CN111126720B

CN111126720B - Farm risk prediction method, device, equipment and storage medium

Info

Publication number: CN111126720B
Application number: CN202010130757.8A
Authority: CN
Inventors: 邱添羽; 周古月; 吴泽衡; 徐倩; 杨强
Original assignee: WeBank Co Ltd
Current assignee: WeBank Co Ltd
Priority date: 2020-02-28
Filing date: 2020-02-28
Publication date: 2024-09-24
Anticipated expiration: 2040-02-28
Also published as: CN111126720A

Abstract

The invention discloses a method, a device, equipment and a storage medium for predicting risk of a farm, wherein the method comprises the following steps: acquiring first position information of a farm to be predicted, and determining a target geographic range corresponding to the farm to be predicted based on the first position information; screening target influence factors falling into the target geographic range from the risk influence factors according to second position information of each preset risk influence factor; and acquiring influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the to-be-predicted farm. The method and the device realize rapid and accurate prediction of the risk situation of the farm.

Description

Farm risk prediction method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for predicting risk of a farm.

Background

African swine fever is an acute, febrile, highly contagious animal infectious disease of pigs caused by African swine fever virus, and the related mortality rate is as high as 100%. African swine fever epidemic situation occurs in succession in the province part of China since the first instance of African swine fever of China is diagnosed by the Chinese animal health and epidemiology center, and the loss is serious. Once an animal infectious disease like african swine fever is found, a prevention and control measure needs to be rapidly and accurately taken to avoid adverse effects on various aspects of society caused by continuous expansion of epidemic situation. In order to make quick and accurate prevention and control measures, the risk situation of each farm needs to be quickly and accurately known. However, the current situation is risk assessment of the farm, which requires an expert to examine the condition of the farm in the field and then evaluate the farm, or rely on the farmer to report risk information of the farm. However, the scheme of field investigation by the expert is obviously low in efficiency, and is difficult to cope with sudden and rapid epidemic situation; the active report of the farmers can cause the conditions of the farmers conceal to breed risk information, and the farmers are difficult to accurately estimate the risk, so that the risk assessment accuracy is low. Failure to quickly and accurately obtain the risk situation of the farm will result in poor prevention and control work effect.

Disclosure of Invention

The invention mainly aims to provide a method, a device, equipment and a storage medium for predicting the risk of a farm, and aims to solve the problem that the current animal epidemic situation cannot quickly and accurately obtain the risk situation of the farm, so that the prevention and control working effect is poor.

In order to achieve the above object, the present invention provides a farm risk prediction method, which includes the steps of:

Acquiring first position information of a farm to be predicted, and determining a target geographic range corresponding to the farm to be predicted based on the first position information;

Screening target influence factors falling into the target geographic range from the risk influence factors according to second position information of each preset risk influence factor;

And acquiring influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the to-be-predicted farm.

Optionally, the target influencing factors include a target waterway network and a target farm, and the step of obtaining the influence data corresponding to the target influencing factors includes:

Determining a waterway network density characteristic value of the target geographic range according to the second position information of the target waterway network and the target geographic range;

Determining a farm density characteristic value of the target geographical range according to the second position information of the target farm and the target geographical range;

And taking the waterway network density characteristic value and the farm density characteristic value as the influence data.

Optionally, the step of determining the farm density characteristic value of the target geographical range according to the second position information of the target farm and the target geographical range comprises:

determining a farm area of the target farm according to the second position information of the target farm;

Determining the total feeding amount of the target farm according to the area of the farm and the preset corresponding relation between the area and the feeding amount;

And calculating to obtain the characteristic value of the density of the farm in the target geographic range according to the total feeding amount and the area of the target geographic range.

Optionally, the step of determining the waterway network density characteristic value of the target geographical range according to the second position information of the target waterway network and the target geographical range includes:

Determining the waterway network length or waterway network area of the target waterway network according to the second position information of the target waterway network;

And calculating to obtain a waterway network density characteristic value of the target geographic range according to the waterway network length and the area of the target geographic range, or calculating to obtain a waterway network density characteristic value of the target geographic range according to the waterway network area and the area of the target geographic range.

Optionally, the risk prediction model includes a preset weight value corresponding to each of the influence data, and the step of inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted includes:

Inputting each influence data into the risk prediction model to call the risk prediction model to calculate a risk coefficient of the farm to be predicted based on the weight value and each influence data;

And taking the risk coefficient as a risk prediction result of the to-be-predicted farm, or determining a risk grade according to the risk coefficient and a preset corresponding relation between the coefficient and the grade, and taking the risk grade as the risk prediction result of the to-be-predicted farm.

Optionally, before the step of screening the target influencing factors falling into the target geographic range from the risk influencing factors according to the second position information of each preset risk influencing factor, the method further includes:

inputting a map to be identified into an influence factor detection model to obtain classification categories of all pixel points in the map to be identified, wherein the influence factor detection model is obtained through pre-training;

Determining target pixel points belonging to risk influence factors from the pixel points based on the classification category;

And determining the actual position of each target pixel point according to the scale of the map to be identified, and obtaining second position information of each risk influence factor based on the actual position.

