Kitchen management system based on food safety protection

Abstract

The invention discloses a kitchen management system based on food safety protection, and relates to the technical field of kitchen management, and the system comprises the following steps: installing a sensor for each heat preservation box, binding the sensor with food information, inputting a distribution route, and accessing real-time weather data; in the driving process of the vehicle, continuously collecting the temperature in the box, the vehicle position and the speed information, and transmitting the information back to the central server in real time; according to the real-time data, the server utilizes a thermodynamic model to predict the temperature when each meal is delivered under the current route; the system judges whether the predicted temperature of a meal exceeds the standard or not, if yes, the optimal distribution sequence is automatically recalculated immediately, and the most dangerous meal is guaranteed preferentially; issuing the new delivery path to a vehicle terminal, and guiding a deliveryman to change the travel to form closed-loop control; and the system stores all operation data and periodically and automatically optimizes and predicts model parameters. According to the invention, accurate prediction and active intervention of future temperature change of the distributed food can be realized.

Description

Technical Field

[0001] This invention belongs to the field of kitchen management technology, and in particular relates to a kitchen management system based on protecting food safety. Background Technology

[0002] In large-scale group meal delivery, such as providing centralized catering services to schools and large enterprises, it is extremely important to ensure that the temperature of the food is above the safety threshold throughout the entire process before it is delivered to consumers.

[0003] For example, a large central kitchen prepares lunches for schools (such as the No. 1 Middle School in a certain city) and carries out hot chain delivery. After the meals are cooked in the central kitchen, they are packaged into multiple insulated delivery boxes and then transported by multiple delivery vehicles to various meal distribution points in the school (such as the meal distribution point in the east and west of the teaching building, the meal distribution point in the gymnasium, etc.).

[0004] In hot summer or extremely cold winter weather, the temperature of the food in the last insulated box can easily drop below 60°C (a dangerous temperature range for rapid bacterial growth) during the delivery journey to the last distribution point due to the repeated opening and closing of the vehicle doors, drastic changes in ambient temperature, and excessive delivery time. This poses a significant food safety risk.

[0005] Existing technologies mainly rely on temperature sensors installed inside insulated boxes for post-event alarms, which cannot predict or proactively intervene before an irreversible temperature drop occurs. They can only passively record the fact that the temperature has exceeded the standard. When the temperature of the food to be delivered has irreversibly dropped to the danger zone before delivery due to fixed routes, traffic delays, or multiple opening and closing of the delivery vehicle, the system can only provide a delayed alarm and cannot provide effective proactive intervention, so food safety risks still exist. Therefore, the following solutions are proposed to address the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a kitchen management system based on food safety protection. By constructing an intelligent decision-making system that integrates real-time temperature monitoring, environmental data perception, and dynamic path planning, it can accurately predict and proactively intervene in future temperature changes of delivered meals, solving the problem of passive monitoring in existing technologies that can only provide delayed alarms and cannot effectively avoid safety hazards before they occur.

[0007] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0008] This invention is a kitchen management system based on protecting food safety. The management system includes a data acquisition module, a vehicle-side data communication module, a human-computer interaction execution module, a cloud-based data communication module, a central data processing and prediction module, an environmental data integration module, a dynamic path planning module, and a model optimization module.

[0009] The workflow of the management system is as follows:

[0010] Step S1, System Initialization: Install sensors on each insulated box and bind them to the food information, while simultaneously recording the delivery route and accessing real-time weather data;

[0011] Step S2, Data Acquisition and Transmission: During the vehicle's journey, the temperature inside the container, vehicle position, and speed information are continuously collected and transmitted back to the central server in real time.

[0012] Step S3, Temperature Prediction Calculation: Based on real-time data, the server uses a thermodynamic model to predict the temperature of each meal when it arrives along the current route;

[0013] Step S4, Risk Decision Optimization: The system determines whether any meal is predicted to exceed the temperature limit. If it does, the system immediately and automatically recalculates the optimal delivery order, prioritizing the most dangerous meal.

[0014] Step S5, Instruction Execution Feedback: The new delivery route is sent to the vehicle terminal to guide the delivery person to change the route, forming a closed-loop control;

[0015] Step S6, Data Recording Iteration: The system stores all operational data and automatically optimizes the predictive model parameters periodically.

