CN116663842A - Digital management system and method based on artificial intelligence - Google Patents

Digital management system and method based on artificial intelligence Download PDF

Info

Publication number
CN116663842A
CN116663842A CN202310709654.0A CN202310709654A CN116663842A CN 116663842 A CN116663842 A CN 116663842A CN 202310709654 A CN202310709654 A CN 202310709654A CN 116663842 A CN116663842 A CN 116663842A
Authority
CN
China
Prior art keywords
demand
data
model
time
neural network
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.)
Pending
Application number
CN202310709654.0A
Other languages
Chinese (zh)
Inventor
赵海龙
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.)
Heilongjiang Zhuojin Technology Co ltd
Original Assignee
Heilongjiang Zhuojin 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 Heilongjiang Zhuojin Technology Co ltd filed Critical Heilongjiang Zhuojin Technology Co ltd
Priority to CN202310709654.0A priority Critical patent/CN116663842A/en
Publication of CN116663842A publication Critical patent/CN116663842A/en
Pending legal-status Critical Current

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
    • 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
    • G06Q10/06313—Resource planning in a project environment
    • 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
    • G06F16/903—Querying
    • G06F16/90335—Query processing
    • 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
    • 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
    • G06Q10/04—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
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Educational Administration (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a digital management system and method based on artificial intelligence, and belongs to the technical field of digital management. The system comprises a data acquisition module, a demand prediction module, a neural network analysis module, a resource management module and a database; the data acquisition module is used for acquiring data related to the requirements; the demand prediction module is used for predicting a time node when the future demand appears; the neural network analysis module is used for distributing resources for the demand after the demand appears; the resource management module is used for finding out a time period when the demand does not appear by using the prediction module on the time sequence, stopping providing resources for the demand, and providing resources for the newly added demand; the database is used for storing the acquired data related to the requirements. According to the invention, the time nodes where the data appear are predicted by establishing the prediction model, and the configuration of resources is optimized by utilizing artificial intelligence aiming at the time nodes, so that the flexible management of the data is realized.

