CN117609413B - Wild animal channel design method and system - Google Patents

Abstract

The application relates to the technical field of wild animal data processing, in particular to a wild animal channel design method and a wild animal channel design system; the process for obtaining the channel density through the deep learning model comprises the following steps: acquiring a training set of the deep learning model; establishing a deep learning model and training to obtain the deep learning model for channel density prediction; inputting parameters of a target area into the deep learning model to obtain predicted channel density; according to the invention, the deep learning model is applied to the channel density parameter design, so that more accurate channel density design data is obtained, and in the process of applying the deep learning model to the channel design parameter design, aiming at the characteristics that the existing data set has the utilization rate and can verify whether the data set is an optimal data set, the data set is further processed by the method, so that the data set is the optimal data set, and the predicted parameter obtained by the model is close to the optimal parameter, so that the scientificity of the channel design is improved.

Description

Wild animal channel design method and system

Technical Field

The invention relates to the technical field of wild animal data processing, in particular to a wild animal channel design method and a wild animal channel design system.

Background

The wild animal channel is a linear habitat and is mainly used for connecting wild animals in more than 2 habitat areas, so that the influence of artificial isolation factors among habitats caused by artificial water flow, roads or human settlement areas is reduced, and the free migration of the wild animals is facilitated. Wild animal channels can be formally divided into 3 types, namely, a top-span channel, a bottom-through channel and a gentle slope channel.

In the prior art, a technical scheme of wild animal channel design is disclosed in, for example, chinese patent (CN 110263107 a), which discloses a construction method of a landscape type animal corridor, by obtaining species distribution data of a first ecological area, determining a target population and species distribution situation applicable to the landscape type animal corridor according to the species distribution data, generating a species distribution diagram, obtaining vegetation data of the first ecological area, generating a regional vegetation type diagram according to the vegetation data, extracting a second ecological area corresponding to a natural forest from the vegetation type diagram, obtaining ecological environment demand information of the target population, determining a target ecological environment channel corresponding to the target population from the second ecological area according to the ecological environment demand information, and constructing the landscape type animal corridor according to the target ecological environment channel, so that threat of ecological environment fragmentation to survival of rare endangered species can be reduced by constructing the landscape type animal corridor, and diffusion and migration of species in an artificially isolated region can be promoted. However, the above-described scheme may result in not high scientificity and accuracy of channel design parameters when designing a wild animal channel by only empirically designing the channel design parameters.

Therefore, there is a great need in the art for a solution for wild animal channel design that improves the discipline and accuracy of the design.

Disclosure of Invention

The technical problem to be solved by the invention is to provide a wild animal channel design method and system for improving the academic system and accuracy of design in view of the defects of the technical scheme.

In order to achieve the above object, according to one aspect of the present invention, there is provided a wild animal channel designing method comprising the steps of:

s1: acquiring target population distribution data of wild animals in a target area;

s2: acquiring the target group according to the target group distribution data;

s3: acquiring the wild animal channel design parameters according to the target group;

the parameters include channel type, channel position, channel size, and channel density;

the process of obtaining the channel density through the deep learning model comprises the following steps:

sa: acquiring a training set of the deep learning model;

sb: establishing a deep learning model and training to obtain the deep learning model for channel density prediction;

sc: and inputting parameters of the target area into the deep learning model to obtain predicted channel density.

Preferably, in the step S1, the target population of the target area is obtained by referring to the data or by setting a wild animal monitoring device in the target area.

Preferably, in S2, the target group is divided into: four groups of large mammals, small and medium mammals, amphibians, reptiles;

further, the target population of the target region wild animals is one or more.

Preferably, in the step S3, the channel types include three types of overpasses, bridge channels and culverts;

further, mammalian channel types are overpass and bridge channels; the type of channel for amphibians and reptiles is culvert.

