CN113303320B - Laser bird repelling method, device, equipment and medium - Google Patents
Laser bird repelling method, device, equipment and medium Download PDFInfo
- Publication number
- CN113303320B CN113303320B CN202110854136.9A CN202110854136A CN113303320B CN 113303320 B CN113303320 B CN 113303320B CN 202110854136 A CN202110854136 A CN 202110854136A CN 113303320 B CN113303320 B CN 113303320B
- Authority
- CN
- China
- Prior art keywords
- wavelength
- weight
- laser
- bird repelling
- bird
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M29/00—Scaring or repelling devices, e.g. bird-scaring apparatus
- A01M29/06—Scaring or repelling devices, e.g. bird-scaring apparatus using visual means, e.g. scarecrows, moving elements, specific shapes, patterns or the like
- A01M29/10—Scaring or repelling devices, e.g. bird-scaring apparatus using visual means, e.g. scarecrows, moving elements, specific shapes, patterns or the like using light sources, e.g. lasers or flashing lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Optics & Photonics (AREA)
- Operations Research (AREA)
- Birds (AREA)
- Insects & Arthropods (AREA)
- Pest Control & Pesticides (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Catching Or Destruction (AREA)
Abstract
The application discloses a laser bird repelling method, a laser bird repelling device, laser bird repelling equipment and a laser bird repelling medium, wherein a first weight of each wavelength is obtained based on wavelength scores of laser under different wavelengths; acquiring a second weight of each wavelength according to operation and maintenance data of the laser under different wavelengths; correcting the first weight according to the second weight of each wavelength to obtain the initial weight of each wavelength, and generating a state table based on the initial weight of each wavelength; when detecting that birds approach, selecting the wavelength corresponding to the maximum initial weight in the current state as a target wavelength to emit laser to drive the birds, and obtaining a bird driving result; updating the initial weight of the target wavelength according to the bird repelling result, keeping the initial weight of the non-target wavelength unchanged, and obtaining an updated state table; and entering the next state, returning to the step of emitting laser to drive the birds until the bird is driven, and improving the technical problem that the existing laser bird-driving device is single in wavelength, easy to adapt to birds and poor in bird-driving effect.
Description
Technical Field
The application relates to the technical field of laser bird repelling, in particular to a laser bird repelling method, device, equipment and medium.
Background
With the improvement of ecological environment, the enhancement of consciousness of protecting wild animals by human beings and the construction of environment-friendly society, the number of birds is increasing year by year. Various accidents caused by birds also increase, such as crop yield reduction caused by crop damage, airplane damage caused by bird collision accidents, tripping caused by bird damage on overhead transmission lines and the like. The bird damage accident described above not only affects crop yield quality, aircraft safety, and transmission line stability, but also often causes an unpredictable economic loss.
Aiming at the problem of bird damage prevention, the bird damage prevention is mainly performed by installing a bird repelling device at present. Bird repellent devices in the current market are various, and a laser bird repellent device is one of the common bird repellent devices. The existing laser bird repeller has the problems of single wavelength, no needle pertinence, need of human intervention and the like, the wavelength of laser is often an important factor influencing bird repelling effect, different bird repelling effects can be generated when lasers with different wavelengths repel birds, and single laser wavelength is often easily adapted by birds, so that the bird repelling effect is poor.
Disclosure of Invention
The application provides a laser bird repelling method, a laser bird repelling device, laser bird repelling equipment and a laser bird repelling medium, which are used for solving the technical problem that the existing laser bird repelling device is single in wavelength and easy to adapt to birds, so that the bird repelling effect is poor.
In view of this, the first aspect of the present application provides a laser bird repelling method, including:
after wavelength scores of laser under different wavelengths are obtained, obtaining a weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and carrying out weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength;
acquiring a second weight of each wavelength according to the operation and maintenance data of the collected laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data;
correcting the first weight according to the second weight of each wavelength to obtain an initial weight of each wavelength, and generating a state table based on the initial weight of each wavelength;
when detecting that birds approach, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result;
updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, and keeping the initial weight of the non-target wavelength in the current state in the state table unchanged to obtain the updated state table;
and entering the next state, returning to the step of selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as the target wavelength when detecting that birds approach, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result until the bird driving is finished.
Optionally, the updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result includes:
determining a reward and punishment value according to the bird repelling result;
acquiring a learning rate based on the reward and punishment value;
updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
Optionally, the determining a reward penalty value according to the bird repelling result includes:
when the bird repelling result is bird repelling success, taking a first preset value as a reward punishment value;
when the bird repelling result is bird repelling failure, taking a second preset value as a reward punishment value;
wherein the first preset value is greater than the second preset value.
Optionally, obtaining the learning rate based on the reward and punishment value includes:
and weighting the deviation value of the average value of the reward punishment value and the historical reward punishment value in the current state through a preset growth coefficient to obtain the learning rate.
Optionally, the updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value includes:
updating the initial weight of the target wavelength in the current state in the state table through a weight updating formula based on the learning rate and the reward and punishment value, wherein the weight updating formula is as follows:
in the formula (I), the compound is shown in the specification,Q(S 0,i ) Is the current state in the state tableS 0Lower target wavelengthi The updated initial weight of the mobile terminal,α(R,β) In order to obtain a learning rate,Ris a reward and punishment value of the prize,
in order to be able to obtain the attenuation coefficient,βin order to preset the growth factor,Q(S 1,i ) Is the next state in the state tableS 1Lower target wavelengthi The initial weight of (2).
This application second aspect provides a laser bird repellent device, includes:
the first obtaining unit is used for obtaining the wavelength scores of the laser under different wavelengths, obtaining the weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and performing weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength;
the second acquisition unit is used for acquiring second weights of the wavelengths according to the collected operation and maintenance data of the laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data;
a correction unit configured to correct the first weight according to the second weight of each wavelength to obtain an initial weight of each wavelength, and generate a state table based on the initial weight of each wavelength;
the laser emission unit is used for selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength when detecting that birds approach, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result;
the updating unit is used for updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, keeping the initial weight of the non-target wavelength in the current state in the state table unchanged, and obtaining the updated state table;
and the triggering unit is used for entering the next state and triggering the laser emission unit until bird repelling is finished.
Optionally, the updating unit specifically includes:
the determining subunit is used for determining a reward and punishment value according to the bird repelling result;
an obtaining subunit, configured to obtain a learning rate based on the reward and punishment value;
and the updating subunit is used for updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
Optionally, the obtaining subunit is specifically configured to:
and weighting the deviation value of the average value of the reward punishment value and the historical reward punishment value in the current state through a preset growth coefficient to obtain the learning rate.
A third aspect of the application provides a laser bird repelling device, which comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute any one of the laser bird repelling methods according to instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium for storing program codes for executing the laser bird repelling method according to any one of the first aspects.
According to the technical scheme, the method has the following advantages:
the application provides a laser bird repelling method, which comprises the following steps: after wavelength scores of laser under different wavelengths are obtained, obtaining a weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and carrying out weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength; acquiring a second weight of each wavelength according to the operation and maintenance data of the collected laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data; correcting the first weight according to the second weight of each wavelength to obtain the initial weight of each wavelength, and generating a state table based on the initial weight of each wavelength; when detecting that birds approach, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result; updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, and keeping the initial weight of the non-target wavelength in the current state in the state table unchanged to obtain an updated state table; entering the next state, returning to the state that when the bird is detected to approach, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as the target wavelength, and emitting laser with the target wavelength to drive the bird, so as to obtain a bird driving result until the bird driving is finished.