Optionally, the risk influencing factors include a waterway network, and before the step of inputting the map to be identified into the influencing factor detection model to obtain the classification category of each pixel point in the map to be identified, the method further includes:

Performing preliminary training on a semantic segmentation model to be trained by adopting positive training data, wherein the positive training data comprises a plurality of pre-acquired remote sensing satellite maps containing waterway networks and waterway network annotation data corresponding to each remote sensing map satellite;

The method comprises the steps of adopting negative example training data or adopting the negative example training data and the positive example training data to adjust a semantic segmentation model after preliminary training, wherein the negative example training data comprises a plurality of remote sensing satellite maps which are acquired in advance and do not contain a waterway network;

When the adjusted model to be trained accords with the preset model condition, the adjusted semantic segmentation model is used as the influence factor detection model, otherwise, the steps are executed again based on the adjusted semantic segmentation model: and performing preliminary training on the semantic segmentation model to be trained by adopting the positive training data.

Optionally, after the step of obtaining the influence data corresponding to the target influence factor and inputting the influence data into a preset risk prediction model to obtain the risk prediction result of the farm to be predicted, the method further includes:

and determining a target prevention and control scheme of the farm to be predicted from preset prevention and control schemes according to the risk prediction result, and outputting the target prevention and control scheme.

In order to achieve the above object, the present invention also provides a farm risk prediction apparatus, including:

The acquisition module is used for acquiring first position information of the farm to be predicted and determining a target geographic range corresponding to the farm to be predicted based on the first position information;

the screening module is used for screening target influence factors falling into the target geographic range from the risk influence factors according to second position information of each preset risk influence factor;

The prediction module is used for acquiring influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the to-be-predicted farm.

To achieve the above object, the present invention also provides a farm risk prediction apparatus comprising: a memory, a processor and a farm risk prediction program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the farm risk prediction method as described above.

In addition, to achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a farm risk prediction program which, when executed by a processor, implements the steps of the farm risk prediction method as described above.

According to the method, the first position information of the farm to be predicted is obtained, and the target geographic range corresponding to the farm to be predicted is determined according to the first position information; screening target influence factors falling into a target geographic range from the risk influence factors according to second position information of the preset risk influence factors; and inputting the influence data of the target influence factors into a risk prediction model to obtain a risk prediction result of the farm to be predicted. According to the method, for farms of which risks are to be predicted in all places, the influence data of risk influence factors in the geographic range corresponding to the farms to be predicted are obtained, and a risk prediction model is set to process the influence data, so that risk prediction results of the farms to be predicted can be obtained; the condition of each farm is not required to be inspected by an expert on the spot, so that the efficiency of predicting the risk of the farm is improved, and the condition of rapid epidemic situation spread can be dealt with; compared with the scheme that farmers actively report risk conditions, the risk conditions of various farms can be predicted more accurately by adopting a unified risk prediction model in the embodiment; based on the rapid and accurate risk prediction result, epidemic situation prevention and control work can be rapidly and pertinently developed, and epidemic situation out-of-control is avoided.

Drawings

FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a flowchart of a first embodiment of a farm risk prediction method according to the present invention;

FIG. 3 is a block diagram of a functional schematic of a preferred embodiment of a farm risk prediction apparatus according to the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

Referring to fig. 1, fig. 1 is a schematic device structure of a hardware running environment according to an embodiment of the present invention.

It should be noted that, the farm risk prediction device in the embodiment of the present invention may be a smart phone, a personal computer, a server, etc., which is not limited herein.

As shown in fig. 1, the farm risk prediction apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.

It will be appreciated by those skilled in the art that the apparatus structure shown in fig. 1 does not constitute a limitation of the farm risk prediction apparatus, and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.

As shown in fig. 1, an operating system, a network communication module, a user interface module, and a farm risk prediction program may be included in a memory 1005, which is a type of computer storage medium. The operating system is a program for managing and controlling equipment hardware and software resources, and supports the running of farm risk prediction programs and other software or programs.

In the device shown in fig. 1, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing communication connection with a server; and processor 1001 may be configured to call a farm risk prediction program stored in memory 1005 and perform the following operations:

Further, the target influencing factors include a target waterway network and a target farm, and the step of obtaining the influence data corresponding to the target influencing factors includes:

Further, the step of determining the farm density characteristic value of the target geographical range according to the second position information of the target farm and the target geographical range comprises the following steps:

Further, the step of determining the waterway network density characteristic value of the target geographical range according to the second position information of the target waterway network and the target geographical range includes:

Further, the risk prediction model includes a preset weight value corresponding to each of the influence data, and the step of inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted includes:

Further, before the step of screening the target influencing factors falling within the target geographical range from the risk influencing factors according to the second location information of the preset risk influencing factors, the processor 1001 may be further configured to invoke a farm risk prediction program stored in the memory 1005 to perform the following operations:

Further, the risk influencing factors include a waterway network, and before the step of inputting the map to be identified into the influencing factor detection model to obtain the classification category of each pixel point in the map to be identified, the processor 1001 may be further configured to invoke a farm risk prediction program stored in the memory 1005 to perform the following operations:

Further, after the step of obtaining the influence data corresponding to the target influence factor and inputting the influence data into a preset risk prediction model to obtain the risk prediction result of the farm to be predicted, the processor 1001 may be further configured to call a farm risk prediction program stored in the memory 1005 to perform the following operations:

Based on the above structure, various embodiments of a farm risk prediction method are presented.

