Agricultural information detection system based on big data

Abstract

The invention relates to the field of agriculture, in particular to an agricultural information detection system based on big data, and the system comprises an agricultural information collection module which is used for collecting crop information, and the crop information comprises crop images; performing information labeling on the crop images, wherein the information labeling is an entry for judging each feature content in the crop images; the agricultural information query module is used for a consumer to query crop information and monitor consumer attention times of various types of crop information; the emphasis analysis module is also used for calculating the attention times of each entry in the crop information; and the agricultural information acquisition module is also used for identifying entries of real-time images in the crop images, and controlling the second image acquisition component to increase the shooting times of the images of the entries in a preset sorting percentage based on the attention times of the entries in the crop information. By adopting the technical scheme of the invention, the focuses of consumers can be captured based on big data, so that the collection emphasis of agricultural information is changed.

Description

Technical Field

[0001] The present invention relates to the field of agriculture, and in particular to an agricultural information detection system based on big data. Background Art

[0002] Consumers have higher and higher requirements for the quality of agricultural products. In order to meet the needs of consumers, an agricultural information traceability system has been launched. The agricultural information traceability system uses RFID and other tags to record and track information in all aspects of agricultural product production, processing, transportation and sales in real time. Smart sensors and status detectors are used to monitor the growth environment and status of agricultural products in real time, such as soil moisture, temperature, light, etc. These data are of great significance for analyzing the growth conditions of agricultural products and predicting the yield. Each agricultural product is sold with a QR code, and consumers can display various test information of agricultural products by scanning the QR code. Some manufacturers optimize the displayed test information, such as adding additional images of agricultural product planting, growth and harvesting in the test information, increasing the authenticity of agricultural product information, enriching the perception of agricultural products, and improving consumers' understanding of agricultural products.

[0003] However, existing technologies often only focus on the output of agricultural information, while ignoring consumers' attention to various information and preferences for various display contents. Some consumers prefer to be able to directly feedback the quality of crops through images, and thus have different requirements for images. Conventional images are all collected in sunny weather, focusing only on the aesthetics of the pictures, and lack the expression of crop quality. Taking the resistance of crops to lodging as an example, conventional images are difficult to reflect the resistance to typhoons and other weather, and thus are weaker in expressing the excellence of agricultural product breeding. Therefore, there is a need for an agricultural information detection system that can capture consumer concerns through big data, thereby changing the focus of agricultural information collection. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an agricultural information detection system based on big data, which can capture consumers' concerns based on big data, thereby changing the focus of agricultural information collection.

[0005] In order to achieve the above purpose, the technical solution of the present invention is as follows: an agricultural information detection system based on big data, comprising: Agricultural information collection module: used to collect crop information, including crop images; the agricultural information collection module is provided with a first image collection component and a second image collection component, the first image collection component has lower pixel than the second image collection component, the first image collection component is used to collect crop images in real time, and the second image collection component is used to shoot crop images, and the crop images are all annotated with information, and the information annotation is an entry for judging each feature content in the crop image; Agricultural information query module: used for consumers to query crop information. The agricultural information query module is also used to monitor the number of consumers' attention to various types of crop information; Focus analysis module: used to judge consumer query tendency according to the number of attentions to each crop information, and optimize the sorting of crop information in the agricultural information query module based on consumer attention tendency; the focus analysis module is also used to calculate the number of attentions to each term in the crop information; the agricultural information acquisition module is also used to identify the terms of real-time images in the crop image based on the trained convolutional neural network, and based on the number of attentions to each term in the crop information, control the second image acquisition component to increase the number of times the images of the terms within the preset sorting percentage are captured.

[0006] The above scheme has the following beneficial effects: 1. In this solution, the first image acquisition component is used to monitor crops for a long time and determine the image content of crops in different periods. The second image acquisition component has higher pixels and can take images with better quality. It is used to record crop information and take pictures to improve the quality of images representing crop information.

[0007] 2. In this solution, the agricultural information query module can provide query capabilities. Consumers can query agricultural product information through the agricultural information query module when consuming, which is convenient for consumers to fully understand the quality level of agricultural product production. At the same time, through the number of consumer attentions, the consumer's preferences are captured, thereby increasing the amount of image collection in the direction that consumers prefer, providing a supply of crop images, allowing users to screen out higher-quality images that are more in line with consumer preferences and increase their attractiveness to consumers.

[0008] Furthermore, whether consumers pay attention to the crop information is determined by consumers triggering clicks and browsing the crop information for a time period longer than a preset time period.

[0009] Beneficial effects: Whether consumers pay attention to crop information can be determined by whether they actively click on it, or whether they stop to watch or read it when browsing the information.

[0010] Furthermore, crop information also includes the production location, production date, seed and seedling source and variety information, fertilizer, pesticide and its supplier information, sowing, fertilization, irrigation and medication date information, growth temperature, soil parameters and quality parameters of agricultural products.

[0011] Beneficial effects: Crop information can also be in the form of text or sensor data, and can include data before, during, and after the production process of various crops, making it easier for consumers to fully understand the quality of agricultural products.

[0012] Furthermore, the entries include the growth stage of agricultural products, weather, lighting, people, scenery, events, quantity of agricultural products, proportion of agricultural products in the screen, proportion of colors and expression of agricultural products’ characteristics.

[0013] Beneficial effects: The entries can summarize various elements in crop images, thereby refining the classification and making it easier to identify the content that consumers are really interested in.

[0014] Furthermore, in the focus analysis module, the number of crop information attentions and the number of entry attentions for different types of agricultural products are collected and calculated separately.

[0015] Beneficial effects: Different crops have different tastes, textures, and environmental requirements, and therefore different attention tendencies, so the number of attentions for different crops and the number of attentions for entries are collected separately.

[0016] Furthermore, the agricultural information query module is also used to store the consumer preference information of each consumer, and the consumer preference information includes consumer identity information, the consumer's query tendency and term preference under various agricultural products.

[0017] Beneficial effects: After collecting consumer preference information, the agricultural information query module can display personalized content that meets consumer preferences based on consumer preference habits.

[0018] Furthermore, consumer preference information also includes consumer consumption records.

[0019] Beneficial effects: Records consumers' consumption records and can push information based on their consumption habits.

[0020] Furthermore, it also includes a crop image library, which is used to store the crop images taken by the second image acquisition component, and the crop images stored in the crop image library are all bound to entry data.

[0021] Beneficial effects: The agricultural information collection module will collect a large number of crop images, which will be stored in the crop image library after screening, so that it is convenient to extract crop images according to different needs and meet the needs of consumers with different preferences.

[0022] Furthermore, the agricultural information query module is used to read consumer preference information, and sort crop information and select crop images in the crop image library based on the query tendency and term preference in the consumer preference information.

[0023] Beneficial effects: Different consumers have different film preferences. Image selection is carried out based on each consumer's query tendency and term preference to provide personalized service content.

[0024] Furthermore, whether consumers pay attention to crop information is captured by setting up cameras, and the openpose system is used to identify the turning angles of the facial features and capture the crop information that the consumers' eyes are focused on. The degree of consumers' attention to crop information is evaluated based on the consumers' gaze time, gaze and return gaze times, return gaze method, gaze order and pupil diameter change indicators.

[0025] Beneficial effects: In addition to using trigger clicks and browsing time to judge the degree of consumer attention, it is also possible to capture the consumer's gaze and use gaze capture technology to obtain the content of the consumer's gaze, and judge the consumer's attention to crop information based on gaze time, gaze and return times, return method, gaze order and pupil diameter changes.

[0026] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a module diagram of an agricultural information detection system based on big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0030] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] The following is further described in detail through specific implementation methods: As attached Figure 1 Shown: An agricultural information detection system based on big data, comprising: Agricultural information collection module: used to collect crop information, including the production location, production date, seeds, seedling sources and variety information of agricultural products, fertilizers, pesticides and their supplier information, sowing, fertilization, irrigation and drug use date information, growth temperature, soil parameters, quality parameters and crop images.

[0032] The agricultural information acquisition module is provided with a first image acquisition component and a second image acquisition component. Both the first image acquisition component and the second image acquisition component are cameras. The first image acquisition component has lower pixels than the second image acquisition component. The second image acquisition component can be set to multiple angles based on cost. The first image acquisition component is used to acquire crop images in real time, and the second image acquisition component is used to shoot crop images. All crop images are annotated with information. The information annotated is an entry for judging the characteristic contents in the crop images. The initial information annotation is performed manually, and the entries include the growth stage of agricultural products, weather, lighting, people, scenery, events, quantity of agricultural products, proportion of agricultural products on the screen, proportion of colors and characteristic performance of agricultural products.

[0033] Agricultural information query module: used for consumers to query crop information. The agricultural information query module is also used to monitor the number of times consumers pay attention to various types of crop information; whether consumers pay attention to crop information is determined by consumers triggering clicks and the length of time spent browsing crop information is greater than a preset time.

[0034] Focus analysis module: used to judge consumer query tendency according to the number of attentions to each crop information, and optimize the crop information sorting in the agricultural information query module based on consumer attention tendency; the focus analysis module is also used to calculate the number of attentions to each term in the crop information; the agricultural information collection module is also used to identify the terms of the real-time image in the crop image based on the trained convolutional neural network; the convolutional neural network is trained based on the information-labeled image, and after the convolutional neural network training is completed, the subsequent crop images are all labeled with information by the convolutional neural network. In the focus analysis module, the number of attentions to crop information and the number of attentions to terms for different types of agricultural products are collected and calculated separately.

[0035] The emphasis analysis module controls the second image acquisition component to increase the number of times images of entries within a preset ranking percentage are captured based on the number of times each entry in the crop information is concerned.

[0036] The first image acquisition component is used to monitor crops for a long time and determine the image content of crops in different periods. The first image acquisition component has low pixels and performance, which effectively reduces the operation and storage costs. The second image acquisition component has higher pixels and can take better quality images. It can be used to record crop information and improve the quality of images representing crop information.

[0037] The agricultural information query module can provide query capabilities. Consumers can query agricultural product information through the agricultural information query module when consuming, which is convenient for consumers to fully understand the quality level of agricultural product production. At the same time, through the number of consumer attentions, it captures consumers' preferences, thereby increasing the amount of image collection in the direction that consumers prefer, and providing a supply of crop images, so that users can screen out higher-quality images that are more in line with consumer preferences and increase their attractiveness to consumers.

[0038] Taking green tea as an example, consumers usually prefer mountains, clouds, humidity, manual labor, tea budding period, and the proportion of green color. Mountains are the natural background and always exist, but they are repelled by clouds. If the clouds are too thick, the mountains will be hidden, and the proportion of green in the picture will decrease, and the sense of ecology will decrease. Therefore, the first image acquisition component will continuously monitor and shoot, judge the real-time status of tea planting, and shoot images under each entry. The number fluctuates with the control of the focus analysis module. During the budding period of tea trees, when clouds and fog are floating in the air, mountains are looming, and there are manual labor picking, fertilizing, weeding and other activities, a large number of images are taken as the growth status of tea trees. Subsequent users read the captured images, so that the images with the best aesthetics are selected as agricultural information. Therefore, when consumers use the agricultural information query module, they can directly obtain the planting location through the mountains, the planting climate through the clouds, the freshness of the crops through the humidity, the original ecology of the tea through the manual work, and the quality of the tea through the budding period of the tea trees, thereby obtaining intuitive tea information directly from the crop images, thereby attracting consumers who are interested in related content.

[0039] When jasmine tea is used as an agricultural product, jasmine and tea are a mixture of two crops with different growth characteristics and needs. The focus analysis module may obtain entries such as fog, humidity, manual work, jasmine flowering period, and the proportion of green color based on consumer preferences, so as to directly pick out images that meet the tea growth environment from the jasmine growth. In this way, consumers can directly obtain information on the quality of jasmine flowers from a single crop image, and indirectly obtain information on the tea growth environment, thereby obtaining information such as the fragrance of jasmine flowers and the natural tea growth environment, directly addressing the core needs of consumers.

[0040] The agricultural information query module is also used to store the consumer preference information of each consumer, which includes the consumer identity information, the consumer's query tendency under various agricultural products, and the term preference. The consumer preference information also includes the consumer's consumption record. It also includes a crop image library, which is used to store the crop images taken by the second image acquisition component, and the crop images stored in the crop image library are all bound to the term data.

[0041] The agricultural information collection module will collect a large number of crop images, which will be stored in the crop image library after screening, making it easy to extract crop images according to different needs and satisfy consumers with different preferences.

[0042] The agricultural information query module is used to read consumer preference information, and sort crop information and select crop images in the crop image library based on the query tendency and term preference in the consumer preference information.

[0043] Different consumers have different film preferences. Image selection is carried out based on each consumer’s query tendency and term preference to provide personalized service content.

[0044] Whether consumers pay attention to crop information is captured by setting up cameras, and the openpose system is used to identify the turning angles of the facial features and capture the crop information that consumers are focusing on. The degree of consumers' attention to crop information is evaluated based on the consumers' gaze time, gaze and return gaze times, return gaze method, gaze order and pupil diameter change indicators.

[0045] In addition to using trigger clicks and browsing time to judge consumers' attention, it is also possible to capture consumers' gazes and use gaze capture technology to obtain what consumers are looking at, and judge consumers' attention to crop information based on gaze time, gaze and return times, return method, gaze order and pupil diameter changes.

[0046] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. An agricultural information detection system based on big data, characterized in that: include: Agricultural information collection module: used to collect crop information, including crop images; the agricultural information collection module is provided with a first image collection component and a second image collection component, the first image collection component has lower pixel than the second image collection component, the first image collection component is used to collect crop images in real time, and the second image collection component is used to shoot crop images, and the crop images are all annotated with information, and the information annotation is an entry for judging each feature content in the crop image; Agricultural information query module: used for consumers to query crop information. The agricultural information query module is also used to monitor the number of consumers' attention to various types of crop information; Focus analysis module: used to judge consumer query tendency according to the number of attentions to each crop information, and optimize the sorting of crop information in the agricultural information query module based on consumer attention tendency; the focus analysis module is also used to calculate the number of attentions to each term in the crop information; the agricultural information acquisition module is also used to identify the terms of real-time images in the crop image based on the trained convolutional neural network, and based on the number of attentions to each term in the crop information, control the second image acquisition component to increase the number of times the images of the terms within the preset sorting percentage are captured.

2. The agricultural information detection system based on big data according to claim 1 is characterized in that: Whether consumers pay attention to crop information is determined by whether consumers trigger clicks and whether the browsing time of crop information is longer than the preset time.

3. The agricultural information detection system based on big data according to claim 2 is characterized in that: Crop information also includes the production location, production date, seed and seedling source and variety information, fertilizer, pesticide and its supplier information, sowing, fertilization, irrigation and drug application date information, growth temperature, soil parameters and quality parameters of agricultural products.

4. The agricultural information detection system based on big data according to claim 3 is characterized in that: The entries include the growth stage of agricultural products, weather, lighting, people, scenery, events, quantity of agricultural products, proportion of agricultural products in the screen, proportion of colors and the characteristics of agricultural products.

5. The agricultural information detection system based on big data according to claim 4 is characterized in that: In the focus analysis module, the number of attentions to crop information and the number of attentions to terms for different types of agricultural products are collected and calculated separately.

6. The agricultural information detection system based on big data according to claim 5 is characterized in that: The agricultural information query module is also used to store the consumer preference information of each consumer, and the consumer preference information includes consumer identity information, the consumer's query tendency and term preference under various agricultural products.

7. The agricultural information detection system based on big data according to claim 6 is characterized in that: Consumer preference information also includes consumers' consumption records.

8. The agricultural information detection system based on big data according to claim 7 is characterized in that: It also includes a crop image library, which is used to store the crop images taken by the second image acquisition component. The crop images stored in the crop image library are all bound with entry data.

9. The agricultural information detection system based on big data according to claim 8 is characterized in that: The agricultural information query module is used to read consumer preference information, and sort crop information and select crop images in the crop image library based on the query tendency and term preference in the consumer preference information.

10. The agricultural information detection system based on big data according to claim 9 is characterized in that: Whether consumers pay attention to crop information is captured by setting up cameras, and the openpose system is used to identify the turning angles of the facial features and capture the crop information that consumers are focusing on. The degree of consumers' attention to crop information is evaluated based on the consumers' gaze time, gaze and return gaze times, return gaze method, gaze order and pupil diameter change indicators.

Images