CN115859209B - Livestock industry poultry breeding abnormality identification method based on feed consumption data - Google Patents
Livestock industry poultry breeding abnormality identification method based on feed consumption data Download PDFInfo
- Publication number
- CN115859209B CN115859209B CN202310077065.5A CN202310077065A CN115859209B CN 115859209 B CN115859209 B CN 115859209B CN 202310077065 A CN202310077065 A CN 202310077065A CN 115859209 B CN115859209 B CN 115859209B
- Authority
- CN
- China
- Prior art keywords
- data
- period
- feed consumption
- window
- acquiring
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The invention discloses a livestock industry poultry raising abnormality identification method based on feed consumption data, which relates to the technical field of data processing and comprises the steps of acquiring the feed consumption data of a period of time before the current moment in the poultry raising process; determining a target period, and dividing feed consumption data of a time period into a plurality of period data according to the target period; acquiring a predicted value of feed consumption of each period of data; acquiring a window parameter value of each period of data; determining a window size of each period of data; obtaining an abnormal factor of each period of data, and obtaining current period of poultry cultivation data; acquiring an influence value of the period data corresponding to each window on the last period data by the period data abnormality factor; obtaining the abnormality degree of the last period data; the invention solves the technical problem of large deviation of the obtained abnormal degree caused by using a fixed window to process abnormal data when carrying out data abnormal analysis in the related technology.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a livestock industry poultry farming abnormal identification method based on feed consumption data.
Background
The poultry farming industry is a basic industry of livestock industry in China, is a main pillar industry of rural economy in China, and is mainly used for raising poultry, such as chicken, duck, goose and other animals. Along with the development of automatic intelligent technology, various processes in poultry farming can realize automatic control, such as feeding of feed, and in general, feeding of feed is determined by the number of poultry and the like, but the feed fed generally remains, so that consumption data of the feed can be judged. In the poultry breeding process, whether the feed consumption data is abnormal or not can be judged by analyzing the abnormal degree of the feed consumption data, when the feed consumption data is abnormal, the poultry breeding condition is checked, abnormal influence is eliminated in time, for example, when the poultry is ill, the prevention and the treatment are carried out in time.
When the prior art is used for carrying out anomaly analysis on feed consumption data in the poultry raising process, the size of a window is firstly required to be calculated, and a window with a fixed size is determined according to the data to be processed when the prior art is used for carrying out anomaly analysis, so that in order to meet the accuracy of a calculation result, a larger window is often selected for analysis, and for the data with smaller anomaly degree in the data to be processed, a large amount of calculation redundancy is caused when the fixed window is used for analysis because an oversized calculation window is not required, and the greater the difference of the anomaly degree between the data is, the greater the window calculation redundancy is; however, in practice, when there is an abnormality in the window calculation data, the degree of abnormality in the calculated data is affected, and the obtained degree of abnormality is greatly deviated.
Disclosure of Invention
In order to solve the technical problem of large deviation of obtained abnormal degree caused by using a fixed window to process abnormal data in the prior art, the invention provides an animal husbandry poultry farming abnormal recognition method based on feed consumption data, which comprises the steps of determining a target period by acquiring the abnormality of the feed consumption data in a past time period, and dividing the feed consumption data in the past time period into a plurality of period data according to the target period; acquiring the window size of each period of data; acquiring current period data, and acquiring an influence value of the current period data by the period data corresponding to each window; acquiring the abnormality degree of the current period data according to the abnormality factor of the current period data and the influence value of the current period data by the period data corresponding to each window, and judging whether the current period data is abnormal or not according to the abnormality degree; in view of this, the present invention is achieved by the following technical means.
