CN114117135A - Big data information analysis method and system based on deep learning and back measurement algorithm - Google Patents
Big data information analysis method and system based on deep learning and back measurement algorithm Download PDFInfo
- Publication number
- CN114117135A CN114117135A CN202111355684.3A CN202111355684A CN114117135A CN 114117135 A CN114117135 A CN 114117135A CN 202111355684 A CN202111355684 A CN 202111355684A CN 114117135 A CN114117135 A CN 114117135A
- Authority
- CN
- China
- Prior art keywords
- weight
- livestock
- feed
- equipment
- growth
- 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.)
- Granted
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 title claims abstract description 42
- 238000005259 measurement Methods 0.000 title description 2
- 244000144972 livestock Species 0.000 claims abstract description 125
- 230000008859 change Effects 0.000 claims abstract description 52
- 238000011161 development Methods 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 244000144977 poultry Species 0.000 claims description 45
- 238000005202 decontamination Methods 0.000 claims description 21
- 230000003588 decontaminative effect Effects 0.000 claims description 21
- 238000005406 washing Methods 0.000 claims description 18
- 238000005303 weighing Methods 0.000 claims description 13
- 238000001035 drying Methods 0.000 claims description 10
- 238000000611 regression analysis Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 9
- 230000003203 everyday effect Effects 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 238000007664 blowing Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000011010 flushing procedure Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000013102 re-test Methods 0.000 claims description 2
- 238000012552 review Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 7
- 238000009395 breeding Methods 0.000 description 7
- 230000001488 breeding effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K39/00—Feeding or drinking appliances for poultry or other birds
- A01K39/01—Feeding devices, e.g. chainfeeders
- A01K39/012—Feeding devices, e.g. chainfeeders filling automatically, e.g. by gravity from a reserve
- A01K39/0125—Panfeeding systems; Feeding pans therefor
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K45/00—Other aviculture appliances, e.g. devices for determining whether a bird is about to lay
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K67/00—Rearing or breeding animals, not otherwise provided for; New or modified breeds of animals
- A01K67/02—Breeding vertebrates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Biodiversity & Conservation Biology (AREA)
- Animal Husbandry (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Birds (AREA)
- Computational Linguistics (AREA)
- Zoology (AREA)
- Animal Behavior & Ethology (AREA)
- Software Systems (AREA)
- Feeding And Watering For Cattle Raising And Animal Husbandry (AREA)
Abstract
The invention is suitable for the field of computers, and provides a big data information analysis method and a big data information analysis system based on a deep learning and back-testing algorithm, wherein the big data information analysis method and the big data information analysis system control a plurality of devices to work cooperatively by receiving working condition information uploaded by the plurality of devices and sending control signals to different devices according to the working condition information of the plurality of devices; monitoring the growth condition of the livestock, storing the working data of the equipment and the growth data of the livestock into a database, performing deep learning and return test analysis on the data in the database, and updating growth demand change curves in different development stages. The system can control the multiple devices to work cooperatively according to the running conditions of the devices and the growth conditions of the livestock, and the system enables the system to have growth performance by analyzing historical data in the database so as to meet continuously changing market demands, adjust the running state of the devices and reduce the workload of workers for manually adjusting the devices.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a big data information analysis method and system based on deep learning and a back test algorithm.
Background
With the rapid development of the animal husbandry industry, the scale and specialization level is continuously improved. The intelligent breeding production management system is based on the application of the key technology of the internet of things, improves and promotes the traditional animal husbandry, develops and innovates the modern intelligent animal husbandry, and accelerates the modernization and informatization construction of the animal husbandry to become more and more important factors for the animal husbandry development. The intelligent livestock breeding system adopts identification technologies such as bar code labels and electronic labels, an intelligent mobile terminal technology, a large-scale database and other related mobile internet technologies and internet of things technologies, and fully utilizes modern informatization technology to manage and serve modern animal husbandry.
The intelligent livestock breeding system realizes comprehensive informatization, business management informatization, management information recycling and information service standardization of important core business of the livestock industry from identification, tracking and query of all links such as agricultural breeding, purchasing, processing, transportation, sale and the like and relevant management of warehouse, asset, enterprise information and the like, and provides important informatization support and service for the livestock enterprise so that the informatization level of the enterprise keeps up with the rapid development of the enterprise.
