CN116777684A - Intelligent canteen management method and system based on digital twinning - Google Patents

Intelligent canteen management method and system based on digital twinning Download PDF

Info

Publication number
CN116777684A
CN116777684A CN202311058862.5A CN202311058862A CN116777684A CN 116777684 A CN116777684 A CN 116777684A CN 202311058862 A CN202311058862 A CN 202311058862A CN 116777684 A CN116777684 A CN 116777684A
Authority
CN
China
Prior art keywords
dining
canteen
model
online
people
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311058862.5A
Other languages
Chinese (zh)
Other versions
CN116777684B (en
Inventor
徐林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Senxunda Intelligent Technology Co ltd
Original Assignee
Jiangsu Senxunda Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Senxunda Intelligent Technology Co ltd filed Critical Jiangsu Senxunda Intelligent Technology Co ltd
Priority to CN202311058862.5A priority Critical patent/CN116777684B/en
Priority to CN202311418171.1A priority patent/CN117474719A/en
Priority to CN202311417324.0A priority patent/CN117474718A/en
Publication of CN116777684A publication Critical patent/CN116777684A/en
Application granted granted Critical
Publication of CN116777684B publication Critical patent/CN116777684B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/12—Hotels or restaurants
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects

Abstract

The invention discloses a digital twinning-based intelligent canteen management method and a digital twinning-based intelligent canteen management system, wherein the method comprises the following steps: establishing a three-dimensional digital model by utilizing a digital twin technology; constructing an online booking platform and a corresponding background management system; designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of online dining users; predicting the flow of people for dining in the dining room in a future time period by using a long-short-term memory network model, and comprehensively estimating the number of people for dining in the dining room by combining the flow of people for dining in the dining room with the number of on-line scheduled people; comparing the actual dining number of the dining room with the estimated dining number of the dining room, and dynamically adjusting a catering plan in the dining room based on the comparison result; and respectively collecting and integrating evaluation feedback of the online dining user and the dining user of the dining hall, and adjusting the management strategy of the dining hall based on the integrated evaluation feedback. According to the invention, by establishing the three-dimensional digital model, the virtual presentation of the whole space of the canteen is realized.