An animal husbandry poultry farming anomaly identification method based on feed consumption data comprises the following steps:
acquiring feed consumption data in a period of time before the current moment in the poultry raising process;
determining a target period according to the feed consumption data in the time period, and dividing the feed consumption data in the time period into a plurality of period data according to the target period;
acquiring the feed consumption corresponding to each period of data, and acquiring window parameter values of each period of data according to the feed consumption of each period of data and the predicted value of the feed consumption of the period of data;
setting a preset window value, wherein the size of the preset window value at least can contain all data in one period of data; acquiring a preset window parameter value of each period data by using the window parameter value of each period data and the window parameter values of adjacent periods; acquiring the window value of each period data according to the preset window parameter value and the preset window value of each period data;
acquiring feed consumption data in the last period data in the feed consumption data; acquiring all windows in which the last period data is located, and obtaining an influence value of the last period data by the period data abnormality factor corresponding to each window according to the abnormality factor of the period data corresponding to each window in all windows in which the last period data is located and the distance from the last period data to all windows in which the last period data is located;
acquiring an anomaly factor of the last period data; acquiring the abnormality degree of the last period data according to the abnormality factor of the last period data and the influence value of the last period data by the period data abnormality factor corresponding to each window; judging whether the last period data is abnormal period data or not according to the abnormality degree of the last period data.
Further, in the process of judging whether the last period data is abnormal period data according to the abnormality degree of the last period data, setting an abnormality degree threshold, and when the abnormality degree of the last period data is greater than the abnormality degree threshold, determining that the last period data is abnormal period data.
Further, the abnormality degree threshold is 0.8, and when the abnormality degree of the last period data is greater than 0.8, the last period data is abnormal period data.
Further, the process of determining the target period according to the feed consumption data in the time period is as follows:
dividing the feed consumption in the time period into a plurality of period data by taking 1 day as a period, and acquiring a first difference degree of the feed consumption between each period data; increasing the period, dividing the feed consumption in the time period into a plurality of period data by taking two days as the period, and acquiring a second difference degree of the feed consumption between each period; continuously increasing the period, dividing the feed consumption number in the time period into a plurality of periods by using the period, and obtaining the difference degree of the feed consumption amount between the data of each period; and acquiring a target period of the feed consumption data in the time period according to the difference degree.
Further, after dividing the feed consumption in the period of time into a plurality of period data in 1 day period, the first degree of difference in feed consumption between each period data is determined by the following formula:
in the method, in the process of the invention,
dividing the feed consumption data in the period of time into a plurality of period data by taking 1 day as a period, and then dividing the period data into a first difference degree of feed consumption between each period data;
dividing the feed consumption data in the period of time into the number of periodic data with 1 day as a period;
to divide the feed consumption data in the period of time into a plurality of period data with 1 day as period
Feed consumption of the individual cycle data;
after dividing the feed consumption data in the period into a plurality of periods with 1 day as a period
Feed consumption of +1 cycle data,
to divide the feed consumption data in the period into a plurality of period data in a period of 1 day.
Further, the increase period is increased up to 7 days.
Further, the window parameter value of the periodic data is determined by:
in the method, in the process of the invention,
is the first
Window parameter values for the individual period data;
a period length representing a period of time;
is the first
Feed consumption of the individual cycle data;
is the first
A predicted value of the feed consumption of the individual cycle data;
is the first
Feed consumption per cycle data
Differences in feed consumption for each cycle;
is the first
Of data of one cycle
The time in the range of the time period,
indicating the size of the range.
Further, the preset data window parameter value of each period data is the maximum value of window parameter values of the period data corresponding to a plurality of windows where each period data is located; the preset window value is 15.
Further, the window value of each period data is determined by the following formula:
in the method, in the process of the invention,
is the first
Window values of the individual period data;
is the first
Window parameter values for the individual period data;
is the first
A preset window value of the periodic data;
is a preset window parameter value.