According to the method, the weight coefficient of each wavelength score is obtained according to the mean value and the standard deviation of the wavelength score of each wavelength, the first weight of each wavelength is further determined, the second weight of each wavelength is obtained according to operation and maintenance data of actually collected laser under different wavelengths, the first weight is corrected according to the second weight of each wavelength, so that the initial weight of each wavelength is more accurate, then laser emitting the wavelength corresponding to the maximum initial weight is selected to bird repellent, the initial weight is updated according to bird repellent results, and laser emitting the wavelength corresponding to the maximum weight is selected again to bird repellent based on the updated initial weight, so that the technical problems that the existing laser bird repeller is single in wavelength, easy to adapt to birds and poor in bird repellent effect are solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a laser bird repelling method provided in an embodiment of the present application;
fig. 2 is a flowchart illustrating a weight updating process according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a laser bird repelling device provided in the embodiment of the present application.
Detailed Description
The application provides a laser bird repelling method, a laser bird repelling device, laser bird repelling equipment and a laser bird repelling medium, which are used for solving the technical problem that the existing laser bird repelling device is single in wavelength and easy to adapt to birds, so that the bird repelling effect is poor.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, please refer to fig. 1, an embodiment of a laser bird repelling method provided by the present application includes:
According to the characteristics of different sensitivity degrees of birds to lasers with different wavelengths, scoring is carried out on the wavelengths by different experts to obtain the wavelength scores of the lasers under different wavelengths by the expertsX ij Wherein, in the step (A),X ij is as followsjFor the expert toiThe scoring of the number of wavelengths is such that,i=1,2,...,n，j=1,2,...,m，nas to the number of wavelengths,mthe total number of experts.
After the wavelength scores are obtained, calculating the mean value and the standard deviation of the wavelength scores of all the wavelengths, wherein the mean value calculation formula is as follows:
the standard deviation calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
is as followsjThe average of the scores for each wavelength is assigned by the expert,S j is as followsjThe standard deviation of the scores for each wavelength is assigned to the bit expert.
Then, calculating the ratio of the standard deviation of the wavelength score of each wavelength to the mean value to obtain the evaluation coefficient of each expert, namely:
in the formula (I), the compound is shown in the specification,C j is as followsjAnd evaluating coefficients of experts.
Normalizing the evaluation coefficients of the experts to obtain the weight coefficient of each wavelength score
Wherein, in the step (A),
in the formula (I), the compound is shown in the specification,
is normalized tojAnd evaluating coefficients of experts.
And carrying out weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength, namely:
in the formula (I), the compound is shown in the specification,r i is as followsiA first weight of a wavelength.
And 102, acquiring a second weight of each wavelength according to the collected operation and maintenance data of the laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data.
Within a period of time after the laser bird repelling device is installed, operation and maintenance data of the laser at different wavelengths collected by operation and maintenance personnel or a camera are recorded, reactions of birds at different wavelengths are recorded, the reactions of the birds at different wavelengths are quantified, and data of different wavelengths under various bird repelling effect indexes can be obtainedf ik The bird repelling effect index can be distinguished according to the effectiveness of repelling birds, and can be divided into bird flying away, bird watching and bird non-response. The specific quantization rule may be specifically set according to actual conditions, and is not specifically limited herein.
The data of different wavelengths under various bird repelling effect indexes are subjected to standardization treatment, and the standardization treatment can be carried out by adopting any one of the following two modes.
The first method is as follows:
the second method comprises the following steps:
in the formula (I), the compound is shown in the specification,f ik is as followsiA wavelength atkThe data under the index of bird repelling effect is acquired,k=1,2,...,q，qthe number of the bird repelling effect indexes is shown;d ik is the normalized firstiA wavelength atkThe data under the index of bird repelling effect is acquired,maxit is indicated that the maximum value is taken,minindicating taking the minimum value.
Calculating the information entropy of each bird repelling effect index according to the standardized data of each wavelength under each bird repelling effect index, namely:
wherein the content of the first and second substances,E k is as followskThe information entropy of the bird repelling effect index is obtained.
And finally, calculating a second weight of each wavelength according to the standardized data of each wavelength under each bird repelling effect index and the information entropy of each bird repelling effect index, namely:
in the formula (I), the compound is shown in the specification,v i is as followsiA second weight of a wavelength.