Description

Intelligent canteen management method and system based on digital twinning
Technical Field
The invention relates to the technical field of canteen management, in particular to a digital twinning-based intelligent canteen management method and system.
Background
The dining hall is a place for supplying dining service, is commonly used in institutions such as schools, factories, office buildings and hospitals, and provides various dining options such as breakfast, lunch, dinner, snacks and beverages, and the main purpose of the dining hall is to provide convenient, quick and economical dining service, so that the nutritional requirements of dinners are met, and service objects are typically staff, students, teaching staff, visitors and the like in the institutions.
The dining room usually adopts buffet form, and the dining person can select the components of dish and food by oneself according to individual taste and eating habit, and dining room management's aim is to provide high quality, safety, health and diversified food choice, satisfies user's demand, and scientific management and operation can ensure that the dining room provides the food service that accords with user's taste, promotes staff and student's physical and mental health, improves work and learning efficiency.
In the intelligent canteen management method, predicting the canteen people flow and preparing meals in advance is an effective strategy, however, a certain deviation may exist between the estimated number of people and the actual canteen dining number, if the estimated number of people is more and the actual dining number of people is less, the food waste is caused, the cost is increased, unnecessary burden is caused to the environment, and if the estimated number of people is less and the actual dining number of people is more, the supply shortage is caused, and the dining user experience is affected. Therefore, it is extremely important to introduce a quick response mechanism in the intelligent canteen management method and to formulate a flexible meal allocation plan adjustment strategy to adapt to the abnormally increased demands of the number of dining persons under special conditions.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a digital twinning-based intelligent canteen management method and system, which are used for overcoming the technical problems existing in the related art.
For this purpose, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided a digital twinning-based intelligent canteen management method, comprising the steps of:
s1, acquiring internal environment data of a canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model;
s2, an online booking platform and a corresponding background management system are built, and booking information of online dining users and dining data of dining halls are processed by using the online booking platform;
s3, designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user;
s4, predicting the flow of people for dining in the dining room in a future time period by using the long-short-period memory network model, combining the flow with the on-line scheduled number of people, and comprehensively estimating the number of people for dining in the dining room;
S5, comparing the actual dining room number with the estimated dining room number, and dynamically adjusting a catering plan in the dining room based on the comparison result;
s6, respectively collecting and integrating evaluation feedback of the on-line dining users and the dining room dining users, and adjusting a dining room management strategy based on the integrated evaluation feedback.
Furthermore, the method for acquiring the internal environment data of the canteen and establishing a three-dimensional digital model by utilizing a digital twin technology to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model comprises the following steps:
s11, deploying sensors and monitoring equipment in the canteen, and collecting environmental data in the canteen, wherein the environmental data at least comprises canteen layout and facilities, people flow data, food data, environmental parameters and personnel information in the canteen;
s12, creating a three-dimensional digital model matched with the environmental data by utilizing a digital twin technology, and setting attributes for each digital entity in the three-dimensional digital model;
s13, defining a behavior rule for each digital entity, and ensuring that each digital entity executes corresponding behaviors according to the current environment and state;
s14, acquiring environment data in the canteen in real time and synchronizing the environment data into the three-dimensional digital model, and updating the behavior rule of the digital entity according to the real-time data to ensure the synchronization and response of the three-dimensional digital model and the entity canteen.
Further, the design and integration of collaborative filtering models into an online booking platform, and recommending dishes according to the preference of online dining users, comprises the following steps:
s31, collecting dining data of online dining users from an online booking platform, wherein the dining data at least comprises online dining user IDs, dish IDs and dining time;
s32, converting the meal data into binary feature vector representation, constructing a limited Boltzmann machine model according to the converted feature vector, and representing corresponding dish features by a visible layer in the limited Boltzmann machine model, wherein the hidden layer represents preference features of the on-line meal user;
s33, initializing parameters of a limited Boltzmann machine model, and training the limited Boltzmann machine model by using a contrast divergence algorithm;
s34, integrating the trained limited Boltzmann machine model into an online booking platform, when the online dining user performs dish booking, taking the preference characteristics of the online dining user as the input of a visible layer, calculating the activation probability of a hidden layer through the limited Boltzmann machine model, and taking the calculation result as the preference characteristics of the online dining user to represent;
s35, recommending dishes based on the preference characteristic representation of the online dining user, and predicting the matching degree of the recommended dishes and the preference characteristic representation of the online dining user, so as to recommend dishes with high matching degree.
Further, the initializing parameters of the restricted boltzmann machine model and training the restricted boltzmann machine model by using a contrast divergence algorithm comprises the following steps:
s331, initializing parameters of a limited Boltzmann machine model, wherein the parameters of the limited Boltzmann machine model comprise a weight matrix, a visible layer bias item and a hidden layer bias item;
s332, forward deducing in a limited Boltzmann machine model by using initialized parameters, inputting the original visible layer data into the limited Boltzmann machine model, and calculating the activation probability of the hidden layer;
s333, taking the activation probability of the hidden layer as input, and calculating the activation probability of the visible layer to obtain the reconstructed visible layer data;
s334, calculating the difference between the original visible layer data and the reconstructed visible layer data, and taking the calculation result as the measurement of contrast divergence;
s335, updating parameters of the limited Boltzmann machine model by using a contrast divergence algorithm, and repeating the steps S332-S334 until an error convergence condition is reached.
Further, the expression of the activation probability of the hidden layer is:
in the method, in the process of the invention,i，jall represent node numbers;