Further, the degree of abnormality of the last period data is obtained by summing the abnormality factor of the last period data and the influence value of the abnormality factor of the period data corresponding to each window.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for identifying abnormal livestock raising based on feed consumption data, which comprises the steps of obtaining feed consumption data in a period of time before the current moment in the poultry raising process, and determining a target period according to the feed consumption data in the period of time before the current moment; dividing the feed consumption data in the time period into a plurality of period data according to the target period, and obtaining the optimal period number of the feed consumption data in the time period; acquiring feed consumption corresponding to each period of data, and acquiring a predicted value of the feed consumption of each period of data; acquiring window parameter values of each period data according to the feed consumption of each period data and the predicted value of the feed consumption; acquiring a preset window parameter value of each period of data, and setting the preset window value; acquiring a window value of each period data according to a preset window parameter value and a preset window value of each period data, and determining the window size of each period data according to the window value of each period data; thus, an optimal window size for each period of data may be determined; further, acquiring an abnormal factor of each period of data, and acquiring current period of poultry farming; acquiring a plurality of windows in which current period data are located; acquiring an influence value of the current periodic data by the periodic data abnormal factor corresponding to each window according to the abnormal factor of the periodic data corresponding to each window and the distance from the current periodic data to the periodic data corresponding to each window; further, obtaining an anomaly factor of the current period data; acquiring the abnormality degree of the current period data according to the abnormality factor of the current period data and the influence value of the current period data by the period data abnormality factor corresponding to each window; judging whether the current period data is abnormal period data or not according to the abnormality degree of the current period data; when the current period data is abnormal, checking the poultry raising condition in time, and taking countermeasures; the invention solves the technical problem of large deviation of the obtained abnormal degree caused by using a fixed window to process abnormal data when carrying out data abnormal analysis in the related technology.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flow chart of a method for identifying abnormal poultry farming according to the present embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method for identifying abnormal livestock poultry farming based on feed consumption data provided in this embodiment, as shown in fig. 1, includes:
s101, acquiring feed consumption data of poultry in a period before the current moment in the breeding process, and dividing the feed consumption data in the period into a plurality of period data according to the abnormality of the feed consumption data in the period;
in this embodiment, the feed data in the poultry farming reflects the feeding state of the poultry, so the feed consumption data every 1 day is recorded during the poultry farming process, and then the feed consumption data in a period of time before the current moment is used as the original data for identifying the abnormal poultry farming; in the abnormality analysis of feed consumption data, abnormality of data is mainly expressed as a difference between data, a degree of float of data, and a degree of interaction between data; therefore, in this embodiment, according to the characteristics of the data itself, the size of the data period and the size of the calculation window involved in the anomaly analysis are determined, and then anomalies of the feed consumption data in the current period are obtained;
the feed consumption amount in the poultry cultivation process is related to the number of the poultry, and a plurality of time points of buying and selling exist in the poultry cultivation process, so in order to accurately obtain the relationship between feed consumption data, the data of the time period when the poultry is not buying and selling needs to be analyzed, so in the embodiment, the time points when the poultry is buying and selling need to be obtained firstly, and the raw data of each feed consumption data analysis is the feed consumption data between two adjacent time nodes of buying and selling;
dividing the feed consumption data into a plurality of period data according to the difference degree of the feed consumption data in the time period, namely dividing the feed consumption data in the time period into a plurality of period data by taking 1 day as a period, and acquiring a first difference degree of the feed consumption amount between each period data; the first degree of difference in feed consumption between each cycle of data is determined by:
in the method, in the process of the invention,
a first degree of difference in the amount of feed consumed between each cycle data after dividing the feed consumption data into a plurality of cycle data in a cycle of 1 day;
dividing feed consumption data into the number of periodic data with 1 day as period;
to divide the feed consumption data into a plurality of period data with 1 day as period
Feed consumption of the individual cycle data;
to divide the feed consumption data into a plurality of cycles at 1 day period
Feed consumption of +1 cycle data,
feed consumption after dividing feed consumption data into a plurality of period data in a period of 1 day;
the period range is enlarged, the feed consumption data in the time period are divided into a plurality of period data by taking two days as a period, and a second difference degree of the feed consumption amount between each period data is obtained; continuously increasing the period range, and acquiring each difference degree corresponding to each period range;
acquiring an optimal period of feed consumption data in a time period according to a plurality of different degrees, and dividing the time period into a plurality of periods according to the optimal period; taking the maximum difference degree as a target difference degree, and taking a period range corresponding to the target difference degree as an optimal period of the feed consumption data in the time period; dividing feed consumption data in a time period into a plurality of periods according to the optimal period;
in this embodiment, in the process of obtaining a plurality of different degrees of the feed consumption, the length range of the period is set to 1 to 7; namely, only obtaining a first difference degree of the feed consumption to a seventh difference degree of the feed consumption, and selecting the maximum value of the difference degrees from the first difference degree to the seventh difference degree of the feed consumption as a target difference degree; taking the period corresponding to the target difference degree as an optimal period, and dividing the time period into a plurality of periods according to the optimal period;