Preferably, the channel location is disposed on a migration or activity route of the wild animal; designing the channel size according to the target population and the channel type;

further, for large mammalian groups, the large mammalian groups are designed into overpass channels or bridge channels, wherein the minimum dimension of the overpass channels is 50m in length and 40m in width;

for small and medium-sized mammal groups, designing a bridge channel, wherein the length of the bridge channel is not less than 10m, and the width of the bridge channel is not less than 2.5m;

for amphibian and reptile populations, culvert channels are designed, wherein the minimum diameter of the culvert channels is 0.3m.

Preferably, in the step S3, the channel design cases at home and abroad are used as training sets;

in this embodiment, the channel design parameters are improved according to the channel utilization rate after the use of the domestic and foreign channel design cases, and if the channel utilization rate is lower than the preset threshold value, the number of the channels is larger, so that the channel utilization rate is not high, and therefore, the channel density needs to be reduced.

It is worth emphasizing that each training set includes: wild animal herds of the target area, number of each herd, channel type, channel density.

Preferably, the deep learning model is an artificial neural network model.

According to another aspect of the present invention, there is provided a wild animal channel design system employing the wild animal channel design method described above, the system comprising:

the target population distribution data acquisition module is used for acquiring target population distribution data of the wild animals in the target area;

the target group acquisition module is connected with the target group distribution data acquisition module and is used for acquiring the target group according to the target group distribution data;

the channel design parameter acquisition module is connected with the target group acquisition module and is used for acquiring the wild animal channel design parameters according to the target group.

According to another aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a data processing program for execution by a processor of a wild animal channel design method as described above.

Based on the technical scheme, the wild animal channel design method and system provided by the application have the following technical effects:

according to the invention, the deep learning model is applied to the channel density parameter design, so that more accurate channel density design data is obtained, and in the process of applying the deep learning model to the channel design parameter design, aiming at the characteristics that the existing data set has the utilization rate and can verify whether the data set is an optimal data set, the data set is further processed by the method, so that the data set is the optimal data set, and the predicted parameter obtained by the model is close to the optimal parameter, so that the scientificity of the channel design is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for designing a wild animal channel according to an embodiment of the present application;

fig. 2 is a flowchart of channel density prediction using a deep learning model according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings of the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The concepts related to the present application will be described with reference to the accompanying drawings. It should be noted that the following descriptions of the concepts are only for making the content of the present application easier to understand, and do not represent a limitation on the protection scope of the present application.

In the first embodiment, in the case of the present embodiment, when the wild animal channel is designed, the position and the structure form of the channel are first clarified, and the channel is considered to be arranged at the place where the mortality rate of the river and the road is high, because the requirement of the wild animal crossing in the area is high, the contradiction between the wild animal crossing and the road traffic is most prominent; secondly, mastering the biological habit and daily or seasonal migration (migration) route of the wild animals; and finally, setting the positions and the number of the channels based on the overall requirements of the regional landscape pattern, and exerting the connection effect of the channels to the maximum extent. Specifically, wild animal channel design should generally consider the following principles:

research principle: systematic research and evaluation are carried out on the effectiveness of the established animal channel, main factors influencing the exertion of the wild animal channel effect are analyzed, the internal relation between the type, habit and animal channel utilization rate of the wild animal is researched, and the practical experience of animal channel design is accumulated.

Economic principle: the most economical design is to achieve maximum protection of the target population with minimal expense.

The design principle of the method is that in the stage of river diversion or road planning and design, the wild animal protection and the wild animal channel design are considered in advance, and if the influence of the construction project on the ecological environment is large, the ecological environment and the engineering budget of the wild animal protection are properly increased, and the animal channel is designed as much as possible to meet the passing requirements of the wild animals.

The structure comprehensive utilization principle: the efficiency of the combined use of the wild animal channel, the protective net, the induction facility and the like is obviously higher than that of the single wild animal channel.

Channel size is in accordance with local regulations: the wild animal can adapt to different channel types and design structures by self-adjusting the life habit, so that the design size of the wild animal channel needs to consider factors such as the size of the target population, the life habit and the like, and the minimum requirement is to meet the passing of the local target population.