The first weight is obtained through subjective scoring of experts, and certain subjectivity exists, so that the method and the device for obtaining the laser weight obtain the second weight according to operation and maintenance data of the actually collected laser under different wavelengths, and correct the first weight through the second weight to obtain more accurate weight. The specific modification method may be that the first weight is weighted by the second weight, that is:
in the formula (I), the compound is shown in the specification,t i is as followsiThe initial, i.e. corrected weight of an individual wavelength,
the scaling factor may be specifically set according to actual conditions, and is not specifically limited herein.
After the initial weight of each wavelength is obtained, a state table is generated based on the initial weight of each wavelength, and the value in the state table is the initial weight corresponding to each wavelength.
And 104, when detecting that birds approach, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result.
The existing detection model can be embedded into the laser bird repelling device to detect whether birds are close to the laser bird repelling device or not, and other detection methods can be used for detecting whether the birds are close to the laser bird repelling device or not. When detecting that birds are close to the laser bird repelling device, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as the target wavelength, and emitting the laser with the target wavelength to repel the birds to obtain a bird repelling result.
And 105, updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, and keeping the initial weight of the non-target wavelength in the current state in the state table unchanged to obtain an updated state table.
Referring to fig. 2, the specific steps of updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result are as follows:
s1051, determining a reward and punishment value according to the bird repelling result;
when the bird repelling result is that bird repelling is successful, taking the first preset value as a reward punishment value;
when the bird repelling result is bird repelling failure, taking the second preset value as a reward punishment value;
wherein the first preset value is greater than the second preset value.
The first preset value and the second preset value may be specific values selected according to actual situations, and are not specifically limited herein.
S1052, acquiring a learning rate based on the reward and punishment values;
the method comprises the following steps of weighting a deviation value of a reward punishment value and a historical reward punishment value average value in the current state through a preset growth coefficient to obtain a learning rate, namely:
in the formula (I), the compound is shown in the specification,α(R,β) In order to obtain a learning rate,Ris the reward and punishment value in the current state,βin order to preset the growth factor,
the average value of the historical reward and punishment values is obtained by calculating the average value of the reward and punishment values obtained by bird repelling of the previously emitted laser.
Learning rateαDetermines the extent to which the newly acquired information overwrites the old information,αat 0, it means that nothing is learned,αwhen 1, only the latest information is considered.
And S1053, updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
Updating the initial weight of the target wavelength in the current state in the state table through a weight updating formula based on the learning rate and the reward and punishment value, wherein the weight updating formula is as follows:
in the formula (I), the compound is shown in the specification,Q(S 0,i ) Is the current state in the state tableS 0Lower target wavelengthi The updated initial weight of the mobile terminal,α(R,β) In order to obtain a learning rate,Ris a reward and punishment value of the prize,
in order to be able to obtain the attenuation coefficient,βin order to preset the growth factor,Q(S 1,i ) Is the next state in the state tableS 1Lower target wavelengthi The initial weight of (2).
Coefficient of attenuation
The importance of the future award is determined,
at 0, it becomes "opportunistic" and only the current reward is considered, whereas when it is 0γNear 1, a long-term high return is strived for. The dynamic learning rate increases the learning amount at high returns and decreases the learning amount at low returns.
This application embodiment, drive the bird back according to the laser of transmission target wavelength, according to driving bird result and confirming reward punishment value and learning rate, and then update the initial weight of this target wavelength, obtain initial weight after the update, when adaptability appears in birds like this, the bird effect of driving of the wavelength of original biggest initial weight value reduces gradually promptly, the reward punishment value that uses this wavelength to obtain this moment and the learning rate that calculates reduce gradually, and then select new wavelength to drive the bird, make laser drive the bird effect and remain the best throughout, bird adaptability problem that bird leads to has been avoided single wavelength to drive the bird.
The initial weight of the target wavelength in the current state in the state table is updated by the method, and the initial weight of the non-target wavelength (i.e. the wavelength except the target wavelength) in the current state in the state table is kept unchanged, so that the updated state table is obtained.
And step 106, entering the next state, and returning to the step 104 until bird repelling is finished.
Entering the next state as the current state, the state table at this time is the state table updated in the above step 105, returning to step 104, when birds are detected, sending the wavelength corresponding to the maximum initial weight in the current state in the state table as the target wavelength to transmit, and updating the initial weight of the target wavelength according to the bird repelling result until bird repelling is finished, wherein the weight updating method of the target weight in each state refers to the weight updating method in the step 105.
In the embodiment of the application, the weight coefficient of each wavelength score is obtained according to the mean value and the standard deviation of the wavelength score of each wavelength, so that the first weight of each wavelength is determined, the second weight of each wavelength is obtained according to the operation and maintenance data of the laser collected actually under different wavelengths, the first weight is corrected according to the second weight of each wavelength, so that the initial weight of each wavelength is more accurate, then the laser emitting the wavelength corresponding to the maximum initial weight is selected to bird repellent, the initial weight is updated according to the bird repellent result, and the laser emitting the wavelength corresponding to the maximum weight is selected again to bird repellent based on the updated initial weight, so that the technical problems that the existing laser bird repeller is single in wavelength, easy to adapt to birds and poor in bird repellent effect are solved.
The above is an embodiment of the laser bird repelling method provided by the application, and the following is a specific application example of the laser bird repelling method provided by the application.
The examples of this application were chosen based on birds having four types of cone cells, which are sensitive to ultraviolet light in addition to red, blue and greennAnd the wavelengths of the 4 kinds of the ultraviolet light, the blue light, the green light and the red light are respectively 360nm, 450nm, 550nm and 650 nm. Suppose there ism=5 experts rate the bird-repelling effect of the laser with different wavelengths according to different rating standards, and the specific scores are shown in table 1 below:
TABLE 1 scoring table
The mean and standard deviation of each expert score were calculated to obtain the evaluation coefficients, as shown in tables 2, 3 and 4.
TABLE 2 mean values of scores
TABLE 3 score Standard deviation
TABLE 4 evaluation coefficients
Normalization processing is performed according to the evaluation coefficients of the experts obtained by the calculation, and a weight coefficient is obtained, as shown in table 5.
TABLE 5 weight coefficients
The wavelength scores are weighted and summed according to the weight coefficients of the wavelength scores to obtain a first weight of each wavelength, as shown in table 6.
TABLE 6 first weight for each wavelength
Standardizing the collected operation and maintenance data, wherein the index of bird repelling effect is divided into bird flying away, bird watching and bird non-response, namelyq=3, as shown in table 7.
Table 7 data of each wavelength before and after standardization under each bird repelling effect index
And calculating the information entropy of each bird repelling effect index according to the standardized data of each wavelength under each bird repelling effect index, as shown in table 8.
And finally, calculating a second weight of each wavelength according to the standardized data of each wavelength under each bird repelling effect index and the information entropy of each bird repelling effect index, as shown in table 9.
TABLE 8 entropy of information
TABLE 9 second weight for each wavelength
The first weight is corrected based on the second weight of each wavelength to obtain an initial weight of each wavelength, as shown in table 10.
TABLE 10 initial weights for each wavelength
Generating a state table based on the initial weight of the obtained wavelength, wherein the state table is provided with statesS 0AndS 1in this case, the initial weights of the same wavelength in each state are the same, and the obtained state table is shown in table 11.
TABLE 11 status table
In the current stateS 0Next, when bird closeness is detected, the largest initial weight Q in the status table is selected (S 0And 4) =43.9836 the corresponding wavelength 4 is the target wavelength emission laser bird repellent. Average value of reward and punishment values at the moment
Is 0, set upβ=0.05, if the bird is successfully driven, a reward and punishment value is setR=10, learning rateα= 0.5; if bird repelling fails, reward punishment valueR=10, learning rateα= 0.5. Then, updating the initial weight of the target wavelength 4 through a weight updating formula, wherein if the bird repelling is successful, the initial weight after the target wavelength 4 is updated is Q (S 04) = 46.78442; if bird repelling fails, the initial weight after the target wavelength 4 is updated is Q (S 04) =36.78442 keeping the initial weight of the non-target wavelength unchanged. After updating the weight, entering the next stateS 1(in the case of only two states in the state table,S 1next one of (2)The state isS 0) If the bird repelling fails last time, the updated state table is shown in table 12.
