CN111695725A - ATM (automatic teller machine) money adding method and device based on heuristic search - Google Patents
ATM (automatic teller machine) money adding method and device based on heuristic search Download PDFInfo
- Publication number
- CN111695725A CN111695725A CN202010487841.5A CN202010487841A CN111695725A CN 111695725 A CN111695725 A CN 111695725A CN 202010487841 A CN202010487841 A CN 202010487841A CN 111695725 A CN111695725 A CN 111695725A
- Authority
- CN
- China
- Prior art keywords
- cash
- atm
- data
- money
- algorithm
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000013210 evaluation model Methods 0.000 claims abstract description 37
- 238000010845 search algorithm Methods 0.000 claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims description 103
- 238000010276 construction Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004140 cleaning Methods 0.000 claims description 13
- 230000002068 genetic effect Effects 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 7
- 238000002922 simulated annealing Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000012549 training Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 8
- 230000002787 reinforcement Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000002354 daily effect Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011867 re-evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
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
- G06Q10/04—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Technology Law (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Educational Administration (AREA)
Abstract
The invention provides an ATM (automatic Teller machine) money adding method and device based on heuristic search, wherein the ATM money adding method based on the heuristic search comprises the following steps: acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM; generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm; selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model; and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme. The invention effectively improves the accuracy of bank cash consumption management and the intelligent level of cash management, reduces the operation and maintenance cost of the bank ATM, and improves the ATM cash service guarantee rate.
Description
Technical Field
The invention relates to the technical field of cash management of automatic teller machines, in particular to an ATM cash adding method and device based on heuristic search.
Background
An ATM ATM is a device that a commercial bank provides for self-service access to cash to customers. In daily operation, a bank needs to make a reasonable cash adding plan for the governed equipment according to related management requirements so as to ensure the availability of the ATM equipment. At present, ATM cash management is mainly carried out by predicting and generating a cash adding plan by using a machine learning method, and then selecting a reasonable cash adding plan by using a reinforcement learning method on the basis of predicting the cash usage amount in a certain period in the future by using a supervision learning method. Because the number of the related ATMs is large, the search space for making the money adding plan is large, the mode of learning and generating the money adding plan through trial and error in reinforcement learning not only needs huge training data amount, but also consumes long training time.
Disclosure of Invention
Aiming at the problems in the prior art, the ATM cash adding method and device based on heuristic search effectively improve the accuracy of bank cash consumption management and the intelligent level of cash management, reduce the operation and maintenance cost of the bank ATM and improve the ATM cash service guarantee rate.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the invention provides an ATM cash adding method based on heuristic search, which includes:
acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM;
generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm;
selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model;
and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme.
In one embodiment, the step of generating an ATM cost evaluation model comprises:
and generating the ATM cost evaluation model according to historical transaction flow data, historical cash adding data, historical clearing period and historical box cash balance of the ATM by using a supervised learning algorithm.
In one embodiment, the selecting an optimal charging scheme among the plurality of charging schemes by using the pre-generated ATM cost evaluation model includes:
constructing a heuristic algorithm library according to a heuristic search algorithm, wherein the heuristic algorithm comprises the following steps: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm;
generating a characteristic construction method corresponding to the heuristic algorithm;
and generating the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period and the money box balance by using the heuristic search algorithm and the characteristic component method.
In one embodiment, the ATM cash adding method based on heuristic search further includes:
and performing data cleaning and data integration operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the cash clearing period, the historical cash clearing period, the cash box balance and the historical cash box balance.
In a second aspect, the present invention provides an ATM cash adding device based on heuristic search, including:
the data acquisition unit is used for acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM;
the cash adding scheme generating unit is used for generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm;
the cash adding scheme selecting unit is used for selecting an optimal cash adding scheme from the plurality of cash adding schemes by utilizing a pre-generated ATM cost evaluation model;
and the ATM cash adding unit is used for adding cash to the ATM according to the transaction running data, the cash adding data, the clearing period and the cash box balance by using the optimal cash adding scheme.
