CN118969022B - Bee colony state monitoring method and system for bee cultivation - Google Patents
Bee colony state monitoring method and system for bee cultivation Download PDFInfo
- Publication number
- CN118969022B CN118969022B CN202411427046.1A CN202411427046A CN118969022B CN 118969022 B CN118969022 B CN 118969022B CN 202411427046 A CN202411427046 A CN 202411427046A CN 118969022 B CN118969022 B CN 118969022B
- Authority
- CN
- China
- Prior art keywords
- sound data
- target sound
- data sequence
- sliding
- certain
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 241000256844 Apis mellifera Species 0.000 claims description 69
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000384 rearing effect Effects 0.000 claims 1
- 238000009395 breeding Methods 0.000 abstract 1
- 230000001488 breeding effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 241000257303 Hymenoptera Species 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 208000024780 Urticaria Diseases 0.000 description 1
- 238000009341 apiculture Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000012907 honey Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
本发明公开了一种用于蜜蜂养殖的蜂群状态监测方法及系统，方法包括：基于时间顺序对所述至少一个声音子数据序列进行重新拼接，得到至少一个目标声音数据序列，并采用预先构建的聚类规则将所述至少一个目标声音数据序列进行聚类处理，得到至少一个目标声音数据集合；将第一目标声音数据集合中的各个第一目标声音数据序列进行对齐，并采用预设的滑动窗口根据预设的滑动规则在各个第一目标声音数据序列上滑动；将每次滑动后，滑动窗口中的任一第一目标声音数据输入至预先构建的状态分类识别模型。这样，能够减少输入后续状态分类识别模型的数据量，并且通过获取不同滑动窗口中的状态结果，使得用户能够得到不同时间段的蜂群状态。
The present invention discloses a bee colony status monitoring method and system for bee breeding, the method comprising: rejoining the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and clustering the at least one target sound data sequence using a pre-constructed clustering rule to obtain at least one target sound data set; aligning each first target sound data sequence in the first target sound data set, and sliding on each first target sound data sequence using a preset sliding window according to a preset sliding rule; after each sliding, any first target sound data in the sliding window is input into a pre-constructed state classification and recognition model. In this way, the amount of data input into the subsequent state classification and recognition model can be reduced, and by obtaining the state results in different sliding windows, the user can obtain the bee colony status in different time periods.
Description
Technical Field
The invention belongs to the technical field of bee culture, and particularly relates to a bee colony state monitoring method and system for bee culture.
Background
Manual inspection of the hives often disturbs the life cycle of the colony, affecting honey production. Therefore, the state of the bee colony is monitored in an automatic monitoring mode, so that a large amount of key information about bee behaviors can be obtained under the conditions of not interrupting the life cycle of the bee colony and reducing human resources, and the bee colony health condition can be judged.
However, in the existing bee colony state monitoring method, a large amount of data is often required to be input for recognition, and particularly when a large number of beehives exist in a large-scale bee-keeping place, after sound data of the bees in all beehives are collected, all the sound data are required to be input into a recognition system, so that the recognition system is easily downtime, and even poor monitoring efficiency is caused.
Disclosure of Invention
The invention provides a bee colony state monitoring method and system for bee culture, which are used for solving the technical problems that the recognition system is down easily and the monitoring efficiency is poor due to the voice data input of a large number of bees.
In a first aspect, the present invention provides a method for monitoring the status of a colony for honeybee cultivation, comprising:
Acquiring sound data sequences of at least one bee colony in a preset time period, and intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence;
re-splicing the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and clustering the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set;
Aligning each first target sound data sequence in a first target sound data set, and sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one target sound data set in the at least one target sound data set;
after each sliding, inputting any first target sound data in the sliding window into a pre-constructed state classification and identification model, wherein the state classification and identification model outputs a state result associated with any first target sound data;
and determining the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
In a second aspect, the present invention provides a colony status monitoring system for bee farming comprising:
the intercepting module is configured to acquire sound data sequences of at least one bee colony in a preset time period, and intercept each sound data sequence at least once by adopting a preset extraction rule to acquire at least one sound sub-data sequence corresponding to each sound data sequence;
The splicing module is configured to re-splice the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and perform clustering processing on the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set;
The sliding module is configured to align each first target sound data sequence in the first target sound data set, and slide on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one target sound data set in the at least one target sound data set;
the output module is configured to input any first target sound data in the sliding window to a pre-constructed state classification and identification model after each sliding, and the state classification and identification model outputs a state result associated with any first target sound data;
And the determining module is configured to determine the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
In a third aspect, an electronic device is provided comprising at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the bee colony condition monitoring method for bee cultivation of any of the embodiments of the present invention.