Table 12 updated state table
When each state of the laser bird repelling device is updated, the state is fed back according to a reward and punishment value of a bird repelling result, a weight updating formula is used for updating, when a certain wavelength fails to repel birds for multiple times, the wavelength weight is reduced by the laser bird repelling device, in addition, the optimal wavelength is selected, and the action executed each time is ensured to be the maximum expected yield; in addition, the embodiment of the application adopts the dynamic learning rate to update the weight, so that the updating process is accelerated, the selection time of the optimal wavelength is shortened, and the problem that the laser bird repelling device generates a new optimal wavelength for too long time when birds generate adaptability is also avoided.
The above is a specific application example of the laser bird repelling method provided by the present application, and the following is an embodiment of the laser bird repelling device provided by the present application.
Referring to fig. 3, an embodiment of the present application provides a laser bird repelling device, including:
the first obtaining unit is used for obtaining the wavelength scores of the laser under different wavelengths, obtaining the weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and carrying out weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength;
the second acquisition unit is used for acquiring a second weight of each wavelength according to the operation and maintenance data of the acquired laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data;
a correction unit for correcting the first weight according to the second weight of each wavelength to obtain an initial weight of each wavelength, and generating a state table based on the initial weight of each wavelength;
the laser emission unit is used for selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength when detecting that birds approach, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result;
the updating unit is used for updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, keeping the initial weight of the non-target wavelength in the current state in the state table unchanged, and obtaining an updated state table;
and the triggering unit is used for entering the next state and triggering the laser emission unit until bird repelling is finished.
As a further improvement, the updating unit specifically includes:
the bird repelling unit is used for repelling birds;
the acquisition subunit is used for acquiring a learning rate based on the reward and punishment values;
and the updating subunit is used for updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
As a further improvement, the acquisition subunit is specifically configured to:
and weighting the deviation value of the average value of the reward punishment value and the historical reward punishment value in the current state through a preset growth coefficient to obtain the learning rate.
In the embodiment of the application, the weight coefficient of each wavelength score is obtained according to the mean value and the standard deviation of the wavelength score of each wavelength, so that the first weight of each wavelength is determined, the second weight of each wavelength is obtained according to the operation and maintenance data of the laser collected actually under different wavelengths, the first weight is corrected according to the second weight of each wavelength, so that the initial weight of each wavelength is more accurate, then the laser emitting the wavelength corresponding to the maximum initial weight is selected to bird repellent, the initial weight is updated according to the bird repellent result, and the laser emitting the wavelength corresponding to the maximum weight is selected again to bird repellent based on the updated initial weight, so that the technical problems that the existing laser bird repeller is single in wavelength, easy to adapt to birds and poor in bird repellent effect are solved.
The embodiment of the application also provides laser bird repelling equipment, which comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the laser bird repelling method in the embodiment of the method according to the instructions in the program code.
The embodiment of the application also provides a computer-readable storage medium, which is used for storing a program code, and the program code is used for executing the laser bird repelling method in the foregoing method embodiment.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (6)
1. A laser bird repelling method is characterized by comprising the following steps:
after wavelength scores of laser under different wavelengths are obtained, obtaining a weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and carrying out weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength;
acquiring a second weight of each wavelength according to the operation and maintenance data of the collected laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data;
correcting the first weight according to the second weight of each wavelength to obtain an initial weight of each wavelength, and generating a state table based on the initial weight of each wavelength;
when detecting that birds approach, selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result;
updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, and keeping the initial weight of the non-target wavelength in the current state in the state table unchanged to obtain the updated state table;
entering a next state, returning to the step of selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength when bird approaching is detected, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result until bird driving is finished;
the updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result comprises:
determining a reward and punishment value according to the bird repelling result;
obtain the learning rate based on reward punishment value specifically includes: weighting a deviation value of the reward and punishment value and the average value of the historical reward and punishment values in the current state through a preset growth coefficient to obtain a learning rate;
updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
2. The laser bird repelling method according to claim 1, wherein the determining a reward penalty value according to the bird repelling result comprises:
when the bird repelling result is bird repelling success, taking a first preset value as a reward punishment value;
when the bird repelling result is bird repelling failure, taking a second preset value as a reward punishment value;
wherein the first preset value is greater than the second preset value.
