阅读说明：本技术 一种基于大数据的蔬菜存放智能管理系统 (Intelligent vegetable storage management system based on big data ) 是由 陈树贤 陈天翔 于 2020-04-08 设计创作，主要内容包括：本发明公开一种基于大数据的蔬菜存放智能管理系统,包括箱体参数采集模块、参数预处理模块、蔬菜图像采集模块、品质预演构建模块、蔬菜清单数据库、优化处理模块、人员检测模块和预警显示终端。本发明通过品质预演构建模块对采集的环境参数进行分析、处理,以统计冰箱内温度、湿度以及各细菌种类的含量变化所对应的预期环境综合品质演变系数,并根据蔬菜图像中蔬菜颜色获取蔬菜的新鲜度系数,优化处理模块根据结合当前环境下的预期环境综合品质演变系数以及环境参数的变化量统计蔬菜品质变化率的影响系数并计算蔬菜预计存放时间,便于判断蔬菜是否变质,且及时提醒用户对冰箱内的蔬菜进行处理,降低对冰箱换寄给你的进一步污染。(The invention discloses a vegetable storage intelligent management system based on big data, which comprises a box body parameter acquisition module, a parameter preprocessing module, a vegetable image acquisition module, a quality preview construction module, a vegetable list database, an optimization processing module, a personnel detection module and an early warning display terminal. According to the invention, the collected environmental parameters are analyzed and processed through the quality preview construction module to count the comprehensive quality evolution coefficient of the expected environment corresponding to the content change of temperature, humidity and various bacteria types in the refrigerator, the freshness coefficient of vegetables is obtained according to the colors of the vegetables in the vegetable image, the optimization processing module counts the influence coefficient of the vegetable quality change rate according to the comprehensive quality evolution coefficient of the expected environment in the current environment and the change amount of the environmental parameters and calculates the predicted storage time of the vegetables, so that whether the vegetables go bad or not can be judged conveniently, the user can be reminded to process the vegetables in the refrigerator in time, and further pollution caused by the change of the refrigerator to the user can be reduced.)

1. The utility model provides an intelligent management system is deposited to vegetables based on big data which characterized in that: the system comprises a box body parameter acquisition module, a parameter preprocessing module, a vegetable image acquisition module, a quality preview construction module, a vegetable list database, an optimization processing module, a personnel detection module and an early warning display terminal;

the device comprises a box body parameter acquisition module, a quality preview construction module and an optimization processing module, wherein the parameter preprocessing module is respectively connected with the box body parameter acquisition module, the quality preview construction module and a vegetable list database;

the box body parameter acquisition module is arranged on a refrigerating layer of the refrigerator and used for detecting the temperature and the humidity in the refrigerating layer of the refrigerator and the content of each bacterial species and sending the detected temperature and the detected humidity in the refrigerating layer and the content of each bacterial species to the parameter preprocessing module;

the device comprises a parameter preprocessing module, a vegetable list database and a quality preview construction module, wherein the parameter preprocessing module is connected with a box parameter acquisition module, is used for receiving the temperature and humidity of a refrigerating layer of a refrigerator and the content of each bacterial type sent by the box parameter acquisition module, counting the average temperature, the average humidity and the content of each bacterial type within a fixed time interval t to obtain an average temperature time period set, an average humidity time period set and a bacterial type time period set, and respectively sending the average temperature time period set, the average humidity time period set and the bacterial type time period set to the vegetable list database and the quality preview construction module;

the vegetable image acquisition module is used for acquiring images of a refrigerator cold storage area, performing high-pass filtering processing on the acquired images, and respectively sending the filtered vegetable images to the quality preview construction module and the optimization processing module;

the quality pre-modeling construction module is used for receiving the average temperature time period set, the average humidity time period set and the bacteria species time period set in the refrigerating chamber of the refrigerator sent by the parameter preprocessing module, respectively comparing the average temperature in the next time period with the average temperature in the previous time period, comparing the average humidity in the next time period with the average humidity in the previous time period, comparing the content corresponding to each bacteria species in the next time period with the content corresponding to the bacteria species in the previous time period, respectively obtaining the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, and counting the comprehensive quality evolution coefficient of the expected environment in the current environment according to the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, the quality preview construction module sends the comprehensive quality evolution coefficient of the expected environment under the current environment, the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set in the refrigerator to the optimization processing module;

meanwhile, the quality preview construction module receives the filtered vegetable image sent by the vegetable image acquisition moduleThe feature extraction is performed on the vegetable image, and the extracted feature is compared with a vegetable type feature set corresponding to each vegetable type in the vegetable list database to obtain a vegetable type feature comparison set R'_k(r′_k1,r′_k2,...,r′_kf,...,r′_kg) According to the vegetable type feature comparison set, the matching degree between the collected image and each vegetable type is counted, the vegetable type with the maximum matching degree is screened, and the vegetable type with the maximum matching degree is sent to the optimization processing module;