Description

Digital management system and method based on artificial intelligence
Technical Field
The invention relates to the technical field, in particular to a digital management system and method based on artificial intelligence.
Background
With the rapid development of globalization and informatization, enterprises are increasingly competing, and enterprise management is becoming more complex and challenging. In the prior art, the digital management system and method mainly adopt the traditional data warehouse and data mining technology, the processing speed is slower, the required storage space is larger, and the requirements on computer hardware equipment are higher. Secondly, the systems and methods are mainly used for analyzing and processing data based on manually set rules and models, lack of flexibility and intelligence, cannot adapt to the changes and requirements of different enterprises and markets, and cannot provide personalized management services. Compared with the prior art, the artificial intelligence technology realizes the rapid analysis and mining of a large amount of data, can provide a customized management solution, and enables enterprises to realize scientific, efficient and intelligent management.
There is a need for an artificial intelligence based digital management system and method that can handle multiple different types of data simultaneously and customize the corresponding management policies.
Disclosure of Invention
The invention aims to provide a digital management system and method based on artificial intelligence, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the system comprises a data acquisition module, a demand prediction module, a neural network analysis module, a resource management module and a database;
the data acquisition module is used for acquiring data related to the requirements; the demand prediction module is used for predicting a time node when the future demand appears; the neural network analysis module is used for distributing resources for the demand after the demand appears; the resource management module is used for finding out a time period when the demand does not appear by using the prediction module on the time sequence, stopping providing resources for the demand, and providing resources for the newly added demand; the database is used for storing the acquired data related to the requirements.
The data acquisition module comprises a demand type acquisition unit and a demand counting unit; the demand type collection unit is used for counting a plurality of demands, for example, keywords can be extracted from work orders, complaints or suggestions submitted by users, the keywords can be automatically classified into different demand types, such as functional demands, bug feedback, improvement suggestions and the like, and then the quantity and proportion of each demand type are counted; the demand counting unit is used for recording the occurrence times and the duration of the demands in the time period, and can know the development trend of each demand type in different time periods, such as which demand types get more attention in the last quarter, and the duration of each demand event is convenient for people to count and predict the change trend and the burst point of the demands in several time periods in the future so as to make countermeasure in advance.
The demand prediction module comprises a demand analysis unit and a prediction result output unit; the demand analysis unit is used for analyzing historical demand data according to the information in the data acquisition module, wherein the historical demand data comprises the aspects of demand types, quantity, duration, occurrence time and the like, and the analysis result can be used for searching the trend and mode of demand occurrence and knowing the characteristics of periodicity, alternation, rhythmicity and the like of the demand; the prediction result output unit is used for outputting a time node when the demand appears, and can predict the future demand according to modes and trends in historical data and combining technologies such as machine learning, artificial intelligence and the like. The prediction results can be specific demand quantity or probability of demand occurrence, and can help us to make decisions and plans better, so that the demands of users and markets can be met more efficiently.
The neural network analysis module comprises a demand characteristic input module, a model training unit and an analysis result output unit; the demand feature input module is used for inputting related feature digitization of the demand so that the neural network model can understand and process, and in some cases, the feature can be the number of predicted demands or the occurrence probability, or other demand related features, such as user attributes, time sequence data, market trend and the like. By digitizing these demand features, we can convert them into a processable format; the model training unit is used for training the resource allocation target, and the unit learns and trains the demand characteristics by using a neural network algorithm so that the neural network can learn some internal rules from historical demand data to better predict future demands. In the training process, the model needs to be continuously adjusted and optimized so as to improve the accuracy and efficiency of prediction; the analysis result output unit is used for outputting the analysis result of the neural network model, and outputting the prediction result processed by the neural network model to other modules for further decision and planning. The predicted result may be the number of demands to be satisfied, the number of resources to be allocated, and information such as a resource allocation scheme. The analysis results can optimize the utilization of resources and improve the benefit of enterprises on the premise of ensuring the quality.
The resource management module comprises a demand replacement unit and a resource allocation unit; the demand replacement unit is used for deleting the non-existing demand and adding a new demand according to the result of the demand prediction module; the resource allocation unit is used for carrying out resource allocation on newly added requirements. The demand replacement unit is typically in close proximity to the demand prediction module. The demand prediction module predicts future demands, and the demand replacement unit judges whether the existing demands are still necessary according to the prediction result, and if not, deletes the demands and adds new demands so as to keep the latest and accuracy of the demands. The demand replacement unit may also provide the information of the deleted and newly added demand to the resource allocation unit for the resource allocation unit to perform the next resource allocation. The resource allocation unit performs resource allocation on the newly added demand according to the information provided by the demand replacement unit. Typical resources include manpower, equipment, time, etc. The resource allocation unit may employ various algorithms, such as greedy algorithms, dynamic programming, etc., to allocate the required resources. The goal of the resource allocation is to ensure that each requirement can be guaranteed by a proper amount of resources, thereby improving the product quality and customer satisfaction.
The database comprises a data storage unit and a data calling unit; the data storage unit is used for storing demand data, resource data, forecast data and statistical data; the data calling unit is used for providing information calling for data analysis, and can extract corresponding data from the database according to different requirements and transmit the data to different analysis modules. For example, when the demand prediction module needs training, the data retrieval unit may provide the historical data to the training module for training. When the analysis result output unit needs to output the analysis result, the data retrieving unit may provide the required data to the result output unit. Therefore, the data calling unit plays a very important role in the whole data analysis process, and the effective realization of the functions can improve the speed and accuracy of data analysis and processing.
A digital management method based on artificial intelligence is characterized in that:
s1, acquiring data related to requirements;
s2, according to the collected data, a mathematical model is established to predict the distribution condition of future demands;
s3, timely deleting resource allocation without requirements according to the distribution conditions of the requirements;