Landscape angle site selection principle: in the construction of wild animal tunnels, the choice of location is important, and site selection based on wild animal track data and road mortality is not the best choice. In contrast, to make the best choice for exerting long-term effects, the location of the wild animal's passageway must be determined from the actual needs of the wild animal's migration corridor and the overall landscape architecture.

Principle of sustainable effect of ensuring channel action: factors influencing the continued functioning of the wild animal pathway are many factors such as the adaptation of the wild animal to environmental changes, population number characteristics, self-life habits, habitat conditions and nearby human behaviour. In order to keep the wild animal channel as continuously as possible to achieve the optimum effect, it is necessary to reduce the influence of various factors as continuously as possible.

As shown in fig. 1, a wild animal channel design method comprises the following steps:

s1: acquiring target population distribution data of wild animals in the target area;

specifically, the target population of the wild animals in the target area refers to a main protection object for setting a wild animal channel, and for different animal populations, protection animals, key animals, dominant species or common species in the local area are generally selected as target populations, and according to animal ecological geography division, the target populations are mainly divided into the following 8 types:

(1) Cold-warm zone conifer forest animal group

Distributed in northeast (north of great and lesser Khingan) and north of Xinjiang Uygur autonomous region (Altaishan region), has simple animal group composition, obvious seasonal cluster phenomenon of birds and weak excavation activity of ground rodents. Among the animals, the elk, red deer, musk, spore and wild boar are the most common, and the dominant species or common species in rodents are sapling squirrel, semi-sapling flower mouse and ground macrophyte Lin Jishu. Ferrets, brown bear, foxes, badgers, etc. are common among the carnivores. The hazelnut, the black-mouth crow and the black-mouth chicken are all giant salamander with frigid poles. Temperate birds, seasonal clusters are more apparent. Amphibious and reptile are few.

(2) Temperate forest, forest grassland animal group

The Chinese medicinal materials are distributed in vast temperate regions of the northeast needle leaf forest zone from south to Qinling, and the first line of Huaihe river to north, and the roe deer, wild boar, zegahorn, ferret, black bear, raccoon dog, ferret, leopard, northeast rabbit, squirrel, hedgehog, etc. in the beast are common or dominant species. The seasonal variation of the bird composition is obvious, and the dominant species and common species are large peaches, swamp peaches, three-way plague ducks, duckling, ash , magpie, girl pheasants and the like. Reptiles are widely found in various places, including tiger-neck snake, yellow-spine snake, red-chain snake, red-spotted snake, pallas pit viper, libane, etc. The dominant species in amphibians are Bufo siccus, bufo siccus dorsi, pleurotus Eryngii, north slit frog, and Rana chensinensis.

(3) Temperate grassland animal group

Distributed in eastern hay lands of the inner Mongolian autonomous region, especially flourishing animals, such as herbivorous rodents (field mice, yellow mice, rats, rabbits and dry forehead), and few ungulates, but a large number of yellow sheep are dominant species, and often grow into large groups of water-repellent weeds to migrate for a long distance. Meat is most commonly eaten by wolves, foxes, ai Chu, ferrets, and most rodents. The variety of birds is not great, and the dominant species commonly distributed are sparrow, horned lark, mongolian lark, mao Tui sandy chicken, eagle carving and the like. The common species in the reptile include beautiful spots, clear grass, broken grass, white brocade snake, intermediate pallas pit viper, etc. Amphibious is poor due to climate influence, and dormitory toads and Chinese wood frog are common species.

(4) Temperate desert, semi-desert animal group

Distributed in western regions of inner Mongolia autonomous region to Xinjiang Uygur autonomous region and Qinghai province Qidamu basin, and in the Lu class, various deratization and sand mouse are common types, including goose throat antelope, donkey etc. Birds are relatively poor, and common horny lark, aeolian lark, crotalaria album and the like. The crawling species are suitable for desert and gobi environments, various kinds of exendins and exendins are used as dominant species, and the snake species are common in the snake species such as python and striped snake. The types and the number of amphibians are very small, and the amphibians are distributed in local areas by green toads.

(5) Plateau forest grassland, grassland and desert animal group

The species distributed on Tibet plateau and its nearby mountain area are predominance species of Tibetan antelope, black lip mouse, bai Weisong field mouse, himalayan marmot, etc., and the birds are predominance species of Tibetan horse chicken, blue horse chicken, black neck crane, mountain quail, snow quail, brown back quail, etc. Two types of them are also known, and more common are bono snow sparrows and the like. The reptiles are more commonly known as Tibet exendin and the like. White-lip deer and horse musk deer form dominant species in regions which are moist in the eastern and southeast regions. Amphibious types also occur.

(6) Subtropical forest, forest irrigated animal group

Distributed in Qinling mountain, south of Huaihe, and east of the middle of the transverse mountain, and more widely distributed in animals are macaque, tibetan unitary monkey, red-belly squirrel, long kistrodon squirrel, etc. In hilly areas, there are common suede, mao Guanlu, sweats, boars, forest musk, etc. Among birds, the black amphibian sun Liu Wa, the black spot side-pleat frog, the gold thread side-pleat frog and the big-body bird are all common types. The coat is mainly composed of dove, eyebrow drawing, vernonia nucifera and shirttail. The reptile is most common in the southern category such as natatorium, cobra, and soldering iron,

(7) Tropical forest and forest irrigation animal group

The lower part of the Laiyana slope, yunnan southwest, yunnan and southeast coasts of the distribution Yu Xima are common types of animals such as chamois, wild boar, porcupine, tail-sweeping porcupine, various domestic rats and the like. Birds are more complex in composition, and common species or dominant species are not consistent in all places, and flowers, birds, rhinoceros and the like are distributed. The breeding method is widely used for sun birds, rhododendrons, spiced birds, bamboo chickens, jungle fowl and the like. Peacock and the like are common in tropical forests in the south of Yunnan.

(8) Farm animal group

The plant species are widely distributed in farmland environments of various places of the whole country, mainly based on the plant species suitable for and dependent on farmland inhabiting conditions, such as sparrow, crow, bald nose crow, jin Yaoyan, bai and the like in birds. The dominant species of agro-murine species differ in the zone to which the different animal groups belong.

The target population should be selected to be predominantly of a locally distributed wild animal species, and non-native species should not be considered as target populations for animal channels, since they are not part of the natural ecosystem of the area and therefore their migration or diffusion should not be considered as an important point. In practice, it is preferable to set wild animal channels for species that are threatened by human factors. In the planning and designing process of the wild animal channel, determining the target population is an important step, and depends on the position and movement mode of the living area of the target population to a large extent. Determining the target population is also of great importance in the monitoring and assessment of wild animal channels.

In this embodiment, the target population of the target area is obtained by referring to the data or by setting a wild animal monitoring device in the target area;

s2: acquiring the target group according to the target group distribution data;

specifically, the target group is divided into: four groups of large mammals, small and medium mammals, amphibians, reptiles;

further, in this embodiment, the target population of wild animals in the target region is one or more.

Illustratively, the S1 obtains the target population distribution data of a target area, and the animal population distribution data of the target area can be basically determined, for example, main animal types of the cold temperature zone conifer animal group include large mammals and small and medium-sized mammals; based on the above, the target group of the region can be determined to be at least one of a large mammal and a medium-small mammal according to the field investigation.

S3: acquiring the wild animal channel design parameters according to the target group;

specifically, the parameters include channel type, channel position, channel size, and channel density;

the channel types comprise three types of overpasses, bridge channels and culverts; the types of mammalian channels are overpass and bridge channels; the type of channel for amphibians and reptiles is culvert.

The wild animal channel is designed to meet the passing requirements of wild animals, and the channel position is arranged on the migration or activity route of the wild animals.