the vegetable list database is used for storing vegetable type characteristics corresponding to various vegetable types, storing vegetable color degrees corresponding to various vegetable types under different quality levels, vegetable type freshness coefficients corresponding to various quality levels, and average temperature time period sets, average humidity time period sets and bacteria type time period sets in a refrigerating layer of the refrigerator, wherein all the vegetable type characteristics under the same vegetable type form a vegetable type characteristic set R_k(r_k1,r_k2,...,r_kf,...,r_kg)，r_kf is the f-th characteristic corresponding to the k-th vegetable type, and the vegetable quality is divided according to the vegetable color under the same vegetable type, and is q_k1,q_k2,...,q_kj,...,q_kn，q_kj represents a vegetable freshness coefficient L q corresponding to the quality grade corresponding to the kth vegetable type and each quality grade of the same vegetable type_k1,Lq_k2,...,Lq_kj,...,Lq_kn，Lq_k1＜Lq_k2＜...＜Lq_kj＜...＜Lq_kn，Lq_kn is less than 1, and the quality grade of each vegetable corresponds to the color and luster degree of the vegetable corresponding to the vegetable type;

the optimization processing module is used for receiving the comprehensive quality evolution coefficient of the expected environment in the current environment in the refrigerator sent by the quality preview construction module and receiving the vegetable types in the collected image, receiving the filtered vegetable image of the vegetable type in each time period sent by the vegetable image acquisition module, comparing the vegetable color corresponding to the vegetable type with the vegetable color corresponding to each quality grade of the vegetable type in the vegetable list database by the optimization processing module, screening out the quality grade corresponding to the vegetable type, according to quality grades corresponding to the vegetable types, vegetable freshness coefficients corresponding to the vegetable types are further screened out to form a vegetable type freshness coefficient set in each time period, and an optimization processing module processes the vegetable type freshness coefficients in each time period to obtain a freshness variation set;

in addition, the optimization processing module extracts the difference between the average temperature and the average humidity of the time period and the previous time period in the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, the difference between the average humidity and the content of each bacteria species, analyzes the influence coefficient of the vegetable quality change rate of the refrigerator under the current environmental parameters, judges whether the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, and simultaneously receives the personnel information sent by the personnel detection module, if the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, the optimization processing module sends the vegetable type with the influence coefficient of the vegetable quality change rate larger than the set influence coefficient threshold of the vegetable quality change rate and the influence coefficient of the vegetable quality change rate to the early warning display terminal, if the influence coefficient of the vegetable quality change rate under the current refrigerator environmental parameters is smaller than the set influence coefficient threshold of the vegetable quality change rate, the optimization processing module counts the estimated storage time of the vegetable freshness coefficient of the vegetable type corresponding to the influence coefficient threshold of the vegetable quality change rate reached from the current vegetable freshness coefficient according to the influence coefficient of the current vegetable quality change rate, and sends the influence coefficient of the vegetable quality change rate and the estimated storage time to the early warning display terminal;

the personnel detection module is arranged on the outer side of the refrigerator door, is a pyroelectric infrared sensor and is used for detecting whether a person is in front of the refrigerator, and once the person is detected in the detection area, the personnel detection module sends personnel information to the optimization processing module;

and the early warning display terminal is used for receiving and displaying the vegetable type of which the influence coefficient of the vegetable quality change rate sent by the optimization processing module is greater than the set influence coefficient threshold of the vegetable quality change rate, the influence coefficient of the vegetable quality change rate corresponding to the vegetable type and the predicted storage time of the vegetable type.

2. The intelligent management system is deposited to vegetables based on big data of claim 1, characterized in that: the calculation formula of the comprehensive quality evolution coefficient of the overdue environment in the current refrigerator environment isw_{Is provided with}Expressed as a set temperature value, s, for the cold storage layer of the refrigerator_{Is provided with}Expressed as a set humidity value, x, for the cold storage layer of the refrigerator_{p threshold}Is expressed as a bacteria content threshold value corresponding to the p-th bacteria species in a set refrigerator refrigerating layer, w ' i is expressed as the difference value between the average temperature in the ith time period and the average temperature in the (i-1) th time period, s ' i is expressed as the difference value between the average humidity in the ith time period and the average humidity in the (i-1) th time period, and x '_pi is the difference between the content of the p-th bacterial species in the i-th time period and the content of the p-th bacterial species in the i-1 th time period, α and β are respectively the influence factors corresponding to temperature and humidity, and the specific values are respectively 0.625, 0.471 and lambda_pExpressed as the influence factor of the p-th bacterial species on the environmental quality, 0 < lambda_p＜1。

3. The intelligent management system is deposited to vegetables based on big data of claim 2, characterized in that: the matching degree calculation formula of the vegetable types isr′_kf is the comparison between the f-th feature corresponding to the k-th vegetable type and the feature in the vegetable image, and if the f-th feature corresponding to the k-th vegetable type is included in the collected vegetable image, r'_kf is equal to 1, otherwise, r'_kf is equal to 0.