3. The laser bird repelling method according to claim 1, wherein the updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and penalty value comprises:
updating the initial weight of the target wavelength in the current state in the state table through a weight updating formula based on the learning rate and the reward and punishment value, wherein the weight updating formula is as follows:
in the formula (I), the compound is shown in the specification,Q(S 0,i ) Is the current state in the state tableS 0Lower target wavelengthi The updated initial weight of the mobile terminal,α(R,β) In order to obtain a learning rate,Ris a reward and punishment value of the prize,γin order to be able to obtain the attenuation coefficient,βin order to preset the growth factor,Q(S 1,i ) Is the next state in the state tableS 1Lower target wavelengthi The initial weight of (2).
4. The utility model provides a laser bird repellent device which characterized in that includes:
the first obtaining unit is used for obtaining the wavelength scores of the laser under different wavelengths, obtaining the weight coefficient of each wavelength score according to the mean value and the standard deviation of the wavelength scores of each wavelength, and performing weighted summation on each wavelength score according to the weight coefficient of each wavelength score to obtain a first weight of each wavelength;
the second acquisition unit is used for acquiring second weights of the wavelengths according to the collected operation and maintenance data of the laser under different wavelengths and the information entropy of each bird repelling effect index calculated on the basis of the operation and maintenance data;
a correction unit configured to correct the first weight according to the second weight of each wavelength to obtain an initial weight of each wavelength, and generate a state table based on the initial weight of each wavelength;
the laser emission unit is used for selecting the wavelength corresponding to the maximum initial weight in the current state in the state table as a target wavelength when detecting that birds approach, and emitting laser with the target wavelength to drive the birds to obtain a bird driving result;
the updating unit is used for updating the initial weight of the target wavelength in the current state in the state table according to the bird repelling result, keeping the initial weight of the non-target wavelength in the current state in the state table unchanged, and obtaining the updated state table;
the triggering unit is used for triggering the laser emitting unit to enter the next state until bird repelling is finished;
the updating unit specifically includes:
the determining subunit is used for determining a reward and punishment value according to the bird repelling result;
an obtaining subunit, configured to obtain a learning rate based on the reward and punishment value, and specifically configured to: weighting a deviation value of the reward and punishment value and the average value of the historical reward and punishment values in the current state through a preset growth coefficient to obtain a learning rate;
and the updating subunit is used for updating the initial weight of the target wavelength in the current state in the state table based on the learning rate and the reward and punishment value.
5. A laser bird repelling device is characterized by comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the laser bird repelling method according to any one of claims 1-3 according to instructions in the program code.
