A common group food safety risk alarm and early warning system for college canteens

Abstract

The present invention discloses a warning and alarm system and method for common group food safety risks in college canteens, belonging to the field of public safety, including a hardware system and a software system; the hardware system includes video recording equipment, temperature and humidity measurement equipment, pesticide residue measurement equipment, bacterial residue measurement equipment, a server, and a short message communication device installed on the peripheral port of the server; the software system includes an intelligent device communication interface module and a mobile phone short message alarm interface module, which can analyze and give early warnings and alarms for excessive pesticide residues in fruits and vegetables, excessive bacterial residues, excessive temperature and humidity in important places, and other common risk factors. Based on big data analysis, the present invention realizes the goal that the system can give real-time warnings when there are precursors of the above-mentioned food safety risks; the test results verify the correctness of the system functions; the present invention significantly improves the efficiency of food risk warning and alarm, is convenient for operation, maintenance and management, and can effectively improve the efficiency of food safety supervision.

Description

Technical Field

[0001] The present invention belongs to the field of public safety, and particularly relates to an alarm and early warning system and method for common group food safety risks in college canteens based on modern information technology. Background Art

[0002] Food safety in college canteens is the lifeline of college canteens. Dining safety is related to the health of all teachers and students in the school and is a hot issue concerned by all teachers and students in the school and social consumers.

[0003] Using advanced modern information technologies such as the Internet of Things and big data to develop an alarm and early warning system for common group food safety risks in college canteens is of great significance for ensuring the health and safety of students and maintaining the harmony and stability of society and schools. Therefore, it is necessary to use advanced modern information technologies such as the Internet of Things and big data to design and develop a new generation of alarm and early warning system for common group food safety risks in college canteens that focuses on the prevention of safety risks. Summary of the Invention

[0004] In view of the above technical problems existing in the prior art, the present invention proposes an alarm and early warning system for common group food safety risks in college canteens, which is reasonably designed, overcomes the deficiencies of the prior art, and has good effects.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An alarm and early warning system for common group food safety risks in college canteens, including a hardware system and a software system;

[0007] The hardware system includes video recording equipment, temperature and humidity measurement equipment, pesticide residue measurement equipment, bacterial residue measurement equipment, a server, and a short message communication device installed at the peripheral port of the server;

[0008] The software system includes an intelligent device communication interface module, a mobile phone short message alarm interface module, a system database, and a data interface. The software system can analyze and give early warnings for excessive pesticide residues in fruits and vegetables, excessive bacterial residues, excessive temperature and humidity in important places, and other common risk factors;

[0009] The video recording equipment is configured to record images of important places including incoming goods, processing, storage, sales, and sample retention;

[0010] The temperature and humidity measurement equipment is configured to collect temperature and humidity data of important places including processing, storage, and sales, and automatically transmit the collected data to the server;

[0011] A pesticide residue measurement device, configured to implement sampling tests including fruits and vegetables, and automatically transmit the collected data to a server;

[0012] A bacteria residue measurement device, configured to implement bacteria sampling tests including cold dish processing areas and tableware, and automatically transmit the collected data to a server;

[0013] A server, configured to receive data collected by a temperature and humidity measurement device, a pesticide residue measurement device, and a bacteria residue measurement device;

[0014] A short message communication device, configured to timely send relevant warning and alarm messages to an administrator;

[0015] A system database, configured to implement storage, retrieval, and operation of massive data;

[0016] A data interface, configured to implement data interaction between a software system and video recording devices, temperature and humidity measurement devices, pesticide residue measurement devices, bacteria residue measurement devices, and short message communication devices;

[0017] A data interface, including an intelligent device communication interface module and a mobile phone short message alarm interface;

[0018] An intelligent device communication interface, configured to implement data interaction between video recording devices, temperature and humidity measurement devices, pesticide residue measurement devices, bacteria residue measurement devices, and a software system;

[0019] A mobile phone short message alarm interface, configured to implement data interaction between a short message communication device and a software system;

[0020] When the intelligent device communication interface detects that the received data is abnormal, it automatically sends a mobile phone short message alarm to the administrator through the mobile phone short message alarm interface.