4. The intelligent management system is deposited to vegetables based on big data of claim 2, characterized in that: influence coefficient of vegetable quality change rate under current environmental parameters of refrigeratorr＜m，Ψ_kThe influence coefficient is expressed as the vegetable quality change rate corresponding to the kth vegetable type, mu is expressed as the expected environment comprehensive quality evolution coefficient under the current environment, u < 1, w ' r is expressed as the difference value between the average temperature in the r-th storage time period and the average temperature in the r-1 th time period, w ' r is expressed as the difference value between the average humidity in the r-th storage time period and the average humidity in the r-1 th time period, and x '_pr is represented as the difference between the content of the p-th bacterial species in the r-th time period and the content of the p-th bacterial species in the r-1 th time period, q'_ki is a difference value between a vegetable freshness coefficient corresponding to the vegetable type in the ith time period and a vegetable freshness coefficient corresponding to the vegetable type in the (i + 1) th time period, dist (w 'r, s' r) is a Euclidean distance between w 'r and w' r, and the higher the influence coefficient of the vegetable quality change rate is, the higher the vegetable deterioration rate is.

5. The intelligent management system is deposited to vegetables based on big data of claim 4, characterized in that: the calculation formula of the predicted storage time of the vegetables isT is the predicted storage time of the kth vegetable type under the influence coefficient of the current vegetable quality change rate, Q_krExpressed as the kth vegetable at the r time periodVegetable freshness coefficient, Q, corresponding to the type of vegetable_{k threshold}The freshness coefficient of the vegetable expressed as the k-th vegetable type reaches the threshold value of the influence coefficient of the vegetable quality change rate, i.e. Q_{k threshold}＝q_k1，Ψ_kAnd the influence coefficient is expressed as the change rate of the vegetable quality corresponding to the kth vegetable type, and t is expressed as the interval fixed time period.

Technical Field

The invention belongs to the technical field of vegetable management, and relates to a vegetable storage intelligent management system based on big data.

Background

A refrigerator is an appliance that maintains a low temperature, prevents food or other articles from being spoiled by maintaining the food or other articles in a constant low-temperature cold state, but the refrigerator only slows down the food decay time in the refrigerator, does not permanently stop the food decay, and the chemical reaction is slowed down at low temperature, but cannot prevent the process of food and certain substances in the air from being rotten due to chemical reaction caused by low temperature from being slowed down, meanwhile, the low temperature also reduces the bacterial reproduction speed in the refrigerator, but the problem that the vegetables are not degraded due to long storage time cannot be avoided, because the rhythm of life of people is fast at present, a lot of nitrate is generated in vegetables stored in a refrigerator along with the storage time, although the nitrate is not toxic, after the vegetables are stored for a period of time, nitrate is reduced to toxic nitrite due to the action of enzymes and bacteria, and the possibility of gastric cancer is increased by the in vivo binding of nitrite to proteinaceous substances.

At present, the refrigerating layer of the refrigerator controls the storage environment of food in the refrigerator by controlling the temperature of the refrigerating layer of the refrigerator, but with the long storage time, the temperature, the humidity and the contents of various bacteria in the cold storage layer of the refrigerator can not be known to judge the influence of the storage environment of the cold storage layer of the refrigerator on the vegetable quality, thereby causing the vegetables stored in the refrigerator to be not eaten up, the vegetables to be deteriorated or rotten and the quality analysis of the vegetables in the refrigerator to be impossible, further prompting the user to remove the deteriorated or rotten vegetables, and also being unable to count the predicted time of the deterioration of the vegetables stored in the refrigerator, so as to prompt the user to eat the vegetables in time and avoid the problem of vegetable waste, in order to solve the problems, an intelligent vegetable storage management system based on big data is designed.

Disclosure of Invention

The invention aims to provide a vegetable storage intelligent management system based on big data, which solves the problems in the prior art.