In one embodiment, the ATM cash adding device based on heuristic search further includes: a model generation unit for generating an ATM cost evaluation model;
the model generation unit is specifically used for generating the ATM cost evaluation model according to historical transaction flow data, historical cash adding data, historical clearing period and historical box cash balance of the ATM by using a supervised learning algorithm.
In one embodiment, the money adding scheme selecting unit includes:
the algorithm library construction module is used for constructing a heuristic algorithm library according to a heuristic search algorithm, wherein the heuristic algorithm comprises the following steps: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm;
the construction method generating module is used for generating a characteristic construction method corresponding to the heuristic algorithm;
and the money adding scheme selection module is used for generating the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period and the money box balance by utilizing the heuristic search algorithm and the characteristic component method.
In one embodiment, the ATM cash adding device based on heuristic search further includes: and the data preprocessing unit is used for performing data cleaning and data integration operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the cash cleaning period, the historical cash cleaning period, the cash box balance and the historical cash box balance.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the ATM cash-in-cash method based on heuristic search when executing the program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a heuristic search based ATM cash-in-place method.
As can be seen from the above description, the ATM banknote adding method and apparatus based on heuristic search provided in the embodiments of the present invention first obtain transaction flow data, banknote adding data, clearing cycle, and banknote box balance of the ATM; then, generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm; selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model; and finally, adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme. The ATM cash adding method and device based on heuristic search effectively improve the accuracy of bank cash consumption management and the intelligent level of cash management, reduce the operation and maintenance cost of bank ATMs and improve the ATM cash service guarantee rate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a first flowchart of a heuristic search based ATM banknote adding method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating step 500 according to an embodiment of the present invention;
FIG. 3 is a flowchart of step 200 in an embodiment of the present invention;
FIG. 4 is a flow chart of a heuristic search based ATM banknote adding method according to an embodiment of the present invention;
FIG. 5 is a flow chart of an ATM cash adding method based on heuristic search in an embodiment of the invention;
FIG. 6 is a block diagram of a first ATM banknote adding device based on heuristic search according to an embodiment of the present invention;
FIG. 7 is a block diagram of a second exemplary ATM banknote adding apparatus according to the present invention, which is based on heuristic search;
fig. 8 is a block diagram of a banknote adding scheme generating unit according to an embodiment of the present invention;
FIG. 9 is a block diagram of a third exemplary ATM banknote adding apparatus according to the present invention, which is based on heuristic search;
fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a specific implementation mode of an ATM (automatic teller machine) money adding method based on heuristic search, and referring to FIG. 1, the method specifically comprises the following steps:
step 100: and acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM.
It is understood that the transaction flow data, the cash adding data, the clearing period and the cash box balance in the step 100 all refer to current data (different from historical data), such as transaction flow data, cash adding data, clearing period and cash box balance of the current day (the current month).
Step 200: and generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm.
The heuristic search algorithm is to evaluate the position of each search by searching in the state space to obtain the best position, and then search from the position until the target. State space search here is a process that represents the problem solving process as finding this path from the initial state to the target state. Because there are many branches in the process of solving the problem, which is mainly caused by uncertainty and incompleteness of the solving conditions in the solving process, a graph is formed by many solving paths, and the graph is a state space. The solution to the problem is actually finding a path in this graph from the beginning to the result. The process of this search is a state space search.
Commonly used state space searches are depth-first and breadth-first. The breadth is preferably looked down layer by layer from the initial state until the target is found. The depth is preferably to find one branch before the other branch in a certain order until the target is found. Breadth and depth first searches have the great disadvantage of being exhaustive in a given state space. This is a suitable algorithm in the case of a small state space, but is not possible when the state space is very large and not predicted. Because of its low efficiency, it is even impossible to accomplish. And the heuristic search algorithm can better solve the problems. Specifically, because the number of the related ATMs is large, and the search space for making the money adding plan is extremely large, the mode of learning and generating the money adding plan through trial and error by reinforcement learning not only needs huge training data amount, but also needs long training time. The method provided in step 200 allows for faster training and provides a reasonable bill loading plan.
Step 300: and selecting an optimal cash adding scheme from the plurality of cash adding schemes by utilizing a pre-generated ATM cost evaluation model.