[0016] Furthermore, the data acquisition module is responsible for collecting key physical data in real time, including the temperature inside the insulated box, the vehicle's position, and speed.

[0017] The environmental data integration module is used to obtain real-time ambient temperature and humidity data of the vehicle's location by calling external API interfaces;

[0018] The vehicle-side data communication module and the cloud-side data communication module are used to establish a stable connection between the vehicle and the cloud server, and are responsible for the secure transmission of uplink and downlink data.

[0019] The central data processing and prediction module is used to store data and run core algorithms to predict the future temperature of food and assess food safety risks.

[0020] The dynamic route planning module is used to immediately recalculate the optimal delivery order when a risk is predicted, so as to prioritize the temperature safety of the most dangerous meals.

[0021] The human-computer interaction execution module is used to provide delivery personnel with a visual interface and voice navigation, and to receive and execute new delivery instructions sent from the cloud.

[0022] The model optimization module is used to continuously learn from historical delivery data and automatically calibrate and optimize the parameters of the prediction model.

[0023] Further, step S1, system initialization, specifically includes the following steps:

[0024] Step S11: Hardware deployment: Install a high-precision temperature sensor (such as DS18B20) and a low-power Bluetooth transmitter module inside each insulated delivery box; install a GPS positioning module and an on-board main control unit (such as a tablet computer) in each delivery vehicle, which has a built-in 4G / 5G communication module; deploy the management system software on the server in the central kitchen.

[0025] Step S12: Data association and binding. The system generates a unique QR code for each batch of meals and affixes it to the corresponding insulated box. After packing, the system scans the QR code to retrieve information about the batch of meals (such as dish name, initial core temperature, etc.). Cooking time Bind the device to the Bluetooth ID of the insulated box;

[0026] Step S13: Delivery plan entry. The delivery person confirms the delivery task on the main control unit, and the system downloads the delivery plan from the server. The plan is an ordered sequence ,in, Representing the The geographical location of the meals requiring delivery and their estimated delivery time. ;

[0027] Step S14: Environmental data access. The main control unit obtains real-time micro-environmental meteorological data based on the GPS location of the delivery vehicle, provided by an authoritative meteorological department, through an API interface, including ambient temperature. and humidity .

[0028] Furthermore, step S2, data acquisition and transmission, specifically includes the following steps:

[0029] Step S21: After the delivery vehicle departs, the temperature sensors in each insulated box will activate at fixed time intervals. (For example, collect the temperature data inside the chamber every 30 seconds) ;

[0030] Step S22: Temperature data is transmitted to the vehicle's main control unit via Bluetooth;

[0031] Step S23: The vehicle main control unit simultaneously receives real-time location information sent by the GPS module. and speed information ;

[0032] Step S24: The onboard main control unit packages the data set The data is uploaded in real time to the central kitchen's server via 4G / 5G network. The current temperature. Current position At the current speed, For timestamps.

[0033] Furthermore, step S3, the temperature prediction calculation, specifically includes the following steps:

[0034] Step S31: The server receives the data stream from the vehicle for the current delivery plan. Each undelivered meal The system initiates temperature prediction calculations;

[0035] Step S32: The system uses a temperature decay prediction model trained with a large amount of experimental data to predict the delivery time of the meal. The center temperature at that time This model comprehensively considers heat convection, heat conduction, and the thermal shock effect caused by opening and closing the cabinet door. Its calculation formula is as follows:

[0036]

[0037] In the formula, For predicted delivery times The core temperature of the food inside the insulated box From the current moment until delivery The predicted average ambient temperature along the path, The initial temperature of the food at the start of delivery or the current temperature calculated by the model. To take into account the overall thermal decay coefficient, For the predicted arrival time from the current moment The time required The average temperature decay coefficient caused by each opening and closing of the cabinet door. For the prediction from the current position to It also requires opening and closing the box door several times;

[0038] Step S33: The system performs loop calculations until all undelivered meals along the current path are obtained. Predicted temperature .

[0039] Furthermore, step S4, risk decision optimization, specifically includes the following steps:

[0040] Step S41: The system will calculate all the results in step S3. Food safety temperature threshold (For example, 60℃) for comparison;

[0041] Step S42: When all All greater than or equal to In this case, the system will maintain the original delivery plan. And display "Status Safe" on the vehicle terminal;

[0042] When at least one meal is detected Predicted temperature When this happens, the system immediately triggers the path optimization algorithm;

[0043] Step S43: The path optimization algorithm recalculates the delivery sequence with the core objective of maximizing the minimum predicted temperature. The algorithm iterates through all possible combinations of remaining meal delivery orders, and for each candidate path... Then, re-execute the prediction calculation in step S3 to obtain the predicted temperature of all meals along the new path, and find the minimum value among them. ;

[0044] Step S44: The system selects to use The largest candidate route will be used as the new optimal delivery plan. ;Right now:

[0045]

[0046] In the formula, For the new optimal delivery plan, To find the optimal operator, For candidate delivery plans, Predict the temperature set for candidate paths. The lowest predicted temperature;

[0047] The optimization process ensures that the system proactively selects the delivery route that maximizes the temperature control of the most dangerous meals.

[0048] Furthermore, step S5, the instruction execution feedback, specifically includes the following steps:

[0049] Step S51: The server will generate a new delivery plan. The data is sent to the onboard main control unit of the corresponding delivery vehicle;

[0050] Step S52: The vehicle's main control unit prompts the delivery person via voice and interface pop-up: "We have detected that the food at XX delivery point has a risk of being served at low temperatures. We have optimized your route. Please go to YY delivery point first." The new navigation route is automatically updated.

[0051] Step S53: The delivery person performs the delivery task according to the new navigation instructions;

[0052] Step S54: The system continues to execute steps S2 to S5, forming a closed-loop control of "data acquisition - prediction - decision-making - execution" until all meals are delivered.

[0053] Furthermore, step S6, the data recording iteration, specifically includes the following steps:

[0054] Step S61: All data during the delivery process, including actual delivery time, actual measured delivery temperature, environmental data, and route change records, are completely stored in the server database.

[0055] Step S62: The system periodically (e.g., weekly) uses the accumulated new data to update the parameters (such as coefficients) in the temperature prediction model. and It performs automatic calibration and optimization, making predictions increasingly accurate over time.

[0056] The present invention has the following beneficial effects:

[0057] 1. This invention continuously calculates future temperature change trends through mathematical models and automatically generates and executes the optimal new delivery plan when risks are predicted. This allows for corrective measures to be taken before the physical cooling process becomes irreversible, reducing the risk of microbial growth caused by food being in dangerous temperature ranges for extended periods.

[0058] 2. This invention maximizes the heat preservation efficiency of existing delivery resources through prediction and intelligent scheduling without additional hardware investment; it obtains the optimal solution through scientific calculation, avoiding additional fuel, manpower and time costs caused by emergency remedies, and achieving a balance between safety goals and economic benefits.

[0059] 3. This invention transforms the management decisions in the delivery process from relying on human experience to automated intelligent decision-making driven by data and guided by models. The decision suggestions provided by the system are based on the fusion of multi-source real-time data and rigorous mathematical calculations, eliminating the uncertainty and lag of human judgment and ensuring the scientific nature and consistency of instructions. In addition, the system constructs a continuously optimized feedback loop. The actual temperature and predicted temperature data accumulated in each delivery task are used to periodically calibrate and iteratively optimize the parameters of the core prediction model, so that the prediction accuracy of the system continuously improves with the extension of usage time, forming a virtuous cycle with self-learning capabilities, and the reliability and practicality of the system are continuously enhanced.

[0060] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a schematic diagram of the structure of a kitchen management system based on protecting food safety according to the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Please see Figure 1 As shown, the present invention is a kitchen management system based on protecting food safety. The management system includes a data acquisition module, a vehicle-side data communication module, a human-computer interaction execution module, a cloud-based data communication module, a central data processing and prediction module, an environmental data integration module, a dynamic path planning module, and a model optimization module.

[0065] The data acquisition module is responsible for collecting key physical data in real time, including the temperature inside the insulated box, vehicle position, and speed.