The purpose of the invention can be realized by the following technical scheme:

a vegetable storage intelligent management system based on big data comprises a box body parameter acquisition module, a parameter preprocessing module, a vegetable image acquisition module, a quality preview construction module, a vegetable list database, an optimization processing module, a personnel detection module and an early warning display terminal;

the device comprises a box body parameter acquisition module, a quality preview construction module and an optimization processing module, wherein the parameter preprocessing module is respectively connected with the box body parameter acquisition module, the quality preview construction module and a vegetable list database;

the box body parameter acquisition module is arranged on a refrigerating layer of the refrigerator and used for detecting the temperature and the humidity in the refrigerating layer of the refrigerator and the content of each bacterial species and sending the detected temperature and the detected humidity in the refrigerating layer and the content of each bacterial species to the parameter preprocessing module;

the device comprises a parameter preprocessing module, a vegetable list database and a quality preview construction module, wherein the parameter preprocessing module is connected with a box parameter acquisition module, is used for receiving the temperature and humidity of a refrigerating layer of a refrigerator and the content of each bacterial type sent by the box parameter acquisition module, counting the average temperature, the average humidity and the content of each bacterial type within a fixed time interval t to obtain an average temperature time period set, an average humidity time period set and a bacterial type time period set, and respectively sending the average temperature time period set, the average humidity time period set and the bacterial type time period set to the vegetable list database and the quality preview construction module;

the vegetable image acquisition module is used for acquiring images of a refrigerator cold storage area, performing high-pass filtering processing on the acquired images, and respectively sending the filtered vegetable images to the quality preview construction module and the optimization processing module;

the quality pre-modeling construction module is used for receiving the average temperature time period set, the average humidity time period set and the bacteria species time period set in the refrigerating chamber of the refrigerator sent by the parameter preprocessing module, respectively comparing the average temperature in the next time period with the average temperature in the previous time period, comparing the average humidity in the next time period with the average humidity in the previous time period, comparing the content corresponding to each bacteria species in the next time period with the content corresponding to the bacteria species in the previous time period, respectively obtaining the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, and counting the comprehensive quality evolution coefficient of the expected environment in the current environment according to the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, the quality preview construction module sends the comprehensive quality evolution coefficient of the expected environment under the current environment, the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set in the refrigerator to the optimization processing module;

meanwhile, the quality preview construction module receives the filtered vegetable image sent by the vegetable image acquisition module, extracts the features of the vegetable image, compares the extracted features with a vegetable type feature set corresponding to each vegetable type in a vegetable list database to obtain a vegetable type feature comparison set R'_k(r′_k1,r′_k2,...,r′_kf,...,r′_kg) According to the vegetable type feature comparison set, the matching degree between the collected image and each vegetable type is counted, the vegetable type with the maximum matching degree is screened, and the vegetable type with the maximum matching degree is sent to the optimization processing module;

the vegetable list database is used for storing vegetable type characteristics corresponding to various vegetable types, storing vegetable color degrees corresponding to various vegetable types under different quality levels, vegetable type freshness coefficients corresponding to various quality levels, and average temperature time period sets, average humidity time period sets and bacteria type time period sets in a refrigerating layer of the refrigerator, wherein all the vegetable type characteristics under the same vegetable type form a vegetable type characteristic set R_k(r_k1,r_k2,...,r_kf,...,r_kg)，r_kf is the f-th characteristic corresponding to the k-th vegetable type, and the vegetable quality is divided according to the vegetable color under the same vegetable type, and is q_k1,q_k2,...,q_kj,...,q_kn，q_kj represents a vegetable freshness coefficient L q corresponding to the quality grade corresponding to the kth vegetable type and each quality grade of the same vegetable type_k1,Lq_k2,...,Lq_kj,...,Lq_kn，Lq_k1＜Lq_k2＜...＜Lq_kj＜...＜Lq_kn，Lq_kn is less than 1, and the quality grade of each vegetable corresponds to the color and luster degree of the vegetable corresponding to the vegetable type;

the optimization processing module is used for receiving the comprehensive quality evolution coefficient of the expected environment in the current environment in the refrigerator sent by the quality preview construction module and receiving the vegetable types in the collected image, receiving the filtered vegetable image of the vegetable type in each time period sent by the vegetable image acquisition module, comparing the vegetable color corresponding to the vegetable type with the vegetable color corresponding to each quality grade of the vegetable type in the vegetable list database by the optimization processing module, screening out the quality grade corresponding to the vegetable type, according to quality grades corresponding to the vegetable types, vegetable freshness coefficients corresponding to the vegetable types are further screened out to form a vegetable type freshness coefficient set in each time period, and an optimization processing module processes the vegetable type freshness coefficients in each time period to obtain a freshness variation set;

in addition, the optimization processing module extracts the difference between the average temperature and the average humidity of the time period and the previous time period in the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, the difference between the average humidity and the content of each bacteria species, analyzes the influence coefficient of the vegetable quality change rate of the refrigerator under the current environmental parameters, judges whether the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, and simultaneously receives the personnel information sent by the personnel detection module, if the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, the optimization processing module sends the vegetable type with the influence coefficient of the vegetable quality change rate larger than the set influence coefficient threshold of the vegetable quality change rate and the influence coefficient of the vegetable quality change rate to the early warning display terminal, if the influence coefficient of the vegetable quality change rate under the current refrigerator environmental parameters is smaller than the set influence coefficient threshold of the vegetable quality change rate, the optimization processing module counts the estimated storage time of the vegetable freshness coefficient of the vegetable type corresponding to the influence coefficient threshold of the vegetable quality change rate reached from the current vegetable freshness coefficient according to the influence coefficient of the current vegetable quality change rate, and sends the influence coefficient of the vegetable quality change rate and the estimated storage time to the early warning display terminal;

the personnel detection module is arranged on the outer side of the refrigerator door, is a pyroelectric infrared sensor and is used for detecting whether a person is in front of the refrigerator, and once the person is detected in the detection area, the personnel detection module sends personnel information to the optimization processing module;

and the early warning display terminal is used for receiving and displaying the vegetable type of which the influence coefficient of the vegetable quality change rate sent by the optimization processing module is greater than the set influence coefficient threshold of the vegetable quality change rate, the influence coefficient of the vegetable quality change rate corresponding to the vegetable type and the predicted storage time of the vegetable type.

Further, the calculation formula of the comprehensive quality evolution coefficient of the overdue environment in the current refrigerator environment isw_{Is provided with}Expressed as a set temperature value, s, for the cold storage layer of the refrigerator_{Is provided with}Expressed as a set humidity value, x, for the cold storage layer of the refrigerator_{p threshold}Is expressed as a bacteria content threshold value corresponding to the p-th bacteria species in a set refrigerator refrigerating layer, w ' i is expressed as the difference value between the average temperature in the ith time period and the average temperature in the (i-1) th time period, s ' i is expressed as the difference value between the average humidity in the ith time period and the average humidity in the (i-1) th time period, and x '_pi is the difference between the content of the p-th bacterial species in the i-th time period and the content of the p-th bacterial species in the i-1 th time period, α and β are respectively the influence factors corresponding to temperature and humidity, and the specific values are respectively 0.625, 0.471 and lambda_pExpressed as the influence factor of the p-th bacterial species on the environmental quality, 0 < lambda_p＜1。

Further, the matching degree calculation formula of the vegetable types isr′_kf is the comparison between the f-th feature corresponding to the k-th vegetable type and the feature in the vegetable image, and if the f-th feature corresponding to the k-th vegetable type is included in the collected vegetable image, r'_kf is equal to 1, otherwise, r'_kf is equal to 0.

Further, the influence coefficient of the vegetable quality change rate under the current environmental parameters of the refrigeratorr＜m，Ψ_kThe influence coefficient is expressed as the vegetable quality change rate corresponding to the kth vegetable type, mu is expressed as the expected environment comprehensive quality evolution coefficient under the current environment, u < 1, w ' r is expressed as the difference value between the average temperature in the r-th storage time period and the average temperature in the r-1 th time period, w ' r is expressed as the difference value between the average humidity in the r-th storage time period and the average humidity in the r-1 th time period, and x '_pr is represented as the difference between the content of the p-th bacterial species in the r-th time period and the content of the p-th bacterial species in the r-1 th time period, q'_ki is a difference value between a vegetable freshness coefficient corresponding to the vegetable type in the ith time period and a vegetable freshness coefficient corresponding to the vegetable type in the (i + 1) th time period, dist (w 'r, s' r) is a Euclidean distance between w 'r and w' r, and the higher the influence coefficient of the vegetable quality change rate is, the higher the vegetable deterioration rate is.

Further, the calculation formula of the predicted storage time of the vegetables isT is the predicted storage time of the kth vegetable type under the influence coefficient of the current vegetable quality change rate, Q_krExpressed as the freshness coefficient of the vegetable, Q, corresponding to the kth vegetable type at the r-th time period_{k threshold}Is expressed as the k-thThe vegetable freshness coefficient, namely Q, corresponding to the influence coefficient threshold value when the vegetable type reaches the vegetable quality change rate_{k threshold}＝q_k1，Ψ_kAnd the influence coefficient is expressed as the change rate of the vegetable quality corresponding to the kth vegetable type, and t is expressed as the interval fixed time period.

The invention has the beneficial effects that:

according to the vegetable storage intelligent management system based on the big data, the temperature and the humidity in the refrigerating layer of the refrigerator and the content of each bacterial type are collected, the collected environmental parameters are analyzed and processed through the quality preview construction module, the comprehensive quality evolution coefficient of the expected environment corresponding to the temperature and the humidity in the refrigerator and the content change of each bacterial type in the vegetable storage time of the refrigerator is counted, the influence degree of the current storage environment of the refrigerator on vegetable fresh keeping is visually displayed through the expected environment quality evolution coefficient under the current environmental parameters, namely, the larger the expected environment quality evolution coefficient in the refrigerator is, the more easily vegetables in the refrigerator deteriorate.

The invention collects the vegetable image in the refrigerator through the vegetable image collecting module and extracts the vegetable image characteristic through the quality preview construction module to identify the vegetable type in the vegetable image, and comparing the vegetable color in the collected image with the vegetable color corresponding to each quality grade under the vegetable type through an optimization processing module to determine the quality grade, so as to extract the freshness coefficient of the vegetables corresponding to the quality grade and process the freshness coefficient of the vegetables in each time period, and the influence coefficient of the vegetable quality change rate is counted by combining the comprehensive quality evolution coefficient of the expected environment under the current environment and the variable quantity of the environmental parameter, the influence coefficient through vegetables quality rate of change can demonstrate the vegetables quality directly perceivedly, judges whether this vegetables kind has already deteriorated to remind the user, in time abandon the vegetables that have deteriorated, guarantee to drink personnel's health.

Simultaneously, the estimated storage time of the vegetable freshness coefficient corresponding to the influence coefficient threshold value that reaches the vegetable quality change rate from the current vegetable freshness coefficient of this vegetable kind is counted according to the influence coefficient of current vegetable quality change rate through the optimization processing module, and carry out early warning suggestion with this vegetable estimated storage time, be convenient for remind the user to eat to the vegetables in the refrigerator as early as possible, avoid the user to forget the vegetables in the refrigerator cold-stored layer, and lead to vegetables rotten, can't eat, the cost of purchasing vegetables is wasted greatly, and simultaneously, pollute the environment of depositing of other vegetables in the refrigerator, cause the environment of depositing and can't satisfy the requirement of depositing of vegetables.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic diagram of a vegetable storage intelligent management system based on big data according to the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, the intelligent vegetable storage management system based on big data comprises a box parameter acquisition module, a parameter preprocessing module, a vegetable image acquisition module, a quality preview construction module, a vegetable list database, an optimization processing module, a personnel detection module and an early warning display terminal.

The parameter preprocessing module is respectively connected with the box parameter acquisition module, the quality preview construction module and the vegetable list database, the quality preview construction module is respectively connected with the vegetable image acquisition module, the vegetable list database and the optimization processing module, and the optimization processing module is respectively connected with the vegetable image acquisition module, the vegetable list database, the personnel detection module and the early warning display terminal.

The box body parameter acquisition module is arranged on a refrigerating layer of the refrigerator and used for detecting the temperature and the humidity in the refrigerating layer of the refrigerator and the content of each bacterial species and sending the detected temperature and the detected humidity in the refrigerating layer and the content of each bacterial species to the parameter preprocessing module;

wherein, box parameter acquisition module includes temperature detecting element, humidity detecting element and bacterium detecting element, and temperature detecting element is temperature sensor for detect the temperature on the cold-stored layer of refrigerator, and humidity detecting element is humidity sensor for detect the humidity on the cold-stored layer of refrigerator, and bacterium detecting element is the bacterium detector for detect the content that each bacterium kind corresponds in the cold-stored layer of refrigerator.

The parameter preprocessing module is connected with the box parameter acquisition module, and is used for receiving the temperature, the humidity and the content of each bacterial species of the refrigerator cold storage layer sent by the box parameter acquisition module, dividing the acquired temperature, humidity and the content of each bacterial species in an interval fixed time period t (t is one of 4h, 6h or 8 h), and counting the average temperature, the average humidity and the content of each bacterial species in the interval fixed time period t to obtain an average temperature time period set W (W1, W2,.., wi.., wm), an average humidity time period set S (S1, S2.,. si.,. sm., sm) and a bacterial species time period set X_p(x_p1,x_p2,...,x_pi,...,x_pm), wi is the average temperature of the refrigerator in the ith time period, si is the average humidity of the refrigerator in the ith time period, x_pi represents the content corresponding to the pth bacterial species in the refrigerator in the ith time period, p represents the number of the bacterial species, p is 1,2,3,4,5,6, and p is 1,2,3,4,5,6 can represent salmonella, shigella, listeria, yersinia, escherichia coli and mold respectively, and the parameter preprocessing module sends the average temperature time period set, the average humidity time period set and the bacterial species time period set to the vegetable list database and the quality preview construction module respectively.

The vegetable image acquisition module is the camera, installs at the refrigerator door inboard, and vegetable image acquisition module is used for carrying out image acquisition to the refrigerator cold-storage district, and adopt high pass filtering to gather the image and handle, improve the definition degree of image, send the vegetable image after filtering processing respectively to quality preview construction module and optimization processing module, and wherein, vegetable is carrying out image acquisition's in-process, and illumination supply degree is the same when keeping gathering, reduces because of the color and luster influence of external illumination intensity change to gathering the image.

The quality pre-modeling construction module is used for receiving the average temperature time period set, the average humidity time period set and the bacteria type time period set in the refrigerating chamber of the refrigerator sent by the parameter preprocessing module, respectively comparing the average temperature in the next time period with the average temperature in the previous time period, comparing the average humidity in the next time period with the average humidity in the previous time period, comparing the content corresponding to each bacteria type in the next time period with the content corresponding to the bacteria type in the previous time period, and respectively obtaining an average temperature comparison time period set W ' (W ' 1, W ' 2, i, W ' i, W ' (m-1)), a set of average humidity versus time periods S '(S' 1, S '2.., S' i.., S '(m-1)) and a set of bacteria species versus time periods X'._p(x′_p1,x′_p2,...,x′_pi,...,x′_p(m-1)), w ' i is the difference between the average temperature in the ith time period and the average temperature in the (i-1) th time period, s ' i is the difference between the average humidity in the ith time period and the average humidity in the (i-1) th time period, and x '_pi is expressed as the difference value between the content of the p-th bacterial species in the ith time period and the content of the p-th bacterial species in the (i-1) th time period, and the expected environment comprehensive quality evolution coefficient under the current environment is counted according to the average temperature comparison time period set, the average humidity comparison time period set and the bacterial species comparison time period set, wherein the calculation formula isw_{Is provided with}Expressed as a set temperature value, s, for the cold storage layer of the refrigerator_{Is provided with}Indicating humidity set for the cold storage level of the refrigeratorDegree value, x_{p threshold}Is expressed as a bacteria content threshold value corresponding to the p-th bacteria species in a set refrigerator refrigerating layer, w ' i is expressed as the difference value between the average temperature in the ith time period and the average temperature in the (i-1) th time period, s ' i is expressed as the difference value between the average humidity in the ith time period and the average humidity in the (i-1) th time period, and x '_pi is the difference between the content of the p-th bacterial species in the i-th time period and the content of the p-th bacterial species in the i-1 th time period, α and β are respectively the influence factors corresponding to temperature and humidity, and the specific values are respectively 0.625, 0.471 and lambda_pExpressed as the influence factor of the p-th bacterial species on the environmental quality, 0 < lambda_pIf the expected environment quality evolution coefficient of the current environment parameter is larger, the influence degree on the storage and the preservation of the vegetables in the refrigerator is larger, the stored vegetables are easier to deteriorate, and the quality preview construction module sends the expected environment comprehensive quality evolution coefficient in the current environment, and the average temperature comparison time period set, the average humidity comparison time period set and the bacteria type comparison time period set in the refrigerator to the optimization processing module;

meanwhile, the quality preview construction module receives the filtered vegetable image sent by the vegetable image acquisition module, extracts the features of the vegetable image, compares the extracted features with a vegetable type feature set corresponding to each vegetable type in a vegetable list database to obtain a vegetable type feature comparison set R'_k(r′_k1,r′_k2,...,r′_kf,...,r′_kg) And according to the vegetable type feature comparison set, counting the matching degree between the collected image and each vegetable type, screening the vegetable type with the maximum matching degree, and sending the vegetable type to the optimization processing module.

Wherein, the matching degree calculation formula of the vegetable species isr′_kf is the comparison between the f-th feature corresponding to the k-th vegetable type and the feature in the vegetable image, and if the f-th feature corresponding to the k-th vegetable type is included in the collected vegetable image, r'_kf is equal to 1, otherwise, r'_kf is equal to 0.

The vegetable list database is used for storing vegetable type characteristics corresponding to various vegetable types, storing vegetable color degrees corresponding to various vegetable types under different quality levels, vegetable type freshness coefficients corresponding to various quality levels, and average temperature time period sets, average humidity time period sets and bacteria type time period sets in the refrigerating layer of the refrigerator, wherein all the vegetable type characteristics under the same vegetable type form a vegetable type characteristic set R_k(r_k1,r_k2,...,r_kf,...,r_kg)，r_kf is the f-th feature corresponding to the k-th vegetable type, g is the number of features, and the vegetable quality is divided according to the vegetable color under the same vegetable type, and q is respectively_k1,q_k2,...,q_kj,...,q_kn，q_kj represents a vegetable freshness coefficient L q corresponding to the quality grade corresponding to the kth vegetable type and each quality grade of the same vegetable type_k1,Lq_k2,...,Lq_kj,...,Lq_kn，Lq_k1＜Lq_k2＜...＜Lq_kj＜...＜Lq_kn，Lq_kn is less than 1, and the quality grade of each vegetable corresponds to the color and luster degree of the vegetable corresponding to the vegetable type.

