Supply chain group meal management and control system based on big data

Abstract

The invention relates to the field of big data management and control, in particular to a supply chain group meal management and control system based on big data, which comprises a dish information module used for collecting delivery time of a plurality of dishes, a train information module used for collecting train information of a plurality of trains, a collection module used for collecting the delivery time and preprocessing the delivery time to generate corresponding preprocessing data, and a management and control module used for managing the corresponding preprocessing data. The system comprises a preprocessing module used for preprocessing data, a learning module used for selecting a plurality of index characteristics of the preprocessing data for learning and generating a standard distribution time length of dishes, and a planning module used for generating a group meal supply plan according to the standard distribution time length and train information, adjusting the learning module according to the group meal supply plan, and visualizing a group meal supply chain by using the learning module. The difficulty of management and control in the distribution process is reduced, the freshness of the food materials in the distribution process is guaranteed, the problem that the food production amount is not easy to control is effectively solved, the problem of information lag of a food supply chain is further avoided, and the practicability of the group meal supply chain is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data management and control, and in particular to a supply chain group meal management and control system based on big data. Background Art

[0002] In the past, the supply of railway meals often resulted in stale or wasted food due to train delays or temperature changes. This method of catering took a long time to start, was inefficient, and resulted in a large consumption of food due to waste. It was especially difficult to guarantee the time for temporary catering on railway trains.

[0003] Chinese patent application publication number: CN107292574A discloses a food supply method and a food supply system. Among them, the food supply method includes: receiving food purchase request information; generating food supply instructions according to the purchase request information; executing the supply instructions, and recording the execution process information obtained during the execution of the supply instructions; uploading the execution process information to the server so that the server can send the execution process information to the terminal. This invention provides a monitoring method for the entire process of food supply. On the one hand, it is convenient for buyers to track the entire process of food harvesting, packaging, and distribution in real time, and truly understand the freshness of the food; on the other hand, the seller also realizes the superiority of his own product services, which can be used as a technical means for merchants to control quality and promote services, and gain the trust of more users.

[0004] Chinese Patent Authorization Announcement No.: CN117829698B discloses a food supply chain scheduling and management system, which belongs to the technical field of supply chain scheduling and management. In the invention, the images of food to be supplied provided by each supply chain are compared with the stored food images to obtain the quality factors of the food to be supplied of each supply chain, and the supply chains that meet the quality requirements are screened out according to the quality factors, and are named candidate supply chains. Then, the fuel consumption of the vehicles, the food loss cost and the quality factor of the food to be supplied are considered from the candidate supply chains, an objective function is established, and the optimal supply chain is screened out. When considering the fuel consumption of the vehicles during transportation, the invention also considers the food loss cost and the quality factor of the food to be supplied, thereby improving the selection accuracy of the optimal supply chain.

[0005] However, the above method has the following problems: there will be a problem of food supply chain information lag during the supply process. Summary of the invention

[0006] To this end, the present invention provides a supply chain group meal management and control system based on big data to overcome the problem of food supply chain information lag in the supply process in the prior art.

[0007] To achieve the above objectives, the present invention provides a supply chain group meal management and control system based on big data, including:

[0008] The dish information module is used to collect the delivery time of each dish in the group meal;

[0009] A train information module, which is used to collect train information of several trains;

[0010] A collection module, which is connected to the dish information module, and is used to collect the delivery time, perform preprocessing, and generate corresponding preprocessing data;

[0011] A learning module, which is connected to the collection module and is used to select several indicator features of the pre-processed data for learning, and generate a standard delivery time of dishes according to the indicator features;

[0012] A planning module, which is connected to the train information module and the learning module, and is used to generate a corresponding group meal supply plan according to the standard delivery time and the train information, and adjust the standard delivery time according to the group meal supply plan;

[0013] The delivery time is the sum of the cooking time, packaging time and transportation time of the dishes;

[0014] The train information includes the train's stop time, departure time and / or passing cities;

[0015] The preprocessed data is fitted according to the delivery time, and the group meal delivery data with a sampling rate of a standard sampling rate is generated, and corresponding indicator features are generated;

[0016] The standard sampling rate is a sampling rate that can be recognized by the learning module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0017] The indicator characteristics include the type of ingredients, cooking method and / or transportation method of each dish.