When the step 300 is implemented, the method specifically comprises the following steps: and (4) modeling the money adding cost in a certain period in the future by using a supervised learning technology (the selection of model algorithms comprises but is not limited to neural network algorithms such as LSTM and traditional machine learning algorithms such as xgboost). Then, the current transaction flow data, the cash adding data, the clearing period and the cash box balance are input into the model, so that the plurality of cash adding schemes generated in the step 200 can be evaluated, and the optimal cash adding scheme is determined. It will be appreciated that the cash dosing scheme evaluated in step 200 using machine learning methods may make cash usage management more efficient and intelligent.
Step 400: and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme.
As can be seen from the above description, the ATM banknote adding method based on heuristic search provided in the embodiment of the present invention first obtains transaction flow data, banknote adding data, clearing cycle, and banknote box balance of the ATM; then, generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm; selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model; and finally, adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme. The ATM cash adding method based on heuristic search provided by the embodiment of the invention effectively improves the accuracy of bank cash consumption management and the intelligent level of cash management, reduces the operation and maintenance cost of the bank ATM, and improves the ATM cash service guarantee rate.
In one embodiment, the ATM cash adding method based on heuristic search further includes:
step 500: generating an ATM cost evaluation model, further, referring to fig. 2, step 500 comprises:
step 501: and generating the ATM cost evaluation model according to historical transaction flow data, historical cash adding data, historical clearing period and historical box cash balance of the ATM by using a supervised learning algorithm.
Cost influencing factors of the ATM cost evaluation model include but are not limited to the length of a cash adding route, the cash adding times, the cash counting processing cost, the cash accounting cost and the cash shortage importance degree. Firstly, a special cost calculation function with the characteristics of the unit region is obtained, and the cost of each day in the past can be obtained by analyzing and processing historical data. But the cost evaluation model fits not the cost of each day, but the sum of the cost costs in one period in the future, called the period cost. The period is selected according to the data condition, and may be 7 days, 30 days, etc.
In the specific implementation of step 500, an initial model of the ATM cost evaluation model is first established according to the cost influencing factors by using a supervised learning algorithm, and then feature data capable of being directly related to the cost is extracted and constructed. And training the initial model according to the characteristic data and a corresponding supervised learning algorithm to generate an ATM cost evaluation model.
In one embodiment, referring to fig. 3, step 200 specifically includes:
step 201: constructing a heuristic algorithm library according to a heuristic search algorithm, wherein the heuristic algorithm comprises the following steps: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm.
Specifically, step 201 provides a set of predetermined heuristics and provides a set of algorithm attempts. The heuristic algorithm library includes, but is not limited to, ant colony algorithm, particle swarm algorithm, genetic algorithm, simulated annealing algorithm. Since the heuristic algorithm cannot guarantee the searching effect, the evaluation of the capability of searching a reasonable money adding plan for each algorithm is required before the system is started. And selecting and calling an algorithm with strong capability for many times to search the money adding plan according to the capability evaluation, and calling an algorithm with poor capability for one time as a supplement so as to obtain relatively stable money adding plan output.
Step 202: and generating a characteristic construction method corresponding to the heuristic algorithm.
Step 202 provides a specific feature construction method for various heuristic algorithms. It can be understood that different heuristic algorithms have different feature search modes, and different feature search modes require different feature construction modes to be selected to ensure the search capability and stability of the algorithms. Taking a genetic algorithm as an example, the feature construction is called encoding, and the mainstream encoding modes include binary encoding, gray code, floating point number encoding and the like.
Step 203: and generating the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period and the money box balance by using the heuristic search algorithm and the characteristic component method.
Specifically, two control modes are provided to determine whether the heuristic algorithm continues to search, and the main control modes include two. The first is time control, which allows the heuristic algorithm to run for a certain time, stopping the algorithm immediately after reaching a running time threshold. And secondly, round control, namely setting a maximum evolution algebra in the genetic algorithm, and stopping the algorithm when the algorithm runs to the maximum algebra. Further, in step 203, in implementation, each round of searching using the heuristic search algorithm generates a solution, and the solution of each round is evaluated by the cost evaluation model. And the heuristic search algorithm generates a scheme in the next round, and the process is circulated until a search ending condition is reached, and the scheme with the best evaluation result is returned. Additionally, it can be appreciated that step 303 reduces the time-consuming training of the model and the amount of training data required compared to reinforcement learning based methods.