6. A computer-readable storage medium for storing program code for performing the laser bird repelling method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854136.9A CN113303320B (en) | 2021-07-28 | 2021-07-28 | Laser bird repelling method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854136.9A CN113303320B (en) | 2021-07-28 | 2021-07-28 | Laser bird repelling method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113303320A CN113303320A (en) | 2021-08-27 |
| CN113303320B true CN113303320B (en) | 2021-11-02 |
Family
ID=77381811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110854136.9A Active CN113303320B (en) | 2021-07-28 | 2021-07-28 | Laser bird repelling method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113303320B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104738023A (en) * | 2015-04-24 | 2015-07-01 | 方仲平 | Intelligent bird repelling device |
| JP3212816U (en) * | 2017-07-12 | 2017-10-05 | 稔晃 鈴木 | Bird pest repayment countermeasure device |
| CN108812634A (en) * | 2018-05-22 | 2018-11-16 | 上海亚明照明有限公司 | Scarer, method, computer readable storage medium and electric terminal |
| CN113053413A (en) * | 2021-03-23 | 2021-06-29 | 广东电网有限责任公司江门供电局 | Method and device for selecting simulated sound bird repelling audio frequency |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6625918B2 (en) * | 2001-12-03 | 2003-09-30 | Tarseam S. Bhullar | Pest deterrent |
-
2021
- 2021-07-28 CN CN202110854136.9A patent/CN113303320B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104738023A (en) * | 2015-04-24 | 2015-07-01 | 方仲平 | Intelligent bird repelling device |
| JP3212816U (en) * | 2017-07-12 | 2017-10-05 | 稔晃 鈴木 | Bird pest repayment countermeasure device |
| CN108812634A (en) * | 2018-05-22 | 2018-11-16 | 上海亚明照明有限公司 | Scarer, method, computer readable storage medium and electric terminal |
| CN113053413A (en) * | 2021-03-23 | 2021-06-29 | 广东电网有限责任公司江门供电局 | Method and device for selecting simulated sound bird repelling audio frequency |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113303320A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Geyle et al. | Quantifying extinction risk and forecasting the number of impending Australian bird and mammal extinctions | |
| Chitwood et al. | White‐tailed deer population dynamics and adult female survival in the presence of a novel predator | |
| Winder et al. | Effects of wind energy development on survival of female greater prairie‐chickens | |
| Candy et al. | Modelling the impact of defoliation by the leaf beetle, Chrysophtharta bimaculata (Coleoptera: Chrysomelidae), on height growth of Eucalyptus regnans | |
| Rota et al. | Space-use and habitat associations of Black-backed Woodpeckers (Picoides arcticus) occupying recently disturbed forests in the Black Hills, South Dakota | |
| Kilgo et al. | Factors affecting breeding season survival of red‐headed woodpeckers in South Carolina | |
| Vanderwerf | Importance of nest predation by alien rodents and avian poxvirus in conservation of Oahu Elepaio | |
| Taylor et al. | Legacy of insect defoliators: increased wind-related mortality two decades after a spruce budworm outbreak | |
| CN113303320B (en) | Laser bird repelling method, device, equipment and medium | |
| Rieucau et al. | Many eyes or many ewes: vigilance tactics in female bighorn sheep Ovis canadensis vary according to reproductive status | |
| JP2017205033A (en) | Countermeasure system against damage by birds or animals | |
| Machado et al. | Citrus black spot severity related to premature fruit drop in sweet orange orchards | |
| Blomberg | The influence of harvest timing on greater sage‐grouse survival: A cautionary perspective | |
| Loveridge et al. | Science and the recreational hunting of lions | |
| White et al. | Investigating the effects of predator removal and habitat management on nest success and breeding population size of a farmland passerine: a case study | |
| KR102234897B1 (en) | Method for recommending agricultural chemical in pest forecast system | |
| Pallante et al. | Calming an aggressor through spontaneous post‐conflict triadic contacts: Appeasement in Macaca tonkeana | |
| Coleman et al. | A 20-year synthesis to the Lymantria dispar slow the spread program | |
| CN113672940A (en) | Service data monitoring method, system, device and medium | |
| CN107704761B (en) | Data processing method and device, electronic equipment and storage medium | |
| Shtienberg et al. | Wheat Disease Control Advisory, a decision support system for management of foliar diseases of wheat in Israel | |
| Bonnot et al. | Factors affecting mourning dove harvest in Missouri | |
| Wilson et al. | Responses of deltapine 16 cotton Gossypium hirsutum L. to simulated attacks by known populations of Heliothis larvae (Lepidoptera: Noctuidae) in a field experiment in Queensland, Australia | |
| Roberts | Atlantic Flyway Breeding Waterfowl Plot Survey | |
| Hoffman et al. | Examination of annual variation in the adult sex ratio of pronghorn (Antilocapra americana) |
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 |