In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program of instructions which, when executed by a processor, cause the processor to perform the steps of the method for monitoring the status of a bee colony for bee raising according to any of the embodiments of the present invention.
According to the bee colony state monitoring method and system for bee cultivation, each first target sound data sequence in the first target sound data set is aligned, a preset sliding window is adopted to slide on each first target sound data sequence according to a preset sliding rule, after each sliding, any first target sound data in the sliding window is input into a pre-built state classification and identification model, so that the data volume of the input of a subsequent state classification and identification model can be reduced, and a user can obtain the bee colony state in different time periods by acquiring state results in different sliding windows, so that the user can manage the bee colony subsequently.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for monitoring the status of a colony for bee cultivation according to an embodiment of the present invention;
FIG. 2 is a block diagram of a colony status monitoring system for bee cultivation according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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.
Referring to fig. 1, a flow chart of a method for monitoring the status of a colony for bee cultivation according to the present application is shown.
As shown in fig. 1, the method for monitoring the state of a bee colony for bee cultivation specifically comprises the following steps:
Step S101, obtaining sound data sequences of at least one bee colony in a preset time period, and intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence.
In this step, a bee recording monitor is installed at the bottom of each beehive through a solar panel, a storage battery, five omnidirectional microphones, a RPi2 controller and Dspic with a digital-to-analog converter (ADC), and is used for collecting the sound signals of the bees in the beehive.
It should be noted that, the sound data sequence of at least one bee colony in the preset time period is obtained, and at least one interception is performed on each sound data sequence by adopting a preset extraction rule, so as to obtain at least one sound sub-data sequence corresponding to each sound data sequence. Therefore, some scene noise can be directly removed, and the possibility of partial loss of the swarm sound data caused by subsequent noise filtering of the sound data can be reduced.
The method comprises the steps of obtaining at least one abnormal sound data, wherein the frequency of sound in a certain sound data sequence is not in a preset frequency range, removing each at least one abnormal sound data in the certain sound data sequence, and obtaining at least one sound sub-data sequence corresponding to the certain sound data sequence.
For example, it is known from spectral analysis of the sound signals of the bee colony that sound frequencies of healthy bee colonies are mainly concentrated around 400Hz and that the main frequencies of cricket sounds in the environment are concentrated around 3 kHz. Thus, by the means described above, the cricket's call in the environment can be removed directly.
Step S102, re-splicing the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and clustering the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set.
In the step, at least one first sound sub-data sequence belonging to a certain sound data sequence is acquired, and the at least one first sound sub-data sequence is spliced based on time sequence to obtain a certain target sound data sequence. And clustering each target sound data sequence belonging to a certain amplitude range to obtain a certain target sound data set corresponding to the certain amplitude range.
Step S103, aligning each first target sound data sequence in the first target sound data set, and sliding on each first target sound data sequence according to a preset sliding rule by using a preset sliding window, where the first target sound data set is any one target sound data set in the at least one target sound data set.
In this step, the sliding distance of each time in the sliding rule is the time length difference between the two first target sound data sequences of the adjacent distance length.
The sliding window is arranged at an initial position of each first target sound data sequence, wherein the initial position is a position where first target sound data of a certain first target sound data sequence is located, the certain first target sound data sequence is a first target sound data sequence with the smallest time length in each first target sound data sequence, a first time length difference value between another first target sound data sequence and the certain first target sound data sequence is obtained, the sliding window is slid on each first target sound data sequence by taking the first time length difference value as a first sliding distance, the other first target sound data sequence is a first target sound data sequence with a distance length adjacent to the certain first target sound data sequence, a second time length difference value between the other first target sound data sequence and the certain first target sound data sequence is obtained, the sliding window is slid on each first target sound data sequence by taking the second time length difference value as a second sliding distance, and the other first target sound data sequence is a first target sound data sequence with a distance adjacent to the other first target sound data sequence.