In one embodiment, referring to fig. 4, the ATM cash adding method based on heuristic search further includes:
step 600: and performing data cleaning and attribute identification operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the clearing period, the historical clearing period, the cash box balance and the historical cash box balance.
Specifically, step 600 mainly includes data cleaning operations such as missing value processing and noise processing, and data integration operations such as data integration and redundancy removal, and data reduction and transformation are also performed when necessary. Through data preprocessing and data noise removal, the method can be better used for subsequent model training.
To further illustrate the present solution, the present invention provides a specific application example of the ATM banknote adding method based on heuristic search, which specifically includes the following contents, see fig. 5.
S1: and acquiring service data.
And acquiring 8 predicted demands of the original service data and the cash demand prediction model (data of service data such as the predicted cash demand within 1 day, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days and 8 days of the ATM in the future). The method specifically comprises the following steps: the transaction flow data of the ATM, the historical transaction flow data (past 28 days), the cash adding data, the historical cash adding data, the clearing period, the historical clearing period, the cash box balance, the historical transaction flow data and cash balance data, legal festivals and holidays related to the cash usage amount and the date data of the cash center allowing the cash adding, weather conditions, the geographical position of equipment, the paying date and repayment date of a branch bank, and the like.
S2: the data is pre-processed.
And performing missing value processing and noise processing on the service data, identifying useful attributes and removing redundant parts to finally obtain high-quality data.
S3: data characteristics are acquired.
And obtaining a group of proper characteristics through business rules, manual experience, characteristic combination and characteristic screening. And taking the data as a sample every day, and calculating the data characteristics of each sample. Specifically, the business personnel can know which factors are used by the business personnel to evaluate the cost according to the experience of the business personnel, and the factors are constructed as characteristic data. All feature data that may be helpful in assessing cost penalties is constructed from experience with traditional machine learning to construct features. And finally, combining and screening the characteristic data. The method for combining the feature data is to select any plurality of feature data to be combined into new feature data, and the feature data which can be constructed by the feature data combination is extremely numerous, so that the feature data importance evaluation algorithm is required to evaluate the necessity of the feature, and the feature data is selected by referring to the evaluation result. And combining the characteristics obtained by the factors to finally obtain a characteristic table.
S4: a cost evaluation model is generated.
And training an initial model of the cost evaluation model, selecting a proper algorithm for model training according to regular data characteristics and data label values, and further generating the cost evaluation model.
S5: and selecting an optimal money adding method by using a heuristic search algorithm and a cost evaluation model.
And stopping training when the model training reaches the standard according to the preset maximum training batch or the maximum acceptable average error. Specifically, daily traffic status data is first acquired. And respectively calling the algorithms in the heuristic algorithm library. And respectively operating various heuristic algorithms, comparing the heuristic algorithms with the cost information of the money adding plan, and performing primary evaluation on the capability of the heuristic algorithms. And constructing data characteristics according to the algorithm type. Different feasible data feature construction methods are tried on various heuristic algorithms and operated respectively, and the algorithm combination capability of each algorithm and each feature construction method is preliminarily evaluated. The algorithm is invoked until a stop condition is triggered. And selecting the algorithm combination with higher capability to run for multiple times as a main searching algorithm and the algorithm combination with lower capability to run for one time as supplement according to the initial evaluation of the algorithm combination capability of each type of heuristic algorithm and each feasible feature construction method. The stopping of the algorithm operation is controlled by a preset maximum time or maximum number of iterations each time.
It will be appreciated that if the model fails to meet the criteria, the model is retrained. Or when the accumulated error reaches a preset threshold value, the cost evaluation model is unqualified, and a retraining mode is needed to be adopted to optimize the model. Specifically, the daily actual cash-in cost is obtained. After the system runs for a period, a period cost penalty can be calculated daily. The effect of the cost evaluation model can be evaluated by calculating the error between the real periodic cost and the periodic cost output by the model. And if the model effect reaches the standard, continuing training the model temporarily. And when the accumulated error is lower and does not reach the preset threshold value, continuing training the model.