[0021] In addition, the present invention also mentions a warning and alarm method for common group food safety risks in college cafeterias. This method uses the warning and alarm system for common group food safety risks in college cafeterias as described above. For the prediction of common food safety risk precursors such as excessive temperature and humidity in important places, excessive pesticide residues in fruits and vegetables, excessive bacteria in cold dishes or cooked foods, and approaching expiration of inventory materials, big data analysis technology based on time series analysis is used to establish prediction models for temperature and humidity data, pesticide residue amounts, bacteria residue amounts, and material consumption amounts; specifically including the following steps:

[0022] Step 1: In terms of predicting temperature and humidity data in important places, a weighted prediction model is established, which includes the influence of historical data of previous years, recent actual observation data, and recent weather forecast data. The historical temperature and humidity measurement data of previous years are from previous paper records and recent digital measurement data. The recent actual observation data are from the data obtained by temperature and humidity measuring instruments. The recent weather forecast data are from the local forecast data on the Internet. The established weighted prediction model is:

[0023]

[0024] Among them, is the predicted temperature value, K T1 is the weighted coefficient corresponding to the historical temperature measurement data, D T1 is the number of points of the historical temperature measurement data, T 1i is the historical temperature measurement data, K T2 is the weighted coefficient corresponding to the recent temperature measurement data, D T2 is the number of points of the recent temperature measurement data, a i is the coefficient of the temperature autoregressive prediction model, T 2i is the recent temperature measurement data, K T3 is the weighted coefficient corresponding to the recent temperature weather forecast data, T f is the weather forecast data of temperature, is the predicted humidity value, K H1 is the weighted coefficient corresponding to the historical humidity measurement data, D H1 is the number of points of the historical humidity measurement data, H 1i is the historical humidity measurement data, K H2 is the weighted coefficient corresponding to the recent humidity measurement data, D H2 is the number of points of the recent humidity measurement data, b i is the coefficient of the temperature autoregressive prediction model, H 2i is the recent humidity measurement data, K H3 is the weighted coefficient corresponding to the recent humidity weather forecast data, H f is the weather forecast data of humidity;; The coefficients a i and b i are calculated by the Levinson recurrence algorithm commonly used in the field of power spectrum estimation;

[0025] When the predicted temperature or humidity data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm to remind the administrator to take preventive measures in time;

[0026] Step 2: In terms of predicting the pesticide residue amount, a weighted prediction model is established, which includes the influencing factors of historical data of previous years, recent actual measurement data, suppliers, and empirical data in the expert database; the historical pesticide residue measurement data of previous years comes from previous paper records and recent digital measurement data; the recent actual measurement data comes from the data obtained by the pesticide residue detector; the supplier information of fruits and vegetables comes from the data in the material warehousing aspect of the system; the expert experience data comes from the data in the expert database on the Internet; the established weighted prediction model corresponds to the following formula:

[0027]

[0028] Among them, is the predicted value of the pesticide residue amount, K P1 is the weighted coefficient corresponding to the historical pesticide residue measurement data of a certain type of fruits and vegetables, D P1 is the number of data points of the historical pesticide residue measurement data of a certain type of fruits and vegetables, P 1i is the historical pesticide residue measurement data of a certain type of fruits and vegetables, K P2 is the weighted coefficient corresponding to the recent pesticide residue measurement data of a certain type of fruits and vegetables, D P2 is the number of data points of the recent pesticide residue measurement data of a certain type of fruits and vegetables, P 2i is the recent pesticide residue measurement data of a certain type of fruits and vegetables, K P3 is the weighted coefficient corresponding to a certain supplier, D P3 is the number of data points of the historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, P 3i is the historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, K P4 is the weighted coefficient corresponding to the expert experience data, is the average measurement data of the pesticide residue of a certain type of fruits and vegetables in the current season and current region;

[0029] When the predicted pesticide residue amount data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm to remind the administrator to take preventive measures in time;

[0030] Step 3: In terms of predicting the bacterial residue amount, a weighted prediction model is established, which includes the influencing factors of historical data of previous years, recent actual measurement data, indoor temperature data, indoor humidity data, and empirical data in the expert database; the historical data of previous years comes from previous paper records and recent digital measurement data; the recent actual measurement data comes from the data obtained by the bacterial residue detector; the indoor temperature data and indoor humidity data come from the data obtained by the temperature and humidity detector; the expert experience data comes from the data in the expert database on the Internet; the established weighted prediction model corresponds to the following formula:

[0031]

[0032] Among them, is the predicted value of the bacterial residue amount, K B1 is the weighting coefficient corresponding to the historical residue measurement data of a certain type of bacteria, D B1 is the number of points of the historical residue measurement data of a certain type of bacteria, B 1i is the historical residue measurement data of a certain type of bacteria, K B2 is the weighting coefficient corresponding to the recent residue measurement data of a certain type of bacteria, D B2 is the number of points of the recent residue measurement data of a certain type of bacteria, B 2i is the recent residue measurement data of a certain type of bacteria, K B3 is the weighting coefficient corresponding to the indoor temperature, D B3 is the number of points of the indoor temperature measurement data, T i is the indoor temperature measurement data, f1 is a function reflecting the influence of indoor temperature on the bacterial residue amount, K B4 is the weighting coefficient corresponding to the indoor humidity, D B4 is the number of points of the indoor humidity measurement data, H i is the indoor humidity measurement data, f2 is a function reflecting the influence of indoor humidity on the bacterial residue amount, K B5 is the weighting coefficient corresponding to the expert experience data, is the average measurement data of the residue amount of a certain type of bacteria in the current season and current region;

[0033] When the predicted bacterial residue amount data exceeds the set threshold, send a mobile phone text message to the system administrator for alarm to remind the administrator to take preventive measures in time;

[0034] Step 4: In terms of the prediction of material consumption, a weighted prediction model including the influence of historical data of previous years, recent actual consumption data, and estimated data of the number of diners is established; the historical data of previous years comes from previous paper record data and digital ledger data in recent years; the recent actual consumption data comes from the data recorded in the system raw material management module; the estimated data of the number of diners comes from the statistical data of previous years; the established weighted prediction model corresponds to the following formula:

[0035]

[0036] Among them, is the predicted value of the consumption amount of a certain type of material in a future period of time, K C1 is the weighting coefficient corresponding to the consumption amount data of a certain type of material in the same period of previous years, D C1 is the number of data points corresponding to the historical consumption amount of a certain type of material, C 1i is the consumption amount data of a certain type of material in the same period of previous years, K C2is the weighted coefficient corresponding to the recent consumption data of a certain type of material, D C2 is the number of data points corresponding to the recent consumption of a certain type of material, C 2i is the consumption data of a certain type of material in the recent period, K C3 is the weighted coefficient corresponding to the per capita consumption of the number of diners is the number of diners estimated based on the statistical data of previous years within a certain period; the predicted consumption data of a certain type of material within a future period is provided to the material planners in the restaurant for reference, aiming to make the formulation of the material procurement plan more reasonable, thereby reducing the safety risk of food expiration caused by oversupply of materials.

[0037] The beneficial technical effects brought by the present invention:

[0038] (1) Make full use of historical data of previous years, recent actual observation data and recent weather forecast data to predict the temperature and humidity data of important places. When the predicted temperature or humidity data exceeds the set threshold, send a text message to the system administrator for alarm, reminding the administrator to take preventive measures in time.

[0039] (2) Make full use of historical data of previous years, recent actual measurement data, supplier and expert databases to predict the pesticide residue amount. When the predicted pesticide residue amount data exceeds the set threshold, send a text message to the system administrator for alarm, reminding the administrator to take preventive measures in time.

[0040] (3) Make full use of historical data of previous years, recent actual measurement data, indoor temperature data, indoor humidity data and expert databases to predict the bacterial residue amount. When the predicted bacterial residue amount data exceeds the set threshold, send a text message to the system administrator for alarm, reminding the administrator to take preventive measures in time.

[0041] (4) Make full use of historical data of previous years, recent actual consumption data and estimated data of the number of diners to predict the material consumption. The predicted consumption data of a certain type of material within a future period is provided to the material planners in the restaurant for reference, making the formulation of the material procurement plan more reasonable, thereby reducing the safety risk of food expiration caused by oversupply of materials. Description of the Drawings

[0042] Figure 1 is the functional implementation flowchart of the temperature and humidity communication interface.

[0043] Figure 2 is the functional implementation flowchart of the over-limit alarm for pesticide residue detection.

[0044] Figure 3 is the schematic diagram of the panel display of the temperature and humidity measuring device.

[0045] Figure 4 Schematic diagram of the data received by the temperature and humidity communication interface.

[0046] Figure 5 Schematic diagram of the web page for browsing agricultural residue detection information.

[0047] Figure 6 Schematic diagram of the data received by the agricultural residue communication interface.

[0048] Figure 7 Schematic diagram of the mobile phone alarm message for materials approaching expiration.

[0049] Figure 8 Schematic diagram of the mobile phone alarm message for excessive bacterial detection.

[0050] Figure 9 Schematic diagram of the mobile phone warning message for agricultural residue detection. Specific implementation manners

[0051] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners:

[0052] Composition of the warning and alarm system

[0053] The hardware system includes video recording equipment, temperature and humidity measurement equipment, pesticide residue measurement equipment, bacterial residue measurement equipment, a server, and a short message communication device installed on the peripheral port of the server; the software system includes an intelligent device communication interface module and a mobile phone short message alarm interface module, which can analyze and give early warnings and alarms for excessive pesticide residues in fruits and vegetables, excessive bacterial residues, excessive temperature and humidity in important places, and other common risk factors.

[0054] Algorithm principle of the warning and alarm system

[0055] In order to enable the system to give real-time alarms or timely early warnings for common group food safety risks (such as: excessive temperature and humidity in important places, excessive pesticide residues in fruits and vegetables, excessive bacteria in cold dishes or cooked foods, unqualified tableware disinfection, approaching expiration of inventory materials, etc.), the following two key technologies have been broken through.

[0056] On the one hand, the Internet of Things technology is used to achieve the interconnection between intelligent devices such as temperature and humidity measurement, pesticide residue measurement, and bacterial residue measurement and the central server. When the real-time measurement data transmitted to the central server exceeds the standard, real-time alarms will be issued. Therefore, in the system, temperature and humidity measurement, pesticide residue measurement, bacterial residue measurement devices with network communication functions and SMS communication devices are equipped. The temperature and humidity measurement device can regularly upload the temperature and humidity measurement data of important places to the central server according to the set time interval. Staff can set appropriate thresholds according to the different requirements of temperature and humidity ranges in different places. When the collected temperature and humidity data exceeds the threshold range, real-time alarms will be sent to the management personnel through the SMS communication device. Staff can use the pesticide residue measurement and bacterial residue measurement devices to conduct sampling tests on the pesticide residues of fruits and vegetables, and the bacterial residues of cold dish rooms and tableware. After the test is completed, the measurement data will be uploaded to the central server through the buttons on the devices. When the collected measurement data exceeds the previously set threshold range, real-time alarms will be sent to the management personnel through the SMS communication device. Staff cannot intervene in the measurement data, ensuring the objectivity of the measurement data.

[0057] On the other hand, based on big data analysis techniques such as neural networks or time series analysis, through the analysis of a large amount of historical data and the combination of knowledge in the expert database, it is possible to timely detect the precursors of common group food safety risks and thus issue timely warnings. The above warning method belongs to the "pre-event" warning before the food safety risk factors occur, and its significance is even greater. For example: The system can, based on the historical data of pesticide residue measurement and combined with the knowledge in the expert database, give the varieties of fruits and vegetables that are prone to excessive pesticide residues in the current season in the area where the school is located, so as to timely issue risk warnings to raw material purchasers.

[0058] The analysis algorithm for the temperature and humidity exceeding the standard in important places is as follows Figure 1 shown;

[0059] In terms of predicting the temperature and humidity data in important places, a weighted prediction model that includes the influence of three aspects, namely historical data of previous years, recent actual observation data, and recent weather forecast data, is established. The historical temperature and humidity measurement data of previous years comes from previous paper record data and recent digital measurement data. The recent actual observation data comes from the data obtained by the temperature and humidity measuring instrument. The recent weather forecast data comes from the local forecast data on the Internet. The established weighted prediction model is:

[0060]

[0061] Among them, is the predicted temperature value, K T1 is the weighted coefficient corresponding to the historical temperature measurement data, D T1 is the number of points of the historical temperature measurement data, T 1iis historical temperature measurement data, K T2 is the weighting coefficient corresponding to recent temperature measurement data, D T2 is the number of points of recent temperature measurement data, a i is the coefficient of the temperature AR (Auto Regressive) prediction model, T 2i is recent temperature measurement data, K T3 is the weighting coefficient corresponding to recent temperature weather forecast data, T f is the weather forecast data of temperature is the predicted humidity value, K H1 is the weighting coefficient corresponding to historical humidity measurement data, D H1 is the number of points of historical humidity measurement data, H 1i is historical humidity measurement data, K H2 is the weighting coefficient corresponding to recent humidity measurement data, D H2 is the number of points of recent humidity measurement data, b i is the coefficient of the temperature AR prediction model, H 2i is recent humidity measurement data, K H3 is the weighting coefficient corresponding to recent humidity weather forecast data, H f is the weather forecast data of humidity. Coefficients a i and b i The values of can be calculated by the Levinson recurrence algorithm commonly used in the field of power spectrum estimation. When the predicted temperature or humidity data exceeds the set threshold, a text message is sent to the system administrator for alarm to remind the administrator to take preventive measures in time.

[0062] Analysis algorithm for excessive pesticide residues in fruits and vegetables, the process of which is as Figure 2 shown;

[0063] In the prediction of pesticide residues, a weighted prediction model including four aspects of influence: historical data of previous years, recent actual measurement data, suppliers, and empirical data in the expert database is established. The historical measurement data of pesticide residues in previous years comes from previous paper record data and recent digital measurement data. The recent actual measurement data comes from the data obtained by the pesticide residue detector. The supplier information of fruits and vegetables comes from the data in the material warehousing aspect of the system. The expert experience data comes from the data in the expert database on the Internet. The established weighted prediction model corresponds to the following formula:

[0064]

[0065] Among them, is the predicted value of pesticide residue, K P1 is the weighting coefficient corresponding to the historical pesticide residue measurement data of a certain type of fruits and vegetables, D P1The number of points of historical pesticide residue measurement data for a certain type of fruits and vegetables, P 1i The historical pesticide residue measurement data for a certain type of fruits and vegetables, K P2 The weighting coefficient corresponding to the recent pesticide residue measurement data for a certain type of fruits and vegetables, D P2 The number of points of recent pesticide residue measurement data for a certain type of fruits and vegetables, P 2i The recent pesticide residue measurement data for a certain type of fruits and vegetables, K P3 The weighting coefficient corresponding to a certain supplier, D P3 The number of points of historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, P 3i The historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, K P4 The weighting coefficient corresponding to the expert experience data The average measurement data of pesticide residues of a certain type of fruits and vegetables in the current season and current region.

[0066] When the predicted pesticide residue data exceeds the set threshold, send a mobile phone text message to the system administrator for alarm to remind the administrator to take preventive measures in time.

[0067] Food bacteria over-standard analysis algorithm

[0068] In the prediction of bacterial residue amount, a weighted prediction model including five aspects of influence: historical data of previous years, recent actual measurement data, indoor temperature data, indoor humidity data, and experience data in the expert database is established. The historical data of previous years comes from previous paper record data and recent digital measurement data. The recent actual measurement data comes from the data obtained by the bacterial residue measuring instrument. The indoor temperature data and indoor humidity data come from the data obtained by the temperature and humidity measuring instrument. The expert experience data comes from the data in the expert database on the Internet. The established weighted prediction model corresponds to the following formula:

[0069]

[0070] Among them, The predicted value of bacterial residue amount, K B1 The weighting coefficient corresponding to the historical residue measurement data of a certain type of bacteria, D B1 The number of points of the historical residue measurement data of a certain type of bacteria, B 1i The historical residue measurement data of a certain type of bacteria, K B2 The weighting coefficient corresponding to the recent residue measurement data of a certain type of bacteria, D B2 The number of points of the recent residue measurement data of a certain type of bacteria, B 2i The recent residue measurement data of a certain type of bacteria, K B3 The weighting coefficient corresponding to the indoor temperature, D B3 The number of points of the indoor temperature measurement data, T iThe indoor temperature measurement data, f1 is a function reflecting the influence of indoor temperature on the bacterial residue amount, K B4 is the weighting coefficient corresponding to the indoor humidity, D B4 is the number of points of the indoor humidity measurement data, H i is the indoor humidity measurement data, f2 is a function reflecting the influence of indoor humidity on the bacterial residue amount, K B5 is the weighting coefficient corresponding to the expert experience data, is the average measurement data of the residue amount of a certain type of bacteria in the current season and current region.

[0071] When the predicted bacterial residue amount data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm, reminding the administrator to take preventive measures in time.

[0072] Test results

[0073] Figure 3 is a schematic diagram of the display on the panel of the temperature and humidity measurement device, which can intuitively display the temperature and humidity information by the device. Figure 4 is a schematic diagram of the data received by the temperature and humidity communication interface, which can display the received temperature and humidity information on the server desktop. Figure 5 is a schematic diagram of the web page for browsing the agricultural residue detection information. Users can view the agricultural residue detection information through a browser. Figure 6 is a schematic diagram of the data received by the agricultural residue communication interface, which can display the received agricultural residue detection information on the server desktop. Figure 7 is a schematic diagram of the mobile phone alarm text message for approaching expiration of supplies, Figure 8 is a schematic diagram of the mobile phone alarm text message for exceeding the standard in bacterial detection. When the above food safety risk problems are found, a mobile phone text message is automatically sent to the system administrator for alarm. Figure 9 is a schematic diagram of the mobile phone warning text message for agricultural residue detection. When it is predicted that there is a risk of exceeding the standard in the agricultural residue detection amount of certain types of vegetables in the near future, a mobile phone text message is automatically sent to the system administrator for warning.

[0074] This application belongs to the food safety early warning and alarm system of the new generation school cafeteria food safety management information platform, which can analyze and give early warning and alarm for excessive pesticide residues in fruits and vegetables, excessive bacterial residues, excessive temperature and humidity in important places, and other common risk factors. Based on the traditional data prediction algorithm, the food safety risk early warning method of this application based on big data analysis realizes the goal of real-time early warning of the system when the above food safety risks appear. The test results verify the correctness of the system function. The developed food safety early warning and alarm system can improve the ability to prevent food safety risks.

[0075] Certainly, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by those skilled in the art within the scope of the essence of the present invention shall also fall within the protection scope of the present invention.

Claims

1. An early warning and alarm system for common group food safety risks in college cafeterias, characterized in that: For the prediction of common precursors of food safety risks such as excessive temperature and humidity in important places, excessive pesticide residues in fruits and vegetables, and excessive bacteria in cold dishes or cooked foods, using big data analysis technology based on time series analysis, a temperature and humidity data prediction model, a pesticide residue prediction model, and a bacteria residue prediction model are established; specifically including: The temperature and humidity data prediction model: A weighted prediction model considering three aspects of influence, namely historical data of previous years, recent actual observation data, and recent weather forecast data, is established; the established weighted prediction model is: Among them, is the predicted temperature value, K T1 is the weighting coefficient corresponding to the historical temperature measurement data, D T1 is the number of points of the historical temperature measurement data, T 1i is the historical temperature measurement data, K T2 is the weighting coefficient corresponding to the recent temperature measurement data, D T2 is the number of points of the recent temperature measurement data, a i is the coefficient of the temperature autoregressive prediction model, T 2i is the recent temperature measurement data, K T3 is the weighting coefficient corresponding to the recent temperature weather forecast data, T f is the weather forecast data of the temperature, is the predicted humidity value, K H1 is the weighting coefficient corresponding to the historical humidity measurement data, D H1 is the number of points of the historical humidity measurement data, H 1i is the historical humidity measurement data, K H2 is the weighting coefficient corresponding to the recent humidity measurement data, D H2 is the number of points of the recent humidity measurement data, b i is the coefficient of the temperature autoregressive prediction model, H 2i is the recent humidity measurement data, K H3 is the weighting coefficient corresponding to the recent humidity weather forecast data, H f is the weather forecast data of the humidity; When the predicted temperature or humidity data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm, reminding the administrator to take preventive measures in a timely manner; The pesticide residue prediction model: A weighted prediction model considering four aspects of influence, namely historical data of previous years, recent actual measurement data, suppliers, and empirical data in the expert database, is established; the established weighted prediction model corresponds to the following formula: Among them, is the predicted value of pesticide residue, K P1 is the weighting coefficient corresponding to the historical pesticide residue measurement data of a certain type of fruits and vegetables, D P1 is the number of points of the historical pesticide residue measurement data of a certain type of fruits and vegetables, P 1i is the historical pesticide residue measurement data of a certain type of fruits and vegetables, K P2 is the weighting coefficient corresponding to the recent pesticide residue measurement data of a certain type of fruits and vegetables, D P2 is the number of points of the recent pesticide residue measurement data of a certain type of fruits and vegetables, P 2i is the recent pesticide residue measurement data of a certain type of fruits and vegetables, K P3 is the weighting coefficient corresponding to a certain supplier, D P3 is the number of points of the historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, P 3i is the historical pesticide residue measurement data of various fruits and vegetables of a certain supplier, K P4 is the weighting coefficient corresponding to the expert experience data, is the average measurement data of pesticide residue of a certain type of fruits and vegetables in the current season and current region; When the predicted pesticide residue data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm, reminding the administrator to take preventive measures in a timely manner; The bacteria residue prediction model: A weighted prediction model considering five aspects of influence, namely historical data of previous years, recent actual measurement data, indoor temperature data, indoor humidity data, and empirical data in the expert database, is established; the established weighted prediction model corresponds to the following formula: Among them, is the predicted value of the bacterial residue amount, K B1 is the weighting coefficient corresponding to the historical residue measurement data of a certain type of bacteria, D B1 is the number of points of the historical residue measurement data of a certain type of bacteria, B 1i is the historical residue measurement data of a certain type of bacteria, K B2 is the weighting coefficient corresponding to the recent residue measurement data of a certain type of bacteria, D B2 is the number of points of the recent residue measurement data of a certain type of bacteria, B 2i is the recent residue measurement data of a certain type of bacteria, K B3 is the weighting coefficient corresponding to the indoor temperature, D B3 is the number of points of the indoor temperature measurement data, T i is the indoor temperature measurement data, f1 is a function reflecting the influence of indoor temperature on the bacterial residue amount, K B4 is the weighting coefficient corresponding to the indoor humidity, D B4 is the number of points of the indoor humidity measurement data, H i is the indoor humidity measurement data, f2 is a function reflecting the influence of indoor humidity on the bacterial residue amount, K B5 is the weighting coefficient corresponding to the expert experience data, is the average measurement data of the residue amount of a certain type of bacteria in the current season and current region; When the predicted bacteria residue data exceeds the set threshold, a mobile phone text message is sent to the system administrator for alarm, reminding the administrator to take preventive measures in a timely manner.

2. The early warning and alarm system for common group food safety risks in college cafeterias according to claim 1, characterized in that: Including a hardware system and a software system; The hardware system includes video recording equipment, temperature and humidity measurement equipment, pesticide residue measurement equipment, bacteria residue measurement equipment, a server, and a short message communication device installed on the peripheral port of the server; The software system includes an intelligent device communication interface module, a mobile phone text message alarm interface module, a system database, and a data interface. The software system can analyze and give early warnings for excessive pesticide residues in fruits and vegetables, excessive bacteria residues, excessive temperature and humidity in important places, and other common risk factors; The video recording equipment is configured to record images of important places including incoming goods, processing, storage, sales, and sample retention; The temperature and humidity measurement equipment is configured to collect temperature and humidity data of important places including processing, storage, and sales, and automatically transmit the collected data to the server; The pesticide residue measurement equipment is configured to conduct sampling tests on fruits and vegetables, etc., and automatically transmit the collected data to the server; The bacteria residue measurement equipment is configured to conduct bacteria sampling tests on cold dish processing rooms and tableware, etc., and automatically transmit the collected data to the server; The server is configured to receive data collected by the temperature and humidity measurement equipment, the pesticide residue measurement equipment, and the bacteria residue measurement equipment; The short message communication device is configured to send relevant early warning and alarm information to the administrator in a timely manner; The system database is configured to store, retrieve, and operate data; The data interface is configured to implement data interaction between the software system and video recording devices, temperature and humidity measurement devices, pesticide residue measurement devices, bacterial residue measurement devices, and SMS communication devices; The data interface includes an intelligent device communication interface module and a mobile phone SMS alarm interface; The intelligent device communication interface is configured to implement data interaction between video recording devices, temperature and humidity measurement devices, pesticide residue measurement devices, bacterial residue measurement devices, and the software system; The mobile phone SMS alarm interface is configured to implement data interaction between the SMS communication device and the software system; When the intelligent device communication interface detects that the received data is abnormal, it automatically sends a mobile phone SMS alarm to the administrator through the mobile phone SMS alarm interface.

Images