Specifically, the animal channel position is designed firstly by defining a migration or migration path of the wild animals along the line, and knowing the relatively concentrated distribution area of the wild animals. The information such as the distribution, population status, foraging, perching, breeding, common natural animal corridor and migration (migration) route of the wild animals along the line, and the main factors such as vegetation, water source, topography and the like affecting the distribution of the wild animals need to be known in detail through a large number of long-term monitoring.

Wherein the channel size is designed according to the target population and the channel type;

specifically, for large mammalian groups, the large mammalian groups are designed into overpass channels or bridge channels, wherein the minimum dimension of the overpass channels is 50m in length and 40m in width;

for small and medium-sized mammal groups, designing a bridge channel, wherein the length of the bridge channel is not less than 10m, and the width of the bridge channel is not less than 2.5m;

for amphibian and reptile populations, culvert channels are designed, wherein the minimum diameter of the culvert channels is 0.3m.

There is little research in the prior art on channel density and no conclusions on the general versatility accepted, but in principle it is already common that the greater the density the better, the greater the number. However, too large a number and density causes a drastic increase in cost, and therefore, there is a need to make a trade-off between economy and efficiency.

In this embodiment, a deep learning prediction method is used to predict the channel density, so as to obtain channel density design data.

Specifically, as shown in fig. 2, the process of obtaining the channel density by the deep learning model is:

sa: acquiring a training set of the deep learning model;

specifically, the channel design cases at home and abroad are used as training sets;

in this embodiment, the channel design parameters are improved according to the utilization rate of the channel after the channel design cases at home and abroad are put into use, so that the channel design parameters are more scientific and accurate.

Specifically, if the channel utilization rate is lower than the preset threshold value, it may indicate that the channel density and the number are more, resulting in low channel utilization rate, so that the channel density needs to be reduced;

for example, the preset threshold is 20%, if the channel utilization is less than 20%, the channel density is adjusted in the direction of decreasing in the channel design scheme, and specifically, the adjustment scale technician determines according to various factors such as the channel utilization and the construction cost.

In the prior art, a technical scheme of applying a deep learning model to channel density parameter design does not exist, the embodiment creatively applies the deep learning model to channel density parameter design so as to obtain more accurate channel density design data, and in the process of applying the deep learning model to channel design parameter design, the method has the characteristic that whether the data set is an optimal data set or not can be verified according to the utilization rate of the existing data set, and the method further improves processing of the data set so that the data set is the optimal data set, thereby enabling the prediction parameters obtained by the model to be close to the optimal parameters and further improving the scientificity of the channel design.

Specifically, the channel design parameters include: channel density; in the present embodiment, the channel density is mainly focused, and other parameters such as the channel size and the channel type are not focused, so only the channel density design parameters are improved.

It is worth emphasizing that each training set comprises: wild animal herds of the target area, number of each herd, channel type, channel density.

Sb: establishing a deep learning model and training to obtain the deep learning model for channel density prediction;

specifically, the deep learning model is an artificial neural network model; in particular, the specific structure of the artificial neural network model is prior art and will not be discussed in detail herein.

In addition, in the training process of the artificial neural network model, whether the training is converged or not is judged through a loss function.

Sc: and inputting parameters of the target area into the deep learning model to obtain predicted channel density.

Specifically, the parameters of the target area are wild animal groups of the target area, the number of each group and the channel type. Therefore, accurate channel density parameters can be obtained, and the channel density parameters can be used for wild animal channel design according to the obtained channel density parameters.

In a second embodiment, the present embodiment includes a wild animal channel design system, the system employing the wild animal channel design method of the first embodiment, the system including:

the target population distribution data acquisition module is used for acquiring target population distribution data of the wild animals in the target area;

the target group acquisition module is connected with the target group distribution data acquisition module and is used for acquiring the target group according to the target group distribution data;

the channel design parameter acquisition module is connected with the target group acquisition module and is used for acquiring the wild animal channel design parameters according to the target group.