The optimization processing module is used for receiving the expected environment comprehensive quality evolution coefficient in the current environment in the refrigerator sent by the quality preview construction module and receiving the vegetable type in the collected image, receiving the vegetable image of the vegetable type in each time period after filtering processing sent by the vegetable image collection module, comparing the vegetable color corresponding to the vegetable type with the vegetable color corresponding to each quality grade in the vegetable list database, screening the quality grade corresponding to the vegetable type, further screening the vegetable freshness coefficient corresponding to the vegetable type according to the quality grade corresponding to the vegetable type, and forming a vegetable type freshness coefficient set Q in each time period_k(q_k1,q_k2,...,q_ki,...,q_km)，q_ki is expressed as the ith time periodCollecting a vegetable freshness coefficient, q, corresponding to a vegetable type in an image_ki∈Lq_k1,Lq_k2,...,Lq_kj,...,Lq_kn, i ═ 1, 2.. times, m, the optimization processing module processes the freshness coefficient of the vegetable type in each time period to obtain a freshness change amount set Q'_k(q′_k1,q′_k2,...,q′_ki,...,q′_k(m-1))，q′_ki is expressed as a difference value between a vegetable freshness coefficient corresponding to the vegetable kind at the i-th time period and a vegetable freshness coefficient corresponding to the vegetable kind at the i + 1-th time period.

In addition, the optimization processing module extracts the difference between the average temperature and the average humidity of the time period and the previous time period in the average temperature comparison time period set, the average humidity comparison time period set and the bacteria species comparison time period set, the difference between the average humidity and the content of each bacteria species, analyzes the influence coefficient of the vegetable quality change rate of the refrigerator under the current environmental parameters, judges whether the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, and simultaneously receives the personnel information sent by the personnel detection module, if the influence coefficient of the vegetable quality change rate under the current environmental parameters is greater than the set influence coefficient threshold of the vegetable quality change rate, and if the influence coefficient of the vegetable quality change rate under the current refrigerator environmental parameters is smaller than the influence coefficient threshold of the set vegetable quality change rate, the optimization processing module counts the estimated storage time of the vegetable freshness coefficient of the vegetable type corresponding to the influence coefficient threshold of the vegetable quality change rate reached from the current vegetable freshness coefficient according to the influence coefficient of the current vegetable quality change rate, and sends the influence coefficient of the vegetable quality change rate and the estimated storage time to the early warning display terminal.

Wherein, the influence coefficient of the vegetable quality change rate under the current environmental parameters of the refrigeratorr＜m，Ψ_kThe influence coefficient is expressed as the vegetable quality change rate corresponding to the kth vegetable type, mu is expressed as the expected environment comprehensive quality evolution coefficient under the current environment, u < 1, w ' r is expressed as the difference value between the average temperature in the r-th storage time period and the average temperature in the r-1 th time period, w ' r is expressed as the difference value between the average humidity in the r-th storage time period and the average humidity in the r-1 th time period, and x '_pr is represented as the difference between the content of the p-th bacterial species in the r-th time period and the content of the p-th bacterial species in the r-1 th time period, q'_ki is a difference value between a vegetable freshness coefficient corresponding to the vegetable type in the ith time period and a vegetable freshness coefficient corresponding to the vegetable type in the (i + 1) th time period, dist (w 'r, s' r) is a Euclidean distance between w 'r and w' r, and the higher the influence coefficient of the vegetable quality change rate is, the higher the vegetable deterioration rate is.

Wherein the calculation formula of the predicted storage time of the vegetables isT is the predicted storage time of the kth vegetable type under the influence coefficient of the current vegetable quality change rate, Q_krExpressed as the freshness coefficient of the vegetable, Q, corresponding to the kth vegetable type at the r-th time period_{k threshold}The freshness coefficient of the vegetable expressed as the k-th vegetable type reaches the threshold value of the influence coefficient of the vegetable quality change rate, i.e. Q_{k threshold}＝q_k1，Ψ_kAnd the influence coefficient is expressed as the change rate of the vegetable quality corresponding to the kth vegetable type, and t is expressed as the interval fixed time period.

Personnel detection module installs in the refrigerator door outside, is pyroelectric infrared sensor for whether detect the refrigerator the place ahead someone, in case detect in the detection area someone, personnel detection module sends personnel information to optimizing process module.

The early warning display terminal is used for receiving the vegetable type of which the influence coefficient of the vegetable quality change rate sent by the optimization processing module is larger than the set influence coefficient threshold of the vegetable quality change rate, the influence coefficient of the vegetable quality change rate corresponding to the vegetable type and the predicted storage time of the vegetable type, and displaying the vegetable type.

The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.