s102, acquiring the feed consumption of each period of data and the predicted value of the feed consumption, wherein the process of acquiring the predicted value of the feed consumption is to acquire the predicted value of the feed consumption by using a BP neural network, input other data in the range of length 2f around the jth period into the BP neural network, and output
A predicted value of the feed consumption in the j-th cycle; the value of f is set to 10 in this embodiment; acquiring window parameter values of the periodic data according to the feed consumption of each periodic data and the predicted value of the feed consumption; the window parameter value of the periodic data is determined by:
in the method, in the process of the invention,
is the first
Window parameter values for the individual period data;
a period length representing a period of time;
is the first
Feed consumption of the individual cycle data;
is the first
A predicted value of the feed consumption of the individual cycle data;
is the first
Feed consumption per cycle data
Differences in feed consumption for each cycle;
is the first
Of data of one cycle
The time in days of the range,
representing the size of the range;
represent the first
The average of the feed consumption differences around each cycle;
the larger the first
The less stable the feed consumption around each cycle;
acquiring a preset data window parameter value and a preset window value of each period data in sequence, and acquiring the window value of each period data according to the preset data window parameter value and the preset window value of each period data and the window parameter value of each period data; the window value of each period data is determined by:
in the method, in the process of the invention,
is the first
Window values of the individual period data;
is the first
Window parameter values for the individual period data;
is a preset window value;
a preset window parameter value;
in this embodiment, the preset data window parameter value of each period data is the maximum value of the window parameter values of the period data corresponding to the windows where each period data is located; the size of the preset window value can at least contain all data in one period of data, in this embodiment, the preset window value is set to 15 according to the specific implementation condition, and the implementer can set other values to be the preset window value according to the specific implementation condition; the window value obtained in the present embodiment can determine the size of the periodic data window, forIn the first place
According to the first period data
The window value of the periodic data may determine the first
Window size of the periodic data is
The method comprises the steps of carrying out a first treatment on the surface of the The size of the window of each period of data may be determined in turn;
s103, acquiring an abnormal factor of each period of data, and acquiring current period of poultry farming; the current period data is the last period data in the plurality of period data; acquiring a plurality of windows in which current period data are located; acquiring an influence value of the current periodic data by the periodic data abnormal factor corresponding to each window according to the abnormal factor of the periodic data corresponding to each window and the distance from the current periodic data to the periodic data corresponding to each window;
in the present embodiment, use is made of
After the algorithm inputs the feed consumption of each period data, the abnormality factor of each period data is output
The method comprises the steps of carrying out a first treatment on the surface of the The influence value of the current period data by the period data abnormality factor corresponding to each window is determined by the following formula:
in the method, in the process of the invention,
is subject to the first period data
The influence value of the periodic data anomaly factor corresponding to each window;
an anomaly factor for the current period data;
for the current period data and the first
A distance between the periodic data;
is the first
Feed consumption of the individual cycle data;
is the first
Feed predictors for each cycle of data; in the middle of
The larger the first
The greater the influence of the cycle data on the abnormality degree of the current cycle data, wherein the cycle data is obtained by
Will be
The value of (1) is converted to [0,1 ]]A section;
the sum of the influence values of the period data abnormality factors corresponding to each window on the current period data is determined by the following formula:
in the method, in the process of the invention,
the current periodic data is subjected to the sum of the influence values of the periodic data abnormality factors corresponding to each window;
is subject to the first period data
The influence value of the periodic data anomaly factor corresponding to each window;
the total number of windows in which the current period is located;
obtaining the abnormality degree of the current period data according to the abnormality factor of the current period and the sum of the influence values of the period data abnormality factors corresponding to each window on the current period data; the degree of abnormality of the current period data is determined by:
in the method, in the process of the invention,
the degree of abnormality of the current period data;
an anomaly factor for the current period data;
the sum of the influence values of the period data abnormal factors corresponding to each window on the current period data is given;
in this embodiment, the current period is to acquire feed consumption data of poultry farming in a time period of one target period backward with the current time in step S101 as a start time;
s104, setting an abnormality degree threshold, and judging whether the current period data is abnormal or not according to the abnormality degree threshold and the abnormality degree of the current period data; when the current period data is abnormal, checking the poultry raising condition, and timely taking countermeasures according to the checking condition;
in this embodiment, the threshold value of the degree of abnormality is set to 0.8 according to the specific implementation condition; when the abnormality degree of the current cycle number is greater than 0.8, the current cycle data is abnormal cycle data; and then manually checking the poultry cultivation condition in the period corresponding to the current period data, timely taking countermeasures when the abnormal cultivation condition occurs, and properly changing the feed feeding amount according to the feed consumption condition and timely taking preventive and therapeutic measures when the abnormal cultivation condition is dead or ill.