representing the visible layerjObservation values of the individual nodes;
Representing the first hidden layeriBias terms for the individual nodes;
representing the first hidden layeriAn activation state of the individual nodes;
Prepresenting activation probability of hidden layer nodes;
representationsigmoidA function;
mrepresenting the expected value of the visible layer;
indicating the first of the hidden layersiThe individual nodejWeights between individual nodes.
Further, the method for predicting the flow of people eating in the dining room in the future time period by using the long-short-term memory network model and combining the flow of people eating in the dining room with the on-line scheduled number of people, and comprehensively estimating the number of people eating in the dining room comprises the following steps:
s41, collecting dining room dining data in a historical time period, wherein the dining data in the historical time period comprises dining dates, dining time, dining number, dining peak time and average dining number;
s42, sorting according to the dining date and the dining time in a time sequence, combining the dining numbers in the same time period to obtain the total dining number of each time period, and forming time sequence data by the dining date of each time period and the corresponding total dining number;
s43, constructing a long-period memory network model based on the time sequence data, and predicting the flow of people eating in the canteen in a future time period by using the long-period memory network model;
S44, subtracting the preset number of people on the reservation platform of the same day from the people flow of dining in the dining room in the future time period, and estimating the number of dining in the dining room;
s45, predicting the dining demand according to the estimated dining number of the dining hall, and preparing the meal in advance according to the dining demand.
Further, the constructing a long-term memory network model based on the time sequence data, and predicting the flow of people having dinner in the dining room in a future time period by using the long-term memory network model comprises the following steps:
s431, defining an input layer and an output layer of a long-short-period memory network model, setting the input layer as the flow of people eating in the canteen in a historical time period, and setting the output layer as the flow of people eating in the canteen in a future time period;
s432, removing invalid data from the neuron state by using a forgetting gate, and reserving valid data related to prediction;
s433, determining the update degree of the neuron state by using an input gate, and outputting a value in a preset range by combining the neuron state at the current moment and the neuron state at the last moment through a tanh activation function;
s434, determining a part to be output in the neuron state at the current moment by using an output gate, multiplying the neuron state converted by the tanh function by the output value of the output gate to obtain a final output result, and taking the output result as the flow of people eating in the canteen in a future time period.
Further, the determining the update degree of the neuron state by using the input gate, and combining the neuron state at the current moment and the neuron state at the last moment to output a value in a preset range through the tanh activation function includes the following steps:
s4331, calculating the state of the neuron at the current moment and the state of the neuron at the last moment by using an input gate, combining the state with the input at the current moment, and mapping the output to a value in a preset range through a tanh activation function to obtain a candidate value of the current state;
s4332, calculating the weight input at the current moment, and outputting a value between 0 and 1 by using a sigmoid activation function as an input door weight value at the current moment;
s4333, multiplying the neuron state at the previous moment by the amnestic gate to obtain the neuron state to be reserved;
s4334, multiplying the current state candidate value by the input gate weight value and adding the current state candidate value and the neuron state to be reserved to obtain the final neuron state at the current moment.
Further, the comparing the actual dining room number with the estimated dining room number, and dynamically adjusting the catering plan in the dining room based on the comparison result comprises the following steps:
S51, acquiring the actual dining number of the dining room by using a sensor and monitoring equipment, and comparing the actual dining number of the dining room with the estimated dining number of the dining room;
s52, if the estimated dining room number is lower than the actual dining room number, judging that the number of people is too small, and increasing the catering amount;
and S53, judging that the number of dining rooms is more or less if the estimated dining room number is higher than the actual dining room number, and reducing the catering amount.
According to another aspect of the invention, there is further provided a digital twinning-based intelligent canteen management system, which comprises a three-dimensional digital model construction module, an online booking platform construction module, a collaborative filtering model integration module, a people flow prediction module, a meal allocation plan adjustment module and a canteen management strategy adjustment module;
the three-dimensional digital model building module is connected with the online booking platform building module, the online booking platform building module is connected with the collaborative filtering model integration module, the collaborative filtering model integration module is connected with the people flow prediction module, the people flow prediction module is connected with the meal allocation plan adjustment module, and the meal allocation plan adjustment module is connected with the canteen management strategy adjustment module;
The three-dimensional digital model construction module is used for collecting internal environment data of the canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology so as to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model;
the online booking platform construction module is used for constructing an online booking platform and a corresponding background management system, and processing booking information of online dining users and recording dining data of dining halls by utilizing the online booking platform;
the collaborative filtering model integration module is used for designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user;
the people flow prediction module is used for predicting the people flow of dining in the dining room in a future time period by using the long-short-period memory network model and comprehensively estimating the number of dining in the dining room by combining the people flow with the on-line scheduled number of people;
the meal allocation plan adjustment module is used for comparing the actual dining room number with the estimated dining room number and dynamically adjusting the meal allocation plan in the dining room based on the comparison result;
and the canteen management strategy adjustment module is used for respectively collecting and integrating evaluation feedback of the online dining user and the canteen dining user and adjusting the canteen management strategy based on the integrated evaluation feedback.
The beneficial effects of the invention are as follows:
1. the invention realizes virtual presentation of the whole space of the canteen by establishing the three-dimensional digital model, can simulate and test various layout schemes on the digital platform, optimizes dining environment, can reflect the running state of the entity canteen at any time by synchronizing the real-time data of the sensor and the model, realizes monitoring of food material storage, equipment running and the like, can evaluate the operation management scheme under various conditions based on the digital twin technology, and improves the decision-making efficiency and accuracy.
2. According to the invention, dishes can be recommended according to the preference of the on-line dining users, so that personalized dish recommendation is realized, the sales of dishes is promoted, the dishes which are possibly interested are displayed to the dining users through accurate recommendation, more dishes are driven to be sold, the menu combination and recommendation are designed according to preference bias of different dining user groups, the tastes of different dining users are more met, and the cost is controlled while the sales of the dishes is increased.
3. According to the invention, the actual dining number is compared with the estimated dining number, so that the catering plan can be adjusted in time, the accuracy of food material purchase and diet supply is improved, the food material waste or supply shortage caused by estimation errors is reduced, the types, the quantity and the like of dishes are flexibly adjusted according to the actual consumption condition, the actual requirements of consumers are met, the estimated accuracy of the future number is improved through the estimation model, the coping capability of the dining hall to emergency conditions is enhanced, if the dining number is abnormally increased or reduced due to special conditions, the fast response can be realized, and powerful data support is provided for intelligent and fine management of the dining hall.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a digital twinning-based intelligent canteen management method according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a digital twinning-based intelligent canteen management system according to an embodiment of the present invention.
In the figure:
1. the three-dimensional digital model building module; 2. an online booking platform construction module; 3. a collaborative filtering model integration module; 4. a traffic prediction module; 5. a meal allocation plan adjustment module; 6. and the canteen management strategy adjustment module.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used for illustrating the embodiments and for explaining the principles of the operation of the embodiments in conjunction with the description thereof, and with reference to these matters, it will be apparent to those skilled in the art to which the present invention pertains that other possible embodiments and advantages of the present invention may be practiced.
According to the embodiment of the invention, a digital twinning-based intelligent canteen management method and system are provided.
The invention will now be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a digital twin-based intelligent canteen management method according to an embodiment of the invention, the method comprising the steps of:
s1, acquiring internal environment data of the canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model.
The method for acquiring the internal environment data of the canteen and establishing a three-dimensional digital model by utilizing a digital twin technology, and realizing real-time synchronization and response of the entity canteen and the three-dimensional digital model comprises the following steps:
s11, deploying sensors and monitoring equipment in the canteen, and collecting environmental data in the canteen, wherein the environmental data at least comprises canteen layout and facilities, people flow data, food data, environmental parameters and personnel information in the canteen;
s12, creating a three-dimensional digital model matched with the environment data by utilizing a digital twin technology, and setting attributes for each digital entity in the three-dimensional digital model.
In particular, digital twinning is a technique that digitizes a physical object, system, or process, simulating and analyzing its behavior and performance by building virtual copies of the physical world. The real-time data and the digital model are interacted and integrated by using the sensor, data acquisition and modeling technology, so that the monitoring, analysis and optimization of the entity are realized.
S13, defining a behavior rule for each digital entity, and ensuring that each digital entity executes corresponding behaviors according to the current environment and state;
s14, acquiring environment data in the canteen in real time and synchronizing the environment data into the three-dimensional digital model, and updating the behavior rule of the digital entity according to the real-time data to ensure the synchronization and response of the three-dimensional digital model and the entity canteen.
S2, an online booking platform and a corresponding background management system are built, and booking information of online dining users and dining data of dining halls are processed by the online booking platform.
Specifically, the on-line subscription platform and the corresponding background management system are constructed mainly by the following aspects:
the front-end interface of the online booking platform comprises pages of user registration login, menu browsing, booking order, payment, evaluation and the like, ensures that dining users can conveniently operate booking flows, and particularly can use HTML, CSS and JavaScript technology to carry out front-end development of webpages.
The back-end logic of the online booking platform is developed, including user authentication, menu management, order processing, payment interfaces and the like, so that correct processing and interaction of data are ensured, and various back-end development languages and frameworks, such as Django or flash of Python and Spring of Java, can be used.
A relational database (e.g., mySQL, postgreSQL, oracle) or a non-relational database (e.g., mongoDB, redis) is used to store user information, menus, orders, etc.
And testing the online booking platform and the background management system to ensure the normal operation of functions and dining user experience.
S3, designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user.
The collaborative filtering model is designed and integrated into an online booking platform, and the recommending of dishes according to the preference of an online dining user comprises the following steps:
s31, collecting dining data of online dining users from an online booking platform, wherein the dining data at least comprises online dining user IDs, dish IDs and dining time;
s32, converting the meal data into binary feature vector representation, constructing a limited Boltzmann machine model according to the converted feature vector, and representing corresponding dish features by a visible layer in the limited Boltzmann machine model, wherein the hidden layer represents preference features of the on-line meal user;
And S33, initializing parameters of the limited Boltzmann machine model, and training the limited Boltzmann machine model by using a contrast divergence algorithm.
Wherein initializing parameters of the restricted boltzmann machine model and training the restricted boltzmann machine model with a contrast divergence algorithm comprises the steps of:
s331, initializing parameters of a limited Boltzmann machine model, wherein the parameters of the limited Boltzmann machine model comprise a weight matrix, a visible layer bias item and a hidden layer bias item;
s332, forward deducing in the limited Boltzmann machine model by using the initialized parameters, inputting the original visible layer data into the limited Boltzmann machine model, and calculating the activation probability of the hidden layer.
The expression of the activation probability of the hidden layer is as follows:
in the method, in the process of the invention,i，jall represent node numbers;
representing the visible layerjObservation values of the individual nodes;
representing the first hidden layeriBias terms for the individual nodes;
representing the first hidden layeriAn activation state of the individual nodes;
Prepresenting activation probability of hidden layer nodes;
representationsigmoidA function;
mrepresenting the expected value of the visible layer;
indicating the first of the hidden layersiThe individual nodejWeights between individual nodes.
S333, taking the activation probability of the hidden layer as input, and calculating the activation probability of the visible layer to obtain the reconstructed visible layer data;
S334, calculating the difference between the original visible layer data and the reconstructed visible layer data, and taking the calculation result as the measurement of contrast divergence;
s335, updating parameters of the limited Boltzmann machine model by using a contrast divergence algorithm, and repeating the steps S332-S334 until an error convergence condition is reached.
S34, integrating the trained limited Boltzmann machine model into an online booking platform, when the online dining user performs dish booking, taking the preference characteristics of the online dining user as the input of a visible layer, calculating the activation probability of a hidden layer through the limited Boltzmann machine model, and taking the calculation result as the preference characteristics of the online dining user to represent;
s35, recommending dishes based on the preference characteristic representation of the online dining user, and predicting the matching degree of the recommended dishes and the preference characteristic representation of the online dining user, so as to recommend dishes with high matching degree.
In particular, the limited boltzmann machine (Restricted Boltzmann Machine, RBM) is a probabilistic generative model that belongs to an unsupervised learning algorithm. The RBM is composed of a visible layer and a hidden layer, and the nodes between the layers are fully connected, but there is no connection between the nodes within the layers.
The nodes of the RBM can be binary (with the value of 0 or 1) or continuous, the training process mainly learns the parameters of the model through maximum likelihood estimation, the RBM aims at learning a probability distribution model capable of maximizing training data, the RBM can be used for tasks such as feature learning, dimension reduction, collaborative filtering and the like, and in the feature learning, the RBM can extract useful feature representations through the potential features of the learning data; in the dimension reduction, the RBM can realize the dimension reduction of the data through the compressed representation of the hidden layer node; in collaborative filtering, RBMs may make recommendations by learning implicit preferences of users for items.
S4, predicting the flow of people eating in the canteen in a future time period by using the long-short-period memory network model, combining the flow with the on-line scheduled number of people, and comprehensively estimating the number of people eating in the canteen.
The method for comprehensively estimating the dining room number of the dining room by using the long-short-term memory network model to predict the flow of people in the dining room in a future time period and combining the flow of people with the online preset number of people comprises the following steps:
s41, collecting dining room dining data in a historical time period, wherein the dining data in the historical time period comprises dining dates, dining time, dining number, dining peak time and average dining number;
S42, sorting according to the dining date and the dining time in a time sequence, combining the dining numbers in the same time period to obtain the total dining number of each time period, and forming time sequence data by the dining date of each time period and the corresponding total dining number;
s43, constructing a long-period memory network model based on the time sequence data, and predicting the flow of people eating in the canteen in a future time period by using the long-period memory network model.
Specifically, long Short-Term Memory (LSTM) is a recurrent neural network (Recurrent Neural Network, RNN) model for modeling and prediction of processing sequence data and time-series data. The LSTM cell contains three key gates inside: an input gate (input gate), a forget gate (for gate), and an output gate (output gate). These gates control the flow of information by learning parameters, enabling the LSTM to selectively remember or forget past information, and generate output based on current inputs.
The method for constructing the long-period memory network model based on the time sequence data and predicting the flow of people eating in the dining room in the future time period by using the long-period memory network model comprises the following steps:
S431, defining an input layer and an output layer of a long-short-period memory network model, setting the input layer as the flow of people eating in the canteen in a historical time period, and setting the output layer as the flow of people eating in the canteen in a future time period;
s432, removing invalid data from the neuron state by using a forgetting gate, and reserving valid data related to prediction;
s433, determining the update degree of the neuron state by using the input gate, and combining the neuron state at the current moment and the neuron state at the last moment to output a value in a preset range through the tanh activation function.
The method for determining the update degree of the neuron state by using the input gate and combining the neuron state at the current moment and the neuron state at the last moment to output a value in a preset range through the tanh activation function comprises the following steps:
s4331, calculating the state of the neuron at the current moment and the state of the neuron at the last moment by using an input gate, combining the state with the input at the current moment, and mapping the output to a value in a preset range through a tanh activation function to obtain a candidate value of the current state. Specifically, the preset range is [ -1,1].
Specifically, the tanh activation function is a nonlinear activation function that maps output values between the ranges [ -1,1].
S4332, calculating the weight input at the current moment, and outputting a value between 0 and 1 by using a sigmoid activation function as an input gate weight value at the current moment.
Specifically, the sigmoid activation function is a nonlinear activation function that maps input values between ranges [0,1 ].
S4333, multiplying the neuron state at the previous moment by the amnestic gate to obtain the neuron state to be reserved;
s4334, multiplying the current state candidate value by the input gate weight value and adding the current state candidate value and the neuron state to be reserved to obtain the final neuron state at the current moment.
S434, determining a part to be output in the neuron state at the current moment by using an output gate, multiplying the neuron state converted by the tanh function by the output value of the output gate to obtain a final output result, and taking the output result as the flow of people eating in the canteen in a future time period.
S44, subtracting the preset number of people on the reservation platform of the same day from the people flow of dining in the dining room in the future time period, and estimating the number of dining in the dining room;
s45, predicting the dining demand according to the estimated dining number of the dining hall, and preparing the meal in advance according to the dining demand.