When intelligent cultivation is carried out, various devices in a cultivation plant need to be managed and controlled, the used devices are increased along with the expansion of the cultivation plant, and the workload of overhauling and parameter adjustment of the devices at regular intervals is increased; moreover, certain association exists among devices in a breeding plant, livestock breeding work needs to be completed in a mutual cooperation mode, running parameters and feeding parameters need to be adjusted correspondingly along with growth of livestock and change of feed, the existing intelligent management and control system needs more conditions for human intervention, the data utilization rate in a database is insufficient, the deep learning capacity is not realized, and the workload of workers is not reduced on the basis of application of the intelligent breeding system.
Disclosure of Invention
The embodiment of the invention provides a big data information analysis method and system based on a deep learning and back-testing algorithm, and aims to solve the problems that the workload of periodically overhauling and parameter adjusting equipment is increased while equipment is increased, the equipment needs to be mutually cooperated along with the growth of livestock, and the operation parameters need to be correspondingly adjusted.
The embodiment of the invention is realized in such a way that, on one hand, a big data information analysis method based on deep learning and echo algorithm comprises the following steps:
acquiring feedback signals of normal online work of a plurality of devices;
receiving working condition information uploaded by a plurality of devices;
according to the working condition information of the plurality of devices, sending control signals to different devices to control the plurality of devices to work cooperatively;
monitoring the growth condition of the livestock, and storing the working data of the equipment and the growth data of the livestock in a database;
and carrying out deep learning and regression analysis on the data in the database, and updating growth demand change curves in different development stages.
As a modified scheme of the invention: the receiving the working condition information uploaded by the multiple devices specifically includes:
receiving feeding data uploaded by feeding equipment, receiving decontamination data uploaded by decontamination equipment, and receiving growth data uploaded by weighing equipment; the feeding equipment comprises a to-be-produced period livestock feeding equipment, a growing period livestock feeding equipment and a cub period livestock feeding equipment; the decontamination equipment comprises livestock cleaning equipment and poultry house cleaning equipment.
As a further improvement of the invention: the sending of the control signal to the different devices according to the working condition information of the multiple devices, wherein the controlling of the multiple devices to cooperatively work specifically includes:
when a timing unit in the feeding equipment reaches a preset time, receiving a feeding demand signal uploaded by the feeding equipment;
sending a starting signal to the driving equipment according to the position information of the feeding equipment sent by the feeding demand signal, and driving the feeding equipment to start working; the feeding equipment feeds the feed with the specified weight every time, feeds back an end signal after the feeding is finished, and uploads the actual weight of the fed feed;
receiving the actual weight of the feed put in each time by the feeding equipment and the feed tower feed data uploaded by the feed tower sensing equipment;
judging whether the actual weight of the fed feed is the same as the weight of the feed reduced in the feed tower or not;
and when the actual weight of the fed feed is different from the weight of the feed reduced in the material tower, sending feed conveying channel maintenance information to the maintenance end.
As another improvement of the invention: the specified weight of the feed put in each time by the feeding equipment is determined according to a preset growth demand change curve, and the growth demand change curve is a change curve of the required feed weight correspondingly every day along with the increase of the growth time of the livestock; wherein the growth demand change curves of the livestock in the period of production and the livestock in the growth period are different.
As a further scheme of the invention: the sending of the control signal to the different devices according to the working condition information of the multiple devices, wherein the controlling of the multiple devices to cooperatively work specifically includes:
when a timing unit in the decontamination equipment reaches preset time, receiving a decontamination feedback signal uploaded by the decontamination equipment;
controlling the gate to be opened, starting the driving equipment to move, and transferring the livestock from the designated channel to the washing area;
after all the poultry enter the washing area, controlling the gate of the washing area to be closed, and simultaneously controlling the poultry house cleaning equipment and the washing equipment in the washing area to be started to simultaneously clean the poultry and the poultry house;
when the livestock is washed, controlling the drying equipment to start, and respectively blowing and drying the livestock and the poultry house;
when the blowing and drying time reaches the designated time, the gate of the washing area is opened, and the driving equipment is controlled to drive the livestock to the poultry house.
As a further scheme of the invention: the monitoring of the growth of the livestock specifically comprises:
when the livestock are transferred to the flushing area from the designated passage, the livestock pass through the weighing narrow passage, the weighing equipment in the weighing narrow passage weighs the passing livestock one by one, and the weight of the livestock is uploaded.
As an optimization scheme of the invention: the step of storing the working data of the plurality of devices and the livestock growth data into the database specifically comprises the following steps:
numbering each poultry house; the livestock with the same growth stage are placed in the same poultry house;
after the weights of the livestock are obtained, comparing the weight difference between the livestock in the same poultry house;
when the weight difference between the maximum weight of the livestock and the minimum weight of the livestock in the same poultry house exceeds an allowable difference value, sending a production abnormity feedback signal to a management end;
analyzing the average weight of the poultry in the same poultry house, and comparing whether the average weight exceeds the normal weight;
when the average weight exceeds the normal weight, sending the weight information of the fed materials which are fed in a reducing way to feeding equipment corresponding to the poultry house;
when the average weight does not exceed the normal weight, sending the weight information of the added and fed feed to feeding equipment corresponding to the poultry house; the weight of the feed is subtracted from the weight of the feed or added to the weight of the feed on the basis of the specified weight, so that the normal growth of the livestock is controlled; the weight of the feed added and the weight of the feed added are preset weights;
and recording the times of reducing the weight of the feed in the whole growth process of the livestock, the times of adding the weight of the feed, the weight value of the livestock after the change of the feed adding amount and the final weight value of the livestock when the livestock is out of the farm in a database.
As a further scheme of the invention: the deep learning and the regression analysis are carried out on the data in the database, and the updating of the growth demand change curves in different development stages specifically comprises the following steps:
performing timing analysis on data stored in the database, and judging whether the final weight value is equal to the expected weight value;
when the final weight value is not equal to the expected weight value, calculating a weight deviation value between the final weight value and the expected weight value;
converting the weight deviation value into a feed deviation value according to the relationship between the weight and the fed feed;
and evenly dividing the deviation value of the feed to the specified weight of the feed put in every day in the growing period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred.
As a modified scheme of the invention: the deep learning and the regression analysis are carried out on the data in the database, and the updating of the growth demand change curves in different development stages specifically comprises the following steps:
identifying the development period of the livestock when the feed input amount is changed; the livestock growth period comprises a cub period, a growth period and a to-be-produced period;
when the feed input amount changes for multiple times, the feed input amount is in different development stages, and data with the changed feed input amount are divided into a plurality of groups of sub data sets according to the development stages;
counting the total change weight value of the feed input quantity changed in each subdata set; the weight of the added feed is a positive value, and the weight of the subtracted feed is a negative value;
and (3) uniformly dividing the total change weight value to the specified weight of the feed put in every day in the development period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred.
In another aspect, a big data information analysis system based on a deep learning and regression algorithm includes:
the equipment normal verification module is used for acquiring feedback signals of normal online work of a plurality of pieces of equipment;
the working condition information receiving module is used for receiving working condition information uploaded by a plurality of devices;
the control module is used for sending control signals to different equipment according to the working condition information of the plurality of equipment and controlling the plurality of equipment to work cooperatively;
the data acquisition and storage module is used for monitoring the growth condition of the livestock and storing the working data of the equipment and the growth data of the livestock into a database;
and the data analysis updating module is used for carrying out deep learning and retest analysis on the data in the database and updating the growth demand change curves in different development stages.
The invention has the beneficial effects that: the method comprises the steps that the working condition information uploaded by a plurality of devices is received, and control signals are sent to different devices according to the working condition information of the devices to control the devices to work cooperatively; monitoring the growth condition of the livestock, storing the working data of the equipment and the growth data of the livestock into a database, performing deep learning and return test analysis on the data in the database, and updating growth demand change curves in different development stages. The system can control the multiple devices to work cooperatively according to the running conditions of the devices and the growth conditions of the livestock, and the system enables the system to have growth performance by analyzing historical data in the database so as to meet continuously changing market demands, adjust the running state of the devices and reduce the workload of workers for manually adjusting the devices.
Drawings
FIG. 1 is a main flow diagram of a big data information analysis method based on deep learning and regression algorithm;
FIG. 2 is a feeding flow diagram in a big data information analysis method based on deep learning and regression algorithms;
FIG. 3 is a flow chart of decontamination in a big data information analysis method based on deep learning and regression algorithm;
FIG. 4 is a feeding regulation flow chart in a big data information analysis method based on deep learning and regression algorithm;
FIG. 5 is a schematic diagram of an internal structure of a big data information analysis system based on a deep learning and echo algorithm.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention controls the cooperative work of a plurality of devices by receiving the working condition information uploaded by the plurality of devices and sending control signals to different devices according to the working condition information of the plurality of devices; monitoring the growth condition of the livestock, storing the working data of the equipment and the growth data of the livestock into a database, performing deep learning and return test analysis on the data in the database, and updating growth demand change curves in different development stages. The system can control the multiple devices to work cooperatively according to the running conditions of the devices and the growth conditions of the livestock, and the system enables the system to have growth performance by analyzing historical data in the database so as to meet continuously changing market demands, adjust the running state of the devices and reduce the workload of workers for manually adjusting the devices.
Fig. 1 shows a main flow chart of a deep learning and echo algorithm-based big data information analysis method according to an embodiment of the present invention, where the deep learning and echo algorithm-based big data information analysis method includes:
step S10: acquiring feedback signals of normal online work of a plurality of devices;
step S11: receiving working condition information uploaded by a plurality of devices;
step S12: according to the working condition information of the plurality of devices, sending control signals to different devices to control the plurality of devices to work cooperatively;
step S13: monitoring the growth condition of the livestock, and storing the working data of the equipment and the growth data of the livestock in a database;
step S14: and carrying out deep learning and regression analysis on the data in the database, and updating growth demand change curves in different development stages. The system has growth performance, and application of historical data in the database is deepened. The growth demand change curve is a theoretical curve summarized according to theory and historical empirical data and is a curve representing the relationship between the growth period of the livestock and the feed weight which should be put in every day.
In addition, the system also acquires monitoring data which is uploaded by the monitoring equipment and used for monitoring the plurality of equipment; and analyzing the monitoring data, and sending maintenance reminding information to the maintenance end when abnormal data appear in the monitoring data. The supervisory equipment can be temperature monitor appearance, environmental monitoring appearance, noise monitor etc. and when the equipment temperature was higher, data were uploaded to the temperature monitor appearance, and when the high temperature, system control new trend system cooled down the pouity dwelling place.
In one aspect of this embodiment, the receiving the working condition information uploaded by the multiple devices specifically includes:
receiving feeding data uploaded by feeding equipment, receiving decontamination data uploaded by decontamination equipment, and receiving growth data uploaded by weighing equipment; the feeding equipment comprises a to-be-produced period livestock feeding equipment, a growing period livestock feeding equipment and a cub period livestock feeding equipment; the decontamination equipment comprises livestock cleaning equipment and poultry house cleaning equipment.
Fig. 2 shows a feeding flow chart in a big data information analysis method based on a deep learning and back-testing algorithm according to an embodiment of the present invention, where sending control signals to different devices according to working condition information of the multiple devices, and controlling the multiple devices to cooperatively work specifically includes:
step S20: when a timing unit in the feeding equipment reaches a preset time, receiving a feeding demand signal uploaded by the feeding equipment;
step S21: sending a starting signal to the driving equipment according to the position information of the feeding equipment sent by the feeding demand signal, and driving the feeding equipment to start working; the feeding equipment feeds the feed with the specified weight every time, feeds back an end signal after the feeding is finished, and uploads the actual weight of the fed feed;
step S22: receiving the actual weight of the feed put in each time by the feeding equipment and the feed tower feed data uploaded by the feed tower sensing equipment;
step S23: judging whether the actual weight of the fed feed is the same as the weight of the feed reduced in the feed tower or not;
step S24: and when the actual weight of the fed feed is different from the weight of the feed reduced in the material tower, sending feed conveying channel maintenance information to the maintenance end. Whether the feeding equipment and the material tower work normally can be monitored, and the amount of the residual feed in the material tower can be monitored laterally through the feeding amount of the feeding equipment, so that the feed can be supplemented into the material tower in time.
In one aspect of this embodiment, the specified weight of feed to be fed by the feeding device per time is determined according to a preset growth demand variation curve, wherein the growth demand variation curve is a variation curve corresponding to the required weight of feed per day as the growth time of the livestock increases; wherein the growth demand change curves of the livestock in the period of production and the livestock in the growth period are different.
Fig. 3 shows a decontamination flow chart in a big data information analysis method based on deep learning and echo-measuring algorithm according to an embodiment of the present invention, where sending control signals to different devices according to working condition information of multiple devices and controlling the multiple devices to cooperatively work specifically includes:
step S30: when a timing unit in the decontamination equipment reaches preset time, receiving a decontamination feedback signal uploaded by the decontamination equipment;
step S31: controlling the gate to be opened, starting the driving equipment to move, and transferring the livestock from the designated channel to the washing area;
step S32: after all the poultry enter the washing area, controlling the gate of the washing area to be closed, and simultaneously controlling the poultry house cleaning equipment and the washing equipment in the washing area to be started to simultaneously clean the poultry and the poultry house;
step S33: when the livestock is washed, controlling the drying equipment to start, and respectively blowing and drying the livestock and the poultry house;
step S34: when the blowing and drying time reaches the designated time, the gate of the washing area is opened, and the driving equipment is controlled to drive the livestock to the poultry house.
In one aspect of this embodiment, the monitoring of the growth of the livestock specifically includes: when the livestock are transferred to the flushing area from the designated passage, the livestock pass through the weighing narrow passage, the weighing equipment in the weighing narrow passage weighs the passing livestock one by one, and the weight of the livestock is uploaded.
Fig. 4 shows a feeding regulation and control flow chart in a big data information analysis method based on deep learning and regression algorithm according to an embodiment of the present invention, where the saving of the working data of multiple devices and the livestock growth data to the database specifically includes:
step S40: numbering each poultry house; the livestock with the same growth stage are placed in the same poultry house;
step S41: after the weights of the livestock are obtained, comparing the weight difference between the livestock in the same poultry house;
step S42: when the weight difference between the maximum weight of the livestock and the minimum weight of the livestock in the same poultry house exceeds an allowable difference value, sending a production abnormity feedback signal to a management end;
step S43: analyzing the average weight of the poultry in the same poultry house, and comparing whether the average weight exceeds the normal weight;
step S44: when the average weight exceeds the normal weight, sending the weight information of the fed materials which are fed in a reducing way to feeding equipment corresponding to the poultry house;
step S45: when the average weight does not exceed the normal weight, sending the weight information of the added and fed feed to feeding equipment corresponding to the poultry house; the weight of the feed is subtracted from the weight of the feed or added to the weight of the feed on the basis of the specified weight, so that the normal growth of the livestock is controlled; the weight of the feed added and the weight of the feed added are preset weights;
step S46: and recording the times of reducing the weight of the feed in the whole growth process of the livestock, the times of adding the weight of the feed, the weight value of the livestock after the change of the feed adding amount and the final weight value of the livestock when the livestock is out of the farm in a database. Monitoring the whole life cycle of the livestock, monitoring the growth state of each stage, and acquiring weight data of different states.
In one aspect of this embodiment, the deep learning and regression analysis of the data in the database, and the updating the growth demand change curves in different developmental stages specifically includes:
step S50: and performing timing analysis on the data stored in the database, and judging whether the final weight value is equal to the expected weight value. And (5) measuring whether the livestock cultured according to the change curve of the theoretical growth demand meets the standard requirements or not.
Step S51: when the final weight value is not equal to the expected weight value, calculating a weight deviation value between the final weight value and the expected weight value;
step S52: converting the weight deviation value into a feed deviation value according to the relationship between the weight and the fed feed;
step S53: and evenly dividing the deviation value of the feed to the specified weight of the feed put in every day in the growing period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred. The final weight value in the historical data is subjected to deep analysis, so that the system can automatically adjust the growth demand change curve, theories and practices are mutually verified and combined, the final weight value of the livestock tends to the expected weight value, and the expected weight value is subjected to fine adjustment change along with the change of markets and the change of people's preference, so that the theoretical growth demand change curve is required to adapt to the change.
In one aspect of this embodiment, the deep learning and regression analysis of the data in the database, and the updating the growth demand change curves in different developmental stages specifically includes:
step S60: identifying the development period of the livestock when the feed input amount is changed; the livestock growth period comprises a cub period, a growth period and a to-be-produced period;
step S61: when the feed input amount changes for multiple times, the feed input amount is in different development stages, and data with the changed feed input amount are divided into a plurality of groups of sub data sets according to the development stages;
step S62: counting the total change weight value of the feed input quantity changed in each subdata set; the weight of the added feed is a positive value, and the weight of the subtracted feed is a negative value;
step S63: and (3) uniformly dividing the total change weight value to the specified weight of the feed put in every day in the development period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred. The feeding weight adding and feeding weight subtracting in historical data are subjected to deep analysis, once the feeding weight is changed in the feeding process, the deviation between a theoretical value and practice is explained, the adjustment needs to be carried out according to actual growth, and a growth demand change curve is changed according to the change of the feeding weight, so that the growth demand change curve is more in line with the actual demand.
Fig. 5 is a schematic diagram illustrating an internal structure of a deep learning and retrieval algorithm-based big data information analysis system according to an embodiment of the present invention, where the deep learning and retrieval algorithm-based big data information analysis system includes:
the device normal verification module 100 is configured to obtain feedback signals of normal online operations of a plurality of devices;
the working condition information receiving module 200 is used for receiving working condition information uploaded by a plurality of devices;
the control module 300 is configured to send a control signal to different devices according to the working condition information of the multiple devices, and control the multiple devices to cooperatively work;
the data acquisition and storage module 400 is used for monitoring the growth condition of the livestock and storing the working data of the devices and the growth data of the livestock into a database;
and the data analysis updating module 500 is used for performing deep learning and regression analysis on the data in the database and updating the growth demand change curves in different development periods.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only represent some preferred embodiments of the present invention, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A big data information analysis method based on deep learning and echo algorithm is characterized by comprising the following steps:
acquiring feedback signals of normal online work of a plurality of devices; the equipment comprises feeding equipment, decontamination equipment, weighing equipment, driving equipment, drying equipment and a material tower;
receiving working condition information uploaded by a plurality of devices;
according to the working condition information of the plurality of devices, sending control signals to different devices to control the plurality of devices to work cooperatively;
monitoring the growth condition of the livestock, and storing the working data of the equipment and the growth data of the livestock in a database;
and carrying out deep learning and regression analysis on the data in the database, and updating growth demand change curves in different development stages.
2. The big data information analysis method based on deep learning and echo algorithm according to claim 1, wherein the receiving the working condition information uploaded by the plurality of devices specifically comprises:
receiving feeding data uploaded by feeding equipment, receiving decontamination data uploaded by decontamination equipment, and receiving growth data uploaded by weighing equipment; the feeding equipment comprises a to-be-produced period livestock feeding equipment, a growing period livestock feeding equipment and a cub period livestock feeding equipment; the decontamination equipment comprises livestock cleaning equipment and poultry house cleaning equipment.
3. The big data information analysis method based on the deep learning and the echo algorithm as claimed in claim 1, wherein the sending of the control signal to the different devices according to the working condition information of the multiple devices, and controlling the multiple devices to cooperatively work specifically comprises:
when a timing unit in the feeding equipment reaches a preset time, receiving a feeding demand signal uploaded by the feeding equipment;
sending a starting signal to the driving equipment according to the position information of the feeding equipment sent by the feeding demand signal, and driving the feeding equipment to start working; the feeding equipment feeds the feed with the specified weight every time, feeds back an end signal after the feeding is finished, and uploads the actual weight of the fed feed;
receiving the actual weight of the feed put in each time by the feeding equipment and the feed tower feed data uploaded by the feed tower sensing equipment;
judging whether the actual weight of the fed feed is the same as the weight of the feed reduced in the feed tower or not;
and when the actual weight of the fed feed is different from the weight of the feed reduced in the material tower, sending feed conveying channel maintenance information to the maintenance end.
4. The deep learning and review algorithm-based big data information analysis method according to claim 3, wherein the specified weight of the feed put in each time by the feeding device is determined according to a preset growth demand variation curve, and the growth demand variation curve is a variation curve of the required feed weight per day with the increase of the growth time of the livestock; wherein the growth demand change curves of the livestock in the period of production and the livestock in the growth period are different.
5. The big data information analysis method based on the deep learning and the echo algorithm as claimed in claim 1, wherein the sending of the control signal to the different devices according to the working condition information of the multiple devices, and controlling the multiple devices to cooperatively work specifically comprises:
when a timing unit in the decontamination equipment reaches preset time, receiving a decontamination feedback signal uploaded by the decontamination equipment;
controlling the gate to be opened, starting the driving equipment to move, and transferring the livestock from the designated channel to the washing area;
after all the poultry enter the washing area, controlling the gate of the washing area to be closed, and simultaneously controlling the poultry house cleaning equipment and the washing equipment in the washing area to be started to simultaneously clean the poultry and the poultry house;
when the livestock is washed, controlling the drying equipment to start, and respectively blowing and drying the livestock and the poultry house;
when the blowing and drying time reaches the designated time, the gate of the washing area is opened, and the driving equipment is controlled to drive the livestock to the poultry house.
6. The big data information analysis method based on deep learning and regression algorithm as claimed in claim 5, wherein said monitoring of livestock growth specifically comprises:
when the livestock are transferred to the flushing area from the designated passage, the livestock pass through the weighing narrow passage, the weighing equipment in the weighing narrow passage weighs the passing livestock one by one, and the weight of the livestock is uploaded.
7. The big data information analysis method based on deep learning and regression algorithm as claimed in claim 6, wherein the saving of the working data of the plurality of devices and the livestock growth data to the database specifically comprises:
numbering each poultry house; the livestock with the same growth stage are placed in the same poultry house;
after the weights of the livestock are obtained, comparing the weight difference between the livestock in the same poultry house;
when the weight difference between the maximum weight of the livestock and the minimum weight of the livestock in the same poultry house exceeds an allowable difference value, sending a production abnormity feedback signal to a management end;
analyzing the average weight of the poultry in the same poultry house, and comparing whether the average weight exceeds the normal weight;
when the average weight exceeds the normal weight, sending the weight information of the fed materials which are fed in a reducing way to feeding equipment corresponding to the poultry house;
when the average weight does not exceed the normal weight, sending the weight information of the added and fed feed to feeding equipment corresponding to the poultry house; the weight of the feed is subtracted from the weight of the feed or added to the weight of the feed on the basis of the specified weight, so that the normal growth of the livestock is controlled; the weight of the feed added and the weight of the feed added are preset weights;
and recording the times of reducing the weight of the feed in the whole growth process of the livestock, the times of adding the weight of the feed, the weight value of the livestock after the change of the feed adding amount and the final weight value of the livestock when the livestock is out of the farm in a database.
8. The big data information analysis method based on deep learning and regression algorithm as claimed in claim 7, wherein said deep learning and regression analysis of data in database, and updating the variation curve of growth demand in different developmental stages specifically comprises:
performing timing analysis on data stored in the database, and judging whether the final weight value is equal to the expected weight value;
when the final weight value is not equal to the expected weight value, calculating a weight deviation value between the final weight value and the expected weight value;
converting the weight deviation value into a feed deviation value according to the relationship between the weight and the fed feed;
and evenly dividing the deviation value of the feed to the specified weight of the feed put in every day in the growing period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred.
9. The big data information analysis method based on deep learning and regression algorithm as claimed in claim 7, wherein said deep learning and regression analysis of data in database, and updating the variation curve of growth demand in different developmental stages specifically comprises:
identifying the development period of the livestock when the feed input amount is changed; the livestock growth period comprises a cub period, a growth period and a to-be-produced period;
when the feed input amount changes for multiple times, the feed input amount is in different development stages, and data with the changed feed input amount are divided into a plurality of groups of sub data sets according to the development stages;
counting the total change weight value of the feed input quantity changed in each subdata set; the weight of the added feed is a positive value, and the weight of the subtracted feed is a negative value;
and (3) uniformly dividing the total change weight value to the specified weight of the feed put in every day in the development period, updating the changed specified weight to a growth demand change curve, and using the updated growth demand change curve when the next round of livestock is bred.
10. A big data information analysis system based on deep learning and regression algorithm, the system comprising:
the equipment normal verification module is used for acquiring feedback signals of normal online work of a plurality of pieces of equipment;
the working condition information receiving module is used for receiving working condition information uploaded by a plurality of devices;
the control module is used for sending control signals to different equipment according to the working condition information of the plurality of equipment and controlling the plurality of equipment to work cooperatively;
the data acquisition and storage module is used for monitoring the growth condition of the livestock and storing the working data of the equipment and the growth data of the livestock into a database;
and the data analysis updating module is used for carrying out deep learning and retest analysis on the data in the database and updating the growth demand change curves in different development stages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111355684.3A CN114117135B (en) | 2021-11-16 | 2021-11-16 | Big data information analysis method and system based on deep learning and back measurement algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111355684.3A CN114117135B (en) | 2021-11-16 | 2021-11-16 | Big data information analysis method and system based on deep learning and back measurement algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114117135A true CN114117135A (en) | 2022-03-01 |
| CN114117135B CN114117135B (en) | 2022-06-14 |
Family
ID=80395816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111355684.3A Active CN114117135B (en) | 2021-11-16 | 2021-11-16 | Big data information analysis method and system based on deep learning and back measurement algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114117135B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115250940A (en) * | 2022-08-29 | 2022-11-01 | 山东大佳机械有限公司 | Self-learning-based feeding system for cultured animals |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108293883A (en) * | 2018-02-08 | 2018-07-20 | 成都灵感元素科技有限公司 | A kind of multi-functional pig house |
| CN109062160A (en) * | 2018-08-22 | 2018-12-21 | 中国农业科学院农业信息研究所 | A kind of intelligence livestock and poultry cultivation management system and method |
| CN109556691A (en) * | 2018-11-05 | 2019-04-02 | 上海睿畜电子科技有限公司 | A kind of method, apparatus and system for estimating field livestock counterpoise |
| CN110889645A (en) * | 2019-12-05 | 2020-03-17 | 中国农业科学院草原研究所 | Method, system and computer readable storage medium for livestock breeding management in pasture |
| CN111587843A (en) * | 2020-06-01 | 2020-08-28 | 陈惠英 | Breeding method and breeding equipment for reducing odor of pig manure |
| CN111742853A (en) * | 2020-07-31 | 2020-10-09 | 刘同友 | Intelligent pig raising growth health dynamic monitoring management system based on big data |
-
2021
- 2021-11-16 CN CN202111355684.3A patent/CN114117135B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108293883A (en) * | 2018-02-08 | 2018-07-20 | 成都灵感元素科技有限公司 | A kind of multi-functional pig house |
| CN109062160A (en) * | 2018-08-22 | 2018-12-21 | 中国农业科学院农业信息研究所 | A kind of intelligence livestock and poultry cultivation management system and method |
| CN109556691A (en) * | 2018-11-05 | 2019-04-02 | 上海睿畜电子科技有限公司 | A kind of method, apparatus and system for estimating field livestock counterpoise |
| CN110889645A (en) * | 2019-12-05 | 2020-03-17 | 中国农业科学院草原研究所 | Method, system and computer readable storage medium for livestock breeding management in pasture |
| CN111587843A (en) * | 2020-06-01 | 2020-08-28 | 陈惠英 | Breeding method and breeding equipment for reducing odor of pig manure |
| CN111742853A (en) * | 2020-07-31 | 2020-10-09 | 刘同友 | Intelligent pig raising growth health dynamic monitoring management system based on big data |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115250940A (en) * | 2022-08-29 | 2022-11-01 | 山东大佳机械有限公司 | Self-learning-based feeding system for cultured animals |
| CN115250940B (en) * | 2022-08-29 | 2024-03-29 | 山东大佳机械有限公司 | Self-learning-based feeding system for farmed animals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114117135B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626536A (en) | Residential electricity consumption energy efficiency evaluation method based on data driving | |
| CN114117135B (en) | Big data information analysis method and system based on deep learning and back measurement algorithm | |
| CN102550438A (en) | Internet of cows | |
| CN110045771B (en) | Intelligent monitoring system for water quality of fishpond | |
| CN116452121B (en) | Intelligent enterprise inventory management system and management platform | |
| CN114693077A (en) | Real-time monitoring and early warning system breeds based on thing networking | |
| CN112101658A (en) | Fattening pig breeding feed consumption prediction method | |
| CN117539169B (en) | Management method and system based on digital twin | |
| CN116384716B (en) | Intelligent factory operation method and platform device based on unified data management | |
| CN117391411A (en) | Product processing management system based on IOT (internet of things) | |
| CN115409563A (en) | Multi-factor-influenced agricultural equipment inventory demand prediction method | |
| CN108416687A (en) | A kind of scale pig-breeding enterprise production management digital Platform system | |
| CN115222450A (en) | Automatic advertisement delivery management system | |
| CN116204566B (en) | Digital factory monitoring big data processing system | |
| CN107742160B (en) | Electromechanical equipment maintenance period self-adaptive prediction method and device | |
| CN112990591A (en) | Multi-dimensional energy consumption data analysis method based on convolutional neural network and enterprise energy consumption prediction model | |
| CN117273541A (en) | Building engineering cost quality evaluation system based on big data | |
| CN117217804A (en) | Intelligent pricing and inventory management method and system | |
| CN117350435A (en) | Method and system for managing industrial prawn culture equipment | |
| CN116916493A (en) | LED lighting lamp operation monitoring data management system | |
| CN111182077A (en) | Cattle and sheep reproductive health early warning system and early warning method | |
| CN115759789A (en) | Intelligent breeding management system based on AI algorithm | |
| CN107341630B (en) | Equipment obsolete spare part management system and method | |
| CN115879050A (en) | IOT-based intelligent agricultural pollution emergency response method and system | |
| CN201311659Y (en) | Enterprise warehouse and production operation control system |
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 |