |
| CN113159244A (en) * | 2021-04-09 | 2021-07-23 | 西安交通大学 | Poultry breeding management system based on Internet of things |
| CN116340746A (en) * | 2023-03-28 | 2023-06-27 | 哈尔滨理工大学 | Feature selection method based on random forest improvement |
| CN117011694A (en) * | 2023-04-24 | 2023-11-07 | 南京林业大学 | Forest tree growth parameter prediction method based on cascade circulation network |
| CN117540304A (en) * | 2024-01-10 | 2024-02-09 | 山东盈和新材料科技有限公司 | Efficient processing method for adhesive production data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4254623B2 (en) * | 2004-06-09 | 2009-04-15 | 日本電気株式会社 | Topic analysis method, apparatus thereof, and program |
-
2024
- 2024-02-28 CN CN202410216870.6A patent/CN117786543B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109669030A (en) * | 2018-12-28 | 2019-04-23 | 佛山科学技术学院 | A kind of industrial injecting products defect diagnostic method based on decision tree |
| CN109859029A (en) * | 2019-01-04 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Abnormal application detection method, device, computer equipment and storage medium |
| CN113159244A (en) * | 2021-04-09 | 2021-07-23 | 西安交通大学 | Poultry breeding management system based on Internet of things |
| CN116340746A (en) * | 2023-03-28 | 2023-06-27 | 哈尔滨理工大学 | Feature selection method based on random forest improvement |
| CN117011694A (en) * | 2023-04-24 | 2023-11-07 | 南京林业大学 | Forest tree growth parameter prediction method based on cascade circulation network |
| CN117540304A (en) * | 2024-01-10 | 2024-02-09 | 山东盈和新材料科技有限公司 | Efficient processing method for adhesive production data |
Non-Patent Citations (1)
| Title |
|---|
| 人类活动对岔巴沟流域洪水过程影响研究;莫淑红;巩瑶;李洁;沈冰;;应用基础与工程科学学报;20190615(第03期);第29-45页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117786543A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117786543B (en) | Digital broiler raising information storage management method and system | |
| Pukkala et al. | A spatial yield model for optimizing the thinning regime of mixed stands of Pinus sylvestris and Picea abies | |
| CN108346142B (en) | Plant growth state identification method based on plant illumination image | |
| Magrach et al. | Plant–pollinator networks in semi‐natural grasslands are resistant to the loss of pollinators during blooming of mass‐flowering crops | |
| Nyombi et al. | Allometric growth relationships of East Africa highland bananas (Musa AAA‐EAHB) cv. Kisansa and Mbwazirume | |
| CN112906298A (en) | Blueberry yield prediction method based on machine learning | |
| CN113192026A (en) | Walnut maturity detection and prediction method based on visible light image | |
| CN117787510B (en) | Optimization method of pesticide residue monitoring process based on time sequence predictive analysis | |
| CN117455062A (en) | Crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
| CN108427862B (en) | Nondestructive measurement method for biomass of multi-variety cotton in whole growth period based on image analysis | |
| CN114782837B (en) | Plant estimation method, plant estimation device, electronic equipment and storage medium | |
| CN114898000A (en) | Red date mature picking analysis method, system and terminal considering environmental factors | |
| CN117911957B (en) | Prevention and control monitoring system and method for ornamental sunflower diseases and insect pests | |
| CN117745148B (en) | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system | |
| Cole | The ecological setting of social evolution: the demography of ant populations | |
| CN117760530A (en) | Wireless dynamic self-adaptive weighing verification method suitable for poultry cultivation | |
| CN115809242A (en) | Meteorological data storage method and system | |
| CN114372611A (en) | Water resource optimal allocation method and device | |
| CN113298280A (en) | Deep mining and intelligent decision algorithm for agricultural breeding big data | |
| CN114931230B (en) | Process execution index analysis characterization method for tobacco leaf baking process | |
| Lindh et al. | Evolution of reproductive phenology in annual social insects competing for floral resources | |
| Zhang et al. | Automatic Weighing and Analysis System for Broiler Chickens Based on Mean-Shift Clustering Analysis | |
| Turley et al. | Detecting bimodality in plant size distributions and its significance for stand development and competition | |
| Kim et al. | Evaluation of a first-event sampling model for monitoring cabbage pests | |
| CN116362416A (en) | Regional longan annual output prediction method and device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |