CN113298537A

CN113298537A - Rice full-chain quality information intelligent detection system and method based on Internet of things

Info

Publication number: CN113298537A
Application number: CN202110486309.6A
Authority: CN
Inventors: 黄汉英; 赵思明; 李鹏飞; 张宾佳; 熊善柏
Original assignee: Huazhong Agricultural University
Current assignee: Huazhong Agricultural University
Priority date: 2021-04-30
Filing date: 2021-04-30
Publication date: 2021-08-24

Abstract

The invention relates to a rice full-chain quality information intelligent detection system and method based on the Internet of things, wherein the system comprises: a planting node monitoring device for monitoring a plurality of planting node parameters; the storage node monitoring equipment is used for monitoring a plurality of storage node parameters; a processing node monitoring device for monitoring a plurality of processing node parameters; the circulation node monitoring equipment is used for monitoring a plurality of circulation node parameters; the information tracing device comprises a food safety big data platform and RFID label equipment, wherein the food safety big data platform comprises a plurality of edge nodes, an edge node manager and a cloud platform, and data uploading sequencing is performed through edge management. The rice production system comprehensively collects the information of each node in the rice industry chain, carries out data processing on various monitoring information through the big data platform, and effectively sorts the information of each node by utilizing edge management, so that the purposes of quick and effective information management and accurate information tracing are achieved, and the safety of rice production is guaranteed.

Description

Rice full-chain quality information intelligent detection system and method based on Internet of things

Technical Field

The invention relates to the technical field of agricultural information, in particular to an intelligent detection system and method for rice full-chain quality information based on the Internet of things.

Background

Rice is the main food for people in most areas of China, and the yield and quality of the produced rice are very important for the people. The industry chain of rice production is including planting, storing up, processing, circulation four nodes, and wherein, every node can all influence the output and the quality of producing rice. In the prior art, a certain node or a certain production factor generated by rice is often monitored respectively, the monitoring form and the monitoring content are single, and the whole industrial chain cannot be completely monitored and judged. In addition, in the prior art, the monitoring information is processed by adopting a traditional data processing mode, and the data processing process lacks high efficiency and rapidity. Therefore, how to efficiently and comprehensively monitor the industrial chain of rice production is an urgent problem to be solved.

Disclosure of Invention

In view of this, there is a need to provide an intelligent detection system and method for quality information of a whole chain of rice based on the internet of things, so as to solve the problem of how to efficiently and comprehensively monitor the industrial chain of rice production.

The invention provides an intelligent detection system for rice full-chain quality information based on the Internet of things, which comprises a plurality of monitoring devices and information tracing devices, wherein the monitoring devices comprise planting node monitoring devices, storage node monitoring devices, processing node monitoring devices and circulation node monitoring devices and are used for monitoring different node parameters, the node parameters comprise planting node parameters, storage node parameters, processing node parameters and circulation node parameters, and the intelligent detection system for rice full-chain quality information based on the Internet of things specifically comprises: the planting node monitoring equipment is used for monitoring a plurality of planting node parameters of the rice planting field under the planting node and transmitting the parameters to the information tracing equipment; the collection and storage node monitoring equipment is used for monitoring a plurality of collection and storage node parameters of the produced paddy of the rice planting field under the collection and storage node and transmitting the parameters to the information tracing equipment; the processing node monitoring equipment is used for monitoring a plurality of processing node parameters in the processing process of the produced paddy under the processing node and transmitting the processing node parameters to the information tracing equipment; the circulation node monitoring equipment is used for monitoring a plurality of circulation node parameters in the circulation process of the processed produced rice under the circulation node and transmitting the circulation node parameters to the information traceability equipment; the information tracing equipment comprises a food safety big data platform and electronic tag equipment, wherein the food safety big data platform is used for carrying out big data processing on a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters and a plurality of circulation node parameters and visualizing a big data processing result; the electronic tag equipment is used for converting the production information of the produced rice into a corresponding RFID tag; the food safety big data platform comprises a cloud platform, an edge node manager and a plurality of edge nodes corresponding to the monitoring devices respectively, wherein: the edge node is used for receiving the corresponding node parameters, performing data filtering on the node parameters and determining filtered parameters to be uploaded; the edge node manager is used for sequencing the processing time delay of each parameter to be uploaded in an ascending order to form a first sequence, and each newly added parameter to be uploaded of the edge node is placed at the tail end of the first sequence; the first sequence is further used for adjusting the first sequence according to the transmission delay of each edge node, and the uploading sequence of the parameters to be uploaded is determined according to the adjusted first sequence; and the cloud platform is used for sequentially carrying out data processing on the uploaded parameters to be uploaded and visualizing the data processing result.

Further, the planting node parameter includes soil parameter, meteorological parameter, insect pest state parameter and water quality parameter, planting node monitoring facilities includes: the soil monitoring equipment is used for monitoring the soil parameters of the rice planting field; the meteorological monitoring equipment is used for monitoring the meteorological parameters of the rice planting field; the pest monitoring equipment is used for acquiring pest image data, carrying out AI analysis, generating the pest state parameters of the rice planting field, carrying out automatic early warning according to the pest state parameters and controlling pesticide spraying; and the water quality monitoring equipment is used for monitoring the water quality parameters of the rice planting field.

Further, the storage node parameters include rice quality parameters and warehouse environment parameters, and the storage node monitoring equipment includes: the rice quality monitoring equipment is used for monitoring the rice quality parameters of the produced rice, wherein the rice quality parameters comprise rice grain yield, polished rice rate, impurity content, water content, pollutant amount, protein content and starch content; and the warehouse monitoring equipment is used for monitoring and storing the warehouse environmental parameters of the produced paddy, wherein the warehouse environmental parameters comprise warehouse temperature and humidity, warehouse dust content, warehouse carbon dioxide content and rat and insect pest states.

Further, a plurality of processing node parameters include rice quality parameter, operation image, processing node monitoring facilities includes: quality monitoring equipment for monitoring the rice quality parameters of the produced rice, wherein the rice quality parameters comprise rice impurity content, imperfect grain content, yellow grain content, consistency, whole rice rate, coarseness rate and chalkiness rate; and the processing process monitoring equipment is used for carrying out video monitoring on the whole processing process and generating the operation image by using AI intelligent analysis so as to determine whether an operator follows the operation image.

Further, the plurality of circulation node parameters include a process state parameter, a route parameter, a trajectory parameter, and a time parameter, and the circulation node monitoring apparatus includes: a video monitor for monitoring the process state parameters of the overall transportation process; and the Beidou navigator is used for monitoring the route parameters, the track parameters and the time parameters in the whole transportation process.

Further, the food safety big data platform comprises a big data acquisition module, a big data collection module, a big data sorting module, a big data analysis module, a big data display module, a big data application module and a big data service module.

Further, the big data application module comprises a risk analysis unit, wherein: and the risk analysis unit is used for comparing the planting node parameters, the processing node parameters and the circulation node parameters with a corresponding pre-stored parameter index library respectively and carrying out early warning according to a parameter comparison result.

Further, the plurality of processing node parameters include operation images, the risk analysis unit is specifically configured to match the operation images with a corresponding pre-stored operation image standard library, and if the operation images are not matched with the pre-stored operation image standard library, an early warning is given.

The invention also provides an intelligent detection method for the quality information of the rice full chain based on the Internet of things, which is based on the intelligent detection system for the quality information of the rice full chain based on the Internet of things and comprises the following steps: acquiring a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters and a plurality of circulation node parameters; performing data filtering on the planting node parameters, the storage node parameters, the processing node parameters and the circulation node parameters, and determining filtered parameters to be uploaded; sequencing the processing time delay of each parameter to be uploaded in an ascending order to form a first sequence, and placing each newly added parameter to be uploaded at the edge node at the tail end of the first sequence; adjusting the first sequence according to the transmission delay of each edge node, and determining the uploading sequence of the parameters to be uploaded according to the adjusted first sequence; and sequentially carrying out data processing on the uploaded parameters to be uploaded, and visualizing the data processing result.