[0018] Furthermore, the dish module includes:

[0019] An input device, which is used to input the names of several dishes;

[0020] A cloud platform, which is used to select the cooking time, packaging time and transportation time of the corresponding dish according to the name of the dish;

[0021] A balance scheduler is connected to the input device and the cloud platform to calculate the delivery time of the dishes.

[0022] Furthermore, the train information module includes:

[0023] A receiver for receiving train information of a plurality of trains in a catering supply chain;

[0024] The server is connected to the receiver and is used to retrieve the stop time, departure time and / or passing cities of the train according to the train information.

[0025] Furthermore, the learning module includes:

[0026] A transmitter, configured to receive the pre-processed data;

[0027] An extractor, connected to the transmitter, for extracting index features of the preprocessed data;

[0028] A matcher connected to the extractor is used to learn the pre-processed data and generate a standard delivery time corresponding to the dish.

[0029] Wherein, the matcher is provided with a standard time generation model;

[0030] The standard time generation model is generated by training the preprocessed data.

[0031] Furthermore, the planning module includes:

[0032] A monitor, which is used to receive the standard delivery time and the train information;

[0033] A regulator, connected to the monitor, for generating the group meal supply plan according to the standard delivery time and the train information;

[0034] A verifier, connected to the regulator, for verifying the group meal supply plan;

[0035] Wherein, the regulator is provided with a supply planning model;

[0036] The verifier is provided with an accuracy threshold, and the accuracy threshold is the minimum standard of accuracy during the actual delivery of the group meal supply plan.

[0037] Furthermore, the dishes to be delivered are input into the input device, the cloud platform retrieves the cooking time, boxing time and transportation time corresponding to the dishes, the balance scheduler calculates the delivery time and transmits it to the collection module, and pre-processes the delivery time to generate the pre-processed data.

[0038] The pre-processing is to standardize the delivery time.

[0039] The standardization process is to divide the delivery time according to a standard sampling rate;

[0040] The standard sampling rate is a sampling rate that can be recognized by the standard time generation model, and is related to the minimum recognition capability of the standard time generation model.

[0041] Furthermore, the transmitter module receives the preprocessed data, generates corresponding indicator features based on the preprocessed data, and transmits the features to the matcher. The standard time generation model obtains the standard delivery time corresponding to the dish.

[0042] Furthermore, the train information module receives the train information of the train and transmits it to the planning module, the monitor receives the standard delivery time and the train information, and the regulator generates the group meal supply plan.

[0043] The process of generating the group meal supply plan is to calculate the least common multiple of the standard delivery time and the train running time, and determine the delivery time of the dishes by the least common multiple to generate the group meal supply plan;

[0044] The train running time is the difference between the train's stop time and departure time.

[0045] Furthermore, the supply plan model in the verifier verifies the group meal supply plan.

[0046] The verification process is to obtain the accuracy of the group meal supply plan during actual delivery, and compare the accuracy with the accuracy threshold.

[0047] Furthermore, when the accuracy rate is greater than the accuracy rate threshold, the learning module is not adjusted; when the accuracy rate is less than the accuracy rate threshold, several indicator features and sampling rate of the learning module are adjusted.

[0048] Compared with the prior art, the present invention utilizes the setting of a dish information module for collecting the delivery time of several dishes, a train information module for collecting the train information of several trains, a collection module for collecting the delivery time and performing preprocessing to generate corresponding preprocessing data, a learning module for selecting several indicator features of the preprocessing data for learning, and generating a standard delivery time for dishes, a planning module for generating a group meal supply plan according to the standard delivery time and train information, and adjusting the learning module according to the group meal supply plan, and using the learning module to visualize the group meal supply chain, thereby reducing the difficulty of controlling the delivery process, ensuring the freshness of the ingredients during the delivery process, effectively solving the problem of difficult control of food production, further avoiding the problem of information lag in the food supply chain, and improving the practicability of the group meal supply chain.

[0049] Furthermore, by setting up a balance scheduler in the dish module, the delivery time of the dishes can be calculated in real time, which improves the operational efficiency of the supply chain, ensures the freshness of the ingredients during the delivery process, and thus reduces the complexity of ingredient traceability.

[0050] Furthermore, by setting an accuracy threshold in the verifier, it is possible to quickly determine whether the learning module needs to be adjusted, thereby further solving the problem of difficult to control food production.

[0051] Furthermore, by preprocessing the delivery time in the collection module, errors caused by mistakes in collecting the delivery time are avoided, thereby improving the accuracy of the model learning results.

[0052] Furthermore, by using the extractor to generate indicator features for preprocessed data, the effective features of the preprocessed data can be quickly selected, and the group meal supply chain is visualized using the learning module, thereby further improving the accuracy of the model learning results.

[0053] Furthermore, by setting up a supply planning model and learning the pre-processed data, the accuracy of the group meal supply plan was improved, and the problem of being unable to trace the food after delivery due to human factors was effectively solved.

[0054] Furthermore, by adjusting several indicator characteristics and sampling rates of the learning module, the intelligent and real-time regulation of the supply chain is achieved, which further avoids the problem of information lag in the food supply chain and improves the practicality of the group meal supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a schematic diagram of the structure of the supply chain group meal management and control system based on big data of the present invention;

[0056] Figure 2 It is a schematic diagram of the structure of the planning module of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0059] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0060] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] See also Figure 1 As shown, it is a schematic diagram of the structure of the supply chain group meal management and control system based on big data of the present invention, including:

[0062] The dish information module is used to collect the delivery time of each dish in the group meal;

[0063] A train information module, which is used to collect train information of several trains;

[0064] A collection module, which is connected to the dish information module, is used to collect the delivery time, perform preprocessing, and generate corresponding preprocessing data;

[0065] A learning module, which is connected to the collection module, is used to select several indicator features of the preprocessed data for learning, and generate the standard delivery time of the dishes according to the indicator features;

[0066] The planning module is connected to the train information module and the learning module, and is used to generate a corresponding group meal supply plan according to the standard delivery time and train information, and adjust the standard delivery time according to the group meal supply plan;

[0067] Among them, the delivery time is the sum of the cooking time, packaging time and transportation time of the dishes;

[0068] Train information includes the train's stop times, departure times, and / or cities it passes through;

[0069] The preprocessed data is fitted according to the delivery time, and the group meal delivery data with a standard sampling rate is generated, and the corresponding indicator features are generated;

[0070] The standard sampling rate is a sampling rate that can be recognized by the learning module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0071] The indicator characteristics include the type of ingredients, cooking method and / or transportation method of each dish.

[0072] Specifically, the dish module includes:

[0073] An input device for inputting the names of several dishes;

[0074] The cloud platform is used to select the cooking time, packaging time and transportation time of the corresponding dishes according to the names of the dishes;

[0075] The balance scheduler is connected to the input device and the cloud platform to calculate the delivery time of the dishes.

[0076] By setting up a balance scheduler in the dish module, the delivery time of dishes can be calculated in real time, which improves the operational efficiency of the supply chain, ensures the freshness of the ingredients during the delivery process, and thus reduces the complexity of ingredient traceability.

[0077] Specifically, the train information module includes:

[0078] A receiver for receiving train information of a plurality of trains in a catering supply chain;

[0079] The server is connected to the receiver and is used to retrieve the stop time, departure time and / or passing cities of the train according to the train information.

[0080] Specifically, the learning modules include:

[0081] A transmitter for receiving pre-processed data;

[0082] An extractor, connected to the transmitter, for extracting indicator features of the preprocessed data;

[0083] The matcher is connected to the extractor to learn the preprocessed data and generate the standard delivery time corresponding to the dishes.

[0084] Among them, a standard time generation model is provided in the matcher;

[0085] The standard temporal generation model is generated by training on preprocessed data.

[0086] See also Figure 2 As shown, it is a schematic diagram of the planning module structure of the present invention, including:

[0087] Monitors for receiving standard delivery times and train information;

[0088] A regulator, which is connected to the monitor and is used to generate a group meal supply plan based on the standard delivery time and train information;

[0089] A verifier, which is connected to the regulator and is used to verify the group meal supply plan;

[0090] Among them, a supply planning model is provided in the regulator;

[0091] The verifier is provided with an accuracy threshold, which is the minimum standard for accuracy during the actual delivery of the group meal supply plan.

[0092] By setting an accuracy threshold in the verifier, it is possible to quickly determine whether the learning module needs to be adjusted, thereby further solving the problem of difficult to control food production.

[0093] Specifically, the dishes to be delivered are input into the input device, the cloud platform retrieves the cooking time, packaging time and transportation time corresponding to the dishes, the balance scheduler calculates the delivery time and transmits it to the collection module, and pre-processes the delivery time to generate pre-processed data.

[0094] Among them, the preprocessing is to standardize the delivery time.

[0095] The normalization process is to divide the delivery time into sections according to the standard sampling rate;

[0096] The standard sampling rate is the sampling rate that can be recognized by the standard time generation model, which is related to the minimum recognition ability of the standard time generation model.

[0097] Embodiment 1:

[0098] If the cooking time of a dish is 30 minutes, the boxing time is 5 minutes, and the transportation time is 60 minutes, the balanced scheduler calculates the delivery time to be 95 minutes.

[0099] By preprocessing the delivery time in the collection module, errors caused by mistakes in collecting delivery time are avoided, thereby improving the accuracy of the model learning results.

[0100] Specifically, the transmitter module receives preprocessed data and generates corresponding indicator features based on the preprocessed data, which are passed into the matcher. The standard time generation model obtains the standard delivery time corresponding to the dishes.

[0101] By using the extractor to generate indicator features for preprocessed data, we can quickly select effective features of the preprocessed data, and use the learning module to visualize the group meal supply chain, thereby further improving the accuracy of the model learning results.

[0102] Specifically, the train information module receives the train information of the train and transmits it to the planning module, the monitor receives the standard delivery time and train information, and the regulator generates a group meal supply plan.

[0103] The process of generating the group meal supply plan is to calculate the least common multiple of the standard delivery time and the train running time, and determine the delivery time of the dishes through the least common multiple to generate the group meal supply plan;

[0104] The train running time is the difference between the train's stop time and departure time.

[0105] Embodiment 2:

[0106] Train H passes through four stations, A, B, C, and D. The distance between AB is 40 minutes, the distance between BC is 50 minutes, and the distance between CD is 30 minutes. There are three kinds of dishes, E, F, and G. The delivery time of dish E is 20 minutes, the delivery time of dish F is 25 minutes, and the delivery time of dish G is 15 minutes. Assuming that train H departs from station A at 10:00, please refer to Table 1, which is the group meal supply plan for train H generated by the standard time generation model.

[0107]

[0108] Table 1

[0109] By setting up a supply planning model and learning the pre-processed data, the accuracy of group meal supply planning is improved, and the problem of being unable to trace the ingredients after delivery due to human factors is effectively solved.

[0110] Specifically, the supply planning model in the verifier verifies the group meal supply plan.

[0111] The verification process is to obtain the accuracy of the actual delivery of the group meal supply plan and compare the accuracy with the accuracy threshold.

[0112] Specifically, when the accuracy is greater than the accuracy threshold, the learning module is not adjusted; when the accuracy is less than the accuracy threshold, several indicator features and sampling rates of the learning module are adjusted.

[0113] Embodiment 3:

[0114] Assuming the accuracy threshold is 80%, if the accuracy of the group meal supply plan during actual delivery is 90%, no adjustment will be made to the learning module.

[0115] Embodiment 4:

[0116] Assume that the accuracy threshold is 80%, the indicator feature is the type of food, and the sampling rate is 10. If the accuracy of the group meal supply plan during actual delivery is 75%, the indicator feature will be reset to the cooking method and the sampling rate will be adjusted to 5.

[0117] By adjusting several indicator characteristics and sampling rates of the learning module, the intelligent and real-time regulation of the supply chain is achieved, which further avoids the problem of information lag in the food supply chain and improves the practicality of the group meal supply chain.

[0118] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The supply chain group meal management and control system based on big data is characterized by: include: The dish information module is used to collect the delivery time of each dish in the group meal; A train information module, which is used to collect train information of several trains; A collection module, which is connected to the dish information module, and is used to collect the delivery time, perform preprocessing, and generate corresponding preprocessing data; A learning module, which is connected to the collection module and is used to select several indicator features of the pre-processed data for learning, and generate a standard delivery time of dishes according to the indicator features; A planning module, which is connected to the train information module and the learning module, and is used to generate a corresponding group meal supply plan according to the standard delivery time and the train information, and adjust the standard delivery time according to the group meal supply plan; The delivery time is the sum of the cooking time, packaging time and transportation time of the dishes; The train information includes the train's stop time, departure time and / or passing cities; The preprocessed data is fitted according to the delivery time, and the group meal delivery data with a sampling rate of a standard sampling rate is generated, and corresponding indicator features are generated; The standard sampling rate is a sampling rate that can be recognized by the learning module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate. The indicator characteristics include the type of ingredients, cooking method and / or transportation method of each dish.

2. The supply chain group meal management and control system based on big data according to claim 1 is characterized in that: The dish information module includes: An input device, which is used to input the names of several dishes; A cloud platform, which is used to select the cooking time, packaging time and transportation time of the corresponding dish according to the name of the dish; A balance scheduler is connected to the input device and the cloud platform to calculate the delivery time of the dishes.

3. The supply chain group meal management and control system based on big data according to claim 2 is characterized in that: The train information module comprises: A receiver for receiving train information of a plurality of trains in a catering supply chain; The server is connected to the receiver and is used to retrieve the stop time, departure time and / or passing cities of the train according to the train information.

4. The supply chain group meal management and control system based on big data according to claim 3 is characterized in that: The learning module includes: A transmitter, configured to receive the pre-processed data; An extractor, connected to the transmitter, for extracting index features of the preprocessed data; A matcher connected to the extractor is used to learn the pre-processed data and generate a standard delivery time corresponding to the dish. Wherein, the matcher is provided with a standard time generation model; The standard time generation model is generated by training the preprocessed data.

5. The supply chain group meal management and control system based on big data according to claim 4 is characterized in that: The planning module includes: A monitor, which is used to receive the standard delivery time and the train information; A regulator, connected to the monitor, for generating the group meal supply plan according to the standard delivery time and the train information; A verifier, connected to the regulator, for verifying the group meal supply plan; Wherein, the regulator is provided with a supply planning model; The verifier is provided with an accuracy threshold, and the accuracy threshold is the minimum standard of accuracy during the actual delivery of the group meal supply plan.

6. The supply chain group meal management and control system based on big data according to claim 5 is characterized in that: The dishes to be delivered are input into the input device, the cloud platform retrieves the cooking time, boxing time and transportation time corresponding to the dishes, the balance scheduler calculates the delivery time and transmits it to the collection module, and pre-processes the delivery time to generate the pre-processed data. The pre-processing is to standardize the delivery time. The standardization process is to divide the delivery time according to a standard sampling rate; The standard sampling rate is a sampling rate that can be recognized by the standard time generation model, and is related to the minimum recognition capability of the standard time generation model.

7. The supply chain group meal management and control system based on big data according to claim 6 is characterized in that: The transmitter module receives the preprocessed data, generates corresponding indicator features based on the preprocessed data, and transmits the features to the matcher. The standard time generation model obtains the standard delivery time corresponding to the dish.

8. The supply chain group meal management and control system based on big data according to claim 7 is characterized in that: The train information module receives the train information of the train and transmits it to the planning module, the monitor receives the standard delivery time and the train information, and the regulator generates the group meal supply plan. The process of generating the group meal supply plan is to calculate the least common multiple of the standard delivery time and the train running time, and determine the delivery time of the dishes by the least common multiple to generate the group meal supply plan; The train running time is the difference between the train's stop time and departure time.

9. The supply chain group meal management and control system based on big data according to claim 8 is characterized in that: The supply plan model in the verifier verifies the group meal supply plan, The verification process is to obtain the accuracy of the group meal supply plan during actual delivery, and compare the accuracy with the accuracy threshold.

10. The supply chain group meal management and control system based on big data according to claim 9 is characterized in that: When the accuracy rate is greater than the accuracy rate threshold, the learning module is not adjusted; when the accuracy rate is less than the accuracy rate threshold, several indicator features and sampling rate of the learning module are adjusted.

Images