[0066] The environmental data integration module is used to obtain real-time ambient temperature and humidity data of the vehicle's location by calling external API interfaces;

[0067] The vehicle-side data communication module and the cloud-side data communication module are used to establish a stable connection between the vehicle and the cloud server, and are responsible for the secure transmission of uplink and downlink data;

[0068] The central data processing and prediction module is used to store data and run core algorithms to predict the future temperature of food and assess food safety risks.

[0069] The dynamic route planning module is used to immediately recalculate the optimal delivery order when a risk is predicted, so as to prioritize the temperature safety of the most dangerous meals.

[0070] The human-computer interaction execution module is used to provide delivery personnel with a visual interface and voice navigation, and to receive and execute new delivery instructions issued from the cloud.

[0071] The model optimization module is used to continuously learn from historical delivery data and automatically calibrate and optimize the parameters of the prediction model.

[0072] The workflow of the management system is as follows:

[0073] Step S1, System Initialization: Install sensors on each insulated box and bind them to the food information, while simultaneously recording the delivery route and accessing real-time weather data;

[0074] Step S1, system initialization specifically includes the following steps:

[0075] Step S11: Hardware deployment: Install a high-precision temperature sensor (such as DS18B20) and a low-power Bluetooth transmitter module inside each insulated delivery box; install a GPS positioning module and an on-board main control unit (such as a tablet computer) in each delivery vehicle, which has a built-in 4G / 5G communication module; deploy the management system software on the server in the central kitchen.

[0076] Step S12: Data association and binding. The system generates a unique QR code for each batch of meals and affixes it to the corresponding insulated box. After packing, the system scans the QR code to retrieve information about the batch of meals (such as dish name, initial core temperature, etc.). Cooking time Bind the device to the Bluetooth ID of the insulated box;

[0077] Step S13: Delivery plan entry. The delivery person confirms the delivery task on the main control unit, and the system downloads the delivery plan from the server. The plan is an ordered sequence ,in, Representing the The geographical location of the meals requiring delivery and their estimated delivery time. ;

[0078] Step S14: Environmental data access. The main control unit obtains real-time micro-environmental meteorological data based on the GPS location of the delivery vehicle, provided by an authoritative meteorological department, through an API interface, including ambient temperature. and humidity .

[0079] Step S2, Data Acquisition and Transmission: During the vehicle's journey, the temperature inside the container, vehicle position, and speed information are continuously collected and transmitted back to the central server in real time.

[0080] Step S2, data acquisition and transmission specifically includes the following steps:

[0081] Step S21: After the delivery vehicle departs, the temperature sensors in each insulated box will activate at fixed time intervals. (For example, collect the temperature data inside the chamber every 30 seconds) ;

[0082] Step S22: Temperature data is transmitted to the vehicle's main control unit via Bluetooth;

[0083] Step S23: The vehicle main control unit simultaneously receives real-time location information sent by the GPS module. and speed information ;

[0084] Step S24: The onboard main control unit packages the data set The data is uploaded in real time to the central kitchen's server via 4G / 5G network. The current temperature. Current position At the current speed, For timestamps.

[0085] Step S3, Temperature Prediction Calculation: Based on real-time data, the server uses a thermodynamic model to predict the temperature of each meal when it arrives along the current route;

[0086] Step S3, temperature prediction calculation specifically includes the following steps:

[0087] Step S31: The server receives the data stream from the vehicle for the current delivery plan. Each undelivered meal The system initiates temperature prediction calculations;

[0088] Step S32: The system uses a temperature decay prediction model trained with a large amount of experimental data to predict the delivery time of the meal. The center temperature at that time This model comprehensively considers heat convection, heat conduction, and the thermal shock effect caused by opening and closing the cabinet door. Its calculation formula is as follows:

[0089]

[0090] In the formula, For predicted delivery times The core temperature of the food inside the insulated box From the current moment until delivery The predicted average ambient temperature along the path, The initial temperature of the food at the start of delivery or the current temperature calculated by the model. To take into account the overall thermal decay coefficient, For the predicted arrival time from the current moment The time required The average temperature decay coefficient caused by each opening and closing of the cabinet door. For the prediction from the current position to It also requires opening and closing the box door several times;

[0091] Step S33: The system performs loop calculations until all undelivered meals along the current path are obtained. Predicted temperature .

[0092] Step S4, Risk Decision Optimization: The system determines whether any meal is predicted to exceed the temperature limit. If it does, the system immediately and automatically recalculates the optimal delivery order, prioritizing the most dangerous meal.

[0093] Step S4, risk decision optimization specifically includes the following steps:

[0094] Step S41: The system will calculate all the results in step S3. Food safety temperature threshold (For example, 60℃) for comparison;

[0095] Step S42: When all All greater than or equal to In this case, the system will maintain the original delivery plan. And display "Status Safe" on the vehicle terminal;

[0096] When at least one meal is detected Predicted temperature When this happens, the system immediately triggers the path optimization algorithm;

[0097] Step S43: The path optimization algorithm recalculates the delivery sequence with the core objective of maximizing the minimum predicted temperature. The algorithm iterates through all possible combinations of remaining meal delivery orders, and for each candidate path... Then, re-execute the prediction calculation in step S3 to obtain the predicted temperature of all meals along the new path, and find the minimum value among them. ;

[0098] Step S44: The system selects to use The largest candidate route will be used as the new optimal delivery plan. ;Right now:

[0099]

[0100] In the formula, For the new optimal delivery plan, To find the optimal operator, For candidate delivery plans, Predict the temperature set for candidate paths. The lowest predicted temperature;

[0101] The optimization process ensures that the system proactively selects the delivery route that maximizes the temperature control of the most dangerous meals.

[0102] Step S5, Instruction Execution Feedback: The new delivery route is sent to the vehicle terminal to guide the delivery person to change the route, forming a closed-loop control;

[0103] Step S5, instruction execution feedback specifically includes the following steps:

[0104] Step S51: The server will generate a new delivery plan. The data is sent to the onboard main control unit of the corresponding delivery vehicle;

[0105] Step S52: The vehicle's main control unit prompts the delivery person via voice and interface pop-up: "We have detected that the food at XX delivery point has a risk of being served at low temperatures. We have optimized your route. Please go to YY delivery point first." The new navigation route is automatically updated.

[0106] Step S53: The delivery person performs the delivery task according to the new navigation instructions;

[0107] Step S54: The system continues to execute steps S2 to S5, forming a closed-loop control of "data acquisition - prediction - decision-making - execution" until all meals are delivered.

[0108] Step S6, Data Recording Iteration: The system stores all operational data and automatically optimizes the predictive model parameters periodically.

[0109] Step S6, the data recording iteration specifically includes the following steps:

[0110] Step S61: All data during the delivery process, including actual delivery time, actual measured delivery temperature, environmental data, and route change records, are completely stored in the server database.

[0111] Step S62: The system periodically (e.g., weekly) uses the accumulated new data to update the parameters (such as coefficients) in the temperature prediction model. and It performs automatic calibration and optimization, making predictions increasingly accurate over time.

[0112] One specific application of this embodiment is:

[0113] Background: A catering company's central kitchen produces lunches for the city's No. 1 Middle School. Today's menu is: braised beef, stir-fried vegetables, and rice. After cooking in the central kitchen, the food is packaged into 12 insulated delivery boxes and transported by a delivery truck to three distribution points at the school: Grade 11 and 12 teaching buildings (L1), Grade 12 teaching building (L2), and the International Department (L3). The original delivery route was as follows: The day was a hot summer day, with an outdoor temperature of [temperature missing]. Temperatures can reach as high as 35°C.

[0114] Implementation steps:

[0115] Step S1: System Initialization and Deployment

[0116] The food is taken out of the pot, and the core temperature is measured as follows: .

[0117] Staff packed the meals into insulated boxes, scanned the QR code on the boxes, and the system linked the meal information to insulated box number 12 and recorded the initial temperature. .

[0118] Delivery driver Zhang San logs into the vehicle terminal to confirm the task; the system downloads the delivery plan. and its estimated delivery time: .

[0119] The vehicle departs; the system retrieves current environmental data from the meteorological API: .

[0120] Step S2, Data Acquisition and Initial Prediction

[0121] The vehicle is in motion; sensor #12 insulated box is uploading current data: The GPS uploads location information, and the system calculates that it will take approximately 8 minutes to reach the first station, L1.

[0122] The system initiates its initial predictive calculation. Built-in system parameters (derived from historical data trained on this model of insulated box and the characteristics of the food): Comprehensive thermal attenuation coefficient. Door opening and closing attenuation coefficient ℃ / time.

[0123] For the originally planned last delivery point L3:

[0124] Predicted arrival time minute.

[0125] Predict the number of times doors are opened and closed (The door must be opened when delivering to L2 and L3).

[0126] Substitute into the prediction model formula:

[0127]

[0128]

[0129]

[0130]

[0131] Calculation results The system determined that the risk was low and maintained the original plan.

[0132] Step S3: Risk Emergence and Re-decision

[0133] The vehicle arrived at L1, and the delivery person opened the delivery door to deliver four boxes of food, which took 5 minutes; after closing the door, the sensor uploaded the new temperature. .

[0134] The system immediately re-executes the forecast calculation. At this point, the remaining delivery points... .

[0135] Predicted temperature upon delivery to L3:

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142] Calculation results It is still above the safety threshold;

[0143] The system continued to proceed towards L2 as originally planned.

[0144] Step S4: Triggering Optimization and Instruction Execution

[0145] The vehicle is about to reach Level 2, and the sensors are reporting the temperature. ;

[0146] The system performed the prediction again. This calculation revealed that if L2 was sent first and then L3 as originally planned, the predicted temperature of L3 would drop to [a lower value]. (Calculation process omitted), already lower than ;

[0147] The system immediately triggers the path optimization algorithm. Candidate paths are generated: .

[0148] for :

[0149] Predicted travel time directly to L3 .

[0150]

[0151]

[0152]

[0153]

[0154] After delivering to L3, proceed to L2 to predict the temperature at L2. (Calculation process omitted);

[0155] Therefore, the new path The lowest predicted temperature is .

[0156] Compare to the original path Lowest predicted temperature .

[0157] According to the decision formula System selection As a new path, namely .

[0158] The vehicle terminal immediately issued a voice prompt: "Warning! The food at the International Department (L3) is expected to be cold. The route has been optimized. Please go to the International Department (L3) first." The navigation map was automatically replanned and L3 was set as the next destination.

[0159] Step S5, Optimization Results

[0160] The delivery driver followed instructions and prioritized delivering the remaining food to L3; the actual measured center temperature of the food upon delivery was... It exceeds safety standards;

[0161] The vehicle then proceeds to L2 to complete the delivery;

[0162] Through this closed-loop control, the system successfully prevented food safety incidents caused by L3 meals falling into dangerous temperature ranges due to prolonged delivery in high-temperature environments; all data, including predicted values, decision logic, and actual temperatures, were recorded for subsequent model optimization.

[0163] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0164] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A kitchen management system based on protecting food safety, characterized in that, The management system includes a data acquisition module, a vehicle-side data communication module, a human-machine interaction execution module, a cloud-based data communication module, a central data processing and prediction module, an environmental data integration module, a dynamic path planning module, and a model optimization module. The workflow of the management system is as follows: Step S1, System Initialization: Install sensors on each insulated box and bind them to the food information, while simultaneously recording the delivery route and accessing real-time weather data; Step S2, Data Acquisition and Transmission: During the vehicle's journey, the temperature inside the container, vehicle position, and speed information are continuously collected and transmitted back to the central server in real time. Step S3, Temperature Prediction Calculation: Based on real-time data, the server uses a thermodynamic model to predict the temperature of each meal when it arrives along the current route; Step S4, Risk Decision Optimization: The system determines whether any meal is predicted to exceed the temperature limit. If it does, the system immediately and automatically recalculates the optimal delivery order, prioritizing the most dangerous meal. Step S5, Instruction Execution Feedback: The new delivery route is sent to the vehicle terminal to guide the delivery person to change the route, forming a closed-loop control; Step S6, Data Recording Iteration: The system stores all operational data and automatically optimizes the predictive model parameters periodically.

2. The kitchen management system based on food safety protection according to claim 1, characterized in that, The data acquisition module is responsible for collecting key physical data in real time, including the temperature inside the insulated box, vehicle position, and speed. The environmental data integration module is used to obtain real-time ambient temperature and humidity data of the vehicle's location by calling external API interfaces; The vehicle-side data communication module and the cloud-side data communication module are used to establish a stable connection between the vehicle and the cloud server, and are responsible for the secure transmission of uplink and downlink data. The central data processing and prediction module is used to store data and run core algorithms to predict the future temperature of food and assess food safety risks. The dynamic route planning module is used to immediately recalculate the optimal delivery order when a risk is predicted, so as to prioritize the temperature safety of the most dangerous meals. The human-computer interaction execution module is used to provide delivery personnel with a visual interface and voice navigation, and to receive and execute new delivery instructions sent from the cloud. The model optimization module is used to continuously learn from historical delivery data and automatically calibrate and optimize the parameters of the prediction model.

3. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S1, system initialization, specifically includes the following steps: Step S11: Hardware deployment: Install a high-precision temperature sensor and a low-power Bluetooth transmitter module inside each insulated delivery box; install a GPS positioning module and an on-board main control unit in each delivery vehicle, wherein the main control unit has a built-in 4G / 5G communication module; deploy the management system software on the server in the central kitchen. Step S12: Data association and binding. The system generates a unique QR code for each batch of meals and affixes it to the corresponding insulated box. After packing, the information of the batch of meals is bound to the Bluetooth ID of the insulated box by scanning the QR code. Step S13: Delivery plan entry. The delivery person confirms the delivery task on the main control unit, and the system downloads the delivery plan from the server. Step S14: Environmental data access. The main control unit obtains real-time micro-environmental meteorological data, including ambient temperature and humidity, based on the GPS location of the delivery vehicle and provided by an authoritative meteorological department through the API interface.

4. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S2, data acquisition and transmission, specifically includes the following steps: Step S21: After the delivery vehicle departs, the temperature sensor in each insulated box collects the temperature data inside the box at fixed time intervals. Step S22: Temperature data is transmitted to the vehicle's main control unit via Bluetooth; Step S23: The vehicle-mounted main control unit simultaneously receives real-time location information and speed information sent by the GPS module; Step S24: The vehicle-mounted main control unit uploads the packaged data set to the central kitchen's server in real time via the 4G / 5 network.

5. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S3, the temperature prediction calculation, specifically includes the following steps: Step S31: The server receives the data stream from the vehicle, and for each undelivered meal in the current delivery plan, the system initiates temperature prediction calculation; Step S32: The system uses a temperature decay prediction model trained with a large amount of experimental data to predict the center temperature of the food when it is delivered. Step S33: The system performs loop calculations until the predicted temperatures of all undelivered meals along the current path are obtained.

6. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S4, risk decision optimization, specifically includes the following steps: Step S41: The system will calculate all the results in step S3. The temperature of the food inside the insulated box was compared with the food safety temperature threshold when the meal was delivered to the point of delivery. Step S42: When all When the food is delivered to the insulated box, if the core temperature of the food is greater than or equal to the food safety temperature threshold, the system will maintain the original delivery plan and display "Status is safe" on the vehicle terminal. When the predicted temperature of at least one meal is detected to be lower than the food safety temperature threshold, the system immediately triggers the path optimization algorithm. Step S43: The path optimization algorithm aims to maximize the minimum predicted temperature and recalculates the delivery sequence. The algorithm iterates through all possible combinations of remaining meal delivery orders. For each candidate path, the prediction calculation in step S3 is re-executed to obtain the predicted temperature of all meals under the new path and find the minimum value. Step S44: The system selects the delivery route that maximizes the lowest predicted temperature among all candidate routes and determines it as the new optimal execution path.

7. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S5, the instruction execution feedback, specifically includes the following steps: Step S51: The server sends the generated new delivery plan to the on-board main control unit of the corresponding delivery vehicle; Step S52: The vehicle-mounted main control unit provides prompts to the delivery person via voice and interface pop-up windows; Step S53: The delivery person performs the delivery task according to the new navigation instructions; Step S54: The system continues to execute steps S2 to S5 until all meals are delivered.

8. A kitchen management system based on food safety protection according to claim 1, characterized in that, Step S6, the data recording iteration, specifically includes the following steps: Step S61: The system stores all data from the delivery process, including actual delivery time, actual measured delivery temperature, environmental data, and route change records, in the server database. Step S62: The system periodically uses the accumulated new data to automatically calibrate and optimize the parameters in the temperature prediction model.

Images