In summary, the embodiment provides a method for identifying abnormal livestock farming poultry farming based on feed consumption data, which includes obtaining feed consumption data in a period of time before a current moment in a poultry farming process; determining a target period according to the feed consumption data in the time period, and dividing the feed consumption data in the time period into a plurality of period data according to the target period; acquiring the feed consumption corresponding to each period of data, and acquiring a predicted value of the feed consumption of each period of data; acquiring window parameter values of each period data according to the feed consumption of each period data and the predicted value of the feed consumption; acquiring a preset window parameter value of each period of data, and setting the preset window value; acquiring a window value of each period data according to a preset window parameter value and a preset window value of each period data, and determining the window size of each period data according to the window value of each period data; acquiring an abnormal factor of each period of data; acquiring feed consumption data of the current period in the poultry raising process; acquiring a plurality of windows in which the current period data is located, and acquiring an influence value of the current period data by the period data abnormality factors corresponding to each window according to the abnormality factors of the period data corresponding to the windows and the distance between the current period data and the period data corresponding to each window; acquiring an abnormal factor of the current period data; acquiring the abnormality degree of the current period data according to the abnormality factor of the current period data and the influence value of the current period data by the period data abnormality factor corresponding to each window; judging whether the current period data is abnormal period data or not according to the abnormality degree of the current period data; the embodiment solves the technical problem that in the related art, the obtained abnormal degree deviation is large due to the fact that the fixed window is used for processing abnormal data when the data abnormal analysis is carried out.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The livestock industry poultry farming abnormal identification method based on the feed consumption data is characterized by comprising the following steps of:
acquiring feed consumption data in a period of time before the current moment in the poultry raising process;
determining a target period according to the feed consumption data in the time period, and dividing the feed consumption data in the time period into a plurality of period data according to the target period;
acquiring the feed consumption corresponding to each period of data, and acquiring window parameter values of each period of data according to the feed consumption of each period of data and the predicted value of the feed consumption of the period of data;
the window parameter value of the periodic data is determined by:
in the method, in the process of the invention,
is->
Window parameter values for the individual period data; />
A period length representing a period of time; />
Is->
Feed consumption of the individual cycle data; />
Is->
A predicted value of the feed consumption of the individual cycle data; />
Is->
Feed consumption and +.>
Differences in feed consumption for each cycle; />
Is->
+.>
Time within range, +_>
Representing the size of the range;
setting a preset window value, wherein the size of the preset window value at least can contain all data in one period of data; acquiring a preset window parameter value of each period data by using the window parameter value of each period data and the window parameter values of adjacent periods; acquiring the window value of each period data according to the preset window parameter value and the preset window value of each period data;
the preset data window parameter value of each period data is the maximum value of window parameter values of the period data corresponding to a plurality of windows where each period data is located; the preset window value is 15;
the window value of each period data is determined by the following formula:
in the method, in the process of the invention,
is->
Window values of the individual period data; />
Is->
Window parameter values for the individual period data; />
Is->
A preset window value of the periodic data; />
A preset window parameter value;
acquiring feed consumption data in the last period data in the feed consumption data; acquiring all windows in which the last period data is located, and obtaining an influence value of the last period data by the period data abnormality factor corresponding to each window according to the abnormality factor of the period data corresponding to each window in all windows in which the last period data is located and the distance from the last period data to all windows in which the last period data is located;
acquiring an anomaly factor of the last period data; acquiring the abnormality degree of the last period data according to the abnormality factor of the last period data and the influence value of the last period data by the period data abnormality factor corresponding to each window; judging whether the last period data is abnormal period data or not according to the abnormality degree of the last period data.