S6: the optimal method of adding banknotes is checked.
Firstly, business feedback information is obtained, and quality feedback information of a bill adding plan generated by business personnel to the system is obtained in the running process of the system. If the quality of the bill adding plan is good, the model is not modified. The money adding plan given by the system obtains good quality evaluation, and the system does not need to carry out any operation. And if the quality of the bill adding plan is poor, optimizing a heuristic algorithm library and adjusting a search control threshold value at the same time. If the bill adding plan given by the system obtains the evaluation of poor quality, the heuristic algorithm combination needs to be adjusted, and the algorithm combination is optimized through the re-evaluation algorithm capability. Meanwhile, the control threshold value of the heuristic algorithm is increased, and the heuristic algorithm is operated to perform more operations.
As can be seen from the above description, the ATM banknote adding method based on heuristic search provided in the embodiment of the present invention first obtains transaction flow data, banknote adding data, clearing cycle, and banknote box balance of the ATM; then, generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm; selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model; and finally, adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme. Specifically, the cash adding cost in a certain period in the future is modeled by using a supervised learning technology, and then the cash adding plan is intelligently planned by adopting a heuristic search technology, so that a basic ATM cash adding plan is provided for business personnel, the workload of related business personnel of a bank is reduced, and the real cash consumption management efficiency is improved. Specifically, the invention has the following beneficial effects:
the invention comprehensively considers the transportation cost, the clearing cost and the cash cost of money adding to intelligently evaluate the money adding cost, and automatically selects a better money adding plan under the ATM management requirement through a heuristic algorithm. Compared with a method based on reinforcement learning, the method reduces the time consumed by model training, effectively improves the accuracy of bank cash consumption management and the intelligent level of cash management, reduces the operation and maintenance cost of the bank ATM, and improves the ATM cash service guarantee rate. In addition, the invention overcomes the defects of long time consumption, large data demand and the like in the current bank cash adding plan established by using reinforcement learning, can quickly finish training and provide a reasonable cash adding plan, provides an intelligent establishing method for the cash adding plan which is quickly deployed on line for the bank, and ensures that the real object cash amount management is more efficient and intelligent.
Based on the same inventive concept, the embodiment of the present application further provides an ATM cash adding device based on heuristic search, which can be used to implement the methods described in the above embodiments, such as the following embodiments. Because the principle of solving the problems of the ATM cash adding device based on heuristic search is similar to that of the ATM cash adding method based on heuristic search, the ATM cash adding device based on heuristic search can be implemented by the ATM cash adding method based on heuristic search, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
The embodiment of the invention provides a specific implementation mode of an ATM cash adding device based on heuristic search, which can realize an ATM cash adding method based on heuristic search, and referring to FIG. 6, the ATM cash adding device based on heuristic search specifically comprises the following contents:
the data acquisition unit 10 is used for acquiring transaction flow data, money adding data, clearing cycle and money box balance of the ATM;
the cash adding scheme generating unit 20 is used for generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm;
a cash adding scheme selecting unit 30, configured to select an optimal cash adding scheme from the plurality of cash adding schemes by using a pre-generated ATM cost evaluation model;
and the ATM cash adding unit 40 is used for adding cash to the ATM according to the transaction running data, the cash adding data, the clearing period and the cash box balance by using the optimal cash adding scheme.
In one embodiment, referring to fig. 7, the ATM cash adding apparatus based on heuristic search further includes: a model generation unit 50 for generating an ATM cost evaluation model;
the model generating unit 50 is specifically configured to generate the ATM cost evaluation model according to the historical transaction flow data, the historical cash adding data, the historical clearing period, and the historical cash balance of the ATM by using a supervised learning algorithm.
In one embodiment, referring to fig. 8, the bill adding scheme generating unit 20 includes:
an algorithm library construction module 201, configured to construct a heuristic algorithm library according to a heuristic search algorithm, where the heuristic algorithm includes: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm;
a construction method generation module 202, configured to generate a feature construction method corresponding to the heuristic algorithm;
and the money adding scheme generating module 203 is configured to generate the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period, and the money box balance by using the heuristic search algorithm and the feature component method.