S4, on the basis of eliminating the resource allocation without the requirement, if no new requirement exists, the new resource allocation is not performed, and if the new requirement exists, the neural network model is utilized to allocate proper resources for the new resource allocation.
In S1, analyzing the distribution of demands over time is a precondition for implementing digital management, and first collecting data related to the demands:
wherein Demand type Indicate the type of demand, N c Indicating the number of required categories, n i Represents the number of i demands, demand time Indicating when the demand has occurred, N t Indicating the number of times the demand has occurred, t i Demand indicating the instant of the ith Demand duration Indicating the duration of demand, N d Indicating the number of times the demand is sustained, d i Indicating the duration of the ith section;
in S2, the following steps are included:
s201, after collecting data related to demand, analyzing the distribution rule of past demand on time sequence and knowing the demand sequence which can be observed at time t, wherein the time span is 1, and the distribution situation of demand on time point is represented by the collective usage Y all Expressed by Y all ＝(Y 1 ，Y 2 ，...，Y n ) The law of demand on time sequence, namely the trend of demand appearance and disappearance is analyzed, so the following time sequence mathematical model is established:
wherein ,Yt Represents the value at time t, c represents a constant, ε t Representing residual error phi i Representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average term;
the model gathers all demand data from the predicted point in time onward. These data are then processed and analyzed using appropriate algorithms and methods to derive the law of the appearance and disappearance of the demand. Finally, according to these rules, the distribution of demands over the future time series is further predicted.
S202, a future demand prediction model is established to further predict the demand, and the model is as follows:
wherein ,representing the value at the predicted future time t, c representing a constant, ε t Representing residual error phi i Representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average term;
in the model, t+1 represents a future time point, and t-i+1 represents all past demand data, namely, the model is built on the basis that a time sequence mathematical model analyzes a demand distribution rule to obtain a distribution condition of future demands, and the dimension of the demand distribution condition described by a future demand prediction model is different from that of the time sequence mathematical model, so that a prediction result is further restored to the dimension of original demand distribution, and a final prediction result can be obtained; by establishing the prediction model, the enterprise can more accurately predict the future demand trend, so that the resource configuration and planning can be more effectively carried out. For example, in the event that a sudden increase in demand is predicted, the enterprise may advance the corresponding resource allocation to meet future demands. Meanwhile, the model can also reduce resource waste and loss of enterprises caused by demand change, and improve the production efficiency and economic benefit of the enterprises.
S203, the distribution condition of the future demand can be obtained through a future demand prediction model, but as the emphasis is on the trend of the generation and disappearance of the predicted demand, for some unpredictable emergencies, the distribution condition of the demand will have errors, and in consideration of the fact that the accuracy of the predicted value plays a vital role in resource management and allocation, the predicted demand distribution condition needs to be corrected, and a predicted value error correction model is established:
wherein ,a predicted value representing a future point in time, y t+1-i Data representing historical time points, w i The representation of the weighting coefficients can be adjusted as required;
for some unpredictable incidents, the accuracy of the predicted values is indeed affected to some extent, which may lead to errors in the predicted demand distribution. Therefore, enterprises need to build a predictive value error correction model to correct for the prediction error. The process of building the predictive value error correction model needs to rely on real-time demand data and predictive results, as well as historical data in the past. First, the range and trend of the prediction error, i.e., the difference between the predicted value and the actual value, are determined from the real-time data and the predicted result. Second, historical data is used to analyze the source and regularity of the prediction error in order to further optimize the prediction model. For example, for certain incidents, relevant predictive models may be built in advance by analyzing their characteristics and effects. Finally, according to the analysis result, proper measures are taken to correct the predicted value. For example, resource allocation schemes, deferring or advancing production of products, etc. may be adjusted to accommodate actual demand changes while reducing the impact of prediction errors.
By establishing the predictive value error correction model, the actual demand condition can be mastered more accurately, and the management and planning of resources can be carried out more effectively. Meanwhile, the model can help enterprises to cope with the influence of emergency, make up for the deficiency of predictive analysis, and improve the production efficiency and innovation ability of the enterprises.
S204, correcting the output of the future demand prediction model by using the predicted value error correction model, and constructing the distribution condition of the demand on the future time node.
In S3, the resource allocation without the demand is removed in real time according to the distribution situation of the demand, the distribution situation of the demand analyzes the distribution situation of the demand through a future demand prediction model, and the following resource discrimination model is established:
wherein ,Zt Represents the sum of all demand numbers present at time t, y represents demand number, f t (y) represents the result of the assignment to the required number y at time t;
generating a judging mechanism of resource allocation about the generation and disappearance of the demand according to the resource judging model: first, the maximum value of y over the time sequence is collected; next, at the time t, the time of the reaction,with the process of changing y from 1 to the maximum value, for y=1, i.e. the required number is 1, analyzing the matching condition of the actual situation and the value set by y, if the required number is indeed 1 in the actual situation, f t (y) =1, otherwise f t (y) =0, calculating f in this way as y increases t A value of (y); after traversing all y values, f corresponding to each y value is carried out t The values of (y) are all accumulated to give Z t If Z t =0, meaning that there is no need at this time, so the resource allocation can be completely deleted, if Z t >And 0, different allocation of resources is needed according to different demand numbers.
The discrimination mechanism based on the resource discrimination model can help enterprises to know the actual demand situation more accurately so as to allocate resources more accurately. The maximum value on the time sequence is collected, and the matching condition of the actual demand quantity and the set numerical value is analyzed, so that the generation and disappearance of the demand can be judged more accurately. After all values are traversed, if no requirement exists at a certain moment, the resource allocation at the moment can be completely deleted, so that resources are saved. If the demand exists, different resource allocation can be performed according to different quantities of the demand so as to meet the demand of the actual demand.
In S4, the following steps are included:
s401, when new requirements appear, the requirements cannot be summarized because of the difference between the requirements, and characteristic information of the requirements needs to be collected;
S402, digitizing the characteristics of the demands as input vectors of a neural network model, and performing resource customization allocation for the occurring demands by using the neural network, so that the following neural network model is established:
wherein X is represented as a feature vector, y k In order to conceal the output value of the layer one,weight, b k To bias, Z k-1 Is the output of the upper layer,/-, is>To output the output value of the layer, w o Is the weight of the output layer, b o Is the bias of the output layer, z h Is the output of the last hidden layer,/->As a loss function, m is the number of training samples;