For example, the time length of the first target sound data series a is 5, the time length of the first target sound data series B is 6, the time length of the first target sound data series C is 9, the time length of the first target sound data series D is 11, the time length of the first target sound data series E is 15, and the time length of the first target sound data series F is 16.
Then, after the first target sound data sequences are aligned side by side, the initial position of the sliding window is at the position where the first target sound data in the first target sound data sequence a is located, the sliding window has a first sliding distance of 6-5=1, a second sliding distance of 9-6=3, a third sliding distance of 11-9=2, a fourth sliding distance of 15-11=4, and a last sliding distance of 16-15=1.
In this embodiment, by identifying one target sound data in the sliding window at a time, obtaining a state result of the target sound data, and giving the state result of the target sound data to other target sound data, the data amount of the input subsequent state classification identification model can be reduced.
Step S104, after each sliding, any first target sound data in the sliding window is input into a pre-constructed state classification and identification model, and the state classification and identification model outputs a state result associated with any first target sound data.
In this step, after each sliding, the sliding window has at least one first target sound data of the first target sound data sequence, and the first target sound data of a certain first target sound data sequence is selected and input into the pre-constructed state classification recognition model.
It should be noted that, the SVDD model is constructed to extract the audio signal of the abnormal state of the bee colony, and then the SVDD classifier is used to classify and identify the effective signal extracted from any one of the first target sound data. The effective signal may be LPCC coefficients, MFCC parameters (Mel-Frequency Cepstrum Coefficients, mel-cepstral coefficients), etc.
Step S105, determining the status of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each status result.
In the step, a state result associated with any one of the first target sound data in the sliding window is obtained, and the state result is associated with other first target sound data in the sliding window, so that at least one state result associated with a certain first target sound data sequence is obtained, whether an abnormal state result exists in the at least one state result associated with the certain first target sound data sequence is judged, if the abnormal state result does not exist, the bee colony corresponding to the certain first target sound data sequence is in a normal state, and if the abnormal state result exists, the bee colony corresponding to the certain first target sound data sequence is in an abnormal state.
In summary, the method aligns each first target sound data sequence in the first target sound data set, slides on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, and inputs any first target sound data in the sliding window to a pre-constructed state classification and identification model after each sliding, so that the data volume of inputting a subsequent state classification and identification model can be reduced, and the user can obtain the bee colony states in different time periods by acquiring state results in different sliding windows, so that the user can manage the bee colony subsequently.
Referring to fig. 2, a block diagram of a colony status monitoring system for bee cultivation according to the present application is shown.
As shown in fig. 2, the bee colony state monitoring system 200 includes an interception module 210, a splicing module 220, a sliding module 230, an output module 240, and a determination module 250.
The system comprises a capturing module 210, a splicing module 220, a sliding module 230, an output module 240, and a state recognition module 250, wherein the capturing module 210 is configured to obtain a sound data sequence of at least one bee colony in a preset time period, and capture each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence, the splicing module 220 is configured to re-splice the at least one sound sub-data sequence based on time sequence to obtain at least one target sound data sequence, and cluster the at least one target sound data sequence by adopting a preset clustering rule to obtain at least one target sound data set, the sliding module 230 is configured to align each first target sound data sequence in a first target sound data set, slide on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one target sound data set in the at least one target sound data set, the output module 240 is configured to input any first target sound data in the sliding window to a preset state recognition module after each sliding, and the state recognition module is configured to output any target sound data in the state recognition module corresponding to the state recognition module to the first sound classification module, and the state recognition module determines that the state data is corresponding to each target sound data in the state classification module.
It should be understood that the modules depicted in fig. 2 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 2, and are not described here again.
In other embodiments, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program, the program instructions, when executed by a processor, cause the processor to perform the method for monitoring the status of a bee colony for bee raising in any of the method embodiments described above;
As one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
Acquiring sound data sequences of at least one bee colony in a preset time period, and intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence;
re-splicing the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and clustering the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set;
Aligning each first target sound data sequence in a first target sound data set, and sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one target sound data set in the at least one target sound data set;
after each sliding, inputting any first target sound data in the sliding window into a pre-constructed state classification and identification model, wherein the state classification and identification model outputs a state result associated with any first target sound data;
and determining the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
The computer readable storage medium may include a stored program area that may store an operating system, an application program required for at least one function, and a stored data area that may store data created from use of the colony status monitoring system for bee raising, etc. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located relative to the processor, which may be connected to the colony status monitoring system for bee raising via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the device includes a processor 310 and a memory 320. The electronic device may further comprise input means 330 and output means 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 3. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing by running non-volatile software programs, instructions and modules stored in the memory 320, i.e. implements the method for monitoring the state of a bee colony for bee raising according to the above-described method embodiment. The input device 330 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the colony status monitoring system for bee raising. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As one embodiment, the electronic device is applied to a bee colony state monitoring system for bee cultivation, and is used for a client, and comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
Acquiring sound data sequences of at least one bee colony in a preset time period, and intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence;
re-splicing the at least one sound sub-data sequence based on the time sequence to obtain at least one target sound data sequence, and clustering the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set;
Aligning each first target sound data sequence in a first target sound data set, and sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one target sound data set in the at least one target sound data set;
after each sliding, inputting any first target sound data in the sliding window into a pre-constructed state classification and identification model, wherein the state classification and identification model outputs a state result associated with any first target sound data;
and determining the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.
Claims (7)
1. A method for monitoring the status of a colony for honeybee cultivation, comprising:
Acquiring sound data sequences of at least one bee colony in a preset time period, and intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence, wherein the sound data comprises frequency and amplitude of sound;
the step of intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence comprises the following steps:
acquiring at least one abnormal sound data of which the frequency of sound in a certain sound data sequence is not in a preset frequency range;
Removing each abnormal sound data in a certain sound data sequence to obtain at least one sound sub-data sequence corresponding to the certain sound data sequence;
Re-splicing the at least one sound sub-data sequence based on time sequence to obtain at least one target sound data sequence, clustering the at least one target sound data sequence by adopting a pre-constructed clustering rule to obtain at least one target sound data set, wherein clustering the at least one target sound data sequence by adopting the pre-constructed clustering rule to obtain at least one target sound data set comprises the following steps:
setting at least one amplitude range;
Clustering each target sound data sequence belonging to a certain amplitude range to obtain a certain target sound data set corresponding to the certain amplitude range;
aligning each first target sound data sequence in the first target sound data set, and sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one of the at least one target sound data set, and the sliding distance of each sliding rule is a time length difference value between two first target sound data sequences with adjacent distance lengths;
The sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window comprises the following steps:
Setting the sliding window at an initial position of each first target sound data sequence, wherein the initial position is a position where first target sound data of a certain first target sound data sequence is located, and the certain first target sound data sequence is a first target sound data sequence with the minimum time length in each first target sound data sequence;
Acquiring a first time length difference value between another first target sound data sequence and a certain first target sound data sequence, and sliding the sliding window on each first target sound data sequence by taking the first time length difference value as a first sliding distance, wherein the another first target sound data sequence is a first target sound data sequence with a distance length adjacent to the certain first target sound data sequence;
acquiring a second time length difference value between a first target sound data sequence and a certain first target sound data sequence, and sliding the sliding window on each first target sound data sequence by taking the second time length difference value as a second sliding distance, wherein the first target sound data sequence is a first target sound data sequence with a distance length adjacent to the other first target sound data sequence;
after each sliding, inputting any first target sound data in the sliding window into a pre-constructed state classification and identification model, wherein the state classification and identification model outputs a state result associated with any first target sound data;
and determining the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
2. The method of claim 1, wherein the re-concatenating the at least one sound sub-data sequence based on time sequence to obtain at least one target sound data sequence comprises:
acquiring at least one first sound sub-data sequence belonging to a certain sound data sequence;
And splicing the at least one first sound sub-data sequence based on the time sequence to obtain a certain target sound data sequence.
3. The method for monitoring the state of a bee colony for bee raising according to claim 1, wherein said inputting any one of the first target sound data in the sliding window after each sliding into the pre-constructed state classification and identification model comprises:
After each sliding, the sliding window has at least one first target sound data of the first target sound data sequence, and the first target sound data of a certain first target sound data sequence is selected and input into a pre-constructed state classification recognition model.
4. The method of claim 1, wherein determining the status of the bee colony corresponding to each of the first target sound data sequences in the first target sound data set based on each status result comprises:
acquiring a state result associated with any one first target sound data in the sliding window, and associating the state result with other first target sound data in the sliding window to obtain at least one state result associated with a certain first target sound data sequence;
Judging whether an abnormal state result exists in at least one state result associated with the certain first target sound data sequence;
If no abnormal state result exists, the bee colony corresponding to the certain first target sound data sequence is in a normal state;
If the abnormal state result exists, the bee colony corresponding to the certain first target sound data sequence is in an abnormal state.
5. A colony status monitoring system for bee rearing, comprising:
The system comprises an intercepting module, a sound extraction module and a sound extraction module, wherein the intercepting module is configured to acquire sound data sequences of at least one bee colony in a preset time period, and intercept each sound data sequence at least once by adopting a preset extraction rule to acquire at least one sound sub-data sequence corresponding to each sound data sequence, wherein the sound data comprises frequency and amplitude of sound;
the step of intercepting each sound data sequence at least once by adopting a preset extraction rule to obtain at least one sound sub-data sequence corresponding to each sound data sequence comprises the following steps:
acquiring at least one abnormal sound data of which the frequency of sound in a certain sound data sequence is not in a preset frequency range;
Removing each abnormal sound data in a certain sound data sequence to obtain at least one sound sub-data sequence corresponding to the certain sound data sequence;
The splicing module is configured to re-splice the at least one sound sub-data sequence based on a time sequence to obtain at least one target sound data sequence, and perform clustering processing on the at least one target sound data sequence by adopting a pre-built clustering rule to obtain at least one target sound data set, wherein the clustering processing on the at least one target sound data sequence by adopting the pre-built clustering rule to obtain the at least one target sound data set comprises:
setting at least one amplitude range;
Clustering each target sound data sequence belonging to a certain amplitude range to obtain a certain target sound data set corresponding to the certain amplitude range;
The sliding module is configured to align each first target sound data sequence in the first target sound data set, and slide on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window, wherein the first target sound data set is any one of the at least one target sound data set, and the sliding distance of each sliding rule is a time length difference value between two first target sound data sequences with adjacent distance lengths;
The sliding on each first target sound data sequence according to a preset sliding rule by adopting a preset sliding window comprises the following steps:
Setting the sliding window at an initial position of each first target sound data sequence, wherein the initial position is a position where first target sound data of a certain first target sound data sequence is located, and the certain first target sound data sequence is a first target sound data sequence with the minimum time length in each first target sound data sequence;
Acquiring a first time length difference value between another first target sound data sequence and a certain first target sound data sequence, and sliding the sliding window on each first target sound data sequence by taking the first time length difference value as a first sliding distance, wherein the another first target sound data sequence is a first target sound data sequence with a distance length adjacent to the certain first target sound data sequence;
acquiring a second time length difference value between a first target sound data sequence and a certain first target sound data sequence, and sliding the sliding window on each first target sound data sequence by taking the second time length difference value as a second sliding distance, wherein the first target sound data sequence is a first target sound data sequence with a distance length adjacent to the other first target sound data sequence;
the output module is configured to input any first target sound data in the sliding window to a pre-constructed state classification and identification model after each sliding, and the state classification and identification model outputs a state result associated with any first target sound data;
And the determining module is configured to determine the state of the bee colony corresponding to each first target sound data sequence in the first target sound data set according to each state result.
6. An electronic device comprising at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411427046.1A CN118969022B (en) | 2024-10-14 | 2024-10-14 | Bee colony state monitoring method and system for bee cultivation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411427046.1A CN118969022B (en) | 2024-10-14 | 2024-10-14 | Bee colony state monitoring method and system for bee cultivation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118969022A CN118969022A (en) | 2024-11-15 |
| CN118969022B true CN118969022B (en) | 2025-02-28 |
Family
ID=93391488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411427046.1A Active CN118969022B (en) | 2024-10-14 | 2024-10-14 | Bee colony state monitoring method and system for bee cultivation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118969022B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108899037A (en) * | 2018-07-05 | 2018-11-27 | 平安科技（深圳）有限公司 | Animal vocal print feature extracting method, device and electronic equipment |
| CN109145032A (en) * | 2018-08-27 | 2019-01-04 | 北京奥金达农业科技发展有限公司 | A kind of bee raising intelligent monitoring method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050049876A1 (en) * | 2003-08-28 | 2005-03-03 | Ian Agranat | Method and apparatus for automatically identifying animal species from their vocalizations |
| CA2891057C (en) * | 2004-11-22 | 2018-11-13 | Kaleo, Inc. | Medicament delivery apparatus and movable indicator |
| CN109599120B (en) * | 2018-12-25 | 2021-12-07 | 哈尔滨工程大学 | Abnormal mammal sound monitoring method based on large-scale farm plant |
| KR102738235B1 (en) * | 2021-12-20 | 2024-12-03 | 세종대학교산학협력단 | Video data labeling method and devicd for animal detection and classification |
| CN114664315A (en) * | 2022-03-11 | 2022-06-24 | 三川智慧科技股份有限公司 | Signal extraction method and device based on noise background |
| CN116978386A (en) * | 2023-01-04 | 2023-10-31 | 云南农业大学 | Voice recognition bee separating method |
| CN118116395A (en) * | 2024-04-02 | 2024-05-31 | 陕西省动物研究所 | Wild animal sound intelligent monitoring system |
-
2024
- 2024-10-14 CN CN202411427046.1A patent/CN118969022B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108899037A (en) * | 2018-07-05 | 2018-11-27 | 平安科技（深圳）有限公司 | Animal vocal print feature extracting method, device and electronic equipment |
| CN109145032A (en) * | 2018-08-27 | 2019-01-04 | 北京奥金达农业科技发展有限公司 | A kind of bee raising intelligent monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118969022A (en) | 2024-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nolasco et al. | To bee or not to bee: Investigating machine learning approaches for beehive sound recognition | |
| CN108664920B (en) | Real-time large-scale cascading face clustering method and device | |
| Uthoff et al. | Acoustic and vibration monitoring of honeybee colonies for beekeeping-relevant aspects of presence of queen bee and swarming | |
| CN109817227B (en) | Abnormal sound monitoring method and system for farm | |
| Sharif et al. | Soundscape indices: new features for classifying beehive audio samples | |
| CN110751960B (en) | Method and device for determining noise data | |
| LU506138B1 (en) | Method for estrus status recognition and individual identity identification of cow based on voiceprint data | |
| CN110140146A (en) | Land use determination system, land use determination method and procedure | |
| CN118352076B (en) | Multi-mode biological calculation driven intelligent poultry health monitoring system and method | |
| CN110692068A (en) | Skill information processing system, method and device | |
| CN113593603A (en) | Audio category determination method and device, storage medium and electronic device | |
| CN114241363A (en) | Process identification method, device, electronic device and storage medium | |
| WO2025076918A1 (en) | Non-intrusive euploidy prediction method and system | |
| CN118969022B (en) | Bee colony state monitoring method and system for bee cultivation | |
| Abdollahi et al. | UrBAN: Urban Beehive Acoustics and PheNotyping Dataset | |
| CN111028862B (en) | Method, apparatus, computer device and storage medium for processing voice data | |
| Chen et al. | A machine learning-based multiclass classification model for bee colony anomaly identification using an IoT-based audio monitoring system with an edge computing framework | |
| Kampelopoulos et al. | Analyzing the beehive’s sound to monitor the presence of the queen bee | |
| CN111277427A (en) | A kind of inspection method and system for data center network equipment | |
| CN110751092B (en) | Agricultural monitoring method and device, storage medium and electronic device based on Internet of Things | |
| CN118568419A (en) | A method and system for optimizing and processing Internet of Things data based on deep-water cages | |
| Borgianni et al. | Spectrogram Based Bee Sound Analysis with DNNs: a step toward Federated Learning approach | |
| CN116264620B (en) | Live broadcast recorded audio data acquisition and processing method and related device | |
| CN112562739A (en) | Large-scale feeding type broiler respiratory disease sound data analysis system | |
| Abdollahi et al. | Performance Comparison of Voice Activity Detectors for Acoustic Beehive Monitoring |
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 |