Referring to fig. 2, fig. 2 is a flowchart of a first embodiment of a farm risk prediction method according to the present invention.

Embodiments of the present invention provide embodiments of farm risk prediction methods, it being noted that although a logical order is shown in the flow chart, in some cases the steps shown or described may be performed in a different order than that shown or described herein. The execution subject of each embodiment of the farm risk prediction method of the present invention may be a smart phone, a personal computer, a server, etc., and for convenience of description, the execution subject is omitted in the following embodiments. In this embodiment, the farm risk prediction method includes:

Step S10, acquiring first position information of a to-be-predicted farm, and determining a target geographic range corresponding to the to-be-predicted farm based on the first position information;

For a farm with risk prediction, the position information of the farm can be acquired first, and the farm is used as the farm to be predicted. The risk refers to the extent to which the farm may be affected when an animal infectious disease such as swine fever is transmitted. There are various ways of obtaining the position information of the farm; for example, the method can be realized by acquiring from a map, and extracting the related information of the farm from the map data based on the acquired electronic map data, wherein the related information comprises the position information of the farm; the method can also be used for extracting the position information of the farm from the farm data reported by the farmers or the farm data acquired in advance; other methods are also possible and are not listed here. It is possible to treat the farm as a point (center point of the farm), the position information being the position information of the point; the farm may be regarded as one area, and the positional information may be positional information of the area. The location information may be latitude and longitude of the farm, or coordinates in a specific coordinate system established in advance, and so on.

And determining a target geographic range corresponding to the farm to be predicted based on the first position information of the farm to be predicted. It should be noted that, for a farm to be predicted, the risk of the farm is to be predicted, and the principle adopted in this embodiment is that the relevant data of the area around the farm can be used as the basis for judging the risk of the farm, and the target geographic range can be the determined area around the farm. In particular, the region may be determined in a variety of ways; for example, a radius value can be preset, the farm is used as a center of a circle, the radius value is used as a radius, the divided circular area can be used as a target geographic range corresponding to the farm, and the position of the target geographic area can be determined according to the position information of the farm and the radius value; or the farm is taken as the center of a rectangle, a matrix side length value is preset, and a matrix area is divided into a target geographic range of the farm; other methods are available, and different methods can be adopted to determine the target geographic range according to different actual application scenes, and are not listed here.

Step S20, screening target influence factors falling into the target geographic range from the risk influence factors according to preset second position information of the risk influence factors;

Various risk factor types, such as farms, water networks, road networks, villages, etc., may be specified in advance, these being different types of factors. The water network may refer to various sizes of rivers, lakes, etc., and the road network may refer to various types of roads, such as national roads, high speeds, etc. Hereinafter, the water network and the road network are collectively referred to as "water network" and may be collectively referred to as "water network" or "road network" and may be separately referred to as "water network". The data of each risk influence factor of a region can be collected in advance, for example, the data of each farm, each water network, each road network and the like of the region can be collected according to the collected data of the risk influence factor of a certain city or a certain region; the data may specifically include the position, the size, etc. of the risk influencing factors, and different data may be obtained according to the type of the risk influencing factors, for example, the collected data of the farm may include the position information, the area, the yield, etc. of the farm, and the collected data of the waterway network may include the position information, the length, etc. of the waterway network. The data may be collected directly from the electronic map data.

After the data of each risk influence factor are obtained, screening target influence factors falling into a target geographic range from each risk influence factor according to the second position information of each risk influence factor. Specifically, for each risk influencing factor, whether the second position information of the risk influencing factor is in the target geographic range or not can be judged, if so, the risk influencing factor is determined to be in the target geographic range, and if not, the risk influencing factor is determined to be not in the target geographic range; and determining risk influence factors in the target geographic range as target influence factors. That is, it is determined which farms, which water networks, etc. of a region are within the target geographic range corresponding to the farms to be predicted. For example, when the location information is longitude and latitude, the location of the target geographic area may be formed by a longitude interval and a latitude interval, so that it needs to be determined whether the longitude of each risk influencing factor falls into the longitude interval, whether the latitude falls into the latitude interval, and if both fall into the latitude interval, determining that the risk influencing factor falls into the target geographic area.

And step S30, obtaining influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the to-be-predicted farm.

And acquiring influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted. Specifically, a risk prediction model may be set in advance, where the risk prediction model may be a model structure such as a linear model or a neural network model, and if the model is a neural network model, the neural network model needs to be trained in advance, and a model obtained after training is adopted to perform risk prediction, and the training process of the neural network model may refer to the existing training process of the neural network model, which is not described in detail herein. The setting principle of the risk prediction model is as follows: and when the input data represents more and denser target influence factors in the target geographic range, the output risk prediction result represents higher risk of the farm to be predicted. The input data of the risk prediction model may be set according to circumstances, and the input data is referred to as influence data. The influence data of the target influence factors can be different according to different types of the target influence factors; for example, for farms, the impact data may be the total area of farms within the target geographic range, and for waterway networks, the impact data may be the total area of waterway networks within the target geographic range.