Further, the intelligent detection method for the quality information of the whole chain of the rice based on the internet of things further comprises the following steps: the plurality of processing node parameters comprise an operation video stream in a processing process, and the data processing process of the operation video stream comprises the following steps: dividing the operation video stream into a plurality of video frame sequence groups, calling an API (application programming interface) algorithm, and counting target identification numbers corresponding to the video frame sequence groups; determining a frame filtering model according to the time delay and the bandwidth of the edge node uploaded to the cloud platform and the target identification number, removing redundant video frame sequence groups according to the frame filtering model, and determining a first frame sequence group; extracting key frames in the first frame sequence group according to the image information entropy of the first frame sequence group, and determining a second frame sequence group; distributing virtual machine resources according to the target identification numbers and the data volume of the second frame sequence groups, and determining an uploading sequence of the second frame sequence groups to the cloud platform; estimating the posture of each frame of image in the second frame sequence group, and determining the position coordinates of a plurality of joint points; determining a joint point distance variable quantity matrix according to the position coordinate variable quantity of the same joint point between two adjacent frames of images in the second frame sequence group; equally dividing the second frame sequence group, and performing matrix addition on the joint point distance variable quantities generated by two adjacent frames in each section of video to obtain a cumulative distance variable quantity matrix of each section as a feature vector of the second frame sequence group; inputting the characteristic vectors into a well-trained deep learning model for classification, and determining corresponding operation specification indexes; and comparing the operation specification index with a corresponding prestored index library, and carrying out early warning on the corresponding processing node according to a comparison result.

Compared with the prior art, the invention has the beneficial effects that: setting planting node monitoring equipment to obtain a plurality of planting node parameters of a rice planting field, so as to effectively monitor the planting state of the rice planting nodes; setting a collection and storage node monitoring device to obtain a plurality of collection and storage node parameters in the processing process of the produced rice, so as to effectively monitor the collection and storage states of the rice collection and storage nodes; setting processing node monitoring equipment to obtain processing node parameters of the rice processing nodes, so as to effectively monitor the processing quality state of the rice processing nodes; setting a circulation node monitoring device to obtain circulation node parameters of the rice circulation node, so as to effectively monitor the circulation state of the rice circulation node; based on the monitoring data of each node, centralized processing is carried out through a food safety big data platform in the information tracing equipment so as to comprehensively monitor the state of each node on the rice production chain, the food safety big data platform is utilized to realize rapid processing of various monitoring data, the processing result is visually operated and displayed to related personnel, and the quality control and management of rice production are facilitated; in addition, the production information of the produced rice is burnt to the corresponding RFID label through the electronic label equipment in the information tracing equipment, so that a consumer can quickly master the production information (batch number, manufacturer, production place and the like) of the rice through the way of scanning the RFID label, the public opening degree and transparency of the rice production information are comprehensively ensured, the selection and supervision of the consumer are facilitated, and the safety of the rice production is further enhanced; in addition, a plurality of node parameters are obtained, data redundancy is effectively avoided by using data filtering operation, meanwhile, ascending sequencing is carried out according to processing time delay, effective virtual machine resource allocation is carried out, a first sequence is reasonably planned, finally, the first sequence is adjusted according to transmission time delay, and finally the uploading sequence of each parameter to be uploaded is determined, so that efficient and rapid data processing and data uploading are guaranteed, the uploading sequence of each node parameter is reasonably allocated, the full-production process of rice is monitored in time, the rapidness and the high efficiency of data uploading of a large food safety data platform and data processing are comprehensively improved, and comprehensive and rapid early warning and early warning monitoring are realized. In conclusion, the invention comprehensively collects the information of each node in the rice industry chain, and carries out data processing on various monitoring information through the big data platform, thereby achieving effective information management and information tracing, ensuring the safety of rice production, meanwhile, the invention utilizes the edge node, the edge manager and the cloud platform, combines the processing delay and the transmission delay to effectively sequence the uploading of each node parameter, ensures the rapid processing of each node parameter in the monitoring process, further realizes the high efficiency and the accuracy of rice generation monitoring, is beneficial to carrying out timely feedback and early warning, and improves the safety of rice production.

Drawings

FIG. 1 is a schematic structural diagram of an intelligent detection system for rice full-chain quality information based on the Internet of things, provided by the invention;

FIG. 2 is a schematic flow diagram of the intelligent detection method for the quality information of the whole chain of rice based on the Internet of things.

Detailed Description

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.

Example 1

The embodiment of the invention provides an intelligent detection system for rice full-chain quality information based on the internet of things, and as seen in combination with fig. 1, fig. 1 is a schematic structural diagram of the intelligent detection system for rice full-chain quality information based on the internet of things, the intelligent detection system for rice full-chain quality information based on the internet of things comprises a plurality of monitoring devices and information tracing devices, the monitoring devices comprise a planting node monitoring device 1, a storage node monitoring device 2, a processing node monitoring device 3 and a circulation node monitoring device 4 and are used for monitoring different node parameters, the node parameters comprise a planting node parameter, a storage node parameter, a processing node parameter and a circulation node parameter, and the intelligent detection system for rice full-chain quality information based on the internet of things specifically comprises: the planting node monitoring equipment 1 is used for monitoring a plurality of planting node parameters of the rice planting field under the planting nodes and transmitting the parameters to the information tracing equipment; the collection and storage node monitoring equipment 2 is used for monitoring the collection and storage node parameters of the produced paddy in the rice planting field under the collection and storage node and transmitting the parameters to the information tracing equipment; the processing node monitoring equipment 3 is used for monitoring a plurality of processing node parameters in the processing process of the produced paddy under the processing node and transmitting the processing node parameters to the information tracing equipment; the circulation node monitoring equipment 4 is used for monitoring a plurality of circulation node parameters in the circulation process of the processed produced rice under the circulation nodes and transmitting the circulation node parameters to the information traceability equipment; the information tracing device 5 comprises a food safety big data platform 501 and an electronic tag device 502, wherein the food safety big data platform is used for carrying out big data processing on a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters and a plurality of circulation node parameters and visualizing a big data processing result; the electronic tag equipment is used for converting the production information of the produced rice into a corresponding RFID tag; the edge node is used for receiving the corresponding node parameters, filtering the data of the node parameters and determining the filtered parameters to be uploaded; the edge node manager is used for sequencing the processing time delay of each parameter to be uploaded in an ascending order to form a first sequence, and each edge node newly added parameter to be uploaded is placed at the tail end of the first sequence; the first sequence is adjusted according to the transmission delay of each edge node, and the uploading sequence of a plurality of parameters to be uploaded is determined according to the adjusted first sequence; and the cloud platform is used for sequentially carrying out data processing on the uploaded parameters to be uploaded and visualizing the data processing result.

In the embodiment of the invention, based on the monitoring data of each node, centralized processing is carried out through a food safety big data platform in the information tracing equipment so as to comprehensively monitor the state of each node on a rice production chain, the big data platform is utilized to realize rapid processing of various monitoring data, the processing result is visually operated and displayed to related personnel, and the quality control and management of rice production are facilitated; in addition, the production information of the produced rice is burnt to the corresponding RFID label through the electronic label equipment in the information tracing equipment, so that a consumer can quickly master the production information (batch number, manufacturer, production place and the like) of the rice through the way of scanning the RFID label, the public opening degree and transparency of the rice production information are comprehensively ensured, the selection and supervision of the consumer are facilitated, and the safety of the rice production is further enhanced; in addition, a plurality of node parameters are obtained, data redundancy is effectively avoided by using data filtering operation, meanwhile, ascending sequencing is carried out according to processing time delay, effective virtual machine resource allocation is carried out, a first sequence is reasonably planned, finally, the first sequence is adjusted according to transmission time delay, and finally the uploading sequence of each parameter to be uploaded is determined, so that efficient and rapid data processing and data uploading are guaranteed, the uploading sequence of each node parameter is reasonably allocated, the full-production process of rice is monitored in time, the rapidness and the high efficiency of data uploading of a large food safety data platform and data processing are comprehensively improved, and comprehensive and rapid early warning and early warning monitoring are realized.

Preferably, planting node parameter includes soil parameter, meteorological parameter, insect pest state parameter and water quality parameter, and planting node monitoring facilities 1 includes: the soil monitoring equipment is used for monitoring soil parameters of the rice planting field; the meteorological monitoring equipment is used for monitoring meteorological parameter pest monitoring equipment of the rice planting field, is used for acquiring pest image data, carrying out AI analysis, generating pest state parameters of the rice planting field, automatically early warning according to the pest state parameters, and controlling pesticide spraying; and the water quality monitoring equipment is used for monitoring the water quality parameters of the rice planting field. Therefore, the rice planting node is arranged to carry out all-around detection on the rice planting environment, and the quality of rice is guaranteed from the source.

Specifically, the soil monitoring equipment mainly comprises an online soil moisture content monitor, a soil component analyzer, a soil heavy metal detector and a gas chromatograph. Wherein, the sensors used by the online soil moisture content monitor are mainly used for detecting the temperature, the humidity, the conductivity, the salinity and the pH value of soil; the soil composition analyzer is mainly used for detecting the content of organic matters, nitrogen and phosphorus in soil; the heavy metal detector is mainly used for detecting the heavy metal content of soil; the gas chromatograph is mainly used for detecting and mainly detecting soil pesticide residues and the like. From this, soil monitoring facilities carries out real-time supervision mainly to the planting soil condition of rice, and heavy metal in the soil, the incomplete pollution of farming can restrain the growth of crop, and the suitable temperature of soil, moisture, pH value etc. can guarantee that the crop is good to be grown, for providing a harmless, good growing environment for the rice, through soil monitoring system real-time supervision soil condition, can get rid of the harm factor, in time regulate and control growing environment, satisfy the crop growth demand. The online soil moisture content monitor monitors soil moisture content, the release and migration of nutrients in soil and the absorption of nutrients by plants are closely related to the soil moisture content, and when the soil moisture content is proper, the release and migration rates of the nutrients are high, so that the effectiveness of the nutrients and the utilization rate of the nutrients in the fertilizer can be improved. In an embodiment of the present invention, the range of the normal soil parameter (i.e., the risk screening value) corresponding to the detected soil parameter and the control is as shown in table 1 below, it should be noted that the range of the normal soil parameter is stored in the big food safety data platform, and when the detected soil parameter exceeds the range of the normal soil parameter, a corresponding warning is issued.

TABLE 1

Specifically, the meteorological monitoring equipment mainly comprises an atmospheric temperature and humidity sensor, a digital air pressure sensor, an air speed sensor, a wind direction sensor, a rainfall sensor, a snow sensor, an illumination sensor, a sunshine duration sensor and a carbon dioxide sensor. Therefore, weather change conditions such as atmospheric temperature, humidity, air pressure, atmospheric pressure, wind speed, wind direction, illumination intensity, sunshine duration, carbon dioxide content and the like are monitored in real time, and the weather data are uploaded to the food safety big data platform in real time.

Particularly, the pest monitoring equipment mainly comprises a video monitor, pesticide spraying equipment, a pest sex-attracting automatic trapper and an intelligent pest situation observation lamp. Wherein: the video monitor is used for acquiring pest image data through the video monitor, transmitting the pest image data to the edge server for AI intelligent identification, identifying corresponding pest types and quantity, carrying out analysis processing, giving out a proper chemical pest killing formula and dosage, killing the pests under the condition of causing minimum pollution, giving out a most reasonable result through AI analysis for pest control, and uploading the analysis result to a food safety big data platform; the pesticide spraying equipment is used for acquiring local pest picture data and overall picture distribution through the video monitor, transmitting the local pest picture data and the overall picture distribution to the edge server for AI intelligent recognition and analysis, generating an efficient killing scheme through AI intelligence according to the obtained pest species, scale and distribution data, and spraying the pesticide at fixed points and in fixed quantity by using the plant protection unmanned aerial vehicle T16 to realize accurate spraying and reduce pollution; the pest sex attractant automatic trap is used for trapping and killing pests by using the placement sex attractant, and can realize monitoring and trapping and killing of different pests by replacing the attracting core. The directional trapping and killing of pests can be realized, and simultaneously, a large data platform for counting, classifying and counting pests and reporting and transmitting food safety in real time can be realized; the intelligent pest situation observation and report lamp attracts phototaxis pests to capture and kill, can identify main pests of rice including but not limited to brown planthopper, white-backed planthopper, rice leaf roller, chilo suppressalis, sesamia inferen and the like, and the video monitor acquires picture data, transmits the picture data to the edge server, performs automatic counting, and uploads the picture data to the food safety big data platform in real time.

It should be noted that the food safety big data platform receives the AI analysis result of the pest image data collected by the video monitor, compares the pest state parameters with the pre-stored pest state database, and controls various communication media to send out early warning information if the pest state parameters exceed the range, so that related personnel can perform protection operation in time. Various communication media include, but are not limited to, network forms and broadcast forms. Therefore, the food safety big data platform receives implementation pest data, carries out early warning and forecast on pest conditions, provides a pest control scheme according to the types and the number of pests, and realizes target prevention and control, selects medicaments with selectivity, low toxicity and little environmental pollution as far as possible, uses few or no chemical pesticides with broad spectrum, and changes the variety and the mixed formula frequently to prevent the pests from generating drug resistance. The application method also adopts the methods of stem coating, root application, injection and the like to reduce the pollution to the environment,

specifically, the water quality monitoring equipment mainly comprises a biochemical oxygen demand detector, a chemical oxygen demand monitor, a water quality monitor and a heavy metal detector. Wherein, the biochemical oxygen demand detector is preferably a BOD water quality detector for detecting the aquatic biochemical oxygen demand (BOD 5); the chemical oxygen demand detector is preferably a COD water quality on-line detector and is used for monitoring chemical oxygen demand (CODCr); the water quality monitor is preferably a GA-DCS 03030 parameter water quality detector and is used for detecting turbidity, chromaticity, ammonia nitrogen, suspended matters, residual chlorine, total chlorine, phosphate, nitrate, nitrite, sulfate, dissolved oxygen, a pH value and water temperature; the heavy metal detection instrument is preferably a water quality heavy metal detection instrument WAOL3000-HM which is used for monitoring seven elements of copper, cadmium, cobalt, nickel, arsenic, mercury and hexavalent chromium.

Based on the above-mentioned biochemical oxygen demand detector, chemical oxygen demand monitor, water quality monitor and heavy metal detector, the normal parameter ranges (i.e. risk screening values) of the corresponding detected water quality parameters (i.e. item categories) and controls are shown in table 2 below:

TABLE 2

In an embodiment of the present invention, a specific application scenario illustrates a monitoring sequence of the above-mentioned planting node monitoring device, in a planting node, the planting node is specifically divided into a plurality of sub-nodes, and a variety screening sub-node, a seedling raising sub-node, a soil preparation sub-node, a seedling transplanting sub-node, a field sub-node and a harvesting sub-node are sequentially provided, and corresponding monitoring devices and monitoring indexes are specifically shown in table 3 below:

TABLE 3

Preferably, the storage node parameters include rice quality parameters and warehouse environment parameters, and the storage node monitoring device 2 includes: the paddy quality monitoring equipment is used for monitoring paddy quality parameters of the produced paddy, wherein the paddy quality parameters comprise paddy yield, polished rice rate, impurity content, water content, pollutant amount, protein content and starch content; and the warehouse monitoring equipment is used for monitoring and storing the environmental parameters of the warehouse for producing the rice, wherein the environmental parameters of the warehouse comprise the temperature and humidity of the warehouse, the dust content of the warehouse, the carbon dioxide content of the warehouse and the pest and pest states of rats. Therefore, the quality of the incoming rice is detected by the rice quality monitoring equipment and uploaded to a large food safety data platform, so that accidental pollution caused when the rice is harvested, stored and received after being harvested and inspected is prevented, the rice quality of the incoming warehouse is ensured to be excellent, and the food safety of the rice at the receiving sub-node is ensured; monitor the warehouse environment through warehouse monitoring facilities, if to the warehouse humiture, the dust, carbon dioxide, the rat damage, the insect pest etc. carries out real-time supervision, and to reach the big data platform of food safety on the detected data, feed back warehouse monitoring system with the analysis and processing result simultaneously, adjust the warehouse humiture, if ventilate, the cooling etc., if the rat damage appears, the insect pest, the system can automatic alarm and preserve the alarm record, the suggestion staff in time handles simultaneously, ensure that the corn is in suitable storage environment, avoid the corn quality to take place the deterioration storing the sub-node.

Specifically, corn quality monitoring facilities includes corn outward appearance quality detector, food safety detector, infrared spectrum appearance analyzer, wherein: the appearance quality detector of the rice, the corresponding quality parameter of the detected rice includes the rice and goes out the rough rate, the polished rice rate, impurity content, moisture content, the yellow grain rice content, the content of the brown rice outside the rice, the intermixing rate, the color and luster according to the national quality standard (GB 1350-; the food safety detector is used for correspondingly detecting the quality parameters of the rice according to the requirement of a mass label (T/CCOA 8-2020) including toxin (such as aflatoxin), pollutant (such as cadmium) and pesticide residue (such as pymetrozine); the infrared spectrum analyzer is used for correspondingly detecting the quality parameters of the rice, including protein, moisture and starch. And comparing the rice quality data with the rice quality data of the receiving sub-nodes, confirming that the rice quality changes little, and taking the rice out of the warehouse, if the rice quality safety problem occurs, if a certain harm factor exceeds the standard, investigating a warehouse monitoring system record, finding out reasons and timely processing the problem, ensuring that the rice is in good quality when the rice is taken out of the warehouse, and ensuring the food safety of the rice.

Specifically, warehouse monitoring facilities includes video monitor, PM2.5 detector, electron nose, temperature and humidity sensor, carbon dioxide sensor, wherein: the video monitor is used for monitoring the storage condition in the warehouse and whether other organisms (such as mice and insects) exist; the intelligent food safety monitoring system is also used for uploading to a food safety big data platform to carry out AI intelligent analysis, and when mice are found, the intelligent food safety monitoring system informs managers to capture and dispose, supervises the managers and prevents the stealing and selling for the sale. The PM2.5 detector is used for monitoring the dust content in the warehouse so as to ensure that the air in the warehouse is clean and tidy; the electronic nose monitors the musty smell and gas (CO2, PH3) in the warehouse, detects the musty smell, indicates that the paddy is damp and goes bad and has problems, sends out an alarm and informs managers to deal with the problem in time; the temperature and humidity sensor is used for monitoring the temperature and humidity of the warehouse and ensuring the proper storage environment; the carbon dioxide sensor is used for monitoring the concentration of carbon dioxide, and the high-concentration CO2 can delay the reduction of the water content and the aging degree of the rice and ensure the freshness and the taste quality of the rice.

In an embodiment of the present invention, a specific application scenario illustrates a monitoring sequence of the storage node monitoring device, where the storage node is specifically divided into a plurality of child nodes, which are a receiving child node, a storage child node, a delivery child node, and corresponding monitoring devices and monitoring indexes, and refer to the following table 4:

TABLE 4

Preferably, the plurality of processing node parameters include a rice quality parameter, an operation image, and the processing node monitoring device 3 includes: the quality monitoring equipment is used for monitoring rice quality parameters of the produced rice, and the rice quality parameters comprise rice impurity content, imperfect grain content, yellow grain content, consistency, whole polished rice rate, coarseness and chalkiness; and the processing process monitoring equipment is used for carrying out video monitoring on the whole processing process and generating an operation image by using AI intelligent analysis so as to determine whether an operator follows the operation image. From this, detect the rice quality through quality monitoring facilities, with on the big data platform of food quality safety is uploaded to the testing data, prevent the unexpected pollution that exists in the rice from the warehouse-out to the processing receiving process, ensure that the rice quality of receiving is good, guarantee the food safety of rice. Through the processing procedure monitoring facilities, personnel's operation safety in the operation process is ensured to and prevent the pollution of operating personnel to the rice, guarantee the quality and the food safety of rice.

Specifically, the quality monitoring equipment comprises a rice impurity remover for monitoring the total impurity amount, the sand and stone particle number and the barnyard grass containing particle number; the rice yield detector is used for monitoring the hulling rate and the rice hulls; the appearance quality detector of the rice has the same functions as the functions applied to the collecting and storing nodes, and is not repeated; the appearance quality detector of the rice is used for monitoring the processing precision, the color and luster, the temperature rise of the rice, the breakage rate, the uneven rate of brown and white and the bran content; the multifunctional food safety detector has the same functions as the functions applied to the storage node, and is not repeated; the online near infrared spectrum analyzer has the same functions as the above-mentioned collection and storage node, and is not described again.

Specifically, the course of working monitoring facilities includes the video monitor, the video data transmission that the video monitor will gather is to the edge server, the edge server passes through AI intelligent analysis, whether analysis operating personnel's wearing accords with the standard requirement, if not conform to the requirement, send alarm signal, simultaneously, still can real time monitoring operating personnel's action standardization, compare with corresponding operating specification, the discovery has the action that does not accord with the standard requirement, will send the police dispatch newspaper and give managers, managers in time looks over and handles. Such as whether the operator has actions which do not meet the standard requirements, such as eating, smoking, calling and the like in the workshop.

In an embodiment of the present invention, a specific application scenario illustrates a monitoring sequence of the processing node monitoring device, where the processing node is specifically divided into a plurality of sub-nodes, which are a receiving sub-node, a clean rice sub-node, a rice hulling sub-node, a clean rice sub-node, a rice husking sub-node, a packaging sub-node, and a finished product sub-node in sequence, and detection devices and detection parameters corresponding to the sub-nodes are shown in table 5:

TABLE 5

Preferably, when the finished product is accepted at the finished product sub-node in the processing node, the RFID tag is attached to the package according to the requirement of the rice product, and the product code, the manufacturing enterprise, the production place, the production date, the data detected by the full chain, and the like are written into the RFID tag for future reference.

Preferably, the plurality of circulation node parameters include a process state parameter, a route parameter, a trajectory parameter, and a time parameter, and the circulation node monitoring apparatus 4 includes: the video monitor is used for monitoring process state parameters of the whole transportation process; and the Beidou navigator is used for monitoring the route parameters, the track parameters and the time parameters of the whole transportation process. From this, use big dipper navigator to carry out the record to route, orbit and the time of whole transportation, use the state of video monitor monitoring transportation overall process. Upload video safety big data platform in real time with above-mentioned monitoring signal, managers can look over the transportation situation of rice through equipment in real time, can look over the starting point of rice transportation, the terminal point of transportation, the planning route of transportation, the actual route of transportation, plan transport time, present transit time, transportation personnel information, the node code of rice, the realization is tracked the rice transportation process full transparence, can guarantee rice transportation efficiency, prevent that transportation personnel from stealing the rice, conspiring to get privately, accomplish effective supervision.

In an embodiment of the present invention, a specific application scenario illustrates a monitoring sequence of the transportation node monitoring device, where the transportation node is specifically divided into a plurality of child nodes, which are a receiving child node, a transportation child node, and a delivery child node in turn, and detection devices and detection parameters corresponding to each child node are as shown in table 6 below:

TABLE 6

It should be noted that, in combination with table 6, the receiving child node uses the RFID to record the node code and the safety data of the whole chain food produced by rice, uses the appearance quality detector of rice to detect the impurity content, imperfect grain content, yellow grain content, consistency, whole rice rate, roughness rate and chalkiness of rice, uses the multifunctional food safety detector to detect toxin (such as aflatoxin), pollutant (such as cadmium) and pesticide residue (such as pymetrozine), uses the online near infrared spectrum analyzer to detect protein, moisture and starch, and uploads the detected protein, moisture and starch to the food safety big data platform, and compares the detected data with the data of the processed child node and the national standard data, if the product meets the quality and food safety requirements, the next transportation child node can be entered. The transport sub-node records the transport route, the transport track and the transport time by using Beidou navigation, and the tracking and positioning of the transport process are realized. The lower cargo node uses a rice appearance quality detector to detect the impurity content, the imperfect grain content, the yellow grain content, the consistency, the whole polished rice rate, the coarseness and the chalkiness of rice, uses a multifunctional food safety detector to detect toxin (such as aflatoxin), pollutant (such as cadmium) and pesticide residue (such as pymetrozine), uses an online near infrared spectrum analyzer to detect protein, moisture and starch, and ensures the quality of the rice after transportation.

Preferably, the food safety big data platform comprises a big data acquisition module, a big data collection module, a big data sorting module, a big data analysis module, a big data display module, a big data application module and a big data service module. Therefore, the food safety big data platform is arranged, the monitoring data of each node is processed in various big data processing modes, and the state of each link is analyzed, so that effective early warning is performed on each link. Preferably, the big data application module comprises a risk analysis unit, wherein: and the risk analysis unit is used for comparing the plurality of planting node parameters, the plurality of collecting and storing node parameters, the plurality of processing node parameters and the plurality of transportation node parameters with the corresponding pre-stored parameter index libraries respectively and carrying out early warning according to parameter comparison results. Therefore, the rice monitoring system is provided with the risk analysis unit, and monitoring parameters are effectively compared and processed, so that the abnormal state is quickly positioned, effective early warning is carried out, and the safety of each link of rice production is ensured.

Preferably, the plurality of processing node parameters include an operation image, the risk analysis unit is specifically configured to match the operation image with a corresponding pre-stored operation image standard library, and if the operation image is not matched with the pre-stored operation image standard library, an early warning is performed. Therefore, the method adopts an image recognition mode, and utilizes data processing modes such as deep learning and pattern recognition to recognize irregular operation scenes, so as to prevent the damage of misoperation of operators to the quality of rice.

Preferably, the plurality of processing node parameters include hazard factor parameters, and the risk analysis unit is specifically configured to compare the hazard factor parameters with a corresponding pre-stored hazard factor standard library, and if the hazard factor parameters exceed a standard range, perform early warning. Specific hazard factor parameters, pre-stored hazard factor standards libraries (including the various limit ranges in table 7) are shown in table 7 below:

TABLE 7

Preferably, after the node parameters (including the planting node parameters, the storage node parameters, the processing node parameters and the circulation node parameters) are obtained, all the node parameters are burned to the RFID label, and when the RFID label is scanned by a consumer, the full-chain production information of the planting node, the storage node, the processing node and the circulation node can be comprehensively obtained through data conversion. It can be understood that, in the present invention, all the node parameters can be used to generate corresponding two-dimensional code information, and the implementation function of the two-dimensional code information is consistent with that of the RFID tag, which is not described herein again.

The following is described with specific experimental data: when the soil monitoring equipment of the planting node monitoring equipment 1 monitors soil parameters of a rice planting field, wherein the temperature and humidity of soil are 20 ℃, the conductivity is 40ms/m, the salt content is 0.5g/kg, the pH value is 11, the content of soil organic matters is 35g/kg, the nitrogen is 1.0g/kg, the phosphorus is 35mg/kg, the content of soil heavy metals is 0.1mg/kg, and the content of soil pesticide residues is 0.02mg/kg, and the pH value is determined to exceed a preset range of 4-9 by comparing with a prestored parameter database, and at the moment, a food big data platform carries out early warning on a planting node to remind related personnel of improving operation according to the soil condition; when the paddy quality monitoring equipment of the storage node monitoring equipment 2 monitors paddy quality parameters of produced paddy, wherein the paddy roughness is 80%, the polished rice rate is 70%, the impurity content is 8%, the water content is 12%, the pollutant content is 0.01mg/kg, the protein content is 6% and the starch content is 70%, the paddy quality parameters are compared with a prestored parameter database, the impurity content is determined to exceed the preset range of 0-1.0%, and at the moment, the food big data platform carries out early warning on the storage nodes to remind relevant personnel to process the rice which does not meet the requirements; when a video monitor of the processing node monitoring equipment 3 transmits acquired video data to the edge server, the edge server carries out AI intelligent analysis, and when an irregular image worn by an operator is obtained, the food big data platform carries out early warning on the processing node to remind relevant personnel of standardizing the operation wear; when the Beidou navigator of the circulation node monitoring equipment 4 monitors the route parameters, the track parameters and the time parameters of the whole transportation process, the route parameters, the track parameters and the time parameters are compared with the prestored parameter database, the phenomenon that the rice is transported by steal is possibly caused when the route parameters, the track parameters and the time parameters are not in accordance with the preset requirements, and the food big data platform carries out early warning on the circulation nodes at the moment to remind related personnel to carry out recovery processing.

Example 2

The embodiment of the invention provides an intelligent detection method for rice full-chain quality information based on the Internet of things, and as seen in combination with fig. 2, fig. 2 is a schematic flow diagram of the intelligent detection method for rice full-chain quality information based on the Internet of things, the intelligent detection method for rice full-chain quality information based on the Internet of things comprises steps S1 to S5, wherein: in step S1, acquiring a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters, and a plurality of circulation node parameters; in step S2, performing data filtering on the plurality of planting node parameters, the plurality of storage node parameters, the plurality of processing node parameters, and the plurality of circulation node parameters, and determining parameters to be uploaded after filtering; in step S3, the processing delays of the parameters to be uploaded are sorted in an ascending order to form a first sequence, and the newly added parameters to be uploaded at each edge node are placed at the end of the first sequence; in step S4, adjusting the first sequence according to the transmission delay of each edge node, and determining an uploading sequence of a plurality of parameters to be uploaded according to the adjusted first sequence; in step S5, data processing is sequentially performed on the uploaded plurality of parameters to be uploaded, and the data processing result is visualized. In the embodiment of the invention, the purpose of effectively monitoring each production link is achieved by carrying out big data processing on the planting node parameter, the storage node parameter, the processing node parameter and the circulation node parameter of each node, and meanwhile, the data processing result is visualized, so that the information management and the operation are facilitated.

In a specific embodiment of the invention, the sensors of the internet of things transmit in parallel, and the bandwidth is adjusted by a target planning method to transmit the tasks to the edge server. When a task is transmitted to a cloud server from an edge server, the tasks on the edge server are sequenced, the tasks are arranged in an ascending order according to the processing delay, a new task is added and placed at the end of the sequence, the transmission delay of each task is calculated, the queuing delay of each task is calculated, the two tasks are added, the task with the largest sum of the transmission delay and the queuing delay is preferentially transmitted according to the descending order of the sum of the two tasks, when the new task is added into the queue, the transmission delay and the queuing delay of each current task are recalculated, the tasks are arranged in a descending order, the task with the largest sum of the transmission delay and the queuing delay is preferentially transmitted, each task with the largest sum of the transmission delay and the queuing delay can be preferentially transmitted, and the queuing delay is reduced. The specific task transmission method comprises the following processes:

the method for transmitting the tasks to the edge server by the sensor of the internet of things comprises the following steps:

(1) calculating transmission delay, and determining channel capacity according to Shannon's theorem: c ═ big₂(1+ S/N), where C is the maximum speed or channel capacity supported by the channel, B is the bandwidth of the channel, S is the average signal power, and N is the average noise power; S/N is the signal to noise ratio. The transmission delay can be expressed as:

wherein D is_iIs the amount of data for task i, B_iAnd S is the average signal power, namely the product of the transmission power provided when the mobile terminal where the ith task is located sends the task i to the edge server and the channel gain of the channel used for transmission, and N is the average noise power in the channel.

(2) Adopting target planning, the model is as follows: the target is as follows:

the constraint conditions are as follows: s.t.C 1:. Sigma B_i≤B；C2：B_op. Wherein, B_opIs the optimal transmission channel resource allocation scheme, and B is the total bandwidth of the wireless communication link for transmitting data. In this way, the task is transmitted to the edge server.

The method for transmitting the task from the edge server to the cloud server comprises the following steps:

(1) calculating the processing delay dproc of each task as follows:

in the equation, the data amount Di of each task is larger than the processing delay dproc of the computing power fie of the upper edge server for each task.

(2) Sequencing each task according to the sequence of the processing time delay from small to large to form an ascending queue q: q ═ D (D)₁，D₂，...，D_i，...，D_n). Wherein, the first task of the queue is uploaded preferentially, and the new task is added to the tail end of the queue. Defining a set before as a set of all tasks arranged in front of the task i, and M is the number of the tasks in the set. After the task processing is finished, the queue is not needed to be queued, and the transmission is directly carried out according to the ascending queue of the processing time delay, namely, under an ideal condition, the transmission of the previous task is finished, and the processing of the next task is just finished. When a task is queued, it is transmitted as follows.

(3) Calculating the transmission time delay d of each task_transComprises the following steps:

in the formula, the data amount D of each task_iThe transmission delay d of each task being greater than the transmission rate C_trans。

(4) Calculating queuing delay d of each task_qComprises the following steps:

in the formula, j belongs to a set before, the set is a set of all tasks arranged in front of the task i, and the sum of the transmission delays of all tasks arranged in front of the task i is the queuing delay.

(6) And adding the transmission delay and the queuing delay of each task, performing descending arrangement, and uploading the task with the maximum sum of the transmission delay and the queuing delay.

(7) And when a new task is added into the queue, recalculating the queuing delay of each task, performing descending arrangement according to the sum of the new transmission delay and the queuing delay, and preferentially uploading the task with the maximum sum of the transmission delay and the queuing delay. And the sum of the transmission delay and the queuing delay of the task is calculated, and the priority transmission with the maximum sum of the transmission delay and the queuing delay is carried out to reduce the queuing delay of the task and enable the task to be transmitted quickly. The task is transmitted to the cloud server through the method.

Preferably, the intelligent detection method for the quality information of the whole chain of rice based on the internet of things further comprises the following steps: and comparing the plurality of planting node parameters, the plurality of collecting and storing node parameters, the plurality of processing node parameters and the plurality of circulating node parameters with the corresponding pre-stored parameter index libraries respectively, and early warning the corresponding nodes according to parameter comparison results. Therefore, early warning is carried out through effective data comparison.

Preferably, the intelligent detection method for the quality information of the whole chain of rice based on the internet of things further comprises the following steps: and converting the production information of the produced rice into a corresponding RFID label. Therefore, direct information tracing of the consumer is facilitated through the arrangement of the RFID tag.

Preferably, the process of operating the video stream processing provided by the present invention includes steps S001 to S009, wherein: in step S001, dividing the operation video stream into a plurality of video frame sequence groups, calling an API algorithm, and counting target identification numbers corresponding to the plurality of video frame sequence groups; in step S002, determining a frame filtering model according to the time delay, bandwidth and target identification number uploaded to the cloud platform by the edge node, removing redundant video frame sequence groups according to the frame filtering model, and determining a first frame sequence group; in step S003, extracting a key frame in the first frame-sequence group according to the entropy of the image information of the first frame-sequence group, and determining a second frame-sequence group; in step S004, allocating virtual machine resources according to the target identification numbers and the data amount of the plurality of second frame sequence groups, and determining an uploading sequence of the second frame sequence groups to the cloud platform; in step S005, performing human body posture estimation on each frame image in the second frame sequence group, and determining position coordinates of a plurality of joint points; in step S006, a joint distance variation matrix is determined according to the amount of variation in the position coordinates of the same joint between two adjacent images in the second frame sequence group; in step S007, the second frame sequence group is divided equally, and the joint point distance variation generated by two adjacent frames in each video segment is subjected to matrix addition to obtain each segment of accumulated distance variation matrix as a feature vector of the second frame sequence group; in step S008, the feature vectors are input into a well-trained deep learning model for classification, and a corresponding operation specification index is determined; in step S009, the operation specification index is compared with the corresponding pre-stored index library, and is directed to the corresponding processing node according to the comparison result. Therefore, an operation video stream in the processing node monitoring equipment is obtained, a frame filtering model in the edge node is utilized, operation of extracting key frames is utilized, data redundancy is effectively avoided, meanwhile, an edge node manager is arranged to carry out effective virtual machine resource allocation according to the uploading state of the processing node, the uploading sequence is reasonably planned, finally, a cloud platform receives a second frame sequence group, characteristic vectors in the second frame sequence group are extracted, whether corresponding operation is standard or not is determined by utilizing a deep learning model, efficient and quick data processing and data uploading are guaranteed, the processing process is monitored in time, data uploading of a food safety big data platform and rapidity and efficiency of data processing are comprehensively improved, and comprehensive and quick early warning and monitoring are achieved.

In a specific embodiment of the present invention, the plurality of process node parameters comprises an operational video stream during the process, wherein: processing edge nodes corresponding to the node parameters, specifically dividing the operation video stream into a plurality of video frame sequence groups, calling an API (application programming interface) algorithm, and counting target identification numbers corresponding to the plurality of video frame sequence groups; the frame filtering model is determined according to the time delay, the bandwidth and the target identification number uploaded to the cloud platform by the edge node, redundant video frame sequence groups are removed according to the frame filtering model, and a first frame sequence group is determined; the image processing device is also used for extracting key frames in the first frame sequence group according to the image information entropy of the first frame sequence group and determining a second frame sequence group; the edge node manager is specifically used for being in communication connection with the plurality of edge nodes, and is used for allocating virtual machine resources according to the target identification numbers and the data volume of the plurality of second frame sequence groups and determining an uploading sequence of the second frame sequence groups to the cloud platform; the cloud platform is specifically used for carrying out human body posture estimation on each frame of image in the second frame sequence group and determining position coordinates of a plurality of joint points; the joint distance variation matrix is also used for determining a joint distance variation matrix according to the position coordinate variation of the same joint between two adjacent frames of images in the second frame sequence group; the second frame sequence group is further used for carrying out average division on the second frame sequence group, and matrix addition is carried out on the joint point distance variable quantities generated by two adjacent frames in each section of video to obtain a cumulative distance variable quantity matrix of each section as a feature vector of the second frame sequence group; and the method is also used for inputting the feature vectors into the completely trained deep learning model for classification and determining the corresponding operation specification index.

In a specific embodiment of the present invention, the processing node is specifically divided into a plurality of sub-nodes, which are sequentially a receiving sub-node, a clean rice sub-node, a rice hulling sub-node, a clean rice sub-node, a rice milling sub-node, a packaging sub-node and a finished product sub-node, wherein 4 paths of cameras are respectively installed in the clean rice sub-node, the rice hulling sub-node, the clean rice sub-node, the rice milling sub-node and the packaging sub-node, and 2 paths of cameras and a total 24 paths of cameras are installed in the finished product sub-node. The bandwidth and the storage space required by the 24 paths of cameras for full-video monitoring in the processing process comprise an uplink bandwidth for transmitting video data to the edge node by the cameras, a downlink bandwidth for receiving the video data by the edge node, a storage space for locally storing the video data for one month by the cameras, a storage space for cleaning the video data once a month by the cameras and the storage space of the edge node. The method for uploading the video images of the 24-channel camera by using the edge calculation comprises the following steps:

the first step is as follows: detecting a moving target object in the operation video stream, identifying the video data of the operation video stream, judging whether a moving target exists or not, extracting an extracted video segment with the moving target, and then carrying out next processing on the extracted video data; the method comprises the following steps of extracting a video clip with a moving target by adopting a three-frame difference method, wherein a specific formula is described as follows:

wherein G (x, y) is G₁(x, y) and g₂(x, y) carrying out logical AND, judging that the continuous three frames of images change, indicating that a moving object exists, and extracting the video clip with the moving object. Therefore, before the identification of the operation behavior specification is carried out, whether a moving target exists needs to be identified, namely an operator has the significance of further carrying out the identification of the operation behavior specification, a video segment with the moving target is extracted through a frame difference method, redundant video segments are removed, and the video segment with the moving target is processed in the next step.

The second step is that: preprocessing is performed by using a frame filtering model, wherein the frame filtering model has the following formula:

wherein, O_i，sFor the identification number of the object of the i-th frame in the video stream S, D_upUploading video frame data volume for ECN, D_maxFor the maximum amount of data allowed to be transmitted per unit time of the network, t_dFor task completion time, τ_dMaximum processing time allowed for completion of the task, T_eIs the total time delay, T, of S sent to the cloud computing center_cThe time delay of the direct transmission cloud platform is adopted. Therefore, after the transmission capacity and the total time delay of the current network both meet the conditions, the ECN Controller allocates an uploading channel and starts task scheduling. When a plurality of cameras are used for collecting data, if all video data are processed, the processing time is longer, resources are wasted, and for repeated video content, namely the same scene content collected by different cameras, the video with the most identified target objects is selected through frame filtering, and is identified and analyzed, so that the data processing time is reduced, and the problem of video data redundancy is solved;

the third step: extracting the key frame, wherein the specific flow is as follows: the joint histogram represents two images I of the same size_iAnd I_iWith the frequency of occurrence of the gray combinations of the pixel pairs at their corresponding locations. For image I of same MxN_i(x，y)、I_j(x, y), the joint probability of the corresponding pixel value pair (p, q) is expressed as:

wherein,

from the above equation, it can be seen that the image I can be obtained by finding the F (p, q) value for all possible pixel value pairs (p, q)_i(x, y) and I_jThe joint histogram symmetry is defined as:

wherein, α is a weight on a diagonal of the joint histogram, which is a smaller normal quantity, and β ═ q (p-q) n represents a weight away from the diagonal element, n in the formula is an integer, δ more intuitively represents the similarity between two frames, as δ approaches to 1, it represents that the joint histogram is more symmetrical, i.e. it indicates that the two images are more similar, and when a target appears rapidly, and the video content such as brightness is emittedWhen obvious change occurs, the similarity between frames changes correspondingly, and the similarity delta between adjacent frames belongs to [0, 1 ]]To avoid missing key frames, the threshold T' is set to 0.9.

According to the continuous characteristic of the monitoring video, in a continuously changing video sequence, the characteristic value of the continuous front and back video frames is gradually changed, namely the change of the image information value of the adjacent frames is not large. In order to reduce the redundancy of data, a frame with the largest information entropy value of an image is selected from a video sequence with close intervals as a key frame

In the formula: n denotes the number of gray levels of an image, x_iIndicates the gray value of the pixel (x, y), p (x)_i) Is the probability of each gray level occurring. In order to prevent redundancy of key frames caused by illumination change and the like in the extracted key frames, one frame with the largest information entropy is selected from adjacent and nearer candidate frames as the key frame. Non-adjacent inter-frame entropy differences of 20 frames apart can be clearly distinguished. Therefore, the key frames are extracted based on the combined histogram, and when the interval of the key candidate frame sequences is less than 20, one frame with the largest information entropy is selected as the key frame.

The fourth step: and (3) scheduling the tasks, wherein the specific flow is as follows: after the ECN Controller allocates the uploading channel, the ECN feeds back the queue information of the uploading video frame. Under different network environments, parameters of uploaded video streams are different after ECN clusters are dynamically adjusted, and data volume of video frame groups is represented as D for convenience of unified scheduling management of ECN controllers_e，i. The ECN average identification target number may be expressed as:

wherein,

for ECN average identification of target number, D_e，iAmount of data for a group of video frames, B_cFor link capacity, O_iIs the number of identification targets of the ith frame. Thus, the ECN Controller assigns a uniform metric to the scheduling of each upload task

At time T, N ECN tasks in the cluster wait to be scheduled, and the completion time of each task after r rounds of scheduling is recorded as T_iThe validity of the ECN uploading task can be reached only by scheduling and completing before the deadline, and the completion time meets t_i＜τ_iIn which τ is_iIs the latest completion time of the ith ECN upload task. The task scheduling needs to consider the limited available resources of the system, can not exceed a threshold value, have

Where r is the number of scheduled rounds, D_iFor the ith frame data amount, M_tScheduling an upper threshold of resources for the task; under the condition that the allocation condition of system resources and the ECN uploading meeting the deadline are considered, the task scheduling time model is as follows:

wherein, t_iFor scheduled completion time, r is the number of scheduled rounds, D_iFor the ith frame data amount, M_tScheduling an upper threshold, τ, of resources for a task_iThe latest completion time of the ith ECN uploading task is the latest completion time of the ith ECN uploading task, so that the video stream data collected by the multiple cameras cannot be uploaded together, and the uploading resources and sequence need to be allocated, so that efficient transmission is realized.

The fifth step: identifying operation behaviors, wherein the specific flow is as follows: firstly, extracting the position coordinates of each frame of human body joint points in a video: carrying out posture estimation on each frame of human body in the video by utilizing an Open-position method to obtain the neck, chest, head, right shoulder, left shoulder, right hip, left hip, right elbow, left elbow, right knee, left knee, right wrist and left wrist of the human bodyPosition coordinates of 15 joint points of wrist, right ankle and left ankle, wherein the coordinate of k-th joint point is represented as L_k＝(x_k，y_k) K is from 1 to 15; then, the position coordinates of each joint point are normalized, a coordinate matrix P is formed by the position coordinates of the 15 joint points after normalization,

wherein (x)_k，y_k) Representing the coordinates after the k-th joint point normalization; and then, calculating a distance variation matrix of the human body joint points of two adjacent frames: according to the coordinate matrix P of two adjacent frames_nAnd P_n-1Calculating a joint point position coordinate variation matrix of two adjacent frames, and calculating a joint point distance variation matrix D according to the joint point position coordinate variation matrix; further, generating video characteristics, averagely dividing the video into 4 sections according to the time length of the video, adding distance variation matrixes D generated by two adjacent frames in each section of the video to obtain accumulated distance variation matrixes Di, wherein i ranges from 1 to 4, carrying out L2 normalization on Di to obtain normalized Di ', and connecting the accumulated distance variation matrixes Di' in series to serve as the characteristics of the whole video: f ═ D1', D2', D3', D4'](ii) a Then, the videos are classified using neural networks: dividing video data into a training set and a testing set, inputting the characteristics of a training set video into a neural network for training to obtain a trained neural network classification model, and inputting the characteristics of a testing set video into the trained neural network classification model to obtain a classification result.

Preferably, the moving target is detected, when the video data of the moving object is acquired by the camera, whether the moving target exists is judged according to algorithm detection and analysis, the video data with the moving target is uploaded, all the video data are not required to be uploaded, only the video data with the moving target object are uploaded, and therefore the data transmission amount and the data transmission time are reduced, and the bandwidth is saved. In the target detection stage, the inter-frame difference method is used for detecting the moving target, so that whether the moving target exists or not is judged through the inter-frame image difference, the moving target is detected and extracted to obtain the video clip with the moving target, and useless video clips are not processed.

The invention discloses an intelligent detection system and method for rice full-chain quality information based on the Internet of things, which are characterized in that on the basis of monitoring data of all nodes, centralized processing is carried out through a food safety big data platform in information tracing equipment so as to comprehensively monitor the states of all nodes on a rice production chain, the big data platform is utilized to realize rapid processing of various monitoring data, the processing result is visually operated and displayed to related personnel, and the rice production quality control and management are facilitated; in addition, the production information of the produced rice is burnt to the corresponding RFID label through the electronic label equipment in the information tracing equipment, so that a consumer can quickly master the production information (batch number, manufacturer, production place and the like) of the rice through a way of scanning the RFID label, the public opening degree and transparency of the rice production information are comprehensively guaranteed, the selection and supervision of the consumer are facilitated, and the safety of the rice production is further enhanced.

According to the technical scheme, the information of each node on the rice industry chain is comprehensively acquired, and various monitoring information is subjected to data processing through the big data platform, so that effective information management and information tracing are achieved, and the safety of rice production is guaranteed.

The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.

Claims

1. The utility model provides a full chain quality information intelligent detection system of rice based on thing networking, its characterized in that includes a plurality of monitoring facilities and information equipment of tracing to the source, a plurality of monitoring facilities include plant node monitoring facility, store up node monitoring facility, processing node monitoring facility and circulation node monitoring facility for monitor different node parameters, node parameter includes plant node parameter, stores up node parameter, processing node parameter, circulation node parameter, the full chain quality information intelligent detection system of rice based on thing networking specifically includes:

the planting node monitoring equipment is used for monitoring a plurality of planting node parameters of the rice planting field under the planting node and transmitting the parameters to the information tracing equipment;

the collection and storage node monitoring equipment is used for monitoring a plurality of collection and storage node parameters of the produced paddy of the rice planting field under the collection and storage node and transmitting the parameters to the information tracing equipment;

the processing node monitoring equipment is used for monitoring a plurality of processing node parameters in the processing process of the produced paddy under the processing node and transmitting the processing node parameters to the information tracing equipment;

the circulation node monitoring equipment is used for monitoring a plurality of circulation node parameters in the circulation process of the processed produced rice under the circulation node and transmitting the circulation node parameters to the information traceability equipment;

the information tracing equipment comprises a food safety big data platform and electronic tag equipment, wherein the food safety big data platform is used for carrying out big data processing on a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters and a plurality of circulation node parameters and visualizing a big data processing result; the electronic tag equipment is used for converting the production information of the produced rice into a corresponding RFID tag;

the food safety big data platform comprises a cloud platform, an edge node manager and a plurality of edge nodes corresponding to the monitoring devices respectively, wherein:

the edge node is used for receiving the corresponding node parameters, performing data filtering on the node parameters and determining filtered parameters to be uploaded;

the edge node manager is used for sequencing the processing time delay of each parameter to be uploaded in an ascending order to form a first sequence, and each newly added parameter to be uploaded of the edge node is placed at the tail end of the first sequence; the first sequence is further used for adjusting the first sequence according to the transmission delay of each edge node, and the uploading sequence of the parameters to be uploaded is determined according to the adjusted first sequence;

and the cloud platform is used for sequentially carrying out data processing on the uploaded parameters to be uploaded and visualizing the data processing result.

2. The intelligent detection system for the quality information of the rice full chain based on the Internet of things according to claim 1, wherein the planting node parameters comprise soil parameters, meteorological parameters, insect pest state parameters and water quality parameters, and the planting node monitoring equipment comprises:

the soil monitoring equipment is used for monitoring the soil parameters of the rice planting field;

the meteorological monitoring equipment is used for monitoring the meteorological parameters of the rice planting field;

the pest monitoring equipment is used for acquiring pest image data, carrying out AI analysis, generating the pest state parameters of the rice planting field, carrying out automatic early warning according to the pest state parameters and controlling pesticide spraying;

and the water quality monitoring equipment is used for monitoring the water quality parameters of the rice planting field.

3. The intelligent detection system for rice full-chain quality information based on the internet of things according to claim 2, wherein the storage node parameters comprise rice quality parameters and warehouse environment parameters, and the storage node monitoring equipment comprises:

the rice quality monitoring equipment is used for monitoring the rice quality parameters of the produced rice, wherein the rice quality parameters comprise rice grain yield, polished rice rate, impurity content, water content, pollutant amount, protein content and starch content;

and the warehouse monitoring equipment is used for monitoring and storing the warehouse environmental parameters of the produced paddy, wherein the warehouse environmental parameters comprise warehouse temperature and humidity, warehouse dust content, warehouse carbon dioxide content and rat and insect pest states.

4. The intelligent detection system for rice full-chain quality information based on the Internet of things according to claim 1, wherein the plurality of processing node parameters comprise rice quality parameters and operation images, and the processing node monitoring equipment comprises:

quality monitoring equipment for monitoring the rice quality parameters of the produced rice, wherein the rice quality parameters comprise rice impurity content, imperfect grain content, yellow grain content, consistency, whole rice rate, coarseness rate and chalkiness rate;

and the processing process monitoring equipment is used for carrying out video monitoring on the whole processing process and generating the operation image by using AI intelligent analysis so as to determine whether an operator follows the operation image.

5. The rice full-chain quality information intelligent detection system based on the internet of things as claimed in claim 1, wherein the plurality of circulation node parameters comprise a process state parameter, a route parameter, a track parameter and a time parameter, and the circulation node monitoring device comprises:

a video monitor for monitoring the process state parameters of the overall transportation process;

and the Beidou navigator is used for monitoring the route parameters, the track parameters and the time parameters in the whole transportation process.

6. The rice full-chain quality information intelligent detection system based on the Internet of things according to claim 1, wherein the food safety big data platform comprises a big data acquisition module, a big data collection module, a big data sorting module, a big data analysis module, a big data display module, a big data application module and a big data service module.

7. The Internet of things-based rice full-chain quality information intelligent detection system as claimed in claim 6, wherein the big data application module comprises a risk analysis unit, wherein:

the risk analysis unit is used for comparing the planting node parameters, the storage node parameters, the processing node parameters and the circulation node parameters with a corresponding pre-stored parameter index library respectively and early warning corresponding nodes according to parameter comparison results.

8. The Internet of things-based rice full-chain quality information intelligent detection system as claimed in claim 7, wherein the plurality of processing node parameters comprise operation images, the risk analysis unit is specifically configured to match the operation images with a corresponding pre-stored operation image standard library, and if not, perform early warning.

9. An intelligent detection method for the quality information of the rice full chain based on the Internet of things is characterized in that based on the intelligent detection system for the quality information of the rice full chain based on the Internet of things according to any one of claims 1 to 8, the intelligent detection method for the quality information of the rice full chain based on the Internet of things comprises the following steps:

acquiring a plurality of planting node parameters, a plurality of storage node parameters, a plurality of processing node parameters and a plurality of circulation node parameters;

performing data filtering on the planting node parameters, the storage node parameters, the processing node parameters and the circulation node parameters, and determining filtered parameters to be uploaded;

sequencing the processing time delay of each parameter to be uploaded in an ascending order to form a first sequence, and placing each newly added parameter to be uploaded at the edge node at the tail end of the first sequence;

adjusting the first sequence according to the transmission delay of each edge node, and determining the uploading sequence of the parameters to be uploaded according to the adjusted first sequence;

and sequentially carrying out data processing on the uploaded parameters to be uploaded, and visualizing the data processing result.

10. The intelligent detection method for rice full-chain quality information based on the internet of things according to claim 9, wherein the plurality of processing node parameters comprise an operation video stream in a processing process, and the data processing process of the operation video stream comprises:

dividing the operation video stream into a plurality of video frame sequence groups, calling an API (application programming interface) algorithm, and counting target identification numbers corresponding to the video frame sequence groups;

determining a frame filtering model according to the time delay and the bandwidth of the edge node uploaded to the cloud platform and the target identification number, removing redundant video frame sequence groups according to the frame filtering model, and determining a first frame sequence group;

extracting key frames in the first frame sequence group according to the image information entropy of the first frame sequence group, and determining a second frame sequence group;

distributing virtual machine resources according to the target identification numbers and the data volume of the second frame sequence groups, and determining an uploading sequence of the second frame sequence groups to the cloud platform;

estimating the posture of each frame of image in the second frame sequence group, and determining the position coordinates of a plurality of joint points;

determining a joint point distance variable quantity matrix according to the position coordinate variable quantity of the same joint point between two adjacent frames of images in the second frame sequence group;

equally dividing the second frame sequence group, and performing matrix addition on the joint point distance variable quantities generated by two adjacent frames in each section of video to obtain a cumulative distance variable quantity matrix of each section as a feature vector of the second frame sequence group;

inputting the characteristic vectors into a well-trained deep learning model for classification, and determining corresponding operation specification indexes;

and comparing the operation specification index with a corresponding prestored index library, and carrying out early warning on the corresponding processing node according to a comparison result.