In a third embodiment, the present embodiment includes a computer-readable storage medium having a data processing program stored thereon, the data processing program being executed by a processor to perform a wild animal channel design method of the first embodiment.

It will be apparent to one of ordinary skill in the art that embodiments herein may be provided as a method, apparatus (device), or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer, and the like. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

The description herein is with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments herein. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

The above examples and/or embodiments are merely for illustrating the preferred embodiments and/or implementations of the present technology, and are not intended to limit the embodiments and implementations of the present technology in any way, and any person skilled in the art should be able to make some changes or modifications to the embodiments and/or implementations without departing from the scope of the technical means disclosed in the present disclosure, and it should be considered that the embodiments and implementations are substantially the same as the present technology.

Claims (7)

1. A method of wild animal channel design comprising the steps of:

s1: acquiring target population distribution data of wild animals in a target area; the target population comprises: the method comprises the steps of cold temperate zone conifer forest animal groups, temperate zone forests, forest grassland animal groups, temperate zone desert animal groups, highland forest grasslands, cold desert animal groups, subtropical forests, forest irrigation animal groups, tropical forests, forest irrigation animal groups and farmland animal groups;

s2: acquiring a target group according to the target group distribution data; the target groups are divided into: four groups of large mammals, small and medium mammals, amphibians, reptiles;

s3: acquiring the wild animal channel design parameters according to the target group;

the parameters include channel type, channel position, channel size, and channel density;

predicting the channel design parameters by adopting a deep learning model;

the process of obtaining the channel density through the deep learning model comprises the following steps:

sa: acquiring a training set of the deep learning model;

the channel design cases at home and abroad are used as training sets; the channel design parameters in the training set are improved according to the channel utilization rate after the channel design cases at home and abroad are put into use, and the channel density parameters are reduced when the channel utilization rate is lower than a preset threshold value;

each training set includes: wild animal groups of the target area, the number of each group, the channel type and the channel density;

sb: establishing a deep learning model and training to obtain the deep learning model for channel density prediction;

sc: and inputting parameters of the target area into the deep learning model to obtain predicted channel density.

2. The method according to claim 1, wherein in S1, the target population of the target area is obtained by referring to the data or by providing a wild animal monitoring device in the target area.

3. The method of claim 1, wherein the target population is one or more.

4. The method according to claim 1, wherein in S3, the channel types include overpass, bridge channel, culvert.

5. The method of claim 4, wherein the mammalian channel types are overpass and bridge channels; the channel types of amphibians and reptiles are culverts;

the channel position is arranged on a migration or activity route of the wild animal; designing the channel size according to the target population and the channel type;

for large mammalian groups, the large mammalian groups are designed into overpass channels or bridge channels, wherein the minimum dimension of the overpass channels is 50m in length and 40m in width;

for small and medium-sized mammal groups, designing a bridge channel, wherein the length of the bridge channel is not less than 10m, and the width of the bridge channel is not less than 2.5m;

for amphibian and reptile populations, culvert channels are designed, wherein the minimum diameter of the culvert channels is 0.3m.

6. The method of claim 1, wherein the deep learning model is an artificial neural network model.

7. A wild animal channel design system employing the wild animal channel design method of any one of claims 1-6, the system comprising:

the target population distribution data acquisition module is used for acquiring target population distribution data of the wild animals in the target area; the target population comprises: the method comprises the steps of cold temperate zone conifer forest animal groups, temperate zone forests, forest grassland animal groups, temperate zone desert animal groups, highland forest grasslands, cold desert animal groups, subtropical forests, forest irrigation animal groups, tropical forests, forest irrigation animal groups and farmland animal groups;

the target group acquisition module is connected with the target group distribution data acquisition module and is used for acquiring a target group according to the target group distribution data; the target groups are divided into: four groups of large mammals, small and medium mammals, amphibians, reptiles;

the channel design parameter acquisition module is connected with the target group acquisition module and is used for acquiring the wild animal channel design parameters according to the target group.