after the neural network model is established, training the neural network model according to the limitation of the input characteristics, and calculating the output value in the neural network for each input characteristic vectorFurther, after deriving the output values in the neural network, a gradient of the loss function value L is calculated>Whereas for each hidden layer k node the gradient of the current node is calculated +.>And calculate the gradient of its input weight and bias by the chain law +.> and />
S404, after calculating the data in the neural network model, applying the data, and firstly, calculating an output value of the neural network by providing an input vector; further, comparing the output value with the true value to calculate the value of the loss function; next, the gradient of the loss function is used to adjust the network parameters to minimize the loss function; specifically, the gradient is calculated from the output layer in a reverse way, and all the parameters are optimized by all nodes which propagate the error signal from the output layer to the hidden layer and the input layer in a reverse way;
S405, the parameters are further updated by executing the process of adjusting the network parameters, each parameter is updated according to the calculated gradient, and the parameters of the network are optimized by continuous iteration, so that the effect of the demand resource allocation reaches the optimal state. Such a process is actually a model training process, and by continuously adjusting parameters and continuously trying different parameter combinations, the model can more accurately predict the demand change trend and distribution condition of demand resources. The neural network model which is trained and optimized can utilize limited resources to the greatest extent on the premise of meeting the requirements, so that the resource utilization rate and benefit are improved. For example, the number and time period of arranging resources on the production line, the resource allocation of the supply chain, the working time of reasonably arranging personnel and the like can be optimized and decided through the trained model. In addition, through reasonable demand resource allocation and optimization, the production efficiency and economic benefit of enterprises can be improved, the production cost is reduced, and the product quality and market competitiveness are improved. Therefore, the neural network model is utilized to predict and configure the demand resources in the enterprise operation and management process, and is a very effective means and strategy.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the time node and duration of the demand, a mathematical model is established, and the distribution situation of the future demand is predicted by utilizing the mathematical model, so that measures can be taken in advance when the demand is met, the pressure of digital management is relieved to a certain extent, and a manager can formulate a corresponding management strategy.
2. According to the demand prediction model, the conditions of old demand elimination and new demand generation exist at different time nodes, so a judging mechanism aiming at the situation is established, the resource allocation of the old demand is deleted by utilizing the judging mechanism, and the proper resource allocation is customized for the new demand by utilizing an artificial intelligence technology.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic block diagram of a digital management system and method based on artificial intelligence according to the present invention;
FIG. 2 is a schematic diagram of a method flow structure of a digital management system and method based on artificial intelligence according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: the system comprises a data acquisition module, a demand prediction module, a neural network analysis module, a resource management module and a database;
the data acquisition module is used for acquiring data related to the requirements; the demand prediction module is used for predicting a time node when the future demand appears; the neural network analysis module is used for distributing resources for the demand after the demand appears; the resource management module is used for finding out a time period when the demand does not appear by using the prediction module on the time sequence, stopping providing resources for the demand, and providing resources for the newly added demand; the database is used for storing the acquired data related to the requirements.
The data acquisition module comprises a demand type acquisition unit and a demand counting unit; the demand type acquisition unit is used for counting a plurality of demands, for example, the demand type acquisition unit can extract keywords from work orders, complaints or suggestions submitted by users, automatically classify the keywords into different demand types, such as functional demands, bug feedback, improvement suggestions and the like, and then count the quantity and proportion of each demand type; the demand counting unit is used for recording the occurrence times and the duration of the demands in the time period, and can know the development trend of each demand category in different time periods, such as which demand types get more attention in the last quarter, and the duration of each demand event is convenient for people to count and predict the change trend and the burst point of the demands in several time periods in the future so as to make countermeasure in advance.
The demand prediction module comprises a demand analysis unit and a prediction result output unit; the demand analysis unit is used for analyzing historical demand data according to the information in the data acquisition module, wherein the historical demand data comprises the aspects of demand types, quantity, duration, occurrence time and the like, and the analysis result can be used for searching the trend and mode of demand occurrence and knowing the characteristics of periodicity, alternation, rhythmicity and the like of the demand; the prediction result output unit is used for outputting a time node when the demand appears, and can predict the future demand according to modes and trends in the historical data and combining technologies such as machine learning, artificial intelligence and the like. The prediction results can be specific demand quantity or probability of demand occurrence, and can help us to make decisions and plans better, so that the demands of users and markets can be met more efficiently.
The neural network analysis module comprises a demand characteristic input module, a model training unit and an analysis result output unit; the demand feature input module is used for inputting related feature digitization of the demand so that the neural network model can understand and process, and in some cases, the feature can be the number of predicted demands or the occurrence probability, or other demand related features such as user attributes, time sequence data, market trend and the like. By digitizing these demand features, we can convert them into a processable format; the model training unit is used for training the resource allocation target, and the unit learns and trains the demand characteristics by using a neural network algorithm so that the neural network can learn some internal rules from the historical demand data to better predict future demands. In the training process, the model needs to be continuously adjusted and optimized so as to improve the accuracy and efficiency of prediction; the analysis result output unit is used for outputting the analysis result of the neural network model, and outputting the prediction result processed by the neural network model to other modules for further decision and planning. The predicted result may be the number of demands to be satisfied, the number of resources to be allocated, and information such as a resource allocation scheme. The analysis results can optimize the utilization of resources and improve the benefit of enterprises on the premise of ensuring the quality.
The resource management module comprises a demand replacement unit and a resource configuration unit; the demand replacement unit is used for deleting the non-existing demand and adding a new demand according to the result of the demand prediction module; the resource allocation unit is used for allocating resources for newly added demands. The demand replacement unit is typically closely coupled to the demand prediction module. The demand prediction module predicts future demands, and the demand replacement unit judges whether the existing demands are still necessary according to the prediction result, and if not, deletes the demands and adds new demands so as to keep the latest and accuracy of the demands. The demand replacement unit may also provide the information of the deleted and newly added demand to the resource allocation unit for the resource allocation unit to perform the next resource allocation. The resource allocation unit performs resource allocation on the newly added demand according to the information provided by the demand replacement unit. Typical resources include manpower, equipment, time, etc. The resource allocation unit may employ various algorithms, such as greedy algorithms, dynamic programming, etc., to allocate the required resources. The goal of the resource allocation is to ensure that each requirement can be guaranteed by a proper amount of resources, thereby improving the product quality and customer satisfaction.
The database comprises a data storage unit and a data calling unit; the data storage unit is used for storing the demand data, the resource data, the forecast data and the statistical data; the data calling unit is used for providing information for data analysis, and can extract corresponding data from the database according to different requirements and transmit the data to different analysis modules. For example, when the demand prediction module requires training, the data retrieval unit may provide historical data to the training module for training. When the analysis result output unit needs to output the analysis result, the data retrieval unit may supply the required data to the result output unit. Therefore, the data retrieval unit plays a very important role in the whole data analysis process, and the effective realization of the functions can improve the speed and accuracy of data analysis and processing.
A digital management method based on artificial intelligence is characterized in that:
s1, acquiring data related to requirements;
s2, according to the collected data, a mathematical model is established to predict the distribution condition of future demands;
s3, timely deleting resource allocation without requirements according to the distribution conditions of the requirements;
S4, on the basis of eliminating the resource allocation without the requirement, if no new requirement exists, the new resource allocation is not performed, and if the new requirement exists, the neural network model is utilized to allocate proper resources for the new resource allocation.
In S1, analyzing the distribution of demands over time is a precondition for implementing digital management, and first collecting data related to the demands:
wherein Demand type Indicate the type of demand, N c Indicating the number of required categories, n i Represents the number of i demands, demand time Indicating when the demand has occurred, N t Indicating the number of times the demand has occurred, t i Demand indicating the instant of the ith Demand duration Indicating the duration of demand, N d Indicating the number of times the demand is sustained, d i Indicating the duration of the ith section;
in S2, the following steps are included:
s201, after collecting the data related to the demand, analyzing the time sequence of the past demandDistribution law and knowledge of demand sequence observable at time t, the prescribed time span being 1, representing collective usage Y of demand distribution at time points all Expressed by Y all ＝(Y 1 ，Y 2 ，...，Y n ) The law of demand on time sequence, namely the trend of demand appearance and disappearance is analyzed, so the following time sequence mathematical model is established:
wherein ,Yt Represents the value at time t, c represents a constant, ε t Representing residual error phi i Representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average term;
the model gathers all demand data from the predicted point in time onward. These data are then processed and analyzed using appropriate algorithms and methods to derive the law of the appearance and disappearance of the demand. Finally, according to these rules, the distribution of demands over the future time series is further predicted.
S202, a future demand prediction model is established to further predict the demand, and the model is as follows:
wherein ,representing the value at the predicted future time t, c representing a constant, ε t Representing residual error phi i Representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average term;
in the model, t+1 represents a future time point, and t-i+1 represents all past demand data, namely, the model is built on the basis that a time sequence mathematical model analyzes a demand distribution rule to obtain a distribution condition of future demands, and the dimension of the demand distribution condition described by a future demand prediction model is different from that of the time sequence mathematical model, so that a prediction result is further restored to the dimension of original demand distribution, and a final prediction result can be obtained; by establishing the prediction model, the enterprise can more accurately predict the future demand trend, so that the resource configuration and planning can be more effectively carried out. For example, in the event that a sudden increase in demand is predicted, the enterprise may advance the corresponding resource allocation to meet future demands. Meanwhile, the model can also reduce resource waste and loss of enterprises caused by demand change, and improve the production efficiency and economic benefit of the enterprises.
S203, the distribution condition of the future demand can be obtained through a future demand prediction model, but as the emphasis is on the trend of the generation and disappearance of the predicted demand, for some unpredictable emergencies, the distribution condition of the demand will have errors, and in consideration of the fact that the accuracy of the predicted value plays a vital role in resource management and allocation, the predicted demand distribution condition needs to be corrected, and a predicted value error correction model is established:
wherein ,a predicted value representing a future point in time, y t+1-i Data representing historical time points, w i The representation of the weighting coefficients can be adjusted as required;
for some unpredictable incidents, the accuracy of the predicted values is indeed affected to some extent, which may lead to errors in the predicted demand distribution. Therefore, enterprises need to build a predictive value error correction model to correct for the prediction error. The process of building the predictive value error correction model needs to rely on real-time demand data and predictive results, as well as historical data in the past. First, the range and trend of the prediction error, i.e., the difference between the predicted value and the actual value, are determined from the real-time data and the predicted result. Second, historical data is used to analyze the source and regularity of the prediction error in order to further optimize the prediction model. For example, for certain incidents, relevant predictive models may be built in advance by analyzing their characteristics and effects. Finally, according to the analysis result, proper measures are taken to correct the predicted value. For example, resource allocation schemes, deferring or advancing production of products, etc. may be adjusted to accommodate actual demand changes while reducing the impact of prediction errors.
By establishing the predictive value error correction model, the actual demand condition can be mastered more accurately, and the management and planning of resources can be carried out more effectively. Meanwhile, the model can help enterprises to cope with the influence of emergency, make up for the deficiency of predictive analysis, and improve the production efficiency and innovation ability of the enterprises.
S204, correcting the output of the future demand prediction model by using the predicted value error correction model, and constructing the distribution condition of the demand on the future time node.
In S3, the resource allocation without the demand is removed in real time according to the distribution situation of the demand, the distribution situation of the demand analyzes the distribution situation of the demand through a future demand prediction model, and the following resource discrimination model is established:
wherein ,Zt Represents the sum of all demand numbers present at time t, y represents demand number, f t (y) represents the result of the assignment to the required number y at time t;