And inputting the influence data into a risk prediction model, processing the influence data by the risk prediction model, and outputting a risk prediction result of the farm to be predicted. The risk prediction result may be in various forms, for example, a score or a rank. The risk level corresponding to various scores or grades may be prescribed in advance, for example, a score of 0 to 10 scores, with the risk level gradually increasing from 0 to 10.

In the embodiment, through obtaining first position information of a to-be-predicted farm, determining a target geographic range corresponding to the to-be-predicted farm according to the first position information; screening target influence factors falling into a target geographic range from the risk influence factors according to second position information of the preset risk influence factors; and inputting the influence data of the target influence factors into a risk prediction model to obtain a risk prediction result of the farm to be predicted. In the embodiment, for farms of which risks are to be predicted in all places, the influence data of risk influence factors in the geographic range corresponding to the farms to be predicted are obtained, and a risk prediction model is set to process the influence data, so that a risk prediction result of the farms to be predicted can be obtained; the condition of each farm is not required to be inspected by an expert on the spot, so that the efficiency of predicting the risk of the farm is improved, and the condition of rapid epidemic situation spread can be dealt with; compared with the scheme that farmers actively report risk conditions, the risk conditions of various farms can be predicted more accurately by adopting a unified risk prediction model in the embodiment; based on the rapid and accurate risk prediction result, epidemic situation prevention and control work can be rapidly and pertinently developed, and epidemic situation out-of-control is avoided.

Further, after the step S30, the method further includes:

And S40, determining a target prevention and control scheme of the farm to be predicted from preset prevention and control schemes according to the risk prediction result, and outputting the target prevention and control scheme.

Further, different prevention and control schemes can be set in advance for different risk prediction results, after the risk prediction result of the farm to be predicted is obtained, an appropriate prevention and control scheme is matched from the prevention and control schemes according to the risk prediction result, the matched prevention and control scheme is determined to be a target prevention and control scheme of the farm to be predicted, and the target prevention and control scheme can be output. The output mode can be output to a display screen for display or can be output in a voice mode, and the output mode can be set differently according to specific application scenes. The control scheme of the farm to be predicted is directly output and displayed, so that a user can intuitively know the control scheme, and control work is performed according to the control scheme. Particularly, for the users who need to perform the prevention and control measures, but do not know which prevention and control measures are, or do not know the risk situation of the farm, such as the farmers or residents around the farm, the prevention and control measures matched with the risk situation of the farm can be conveniently and directly obtained, so that the prevention and control work is more facilitated to be performed.

Based on the risk prediction method in the embodiment, the risk prediction method can be actually applied in the form of mobile phones or computer application software, so that a user can input relevant information, such as position information, of the farm to be predicted based on the installed application program, and a risk prediction result of the farm to be predicted, even a prevention and control scheme, can be directly obtained.

Further, based on the first embodiment, a second embodiment of the farm risk prediction method according to the present invention is provided, in this embodiment, the target influencing factors include a target waterway network and a target farm, and the step of obtaining the influence data corresponding to the target influencing factors in step S30 includes:

Step S301, determining a waterway network density characteristic value of the target geographic range according to second position information of the target waterway network and the target geographic range;

further, in the present embodiment, the target influencing factors may be a target waterway network and a target farm. That is, the types of risk influencing factors may include waterway networks and farms. After the target farm and the target waterway network falling into the target geographic range are determined, the influence data of the target farm and the target waterway network can be acquired.

Specifically, the waterway network density characteristic value of the target geographic range is determined according to the second position information of the target waterway network and the target geographic range. The calculation method of the waterway network density characteristic value is various, for example, the calculation method can be a result of dividing the total area of the target waterway network by the total area of the target geographic range.

Further, step S301 includes:

step S3011, determining the waterway network length or waterway network area of the target waterway network according to the second position information of the target waterway network;

step S3012, calculating to obtain a waterway network density characteristic value of the target geographic range according to the waterway network length and the area of the target geographic range, or calculating to obtain a waterway network density characteristic value of the target geographic range according to the waterway network area and the area of the target geographic range.

Specifically, the length or the area of the target waterway network can be determined according to the second position information of the target waterway network, and the calculation process of the area and the length can be as follows: the total area of the target geographic range can be determined according to the position information of the target geographic range, for example, the total area of the target geographic range can be calculated according to the longitude and latitude interval of the target geographic range; determining the length of the target waterway network according to the second position information of the target waterway network, for example, a river or a road can be represented by the longitude and latitude of two points, calculating the length of the river or the road according to the longitude and latitude of the two points, and adding the lengths of all the rivers or the roads to obtain the length of the target waterway network; the total area of the target waterway network can also be determined according to the second position information of the target waterway network, for example, one river or one road can be represented by a longitude and latitude interval, the area of the river or the road is calculated according to the longitude and latitude interval, and the areas of all the rivers or the roads are added to obtain the total area of the target waterway network.

The waterway network density characteristic value may be a result obtained by dividing the total area of the target waterway network by the total area of the target geographic range, or may be a result obtained by dividing the length of the target waterway network by the total area of the target geographic range.

Step S302, determining a farm density characteristic value of the target geographical range according to second position information of the target farm and the target geographical range;

And determining a farm density characteristic value of the target geographical range according to the second position information of the target farm and the target geographical range. Specifically, the farm density characteristic value may be a result of dividing the total area of the target farm by the total area of the target geographic range. The total area calculation method of the target farm can be as follows: each target farm can be represented by a longitude and latitude interval, the area of each target farm is calculated according to the longitude and latitude interval, and then the areas are added to obtain the total area of the target farms.

And step S303, taking the waterway network density characteristic value and the farm density characteristic value as the influence data.

And taking the waterway network density characteristic value and the farm density characteristic value as influence data of target influence factors, namely inputting the waterway network density characteristic value and the farm density characteristic value into a risk prediction model to obtain a risk prediction result of the farm to be predicted.

In the embodiment, the risk prediction result of the farm to be predicted is calculated by calculating the farm density characteristic value and the waterway network density characteristic value of the target geographic range corresponding to the farm to be predicted, inputting the farm density characteristic value and the waterway network density characteristic value into the risk prediction model, and predicting the risk of the farm according to the density characteristic of the farm and the waterway network of the target geographic range is achieved, and the infection characteristic of the actual animal infectious diseases is combined, so that the predicted risk prediction result is more accurate.

Further, the step S302 includes:

Step S3021, determining a farm area of the target farm according to the second position information of the target farm;

the farm density characteristic may also be the result of dividing the total rearing volume of the target farm by the total area of the target geographical range, i.e. the farm density characteristic may be the rearing density. The total feeding amount calculation method of the target farm can be as follows:

And determining the farm area of the target farm according to the second position information of the target farm, namely the total area calculation process of the target farm.

Step S3022, determining a total feeding amount of the target farm according to the farm area and a preset correspondence between the area and the feeding amount;

The correspondence between the area of the farm and the feeding amount may be set in advance, for example, a pig produced at 1.5 square meters is set. And determining the total feeding amount of the target farm according to the calculated farm area of the target farm and the corresponding relation. For example, if the farm area is 150 square meters, the total feeding of the target farm is 100 pigs according to the example described above.

And step S3023, calculating a farm density characteristic value of the target geographical range according to the total feeding amount and the area of the target geographical range.

And calculating to obtain the characteristic value of the density of the farm in the target geographic range according to the total feeding amount and the total area of the target geographic range. Specifically, the total feeding amount can be divided by the total area, and the result is taken as a characteristic value of the density of the farm.

Further, the risk prediction model includes a preset weight value corresponding to each of the influence data, and the step of inputting the influence data into a preset risk prediction model in step S30 to obtain a risk prediction result of the farm to be predicted includes:

Step S304, inputting each influence data into the risk prediction model to call the risk prediction model to calculate a risk coefficient of the farm to be predicted based on the weight value and each influence data;

Further, the risk prediction model may be a linear model, and includes weight values corresponding to each of the influence data, for example, when the influence data is a farm density characteristic value and a waterway network density characteristic value, the weight corresponding to the farm density characteristic value, the weight corresponding to the water network density characteristic value and the weight corresponding to the road network density characteristic value may be set respectively.

After the influence data of the target influence factors are obtained, inputting the influence data into a risk prediction model to call the risk prediction model to calculate the risk coefficient of the farm to be predicted based on the weight values and the influence data. Specifically, each influence data may be multiplied by a corresponding weight value, and then each result obtained by the multiplication is added, and the added result is used as a risk coefficient, that is, the nature of the risk prediction model may be a linear model. It should be noted that, each weight value in the risk prediction model may be set according to a specific experience.

Step S305, taking the risk coefficient as a risk prediction result of the farm to be predicted, or determining a risk level according to the risk coefficient and a preset corresponding relation between the coefficient and the level, and taking the risk level as a risk prediction result of the farm to be predicted.

After the risk coefficient is obtained, the risk coefficient can be directly used as a risk prediction result of the farm to be predicted. The corresponding relation between the risk coefficients and the grades can also be preset, for example, the risk coefficients are ordered from low to high, the lowest 1/4 is divided into a first grade, 1/4-1/2 is divided into a second grade, 1/2-3/4 is divided into a third grade, and the highest 1/4 is divided into a fourth grade. It should be noted that the dividing line for dividing the number of grades and each grade may be selected according to specific experience. And determining which risk level the risk coefficient corresponds to according to the obtained risk coefficient and the corresponding relation between the coefficient and the grade, and taking the determined risk level as a risk prediction result of the farm to be predicted. According to different actual demands of users, risk prediction results can be different, and risk levels can be more visual for part of users, so that the users can make targeted prevention and control schemes more conveniently.

Further, based on the first and second embodiments, a third embodiment of the farm risk prediction method according to the present invention is provided, where in the present embodiment, the farm risk prediction method further includes:

S50, inputting a map to be identified into an influence factor detection model to obtain classification categories of all pixel points in the map to be identified, wherein the influence factor detection model is obtained through pre-training;

The data of each risk influencing factor may be collected in advance, and in this embodiment, the collection method may be: an influence factor detection model may be pre-trained for identifying risk influence factors in the map. The influence factor detection model may be a multi-classification model for identifying to which of a plurality of risk influence factors each pixel point in the map belongs; the influence factor detection model may also be a classification model for identifying whether each pixel point in the map belongs to a risk influence factor. The influencing factor detection model can be a common image target detection model, such as a semantic image segmentation model DeepLab-v3+.