In one embodiment, referring to fig. 9, the ATM cash adding apparatus based on heuristic search further includes: and the data preprocessing unit 60 is used for performing data cleaning and data integration operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the cash cleaning period, the historical cash cleaning period, the cash box balance and the historical cash box balance.
As can be seen from the above description, the ATM banknote adding apparatus based on heuristic search provided in the embodiment of the present invention first obtains transaction flow data, banknote adding data, clearing cycle, and banknote box balance of the ATM; then, generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm; selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model; and finally, adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme. Specifically, the cash adding cost in a certain period in the future is modeled by using a supervised learning technology, and then the cash adding plan is intelligently planned by adopting a heuristic search technology, so that a basic ATM cash adding plan is provided for business personnel, the workload of related business personnel of a bank is reduced, and the real cash consumption management efficiency is improved. Specifically, the invention has the following beneficial effects:
the invention comprehensively considers the transportation cost, the clearing cost and the cash cost of money adding to intelligently evaluate the money adding cost, and automatically selects a better money adding plan under the ATM management requirement through a heuristic algorithm. Compared with a method based on reinforcement learning, the method reduces the time consumed by model training, effectively improves the accuracy of bank cash consumption management and the intelligent level of cash management, reduces the operation and maintenance cost of the bank ATM, and improves the ATM cash service guarantee rate. In addition, the invention overcomes the defects of long time consumption, large data demand and the like in the current bank cash adding plan established by using reinforcement learning, can quickly finish training and provide a reasonable cash adding plan, provides an intelligent establishing method for the cash adding plan which is quickly deployed on line for the bank, and ensures that the real object cash amount management is more efficient and intelligent.
The embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all steps in the ATM cash adding method based on heuristic search in the foregoing embodiment, and referring to fig. 10, the electronic device specifically includes the following contents:
a processor (processor)1201, a memory (memory)1202, a communication interface 1203, and a bus 1204;
the processor 1201, the memory 1202 and the communication interface 1203 complete communication with each other through the bus 1204; the communication interface 1203 is used for implementing information transmission between related devices such as a server-side device, a computing unit, a client device, and the like.
The processor 1201 is configured to call the computer program in the memory 1202, and the processor executes the computer program to implement all the steps in the ATM banknote adding method based on heuristic search in the above embodiments, for example, the processor executes the computer program to implement the following steps:
step 100: and acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM.
Step 200: and generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm.
Step 300: and selecting an optimal cash adding scheme from the plurality of cash adding schemes by utilizing a pre-generated ATM cost evaluation model.
Step 400: and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme.
Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps in the heuristic search based ATM banknote adding method in the foregoing embodiments, where the computer-readable storage medium stores a computer program, and the computer program when executed by a processor implements all steps of the heuristic search based ATM banknote adding method in the foregoing embodiments, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: and acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM.
Step 200: and generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm.
Step 300: and selecting an optimal cash adding scheme from the plurality of cash adding schemes by utilizing a pre-generated ATM cost evaluation model.
Step 400: and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An ATM cash adding method based on heuristic search is characterized by comprising the following steps:
acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM;
generating a plurality of money adding schemes of the ATM according to the transaction flow data, the money adding data, the clearing period, the money box balance and a heuristic search algorithm;
selecting an optimal money adding scheme from the plurality of money adding schemes by utilizing a pre-generated ATM cost evaluation model;
and adding money to the ATM according to the transaction running data, the money adding data, the clearing period and the money box balance by using the optimal money adding scheme.
2. An ATM cash-in method according to claim 1, wherein the step of generating an ATM cost evaluation model comprises:
and generating the ATM cost evaluation model according to historical transaction flow data, historical cash adding data, historical clearing period and historical box cash balance of the ATM by using a supervised learning algorithm.