generating a judging mechanism of resource allocation about the generation and disappearance of the demand according to the resource judging model: first, the maximum value of y over the time sequence is collected; secondly, at t, with the course of y changing from 1 to the maximum value, for y=1, i.e. the required number is 1, the actual condition and the y is set to match the state of the numerical value, if the required quantity in the actual state is 1, f t (y) =1, otherwise f t (y) =0, calculating f in this way as y increases t A value of (y); after traversing all y values, f corresponding to each y value is carried out t The values of (y) are all accumulated to give Z t If Z t =0, meaning that there is no need at this time, so the resource allocation can be completely deleted, if Z t >And 0, different allocation of resources is needed according to different demand numbers.
The discrimination mechanism based on the resource discrimination model can help enterprises to know the actual demand situation more accurately so as to allocate resources more accurately. The maximum value on the time sequence is collected, and the matching condition of the actual demand quantity and the set numerical value is analyzed, so that the generation and disappearance of the demand can be judged more accurately. After all values are traversed, if no requirement exists at a certain moment, the resource allocation at the moment can be completely deleted, so that resources are saved. If the demand exists, different resource allocation can be performed according to different quantities of the demand so as to meet the demand of the actual demand.
In S4, the following steps are included:
S401, when new requirements appear, the requirements cannot be summarized because of the difference between the requirements, and characteristic information of the requirements needs to be collected;
s402, digitizing the characteristics of the demands as input vectors of a neural network model, and performing resource customization allocation for the occurring demands by using the neural network, so that the following neural network model is established:
wherein X is represented as a feature vector, y k In order to conceal the output value of the layer one,weight, b k To bias, Z k-1 Is the output of the upper layer,/-, is>To output the output value of the layer, w o Is the weight of the output layer, b o Is the bias of the output layer, z h Is the output of the last hidden layer,/->As a loss function, m is the number of training samples;
after the neural network model is established, training the neural network model according to the limitation of the input characteristics, and calculating the output value in the neural network for each input characteristic vectorFurther, after deriving the output values in the neural network, a gradient of the loss function value L is calculated>Whereas for each hidden layer k node the gradient of the current node is calculated +.>And calculate the gradient of its input weight and bias by the chain law +.> and />
S404, after calculating the data in the neural network model, applying the data, and firstly, calculating an output value of the neural network by providing an input vector; further, comparing the output value with the true value to calculate the value of the loss function; next, the gradient of the loss function is used to adjust the network parameters to minimize the loss function; specifically, the gradient is calculated from the output layer in a reverse way, and all the parameters are optimized by all nodes which propagate the error signal from the output layer to the hidden layer and the input layer in a reverse way;
S405, the parameters are further updated by executing the process of adjusting the network parameters, each parameter is updated according to the calculated gradient, and the parameters of the network are optimized by continuous iteration, so that the effect of the demand resource allocation reaches the optimal state. Such a process is actually a model training process, and by continuously adjusting parameters and continuously trying different parameter combinations, the model can more accurately predict the demand change trend and distribution condition of demand resources. The neural network model which is trained and optimized can utilize limited resources to the greatest extent on the premise of meeting the requirements, so that the resource utilization rate and benefit are improved. For example, the number and time period of arranging resources on the production line, the resource allocation of the supply chain, the working time of reasonably arranging personnel and the like can be optimized and decided through the trained model. In addition, through reasonable demand resource allocation and optimization, the production efficiency and economic benefit of enterprises can be improved, the production cost is reduced, and the product quality and market competitiveness are improved. Therefore, the neural network model is utilized to predict and configure the demand resources in the enterprise operation and management process, and is a very effective means and strategy.
Example 1:
suppose we have a period of historical time series data Y t, wherein ,Y1 ＝15，Y 2 ＝25，Y 3 ＝10，Y 4 ＝8，Y 5 ＝18，Y 6 =20. Predicting the demand number of 3 time points in the future by using a prediction model, namely Y 7 ＝22，Y 8 ＝26，Y 9 ＝30。
Listing the distribution of the number of demands on each time node:
from the above distribution, we can calculate the number of demands Zt present on each time node t, namely:
Z 1 ＝1
Z 2 ＝0.3×25+0.7×15＝18
Z 3 ＝0.5×10+0.3×20+0.2×25＝13.5
Z 4 ＝0.2×10+0.6×15+0.1×20+0.1×25＝14.5
Z 5 ＝0.4×8+0.2×15+0.3×20＝12.2
it is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the above is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that the present invention is described in detail with reference to the foregoing embodiments, and modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The utility model provides a digital management system based on artificial intelligence which characterized in that: the system comprises a data acquisition module, a demand prediction module, a neural network analysis module, a resource management module and a database;
the data acquisition module is used for acquiring data related to the requirements; the demand prediction module is used for predicting a time node when the future demand appears; the neural network analysis module is used for distributing resources for the demand after the demand appears; the resource management module is used for finding out a time period when the demand does not appear by using the prediction module on the time sequence, stopping providing resources for the demand, and providing resources for the newly added demand; the database is used for storing the acquired data related to the requirements.
2. The artificial intelligence based digital management system of claim 1, wherein: the data acquisition module comprises a demand type acquisition unit and a demand counting unit;
the demand type acquisition unit is used for counting a plurality of demands; the demand counting unit is used for recording the times and duration of the demand occurring in the time period.
3. An artificial intelligence based digital management system according to claim 2, wherein: the demand prediction module comprises a demand analysis unit and a prediction result output unit;
The demand analysis unit is used for analyzing the distribution condition of demands on the historical time sequence according to the information in the data acquisition module; the prediction result output unit is used for outputting a time node when the demand appears.
4. A digital management system based on artificial intelligence according to claim 3, characterized in that: the neural network analysis module comprises a demand characteristic input module, a model training unit and an analysis result output unit;
the demand characteristic input module is used for inputting the related characteristic digitization of the demand; the model training unit is used for training the resource allocation target; and the analysis result output unit is used for outputting the analysis result of the neural network model.
5. The artificial intelligence based digital management system of claim 4, wherein: the resource management module comprises a demand replacement unit and a resource allocation unit;
the demand replacement unit is used for deleting the non-existing demand and adding a new demand according to the result of the demand prediction module; the resource allocation unit is used for carrying out resource allocation on newly added requirements.
6. The artificial intelligence based digital management system of claim 5, wherein: the database comprises a data storage unit and a data calling unit;
The data storage unit is used for storing demand data, resource data, forecast data and statistical data; the data retrieval unit is used for providing information retrieval for data analysis.
7. A digital management method based on artificial intelligence is characterized in that:
s1, acquiring data related to requirements;
s2, according to the collected data, a mathematical model is established to predict the distribution condition of future demands;
s3, timely deleting resource allocation without requirements according to the distribution conditions of the requirements;
s4, on the basis of eliminating the resource allocation without the requirement, if no new requirement exists, the new resource allocation is not performed, and if the new requirement exists, the neural network model is utilized to allocate proper resources for the new resource allocation.
8. The digital management method based on artificial intelligence according to claim 7, wherein:
in S1, analyzing the distribution of demands over time is a precondition for implementing digital management, and first collecting data related to the demands:
wherein Demand type Indicate the type of demand, N c Indicating the number of required categories, n i Represents the number of i demands, demand time Indicating when the demand has occurred, N t Indicating the number of times the demand has occurred, t i Demand indicating the instant of the ith Demand duration Indicating the duration of demand, N d Indicating the number of times the demand is sustained, d i Indicating the duration of the ith section; in S2, the following steps are included:
s201, after collecting the data related to the demand, analyzing the distribution rule of the past demand on the time sequence and knowing the demand sequence which can be observed at the time t, and definingSpan 1, representing the collective usage Y of the distribution of demand at a point in time all Expressed by Y all ＝(Y 1 ，Y 2 ，...，Y n ) The law of demand on time sequence, namely the trend of demand appearance and disappearance is analyzed, so the following time sequence mathematical model is established:
wherein ,Yt Represents the value at time t, c represents a constant, ε t The residual is represented by a representation of the residual,representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average term;
the model is built, the trend of all the demands from the predicted time point forward on the time sequence is described, the law of the appearance and disappearance of the demands is obtained, and the distribution condition of the demands on the future time sequence is further predicted by utilizing the law;
s202, predicting the demand by establishing a future demand prediction model, wherein the model is as follows:
wherein ,Representing the value at the predicted future time t, c representing a constant, ε t Representing residual error,/->Representing the autoregressive term coefficient, θ i Coefficients representing the moving average term, p representing the order of the autoregressive term, q representing the order of the moving average termA number;
in the model, t+1 represents a future time point, and t-i+1 represents all past demand data, namely, the model is built on the basis that a time sequence mathematical model analyzes a demand distribution rule to obtain a distribution condition of future demands, and the dimension of the demand distribution condition described by a future demand prediction model is different from that of the time sequence mathematical model, so that a prediction result is further restored to the dimension of original demand distribution, and a final prediction result can be obtained;
s203, the distribution condition of the future demand can be obtained through a future demand prediction model, but as the emphasis is on the trend of the generation and disappearance of the predicted demand, for some unpredictable emergencies, the distribution condition of the demand will have errors, and in consideration of the fact that the accuracy of the predicted value plays a vital role in resource management and allocation, the predicted demand distribution condition needs to be corrected, and a predicted value error correction model is established:
wherein ,a predicted value representing a future point in time, y t+1-i Data representing historical time points, w i The representation of the weighting coefficients can be adjusted as required;
s204, correcting the output of the future demand prediction model by using the predicted value error correction model, and constructing the distribution condition of the demand on the future time node.
9. The digital management method based on artificial intelligence according to claim 8, wherein:
in S3, the resource allocation without the demand is removed in real time according to the distribution situation of the demand, the distribution situation of the demand analyzes the distribution situation of the demand through a future demand prediction model, and the following resource discrimination model is established:
wherein ,Zt Represents the sum of all demand numbers present at time t, y represents demand number, f t (y) represents the result of the assignment to the required number y at time t;
generating a judging mechanism of resource allocation about the generation and disappearance of the demand according to the resource judging model: first, the maximum value of y over the time sequence is collected; secondly, at t, as y changes from 1 to the maximum value, for y=1, i.e. the required number is 1, the matching condition of the actual situation and the value set by y is analyzed, and if the required number is indeed 1 in the actual situation, f t (y) =1, otherwise f t (y) =0, calculating f in this way as y increases t A value of (y); after traversing all y values, f corresponding to each y value is carried out t The values of (y) are all accumulated to give Z t If Z t =0, meaning that there is no need at this time, so the resource allocation can be completely deleted, if Z t >And 0, different allocation of resources is needed according to different demand numbers.
10. The digital management method based on artificial intelligence according to claim 9, wherein:
in S4, the following steps are included:
s401, when new requirements appear, the requirements cannot be summarized because of the difference between the requirements, and characteristic information of the requirements needs to be collected;
s402, digitizing the characteristics of the demands as input vectors of a neural network model, and performing resource customization allocation for the occurring demands by using the neural network, so that the following neural network model is established:
wherein X is represented as a feature vector, y k In order to conceal the output value of the layer one,weight, b k To bias, Z k-1 Is the output of the upper layer,/-, is>To output the output value of the layer, w o Is the weight of the output layer, b o Is the bias of the output layer, z h Is the output of the last hidden layer,/- >As a loss function, m is the number of training samples;
after the neural network model is established, training the neural network model according to the limitation of the input characteristics, and calculating the output value in the neural network for each input characteristic vectorFurther, after deriving the output values in the neural network, a gradient of the loss function value L is calculated>Whereas for each hidden layer k node the gradient of the current node is calculated +.>And calculate the gradient of its input weight and bias by the chain law +.> and />
S404, after calculating the data in the neural network model, applying the data, and firstly, calculating an output value of the neural network by providing an input vector; further, comparing the output value with the true value to calculate the value of the loss function;
next, the gradient of the loss function is used to adjust the network parameters to minimize the loss function; specifically, the gradient is calculated from the output layer in a reverse way, and all the parameters are optimized by all nodes which propagate the error signal from the output layer to the hidden layer and the input layer in a reverse way;
s405, the parameters are further updated by executing the process of adjusting the network parameters, each parameter is updated according to the calculated gradient, and the parameters of the network are optimized by continuous iteration, so that the effect of the demand resource allocation reaches the optimal state.
CN202310709654.0A 2023-06-15 2023-06-15 Digital management system and method based on artificial intelligence Pending CN116663842A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310709654.0A CN116663842A (en) 2023-06-15 2023-06-15 Digital management system and method based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310709654.0A CN116663842A (en) 2023-06-15 2023-06-15 Digital management system and method based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN116663842A true CN116663842A (en) 2023-08-29

Family

ID=87715038

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310709654.0A Pending CN116663842A (en) 2023-06-15 2023-06-15 Digital management system and method based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN116663842A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117666462A (en) * 2024-01-31 2024-03-08 成都苔岑智能设备有限公司 PLC product standardization control system based on independent allocation of multiple parameters

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008428A (en) * 2014-05-19 2014-08-27 上海交通大学 Product service demand forecasting and resource optimization configuration method
CN110443413A (en) * 2019-07-23 2019-11-12 华南理工大学 The construction method of Power Material demand forecast system and Power Material demand model
CN111612183A (en) * 2019-02-25 2020-09-01 北京嘀嘀无限科技发展有限公司 Information processing method, information processing device, electronic equipment and computer readable storage medium
KR102294125B1 (en) * 2020-10-27 2021-08-26 (주)한알 Method and system for predicting product demand using artificial intelligence
CN113361745A (en) * 2021-05-07 2021-09-07 云南电网有限责任公司曲靖供电局 Power distribution network material demand prediction method and system
CN114239385A (en) * 2021-11-30 2022-03-25 南京邮电大学 Intelligent decision making system and method for warehouse resource allocation
WO2022152065A1 (en) * 2021-01-12 2022-07-21 上海追日电气有限公司 Charging and energy supply optimization method and apparatus for charging management system
KR20220115357A (en) * 2021-02-10 2022-08-17 주식회사 티라유텍 A method and apparatus for generating future demand forecast data based on attention mechanism

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008428A (en) * 2014-05-19 2014-08-27 上海交通大学 Product service demand forecasting and resource optimization configuration method
CN111612183A (en) * 2019-02-25 2020-09-01 北京嘀嘀无限科技发展有限公司 Information processing method, information processing device, electronic equipment and computer readable storage medium
CN110443413A (en) * 2019-07-23 2019-11-12 华南理工大学 The construction method of Power Material demand forecast system and Power Material demand model
KR102294125B1 (en) * 2020-10-27 2021-08-26 (주)한알 Method and system for predicting product demand using artificial intelligence
WO2022152065A1 (en) * 2021-01-12 2022-07-21 上海追日电气有限公司 Charging and energy supply optimization method and apparatus for charging management system
KR20220115357A (en) * 2021-02-10 2022-08-17 주식회사 티라유텍 A method and apparatus for generating future demand forecast data based on attention mechanism
CN113361745A (en) * 2021-05-07 2021-09-07 云南电网有限责任公司曲靖供电局 Power distribution network material demand prediction method and system
CN114239385A (en) * 2021-11-30 2022-03-25 南京邮电大学 Intelligent decision making system and method for warehouse resource allocation

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117666462A (en) * 2024-01-31 2024-03-08 成都苔岑智能设备有限公司 PLC product standardization control system based on independent allocation of multiple parameters
CN117666462B (en) * 2024-01-31 2024-05-17 成都苔岑智能设备有限公司 PLC product standardization control system based on independent allocation of multiple parameters

Similar Documents

Publication Publication Date Title
CN111401808A (en) Material agreement inventory demand prediction method based on hybrid model
US11836582B2 (en) System and method of machine learning based deviation prediction and interconnected-metrics derivation for action recommendations
CN109034861A (en) Customer churn prediction technique and device based on mobile terminal log behavioral data
CN115497272B (en) Construction period intelligent early warning system and method based on digital construction
CN117391641B (en) Pilatory production flow management method and system
CN109919423B (en) intelligent water affair management method and system based on deep learning
CN116663842A (en) Digital management system and method based on artificial intelligence
CN112396231B (en) Modeling method and device for space-time data, electronic equipment and readable medium
CN113205223A (en) Electric quantity prediction system and prediction method thereof
JP2023504103A (en) MODEL UPDATE SYSTEM, MODEL UPDATE METHOD AND RELATED DEVICE
US11468271B2 (en) Method of data prediction and system thereof
US20200050982A1 (en) Method and System for Predictive Modeling for Dynamically Scheduling Resource Allocation
CN116245030A (en) Deep learning water demand prediction method with automatic parameter feedback adjustment
CN117671992A (en) Intelligent bus dispatching method and system
Badakhshan et al. Deploying hybrid modelling to support the development of a digital twin for supply chain master planning under disruptions
Shankar et al. Analyzing attrition and performance of an employee using machine learning techniques
CN112514352A (en) Method, device, system, storage medium and terminal for updating scheduling rule
CN115689331A (en) Power transmission and transformation project quantity rationality analysis method based on MLP
Zhang et al. Multivariate and multi-frequency LSTM based fine-grained productivity forecasting for industrial IoT
CN112699235A (en) Method, equipment and system for analyzing and evaluating resume sample data
CN114519444A (en) Hierarchical time sequence prediction method
Jiang et al. Measurement based traffic prediction using fuzzy logic
CN117787569B (en) Intelligent auxiliary bid evaluation method and system
Sample et al. Predicting Trouble Ticket Resolution
WO2022227213A1 (en) Industry recommendation method and apparatus, computer device and storage medium

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