2. The method for identifying abnormal livestock raising based on feed consumption data according to claim 1, wherein in the process of judging whether the last period data is abnormal period data according to the abnormality degree of the last period data, an abnormality degree threshold is set, and when the abnormality degree of the last period data is greater than the abnormality degree threshold, the last period data is abnormal period data.
3. A method of identifying livestock farming anomalies based on feed consumption data as set forth in claim 2, wherein the threshold level of anomalies is 0.8 and the last cycle data is anomalous cycle data when the level of anomalies in the last cycle data is greater than 0.8.
4. A method for identifying abnormal livestock farming based on feed consumption data according to claim 1, wherein the process of determining a target period from the feed consumption data during the period of time is:
dividing the feed consumption in the time period into a plurality of period data by taking 1 day as a period, and acquiring a first difference degree of the feed consumption between each period data; increasing the period, dividing the feed consumption in the time period into a plurality of period data by taking two days as the period, and acquiring a second difference degree of the feed consumption between each period; continuously increasing the period, dividing the feed consumption number in the time period into a plurality of periods by using the period, and obtaining the difference degree of the feed consumption amount between the data of each period; and acquiring a target period of the feed consumption data in the time period according to the difference degree.
5. A method for identifying abnormal livestock farming based on feed consumption data according to claim 4, wherein after dividing the feed consumption in the period of time into a plurality of period data on a 1 day period, a first degree of difference in feed consumption between each period data is determined by:
in the method, in the process of the invention,
dividing the feed consumption data in the period of time into a plurality of period data by taking 1 day as a period, and then dividing the period data into a first difference degree of feed consumption between each period data; />
Dividing the feed consumption data in the period of time into the number of periodic data with 1 day as a period; />
After the feed consumption data in the period of time is set to a plurality of period data on a 1 day period>
Feed consumption of the individual cycle data; />
After dividing the feed consumption data in the period into a plurality of periods with 1 day as a period +.>
Feed consumption of +1 cycle data, +.>
To divide the feed consumption data in the period into a plurality of period data in a period of 1 day.
6. A method of identifying abnormal livestock farming based on feed consumption data as claimed in claim 5 wherein said period of increase is up to 7 days.
7. A method for identifying abnormal livestock farming based on feed consumption data according to claim 1, wherein the degree of abnormality of the last period data is obtained by summing the abnormality factor of the last period data with the influence value of the last period data by the period data abnormality factor corresponding to each window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077065.5A CN115859209B (en) | 2023-02-08 | 2023-02-08 | Livestock industry poultry breeding abnormality identification method based on feed consumption data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077065.5A CN115859209B (en) | 2023-02-08 | 2023-02-08 | Livestock industry poultry breeding abnormality identification method based on feed consumption data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115859209A CN115859209A (en) | 2023-03-28 |
| CN115859209B true CN115859209B (en) | 2023-05-16 |
Family
ID=85657716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310077065.5A Active CN115859209B (en) | 2023-02-08 | 2023-02-08 | Livestock industry poultry breeding abnormality identification method based on feed consumption data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859209B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980874A (en) * | 2017-03-13 | 2017-07-25 | 南京邮电大学 | A kind of multi-time Scales dimension data fusion method towards distribution big data |
| CN115221471A (en) * | 2022-07-18 | 2022-10-21 | 山东云天安全技术有限公司 | Abnormal data identification method and device, storage medium and computer equipment |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7702401B2 (en) * | 2007-09-05 | 2010-04-20 | Fisher-Rosemount Systems, Inc. | System for preserving and displaying process control data associated with an abnormal situation |
| US11257161B2 (en) * | 2011-11-30 | 2022-02-22 | Refinitiv Us Organization Llc | Methods and systems for predicting market behavior based on news and sentiment analysis |
| CN106302487B (en) * | 2016-08-22 | 2019-08-09 | 中国农业大学 | Agriculture internet of things data throat floater real-time detection processing method and processing device |
| CN111275307B (en) * | 2020-01-16 | 2023-09-05 | 生态环境部华南环境科学研究所 | Quality control method for high-frequency continuous observation data of automatic online station for water quality |
| CN111538897B (en) * | 2020-03-16 | 2023-06-02 | 北京三快在线科技有限公司 | Recommended abnormality detection method, recommended abnormality detection device, electronic equipment and readable storage medium |
| CN112101658A (en) * | 2020-09-14 | 2020-12-18 | 安徽工业大学 | Fattening pig breeding feed consumption prediction method |
| CN115269241A (en) * | 2022-07-20 | 2022-11-01 | 天翼云科技有限公司 | Method, device and storage medium for carrying out anomaly detection on periodic data |
| CN115412455B (en) * | 2022-07-28 | 2023-12-19 | 南京航空航天大学 | Method and device for detecting abnormality of multiple performance indexes of server based on time sequence |
| CN115643193A (en) * | 2022-10-21 | 2023-01-24 | 杭州安恒信息技术股份有限公司 | Network traffic anomaly detection method, device, equipment and medium |
-
2023
- 2023-02-08 CN CN202310077065.5A patent/CN115859209B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980874A (en) * | 2017-03-13 | 2017-07-25 | 南京邮电大学 | A kind of multi-time Scales dimension data fusion method towards distribution big data |
| CN115221471A (en) * | 2022-07-18 | 2022-10-21 | 山东云天安全技术有限公司 | Abnormal data identification method and device, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115859209A (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kashiha et al. | Development of an early warning system for a broiler house using computer vision | |
| Mertens et al. | Statistical control charts as a support tool for the management of livestock production | |
| Huybrechts et al. | Early warnings from automatic milk yield monitoring with online synergistic control | |
| CN114167922B (en) | Farming and pasturing intelligent analysis method and system based on multi-sensor data acquisition | |
| CN112000051A (en) | Livestock breeding management system based on Internet of things | |
| Mertens et al. | An intelligent control chart for monitoring of autocorrelated egg production process data based on a synergistic control strategy | |
| CN112684838A (en) | Pig farm environmental control system based on epidemic prevention | |
| CN115859209B (en) | Livestock industry poultry breeding abnormality identification method based on feed consumption data | |
| CN114372408A (en) | Short-term power load prediction method and device based on chaotic sparrow search algorithm | |
| US5715185A (en) | Animal feed system | |
| CN116843085B (en) | Freshwater fish growth monitoring method, device, equipment and storage medium | |
| CN109359624B (en) | Neural network-based prediction method and prediction device for feeding behavior of laying hens | |
| CN116649236B (en) | Cow breeding feeding monitoring management system | |
| CN117482827A (en) | Feed on-line production monitoring system based on big data analysis | |
| CN115342937B (en) | Temperature anomaly detection method and device | |
| CN111815472A (en) | Agricultural breeding environment monitoring system based on big data and environment analysis method | |
| CN111524023A (en) | Greenhouse adjusting method and system | |
| Fernández et al. | Real-time modelling of individual weight response to feed supply for fattening pigs | |
| Sokullu et al. | Iot based livestock precision feeding system using machine learning | |
| CN109242219A (en) | The prediction technique of laying hen foraging behaviour and the prediction meanss of laying hen foraging behaviour | |
| CN112633107A (en) | Intelligent forestry monitoring method, device, equipment and storage medium | |
| CN110738351A (en) | intelligent monitoring device, system and control method | |
| Quiniou et al. | Precision feeding with a decision support tool dealing with daily and individual pigs' body weight | |
| Woudenberg et al. | Real-time adaptive problem detection in poultry | |
| CN117786584B (en) | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
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 |