And taking the map of the region of the cultivation place to be predicted as a map to be recognized, and inputting the map to be recognized into an influence factor detection model to obtain the classification category of each pixel point in the map to be recognized. The classification category is used for indicating which risk influence factor the corresponding pixel belongs to, or is used for indicating whether the corresponding pixel belongs to a certain risk influence type.

Step S60, determining target pixel points belonging to risk influence factors from the pixel points based on the classification category;

And determining target pixel points belonging to the risk influence factors from the pixel points according to the classification category of the pixel points. That is, according to the classification category, it is determined which pixels belong to the risk influencing factors, and if the pixel belongs to the risk influencing factors in the case of multiple classifications, it is also determined to which type of risk influencing factors the pixel belongs. For example, when the multiple classifications include four classifications that do not belong to risk influencing factors, farms, water networks and road networks, the classification of each pixel point is used for determining which pixels point of each classification are respectively.

And step S70, determining the actual position of each target pixel point according to the scale of the map to be identified, and obtaining second position information of each risk influence factor based on the actual position.

And determining the actual position of each target pixel point according to the scale of the map to be identified. Specifically, according to the scale of the map to be identified, it can be determined how many areas each pixel represents actually, and then according to the longitude and latitude intervals of the map to be identified, the longitude and latitude intervals of each target pixel can be determined.

It should be noted that, for the pixel points belonging to the farm identified in the map to be identified, when the area actually corresponding to one pixel point is relatively small, it is possible that one pixel point represents one cultivation house (i.e. a unit smaller than the farm), at this time, a clustering algorithm may be adopted to cluster the identified multiple pixel points, or cluster longitude and latitude intervals corresponding to the multiple pixel points, and cluster multiple cultivation houses with relatively close distances into one farm. The clustering algorithm may employ a conventional clustering algorithm, such as a neighbor clustering method. The latitude and longitude of the farm can be the center of the cluster, and the feeding amount of the farm can be the sum of the feeding amounts of all the cultivation houses in the range of the cluster.

Further, the risk influencing factors comprise a waterway network, and the farm risk prediction method further comprises:

Step A10, performing preliminary training on a semantic segmentation model to be trained by adopting positive training data, wherein the positive training data comprises a plurality of pre-acquired remote sensing satellite maps containing waterway networks and waterway network annotation data corresponding to each remote sensing map satellite;

In this embodiment, the risk influencing factors may include a waterway network, the influencing factor detection model may be a multi-classification model formed by a semantic segmentation model, and the output results of the preset influencing factor detection model are three categories: not risk influencing factors, water networks and road networks. The training mode of the influence factor detection model can be as follows:

And acquiring a plurality of remote sensing satellite maps containing the waterway network in advance, and acquiring marking data of the waterway network in the remote sensing satellite maps, namely, the waterway network marking data. The waterway network marking data can be a mask map corresponding to the remote sensing satellite picture, and the mask map has classification categories corresponding to each pixel point of the remote sensing satellite picture, for example, 0 indicates that the pixel point does not belong to risk influence factors, 1 indicates that the pixel point belongs to a water network, 2 indicates that the pixel point belongs to a road network, and the mask map can adopt different colors to represent different categories. And taking a plurality of remote sensing satellite maps containing waterway networks and waterway network annotation data as positive training data.

Firstly, adopting positive training data to perform preliminary training on a semantic segmentation model to be trained. The preliminary training process may employ an existing machine learning model training process.

Step A20, negative example training data or negative example training data and positive example training data are adopted to adjust a semantic segmentation model after preliminary training, wherein the negative example training data comprise a plurality of remote sensing satellite maps which are acquired in advance and do not contain a waterway network;

The remote sensing satellite map which does not contain the waterway network is collected in advance and used as negative training data, the proportion of the negative training data to the positive training data can be set according to actual experience, for example, the negative training data can be one tenth of the positive training data. After the preliminary training, the semantic segmentation model after the preliminary training is adjusted by adopting the negative training data and the positive training data together, or the semantic segmentation model after the preliminary training is adjusted by adopting the negative training data alone, and the adjustment at the moment can be fine adjustment. Specifically, the fine tuning is trained by adopting the positive training data and the negative training data together, and the training process can also be a training process of the existing machine learning model. During fine tuning, the super parameters of the model may be adjusted according to the ratio of the positive training data to the negative training data, and then fine tuning training may be performed after the adjustment, for example, the negative training data may be one tenth of the positive training data, and the learning rate of the fine tuning stage may also be set to one tenth of the initial training stage.

Step A30, when the adjusted model to be trained accords with the preset model condition, the adjusted semantic segmentation model is used as the influence factor detection model, otherwise, the step is executed again based on the adjusted semantic segmentation model: and performing preliminary training on the semantic segmentation model to be trained by adopting the positive training data.

And taking the semantic segmentation model after fine adjustment as an influence factor detection model so as to detect risk influence factors by adopting the influence factor detection model later.

Detecting whether the adjusted semantic segmentation model meets preset model conditions, and if so, taking the adjusted semantic segmentation model as an influence factor detection model so as to detect risk influence factors by adopting the influence factor detection model later. Otherwise, if the preset model condition is not met, performing preliminary training on the adjusted semantic segmentation model by adopting positive training data, and performing adjustment training until the preset model condition is detected to be met. The preset model condition may be a condition set in advance according to a performance requirement of the model, for example, a loss function of the model may be converged to be a condition, or an objective index of the performance of the commonly used detection model may be used as a condition, for example, an objective index such as an accuracy rate, a recall rate, an IOU (Intersection over Union, an intersection ratio), and the like. The calculation method of each objective index may refer to the existing index calculation method, and will not be described in detail herein.

In the embodiment, the map to be identified is detected and identified by training an influence factor detection model in advance to obtain the data of each risk influence factor in the map to be identified, so that the risk influence factors of each region can be intelligently and rapidly obtained, and the risk prediction efficiency of the farm to be predicted is improved. And, to some data of risk influence factor that can't draw from map data, can detect through influence factor detection model to make the data of risk influence factor more comprehensive, and then make the data that the risk prediction was based on more accurate, comprehensive, make the risk prediction result more accurate.

And the model after preliminary training is subjected to preliminary training by adopting positive example training data, and then the model after preliminary training is subjected to fine adjustment by adopting the positive example training data and the negative example training data together, namely, correction is performed through the negative example, so that false detection of the model is reduced. And fine tuning is carried out on the model through the positive training data and the negative training data together, so that the training effect of the positive training data is prevented from being covered due to the fact that the negative training data is adopted entirely.

In addition, an embodiment of the present invention further provides a farm risk prediction apparatus, referring to fig. 3, where the farm risk prediction apparatus includes:

the obtaining module 10 is configured to obtain first location information of a farm to be predicted, and determine a target geographic range corresponding to the farm to be predicted based on the first location information;

the screening module 20 is configured to screen target influencing factors falling into the target geographic range from the risk influencing factors according to second location information of preset risk influencing factors;

The prediction module 30 is configured to obtain influence data corresponding to the target influence factor, and input the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted.

Further, the target influencing factors include a target waterway network and a target farm, and the prediction module 30 includes:

the first determining unit is used for determining a waterway network density characteristic value of the target geographic range according to the second position information of the target waterway network and the target geographic range;

A second determining unit, configured to determine a farm density feature value of the target geographical range according to second location information of the target farm and the target geographical range;

and the third determining unit is used for taking the waterway network density characteristic value and the farm density characteristic value as the influence data.

Further, the second determining unit includes:

a first determining subunit, configured to determine a farm area of the target farm according to the second position information of the target farm;

a second determining subunit, configured to determine a total feeding amount of the target farm according to the farm area and a preset correspondence between the area and the feeding amount;

and the first calculating subunit is used for calculating the farm density characteristic value of the target geographic range according to the total feeding amount and the area of the target geographic range.

Further, the first determination unit includes:

A third determining subunit, configured to determine a waterway network length or a waterway network area of the target waterway network according to the second position information of the target waterway network;

And the second determination subunit is used for calculating to obtain the waterway network density characteristic value of the target geographic range according to the waterway network length and the area of the target geographic range, or calculating to obtain the waterway network density characteristic value of the target geographic range according to the waterway network area and the area of the target geographic range.

Further, the risk prediction model includes a preset weight value corresponding to each of the impact data, and the prediction module 30 includes:

The input unit is used for inputting the influence data into the risk prediction model so as to call the risk prediction model to calculate the risk coefficient of the farm to be predicted based on the weight value and the influence data;

And the fourth determining unit is used for taking the risk coefficient as a risk prediction result of the farm to be predicted, or taking the risk grade as the risk prediction result of the farm to be predicted after determining the risk grade according to the risk coefficient and a preset corresponding relation between the coefficient and the grade.

Further, the farm risk prediction device further includes:

The input module is used for inputting the map to be identified into an influence factor detection model to obtain the classification category of each pixel point in the map to be identified, wherein the influence factor detection model is obtained by training in advance;

the first determining module is used for determining target pixel points belonging to risk influence factors from the pixel points based on the classification category;

And the second determining module is used for determining the actual position of each target pixel point according to the scale of the map to be identified and obtaining second position information of each risk influence factor based on the actual position.

Further, the risk influencing factors include a waterway network, and the farm risk prediction device further includes:

The system comprises a primary training module, a primary training module and a semantic segmentation module, wherein the primary training module is used for carrying out primary training on a semantic segmentation model to be trained by adopting positive training data, and the positive training data comprises a plurality of pre-acquired remote sensing satellite maps containing waterway networks and waterway network mark annotation data;

The adjustment module is used for adjusting the semantic segmentation model after preliminary training by adopting negative example training data or adopting the negative example training data and the positive example training data, wherein the negative example training data comprises a plurality of remote sensing satellite maps which are acquired in advance and do not contain a waterway network;

the third determining module takes the adjusted semantic segmentation model as the influence factor detection model when the adjusted model to be trained accords with the preset model condition, otherwise, the step is executed again based on the adjusted semantic segmentation model: and performing preliminary training on the semantic segmentation model to be trained by adopting the positive training data.

Further, the farm risk prediction device further includes:

and the output module is used for determining a target prevention and control scheme of the farm to be predicted from preset prevention and control schemes according to the risk prediction result and outputting the target prevention and control scheme.

The expansion content of the specific implementation mode of the farm risk prediction device is basically the same as that of each embodiment of the farm risk prediction method, and no description is given here.

In addition, the embodiment of the invention also provides a computer readable storage medium, wherein the storage medium is stored with a farm risk prediction program, and the farm risk prediction program realizes the steps of a farm risk prediction method when being executed by a processor.

Embodiments of the farm risk prediction apparatus and the computer readable storage medium according to the present invention may refer to embodiments of the farm risk prediction method according to the present invention, and will not be described herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. A method of farm risk prediction, the method comprising the steps of:

screening target influence factors falling into the target geographic range from the risk influence factors according to second position information of each preset risk influence factor, wherein multiple types of risk influence factors are preset;

Acquiring influence data corresponding to the target influence factors, and inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted, wherein the influence data of the target influence factors are different according to different types of the target influence factors, and the risk refers to the degree of influence possibly received by the farm under the condition of animal infectious disease transmission;

Before the step of screening the target influencing factors falling into the target geographic range from the risk influencing factors according to the second position information of each preset risk influencing factor, the method further comprises the following steps:

determining the actual position of each target pixel point according to the scale of the map to be identified, and obtaining second position information of each risk influence factor based on the actual position;

The target influence factors comprise a target waterway network and a target farm, and the step of acquiring the influence data corresponding to the target influence factors comprises the following steps:

Determining a waterway network density characteristic value of the target geographical range according to the second position information of the target waterway network and the target geographical range, wherein the waterway network density characteristic value is a result obtained by dividing the total length of the target waterway network by the total area of the target geographical range or a result obtained by dividing the total area of the target waterway network by the total area of the target geographical range; determining the total area of the target geographic range according to the position information of the target geographic range, determining the total length of the target waterway network according to the second position information of the target waterway network, wherein one river or one road is represented by the longitude and latitude of two points, calculating the lengths of the river or the road according to the longitude and latitude of the two points, and adding the lengths of all the rivers or the roads to obtain the total length of the target waterway network; or determining the total area of the target waterway network according to the second position information of the target waterway network, wherein one river or one road is represented by a longitude and latitude interval, calculating the area of the river or the road according to the longitude and latitude interval, and adding the areas of all the rivers or the roads to obtain the total area of the target waterway network;

2. The farm risk prediction method of claim 1, wherein the step of determining a farm density characteristic value for the target geographical range from the second location information of the target farm and the target geographical range comprises:

3. The method for predicting risk of a farm according to claim 1, wherein the risk prediction model includes a preset weight value corresponding to each of the influence data, and the step of inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted includes:

4. The method for predicting risk of a farm according to claim 1, wherein the risk influencing factors include a waterway network, and before the step of inputting the map to be identified into the influencing factor detection model to obtain the classification category of each pixel point in the map to be identified, the method further comprises:

5. The method for predicting risk of a farm according to any one of claims 1 to 4, wherein the step of obtaining the influence data corresponding to the target influence factor, and inputting the influence data into a preset risk prediction model to obtain the risk prediction result of the farm to be predicted further comprises:

6. A farm risk prediction device, characterized in that the farm risk prediction device comprises:

The system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring first position information of a to-be-predicted farm and determining a target geographic range corresponding to the to-be-predicted farm based on the first position information, wherein a plurality of types of risk influence factors are preset;

the prediction module is used for acquiring influence data corresponding to the target influence factors, inputting the influence data into a preset risk prediction model to obtain a risk prediction result of the farm to be predicted, wherein the influence data of the target influence factors are different according to different types of the target influence factors, and the risk refers to the degree of influence possibly received by the farm under the condition of animal infectious disease transmission;

The farm risk prediction device further comprises:

the second determining module is used for determining the actual position of each target pixel point according to the scale of the map to be identified and obtaining second position information of each risk influence factor based on the actual position;

The target influencing factors comprise a target waterway network and a target farm, and the prediction module comprises:

A first determining unit, configured to determine a waterway network density feature value of the target geographical range according to the second location information of the target waterway network and the target geographical range, where the waterway network density feature value is a result obtained by dividing a total length of the target waterway network by a total area of the target geographical range, or is a result obtained by dividing a total area of the target waterway network by a total area of the target geographical range; determining the total area of the target geographic range according to the position information of the target geographic range, determining the total length of the target waterway network according to the second position information of the target waterway network, wherein one river or one road is represented by the longitude and latitude of two points, calculating the lengths of the river or the road according to the longitude and latitude of the two points, and adding the lengths of all the rivers or the roads to obtain the total length of the target waterway network; or determining the total area of the target waterway network according to the second position information of the target waterway network, wherein one river or one road is represented by a longitude and latitude interval, calculating the area of the river or the road according to the longitude and latitude interval, and adding the areas of all the rivers or the roads to obtain the total area of the target waterway network;

7. A farm risk prediction apparatus, characterized in that the farm risk prediction apparatus comprises: a memory, a processor and a farm risk prediction program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the farm risk prediction method of any of claims 1 to 5.

8. A computer readable storage medium, characterized in that it has stored thereon a farm risk prediction program, which when executed by a processor, implements the steps of the farm risk prediction method according to any of claims 1 to 5.