3. The ATM cash-in method of claim 1, wherein the generating of the plurality of cash-in schemes of the ATM based on the transaction flow data, the cash-in data, the clearing cycle, the cash box balance, and a heuristic search algorithm comprises:
constructing a heuristic algorithm library according to a heuristic search algorithm, wherein the heuristic algorithm comprises the following steps: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm;
generating a characteristic construction method corresponding to the heuristic algorithm;
and generating the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period and the money box balance by using the heuristic search algorithm and the characteristic component method.
4. An ATM cash-in method according to claim 1, further comprising:
and performing data cleaning and data integration operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the cash clearing period, the historical cash clearing period, the cash box balance and the historical cash box balance.
5. An ATM cash adding device based on heuristic search is characterized by comprising:
the data acquisition unit is used for acquiring transaction flow data, money adding data, clearing period and money box balance of the ATM;
the cash adding scheme generating unit is used for generating a plurality of cash adding schemes of the ATM according to the transaction running data, the cash adding data, the clearing period, the cash box balance and a heuristic search algorithm;
the cash adding scheme selecting unit is used for selecting an optimal cash adding scheme from the plurality of cash adding schemes by utilizing a pre-generated ATM cost evaluation model;
and the ATM cash adding unit is used for adding cash to the ATM according to the transaction running data, the cash adding data, the clearing period and the cash box balance by using the optimal cash adding scheme.
6. An ATM cash adding apparatus according to claim 5, further comprising: a model generation unit for generating an ATM cost evaluation model;
the model generation unit is specifically used for generating the ATM cost evaluation model according to historical transaction flow data, historical cash adding data, historical clearing period and historical box cash balance of the ATM by using a supervised learning algorithm.
7. An ATM cash adding apparatus according to claim 5, wherein the cash adding scheme generating unit includes:
the algorithm library construction module is used for constructing a heuristic algorithm library according to a heuristic search algorithm, wherein the heuristic algorithm comprises the following steps: ant colony algorithm, particle swarm algorithm, genetic algorithm and simulated annealing algorithm;
the construction method generating module is used for generating a characteristic construction method corresponding to the heuristic algorithm;
and the money adding scheme generating module is used for generating the plurality of money adding schemes according to the transaction running data, the money adding data, the clearing period and the money box balance by utilizing the heuristic search algorithm and the characteristic component method.
8. An ATM cash adding apparatus according to claim 5, further comprising:
and the data preprocessing unit is used for performing data cleaning and data integration operation on the transaction flow data, the historical transaction flow data, the cash adding data, the historical cash adding data, the cash cleaning period, the historical cash cleaning period, the cash box balance and the historical cash box balance.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for ATM banking based on a heuristic search of one of the claims 1 to 4.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for ATM banking based on a heuristic search of one of the claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010487841.5A CN111695725A (en) | 2020-06-02 | 2020-06-02 | ATM (automatic teller machine) money adding method and device based on heuristic search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010487841.5A CN111695725A (en) | 2020-06-02 | 2020-06-02 | ATM (automatic teller machine) money adding method and device based on heuristic search |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111695725A true CN111695725A (en) | 2020-09-22 |
Family
ID=72479238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010487841.5A Pending CN111695725A (en) | 2020-06-02 | 2020-06-02 | ATM (automatic teller machine) money adding method and device based on heuristic search |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695725A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191880A (en) * | 2021-05-24 | 2021-07-30 | 中国工商银行股份有限公司 | Bank teller terminal cash adding suggestion determination method and device |
| CN113593147A (en) * | 2021-08-03 | 2021-11-02 | 中国银行股份有限公司 | ATM balance display method, device, server, medium and product |
| CN114233142A (en) * | 2021-11-19 | 2022-03-25 | 中国建设银行股份有限公司 | Safe box monitoring method and device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5291477A (en) * | 1992-08-10 | 1994-03-01 | Bell Communications Research, Inc. | Method and system for multicast routing in an ATM network |
| US20130091088A1 (en) * | 2011-10-07 | 2013-04-11 | George Forman | Making a recommendation to a user that is currently generating events based on a subset of historical event data |
| JP2017058194A (en) * | 2015-09-15 | 2017-03-23 | アイシン・エィ・ダブリュ株式会社 | Route search system, route search method and computer program |
| CN109472693A (en) * | 2018-11-19 | 2019-03-15 | 中国银行股份有限公司 | A kind of ATM cash concocting method and device |
| CN110415462A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Atm device adds paper money optimization method and device |
| US20200167839A1 (en) * | 2018-11-23 | 2020-05-28 | International Business Machines Corporation | Intelligent dynamic parking for autonomous vehicles |
-
2020
- 2020-06-02 CN CN202010487841.5A patent/CN111695725A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5291477A (en) * | 1992-08-10 | 1994-03-01 | Bell Communications Research, Inc. | Method and system for multicast routing in an ATM network |
| US20130091088A1 (en) * | 2011-10-07 | 2013-04-11 | George Forman | Making a recommendation to a user that is currently generating events based on a subset of historical event data |
| JP2017058194A (en) * | 2015-09-15 | 2017-03-23 | アイシン・エィ・ダブリュ株式会社 | Route search system, route search method and computer program |
| CN109472693A (en) * | 2018-11-19 | 2019-03-15 | 中国银行股份有限公司 | A kind of ATM cash concocting method and device |
| US20200167839A1 (en) * | 2018-11-23 | 2020-05-28 | International Business Machines Corporation | Intelligent dynamic parking for autonomous vehicles |
| CN110415462A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Atm device adds paper money optimization method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191880A (en) * | 2021-05-24 | 2021-07-30 | 中国工商银行股份有限公司 | Bank teller terminal cash adding suggestion determination method and device |
| CN113593147A (en) * | 2021-08-03 | 2021-11-02 | 中国银行股份有限公司 | ATM balance display method, device, server, medium and product |
| CN114233142A (en) * | 2021-11-19 | 2022-03-25 | 中国建设银行股份有限公司 | Safe box monitoring method and device, computer equipment and storage medium |
| CN114233142B (en) * | 2021-11-19 | 2023-10-31 | 中国建设银行股份有限公司 | Safe box monitoring method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415462B (en) | ATM equipment banknote adding optimization method and device | |
| Paithankar et al. | Open pit mine production schedule optimization using a hybrid of maximum-flow and genetic algorithms | |
| CN111695725A (en) | ATM (automatic teller machine) money adding method and device based on heuristic search | |
| Gutierrez-Rodríguez et al. | Selecting meta-heuristics for solving vehicle routing problems with time windows via meta-learning | |
| Kim et al. | An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms | |
| Kim et al. | Robust multiarmed bandit problems | |
| Malitsky et al. | Tuning parameters of large neighborhood search for the machine reassignment problem | |
| CN110490392A (en) | Site bank note distribution method and device | |
| US20210042297A1 (en) | Automated feature generation for machine learning application | |
| CN109324905A (en) | Database operation method, device, electronic equipment and storage medium | |
| CN110288460A (en) | Collection prediction technique, device, equipment and storage medium based on propagated forward | |
| CN110633863A (en) | Bank note distribution prediction method and device based on GBDT algorithm | |
| Armenise et al. | A generative solution for ATM cash management | |
| Pedersen et al. | Optimizing a condition-based maintenance policy by taking the preferences of a risk-averse decision maker into account | |
| Shaabani et al. | A matheuristic for the multi-product maritime inventory routing problem | |
| CN113191880A (en) | Bank teller terminal cash adding suggestion determination method and device | |
| Hu et al. | Challenges of automated machine learning on causal impact analytics for policy evaluation | |
| Cai et al. | Robust multi-equipment scheduling for U-shaped container terminals concerning double-cycling mode and uncertain operation time with cascade effects | |
| US20230267007A1 (en) | System and method to simulate demand and optimize control parameters for a technology platform | |
| Ghodrati et al. | ATM cash management using genetic algorithm | |
| CN115375474A (en) | Information prompting method and device and electronic equipment | |
| KR102433431B1 (en) | Improved prediction system and prediction method using heterogeneous data | |
| Guan et al. | Constructing interdependent risks network of project portfolio based on bayesian network | |
| Yaakoubi et al. | A data-driven approach for the simultaneous stochastic optimization of mining complexes | |
| Li et al. | Gate appointment design in a container terminal: A robust optimization approach |
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 |