S5, comparing the actual dining room number with the estimated dining room number, and dynamically adjusting the catering plan in the dining room based on the comparison result.
The method for dynamically adjusting the catering plan in the canteen based on the comparison result comprises the following steps of:
s51, acquiring the actual dining number of the dining room by using a sensor and monitoring equipment, and comparing the actual dining number of the dining room with the estimated dining number of the dining room;
s52, if the estimated dining room number is lower than the actual dining room number, judging that the number of people is too small, and increasing the catering amount.
Specifically, when the situation of 'people have few dishes' occurs, the following meal plan can be adopted:
the meal preparation amount is reduced: the purchasing quantity of food materials is reduced or the quantity of dishes is reduced, so that the waste of the food materials is avoided.
Providing a promotional program: pushing out preferential activities, packages or discounts, and attracting more dining users to visit the canteen.
And S53, judging that the number of dining rooms is more or less if the estimated dining room number is higher than the actual dining room number, and reducing the catering amount.
Specifically, when the situation of more people and less dishes occurs, the following meal allocation plan can be adopted:
increasing the meal preparation amount: the food material purchasing quantity is increased or the dish quantity is increased so as to meet the demands of more dining users.
Adjusting the types of dishes: increasing the variety of hot-sell dishes or popular dishes attracts more dining users to select.
The service speed is quickened: the number of caterers is increased, the dish making and feeding speed is increased, and the waiting time of dining users is shortened.
S6, respectively collecting and integrating evaluation feedback of the on-line dining users and the dining room dining users, and adjusting a dining room management strategy based on the integrated evaluation feedback.
Specifically, the collected evaluation feedback is integrated and classified, and common problems, complaints, suggestions, surface and other contents are arranged according to the subject and the content of the evaluation, and the frequency and the proportion of different opinions are counted.
And (3) carrying out deep analysis on the integrated evaluation feedback, searching for commonalities and problem points, knowing the evaluation of dining users on aspects of canteen food quality, service level, environmental sanitation and the like, and finding out the pain points and the improvement space.
And (3) according to the analysis result, a corresponding improvement strategy is formulated, a solution is found aiming at the problem point in the feedback of the dining user, and the aim and measures of improvement are definitely achieved. The method specifically comprises improvement measures in aspects of adjusting the types of dishes, optimizing the food manufacturing process, improving the service quality, improving the dining environment and the like.
As shown in fig. 2, according to another embodiment of the present invention, there is further provided a digital twin-based intelligent canteen management system, which includes a three-dimensional digital model building module 1, an online booking platform building module 2, a collaborative filtering model integrating module 3, a people flow prediction module 4, a catering plan adjusting module 5 and a canteen management policy adjusting module 6;
the three-dimensional digital model building module 1 is connected with the online booking platform building module 2, the online booking platform building module 2 is connected with the collaborative filtering model integration module 3, the collaborative filtering model integration module 3 is connected with the people flow prediction module 4, the people flow prediction module 4 is connected with the meal allocation plan adjustment module 5, and the meal allocation plan adjustment module 5 is connected with the canteen management strategy adjustment module 6;
the three-dimensional digital model construction module 1 is used for collecting internal environment data of the canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology so as to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model;
the online booking platform construction module 2 is used for constructing an online booking platform and a corresponding background management system, and processing booking information of online dining users and recording dining data of dining halls by utilizing the online booking platform;
The collaborative filtering model integration module 3 is used for designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user;
the people flow prediction module 4 is used for predicting the people flow of dining in the dining room in a future time period by utilizing the long-short-period memory network model and comprehensively estimating the number of dining in the dining room by combining the people flow with the on-line scheduled number of people;
the meal allocation plan adjustment module 5 is used for comparing the actual dining number of the dining hall with the estimated dining number of the dining hall, and dynamically adjusting the meal allocation plan in the dining hall based on the comparison result;
and the canteen management policy adjustment module 6 is used for respectively collecting and integrating evaluation feedback of the online dining user and the canteen dining user, and adjusting the canteen management policy based on the integrated evaluation feedback.
In summary, by means of the technical scheme, the invention realizes virtual presentation of the whole space of the dining room by establishing the three-dimensional digital model, can simulate and test various layout schemes on the digital platform, optimizes dining environment, can reflect the running state of the entity dining room at any time by synchronizing the real-time data of the sensor and the model, realizes monitoring of food storage, equipment running and the like, can evaluate the operation management scheme under various conditions based on the digital twin technology, and improves the decision-making efficiency and accuracy.
According to the invention, dishes can be recommended according to the preference of the on-line dining users, so that personalized dish recommendation is realized, the sales of dishes is promoted, the dishes which are possibly interested are displayed to the dining users through accurate recommendation, more dishes are driven to be sold, the menu combination and recommendation are designed according to preference bias of different dining user groups, the tastes of different dining users are more met, and the cost is controlled while the sales of the dishes is increased.
According to the invention, the actual dining number is compared with the estimated dining number, so that the catering plan can be adjusted in time, the accuracy of food material purchase and diet supply is improved, the food material waste or supply shortage caused by estimation errors is reduced, the types, the quantity and the like of dishes are flexibly adjusted according to the actual consumption condition, the actual requirements of consumers are met, the estimated accuracy of the future number is improved through the estimation model, the coping capability of the dining hall to emergency conditions is enhanced, if the dining number is abnormally increased or reduced due to special conditions, the fast response can be realized, and powerful data support is provided for intelligent and fine management of the dining hall.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (10)

1. The intelligent canteen management method based on digital twinning is characterized by comprising the following steps:
s1, acquiring internal environment data of a canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model;
s2, an online booking platform and a corresponding background management system are built, and booking information of online dining users and dining data of dining halls are processed by using the online booking platform;
s3, designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user;
s4, predicting the flow of people for dining in the dining room in a future time period by using the long-short-period memory network model, combining the flow with the on-line scheduled number of people, and comprehensively estimating the number of people for dining in the dining room;
s5, comparing the actual dining room number with the estimated dining room number, and dynamically adjusting a catering plan in the dining room based on the comparison result;
s6, respectively collecting and integrating evaluation feedback of the on-line dining users and the dining room dining users, and adjusting a dining room management strategy based on the integrated evaluation feedback.
2. The intelligent canteen management method based on digital twinning according to claim 1, wherein the steps of collecting the internal environment data of the canteen, establishing a three-dimensional digital model by using a digital twinning technology, and realizing real-time synchronization and response of the entity canteen and the three-dimensional digital model comprise the following steps:
S11, deploying sensors and monitoring equipment in the canteen, and collecting environmental data in the canteen, wherein the environmental data at least comprises canteen layout and facilities, people flow data, food data, environmental parameters and personnel information in the canteen;
s12, creating a three-dimensional digital model matched with the environmental data by utilizing a digital twin technology, and setting attributes for each digital entity in the three-dimensional digital model;
s13, defining a behavior rule for each digital entity, and ensuring that each digital entity executes corresponding behaviors according to the current environment and state;
s14, acquiring environment data in the canteen in real time and synchronizing the environment data into the three-dimensional digital model, and updating the behavior rule of the digital entity according to the real-time data to ensure the synchronization and response of the three-dimensional digital model and the entity canteen.
3. The digital twinning-based intelligent canteen management method according to claim 1, wherein the designing and integrating collaborative filtering model into an online booking platform, recommending dishes according to preference of an online dining user comprises the steps of:
s31, collecting dining data of online dining users from an online booking platform, wherein the dining data at least comprises online dining user IDs, dish IDs and dining time;
S32, converting the meal data into binary feature vector representation, constructing a limited Boltzmann machine model according to the converted feature vector, and representing corresponding dish features by a visible layer in the limited Boltzmann machine model, wherein the hidden layer represents preference features of the on-line meal user;
s33, initializing parameters of a limited Boltzmann machine model, and training the limited Boltzmann machine model by using a contrast divergence algorithm;
s34, integrating the trained limited Boltzmann machine model into an online booking platform, when the online dining user performs dish booking, taking the preference characteristics of the online dining user as the input of a visible layer, calculating the activation probability of a hidden layer through the limited Boltzmann machine model, and taking the calculation result as the preference characteristics of the online dining user to represent;
s35, recommending dishes based on the preference characteristic representation of the online dining user, and predicting the matching degree of the recommended dishes and the preference characteristic representation of the online dining user, so as to recommend dishes with high matching degree.
4. A digital twinning-based intelligent canteen management method according to claim 3, characterized in that the initializing parameters of the restricted boltzmann machine model and training the restricted boltzmann machine model with a contrast divergence algorithm comprises the steps of:
S331, initializing parameters of a limited Boltzmann machine model, wherein the parameters of the limited Boltzmann machine model comprise a weight matrix, a visible layer bias item and a hidden layer bias item;
s332, forward deducing in a limited Boltzmann machine model by using initialized parameters, inputting the original visible layer data into the limited Boltzmann machine model, and calculating the activation probability of the hidden layer;
s333, taking the activation probability of the hidden layer as input, and calculating the activation probability of the visible layer to obtain the reconstructed visible layer data;
s334, calculating the difference between the original visible layer data and the reconstructed visible layer data, and taking the calculation result as the measurement of contrast divergence;
s335, updating parameters of the limited Boltzmann machine model by using a contrast divergence algorithm, and repeating the steps S332-S334 until an error convergence condition is reached.
5. The digital twinning-based intelligent canteen management method according to claim 4, wherein the expression of the activation probability of the hidden layer is:
in the method, in the process of the invention,i，jall represent node numbers;
representing the visible layerjObservation values of the individual nodes;
representing the first hidden layeriBias terms for the individual nodes;
representing the first hidden layer iAn activation state of the individual nodes;
Prepresenting activation probability of hidden layer nodes;
representationsigmoidA function;
mrepresenting the expected value of the visible layer;
indicating the first of the hidden layersiThe individual nodejWeights between individual nodes.
6. The intelligent dining room management method based on digital twinning according to claim 1, wherein the predicting the flow of people for dining room to take dinner in a future time period by using a long-short-term memory network model and combining with the on-line scheduled number of people, the comprehensively estimating the number of people for dining room to take dinner comprises the following steps:
s41, collecting dining room dining data in a historical time period, wherein the dining data in the historical time period comprises dining dates, dining time, dining number, dining peak time and average dining number;
s42, sorting according to the dining date and the dining time in a time sequence, combining the dining numbers in the same time period to obtain the total dining number of each time period, and forming time sequence data by the dining date of each time period and the corresponding total dining number;
s43, constructing a long-period memory network model based on the time sequence data, and predicting the flow of people eating in the canteen in a future time period by using the long-period memory network model;
S44, subtracting the preset number of people on the reservation platform of the same day from the people flow of dining in the dining room in the future time period, and estimating the number of dining in the dining room;
s45, predicting the dining demand according to the estimated dining number of the dining hall, and preparing the meal in advance according to the dining demand.
7. The digital twin-based intelligent canteen management method according to claim 6, wherein the constructing a long-short-term memory network model based on time series data and predicting the flow of people eating a canteen in a future time period by using the long-short-term memory network model comprises the steps of:
s431, defining an input layer and an output layer of a long-short-period memory network model, setting the input layer as the flow of people eating in the canteen in a historical time period, and setting the output layer as the flow of people eating in the canteen in a future time period;
s432, removing invalid data from the neuron state by using a forgetting gate, and reserving valid data related to prediction;
s433, determining the update degree of the neuron state by using an input gate, and outputting a value in a preset range by combining the neuron state at the current moment and the neuron state at the last moment through a tanh activation function;
s434, determining a part to be output in the neuron state at the current moment by using an output gate, multiplying the neuron state converted by the tanh function by the output value of the output gate to obtain a final output result, and taking the output result as the flow of people eating in the canteen in a future time period.
8. The intelligent canteen management method based on digital twinning according to claim 7, wherein the determining the update degree of the neuron state by using the input gate and combining the neuron state at the current time and the neuron state output at the previous time by using the tanh activation function to output the value within the preset range includes the steps of:
s4331, calculating the state of the neuron at the current moment and the state of the neuron at the last moment by using an input gate, combining the state with the input at the current moment, and mapping the output to a value in a preset range through a tanh activation function to obtain a candidate value of the current state;
s4332, calculating the weight input at the current moment, and outputting a value between 0 and 1 by using a sigmoid activation function as an input door weight value at the current moment;
s4333, multiplying the neuron state at the previous moment by the amnestic gate to obtain the neuron state to be reserved;
s4334, multiplying the current state candidate value by the input gate weight value and adding the current state candidate value and the neuron state to be reserved to obtain the final neuron state at the current moment.
9. The intelligent dining room management method based on digital twinning according to claim 8, wherein the comparing the actual dining room number with the estimated dining room number and dynamically adjusting the catering plan in the dining room based on the comparison result comprises the following steps:
S51, acquiring the actual dining number of the dining room by using a sensor and monitoring equipment, and comparing the actual dining number of the dining room with the estimated dining number of the dining room;
s52, if the estimated dining room number is lower than the actual dining room number, judging that the number of people is too small, and increasing the catering amount;
and S53, judging that the number of dining rooms is more or less if the estimated dining room number is higher than the actual dining room number, and reducing the catering amount.
10. A digital twin-based intelligent canteen management system for implementing the digital twin-based intelligent canteen management method of any one of claims 1-9, characterized in that the system comprises a three-dimensional digital model building module, an online booking platform building module, a collaborative filtering model integration module, a people flow prediction module, a catering plan adjustment module and a canteen management strategy adjustment module;
the three-dimensional digital model building module is connected with the online booking platform building module, the online booking platform building module is connected with the collaborative filtering model integration module, the collaborative filtering model integration module is connected with the people flow prediction module, the people flow prediction module is connected with the meal allocation plan adjustment module, and the meal allocation plan adjustment module is connected with the canteen management strategy adjustment module;
The three-dimensional digital model construction module is used for collecting internal environment data of the canteen, and establishing a three-dimensional digital model by utilizing a digital twin technology so as to realize real-time synchronization and response of the entity canteen and the three-dimensional digital model;
the online booking platform construction module is used for constructing an online booking platform and a corresponding background management system, and processing booking information of online dining users and recording dining data of dining halls by utilizing the online booking platform;
the collaborative filtering model integration module is used for designing a collaborative filtering model and integrating the collaborative filtering model into an online booking platform, and recommending dishes according to the preference of an online dining user;
the people flow prediction module is used for predicting the people flow of dining in the dining room in a future time period by using the long-short-period memory network model and comprehensively estimating the number of dining in the dining room by combining the people flow with the on-line scheduled number of people;
the meal allocation plan adjustment module is used for comparing the actual dining room number with the estimated dining room number and dynamically adjusting the meal allocation plan in the dining room based on the comparison result;
and the canteen management strategy adjustment module is used for respectively collecting and integrating evaluation feedback of the online dining user and the canteen dining user and adjusting the canteen management strategy based on the integrated evaluation feedback.
CN202311058862.5A 2023-08-22 2023-08-22 Intelligent canteen management method and system based on digital twinning Active CN116777684B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202311058862.5A CN116777684B (en) 2023-08-22 2023-08-22 Intelligent canteen management method and system based on digital twinning
CN202311418171.1A CN117474719A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning
CN202311417324.0A CN117474718A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311058862.5A CN116777684B (en) 2023-08-22 2023-08-22 Intelligent canteen management method and system based on digital twinning

Related Child Applications (2)

Application Number Title Priority Date Filing Date
CN202311418171.1A Division CN117474719A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning
CN202311417324.0A Division CN117474718A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning

Publications (2)

Publication Number Publication Date
CN116777684A true CN116777684A (en) 2023-09-19
CN116777684B CN116777684B (en) 2023-11-17

Family

ID=87993456

Family Applications (3)

Application Number Title Priority Date Filing Date
CN202311418171.1A Pending CN117474719A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning
CN202311058862.5A Active CN116777684B (en) 2023-08-22 2023-08-22 Intelligent canteen management method and system based on digital twinning
CN202311417324.0A Pending CN117474718A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN202311418171.1A Pending CN117474719A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202311417324.0A Pending CN117474718A (en) 2023-08-22 2023-08-22 Management method and system based on digital twinning

Country Status (1)

Country Link
CN (3) CN117474719A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104091295A (en) * 2014-07-07 2014-10-08 东南大学 Canteen service quality evaluation system and method
CN107977906A (en) * 2017-12-18 2018-05-01 国网浙江省电力公司综合服务分公司 Wisdom health dining room system
CN112070592A (en) * 2020-09-16 2020-12-11 江西太空机器人科技有限公司 Healthy diet management method, device, storage medium and system for intelligent canteen
CN115375507A (en) * 2022-10-26 2022-11-22 山东济宁烟草有限公司 Intelligent canteen management method and system based on digital twin

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104091295A (en) * 2014-07-07 2014-10-08 东南大学 Canteen service quality evaluation system and method
CN107977906A (en) * 2017-12-18 2018-05-01 国网浙江省电力公司综合服务分公司 Wisdom health dining room system
CN112070592A (en) * 2020-09-16 2020-12-11 江西太空机器人科技有限公司 Healthy diet management method, device, storage medium and system for intelligent canteen
CN115375507A (en) * 2022-10-26 2022-11-22 山东济宁烟草有限公司 Intelligent canteen management method and system based on digital twin

Also Published As

Publication number Publication date
CN116777684B (en) 2023-11-17
CN117474718A (en) 2024-01-30
CN117474719A (en) 2024-01-30

Similar Documents

Publication Publication Date Title
Zhong et al. Construction and empirical research on acceptance model of service robots applied in hotel industry
US11799976B2 (en) Needs-matching navigator system
Sun et al. Forecasting tourist arrivals with machine learning and internet search index
Yadegaridehkordi et al. Predicting determinants of hotel success and development using Structural Equation Modelling (SEM)-ANFIS method
Wallsten et al. State of the art—Encoding subjective probabilities: A psychological and psychometric review
Chen et al. Improving the forecasting accuracy of air passenger and air cargo demand: the application of back-propagation neural networks
Li et al. Impact of cultural contact on satisfaction and attachment: mediating roles of creative experiences and cultural memories
Hess et al. Improving the quality of demand forecasts through cross nested logit: a stated choice case study of airport, airline and access mode choice
Zeng et al. Household and living arrangement projections
Morand et al. Demographic modelling: the state of the art
Lam et al. Support vector machine and entropy based decision support system for property valuation
Faezirad et al. Preventing food waste in subsidy-based university dining systems: An artificial neural network-aided model under uncertainty
Nase et al. Urban design quality and real estate value: in search of a methodological framework
Wang et al. Is robot hotel a future trend? Exploring the incentives, barriers and customers' purchase intention for robot hotel stays
Wang et al. AI in health tourism: developing a measurement scale
Hu et al. How does customer psychological empowerment affect value co-creation? An empirical study of travel agencies in Mainland China
Chao Estimating project overheads rate in bidding: DSS approach using neural networks
CN116777684B (en) Intelligent canteen management method and system based on digital twinning
Dompere Cost-benefit analysis and the theory of fuzzy decisions: identification and measurement theory
Chen An extension of importance-performance analysis method: integrated with fuzzy MICMAC
Xu et al. A new approach to decision-making with key constraint and its application in enterprise information systems
Haryanti et al. Decision Support System for Selection of Zakat Mustahik Using Analytical Network Process Method
Cha et al. A Conceptual Framework for Developing Indoor Spatial Choice Model
Feng An intelligent decision support system based on human–machine interaction and dynamic track of psychological evaluation criterion
Arifin et al. Anticipated ROI Methods for the Quantification of Servicescape Upgrading based on Intangible Values: A Literature Analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant