WO2014097011A1

WO2014097011A1 - A method and system for managing data units in a plurality of unit stores

Info

Publication number: WO2014097011A1
Application number: PCT/IB2013/060233
Authority: WO
Inventors: Sundara Srikanth SAMPARA
Original assignee: S S Analytics Solutions Private Limited
Priority date: 2012-12-19
Filing date: 2013-11-19
Publication date: 2014-06-26

Abstract

Embodiment of the present disclosure relates to a method for managing data units in a plurality of unit stores. The method comprises acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores by an acquiring module configured in a central server. The central server is communicatively connected to the plurality of unit stores over a distributed network. The acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores are pre- processed by a pre-processing module configured in the central server to obtain one or more transformed data pertaining to the acquired one or more behavioral data. A quantity of the data units are predicted which are required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data by a prediction module configured in the central server. Replenishment schedules are generated for the one or more unit stores by an optimization module configured in the central server. The replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores. At least one route plan is generated by a route generation module configured in the central server to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

Description

A METHOD AND SYSTEM FOR MANAGING DATA UNITS IN A PLURALITY

OF UNIT STORES

CROSS-REFERENCE TO RELATED APPLICATION The present application claims priority to Indian patent application serial number 5320/CHE/2012 filed on December 19, 2012, the entire contents of which are incorporated by reference.

TECHNICAL FIELD

Embodiments of the present disclosure relate to data management and forecasting system in a distributed network environment. More particularly, embodiments of the present disclosure relate to method and system for managing data units in a plurality of unit stores.

BACKGROUND OF THE DISCLOSURE

Generally, unit stores, for example, cash dispensing machines are located at places such as banks, stores, shopping malls, or indeed anywhere where people need the convenience of being able to withdraw cash. The unit stores are located in remote areas as well. The cash dispensing machines are referred to as Automated Teller Machines (ATMs) that are associated to a bank or financial institution or an enterprise. Each of the cash dispensing machines holds some amount of cash that could be withdrawn by one or more users. Some cash dispensing machines are regularly in use by the users whereas some cash dispensing machines are not used in a regular pattern by the users. For example, cash dispensing machines located in stores, shopping malls etc. are used frequently. The cash dispensing machines located in remote areas are used less frequently as compared to the cash dispensing machines located in busy areas. The cash in cash dispensing machines used in regular pattern are referred to as non-idle-cash. Whereas, cash in the cash dispensing machines which are not used in regular pattern are referred to as idle-cash.

Cash has cost and financial institutions or enterprises or banks always like to have minimal idle-cash. However, the existing arts do not provide any method for managing the idle-cash. Managing the idle-cash in a variety of ways, for example, transferring the cash at right time and in right quantity to the cash dispensing machines which are out of cash etc. is a challenge. This is because such management of the cash requires high level of predictions on cash demands. Conventionally, rudimentary demand forecasting models are used, which perform most of the cash handling decisions based on rules related to economic re-order quantities and minimum threshold levels. These levels are set purely based on experiences of individuals and human intuition. However, as the enterprises are expanding, the approach based on human intuition is not scaling up to meet the requirement of actual business scenario.

Further, conventional methods do not perform predicting and forecasting cash requirement at right time and in right quantity with proper replenishment schedules and cash movement. Furthermore, conventional methods still rely on human intuition and basic (for example, excel based) forecasting methods to understand the demand for cash in spite of automation. The same challenge pertains to unit stores related to commodities, gadgets and other related unit stores in banks, or financial institutions or Forex (foreign exchange market). Therefore, there is a need to provide a method for consuming idle data units, for example, cash at right time and in right quantity with proper replenishment schedules and route planning for deployment.

SUMMARY

The shortcomings of the prior art are overcome through the provision of a method and a system as described in the description.

A system for managing data units in real-time is disclosed as an embodiment of the present disclosure. The system comprises a plurality of unit stores and a central server. The plurality of unit stores comprises data units. The central server is communicatively connected to the plurality of unit stores over a distributed network. The central server comprises an acquiring module, a pre-processing module, a prediction module, an optimization module and a route generation module. The acquiring module acquires one or more behavioral data associated to one or more unit stores of the plurality of unit stores. The pre-processing module pre-processes the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data. The prediction module predicts a quantity of the data units required at one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data. The optimization module generates replenishment schedules for the one or more unit stores. The replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores. The route generation module generates at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules. Embodiment of the present disclosure is related to a non-transitory computer readable medium including operations stored thereon for real-time managing data units in a plurality of unit stores which is processed by a central server. The central server is communicatively connected to the plurality of unit stores over a distributed network. The central server performs acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores. Pre-processing the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data. Predicting a quantity of the data units required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data. Generating replenishment schedules for the one or more unit stores, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores. Generating at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

A computer program for real-time managing data units in a plurality of unit stores is disclosed as an embodiment of the present disclosure. The computer program comprises code segment for acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores. A code segment for pre-processing the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data. A code segment for predicting a quantity of the data units required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data. A code segment generating replenishment schedules for the one or more unit stores, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores. A code segment for generating at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The features of the present disclosure are set forth with particularity in the appended claims. The disclosure itself, together with further features and attended advantages, will become apparent from consideration of the following detailed description, taken in conjunction with the accompanying drawings. One or more embodiments of the present disclosure are now described, by way of example only, with reference to the accompanied drawings wherein like reference numerals represent like elements and in which: Figure 1 illustrates an exemplary high level system for managing data units in a plurality of unit stores according to an embodiment of the present disclosure;

Figure 2 illustrates a block diagram of central server with various modules engaged in managing data units in a plurality of unit stores according to an embodiment of the present disclosure; and

Figure 3 shows an exemplary flowchart illustrating a method for managing data units according to an embodiment of the present disclosure.

The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION

The foregoing has broadly outlined the features and technical advantages of the present disclosure in order that the detailed description of the disclosure that follows may be better understood. Additional features and advantages of the disclosure will be described hereinafter which form the subject of the claims of the disclosure. It should be appreciated by those skilled in the art that the conception and specific embodiment disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure. It should also be realized by those skilled in the art that such equivalent constructions do not depart from the spirit and scope of the disclosure as set forth in the appended claims. The novel features which are believed to be characteristic of the disclosure, both as to its organization and method of operation, together with further objects and advantages will be better understood from the following description when considered in connection with the accompanying figures. It is to be expressly understood, however, that each of the figures is provided for the purpose of illustration and description only and is not intended as a definition of the limits of the present disclosure. Embodiment of the present disclosure relates to make an efficient use of data units. More particularly, embodiment of the present disclosure relates to management of the data units in unit stores. The data units include, but are not limited to, monetary resources such as cash and non-monetary resources such as commodities, products, and groceries etc. In some unit stores, the data units are regular in use whereas in other unit stores, the data units are idle in usage. Therefore, the data units which are idle in usage are optimized towards the one or more unit stores which are out of stock of the data units in order to maintain minimal idle data units in all the unit stores. Hence, for optimizing the data units, the present disclosure provides a method which includes analyzing behavioral data of the one or more unit stores associated to an enterprise or financial institution or bank or branch of bank. The behavioral data of the one or more unit stores are acquired and are pre-processed to obtain a transformed data. From the transformed data, a prediction is performed on quantity of data units required by the one or more unit stores which are out of stock of the data units. To replenish the predicted quantity of the data units to the one or more unit stores, replenishment schedules are generated which includes the quantity of data unit to be refilled, time intervals at which the data units are required by the one or more unit stores and denomination in which the quantity of the data units are required. For replenishing the data units, at least one route plan is generated through which the data units are deployed in the one or more unit stores requiring the data units to make use of data units idle in usage and thus eliminate out of stock state of the data units in the unit stores.

Henceforth, embodiments of the present disclosure are explained with the help of exemplary diagrams and one or more examples. However, such exemplary diagrams and examples are provided for the illustration purpose for better understanding of the present disclosure and should not be construed as limitation on scope of the present disclosure.

Figure 1 illustrates an exemplary high level system with a plurality of unit stores (100) (1) 100 (2),...., 100 (n), collectively referred to as (100), a central server 104 and one or more computing devices 106 connected over a distributed network 102 according to an embodiment of the present disclosure. The system includes n number of unit stores. In a non-limiting embodiment, the plurality of unit stores (100) are storage stores including, but not limited to, Automated Teller Machines (ATMs), financial institutions, Forex related stores, commercial stores, product stores, commodities stores, grocery stores and other related unit stores. The plurality of unit stores 100 are associated to establishments including, but not limiting to, an enterprise, industry, commercial establishment, finance related establishment, foreign exchange market (currency market), and other establishments. For example, XYZ bank is considered to be an enterprise and there exists n number of unit stores such as ATMs associated to the XYZ bank. In an embodiment, the plurality of unit stores 100 is associated to single establishment. For example, ATM 1, ATM 2, ATM 3,...., ATM n are associate to XYZ bank. Each of the plurality of unit stores 100 comprises data units. The data units can be resources including, but not limited to, monetary resources and non-monetary resources. The monetary resources include currency, cash etc. The non-monetary resources include, but does not limit to, commodities, products, groceries etc. Few non-limiting examples of non-monetary resources could be electronic appliances, jewelry, fabrics, and etc. In an embodiment, the plurality of unit stores 100 includes monetary storage units 101a (1), ...101a (n) referred to as 101a and non-monetary servers 101b (l),...,(n) referred to as 101b . The monetary storage units store the monetary resources and the non-monetary storage units store the non-monetary resources. The information of the monetary resources and the non-monetary resources in the monetary storage units and the non-monetary storage units are maintained by monetary servers 101a and non-monetary serverslOlb respectively. Each of the monetary server and the non-monetary server comprises a processing unit and a storage unit. The processing unit of each of the monetary server and the non-monetary server maintain inflow, outflow, deposit, withdrawal, supply, consumption and delivery of monetary resources and non-monetary resources.

The distributed network 102 includes, but does not limit to, a wide-area-network (WAN), wireless network such as Internet and WIFI etc. and a peer to peer (P2P) network. In a preferred embodiment, the WAN is the Internet network representing all of the lines, equipment, and connection points that make up the Internet as a whole, including any connected sub-networks. Therefore, there are no geographic limitations to the practice of the technology disclosed in the present disclosure. WAN may be referred to in this specification as Internet reflecting the preferred application of the present invention to perform real-time management of the data units in the plurality of unit stores.

The central server 104 is communicatively connected to the plurality of unit stores 100 over the distributed network 102. In an embodiment, the central server 104 is a server owned by a service provider who manages the data units in the plurality of servers. In an embodiment, the central server 104 is owned by one or more establishments such as enterprise, industry, commercial establishment, finance related establishment, foreign exchange market (currency market), and other establishments. The central server 104 is involved in performing management of the data units in the plurality of unit stores 100. Particularly, the central server 104 is communicatively connected to the monetary servers 101a and the non-monetary servers 101b through the distributed network 102 to retrieve information on the data units' i.e. monetary resources and the non-monetary resources for managing the data units in the plurality of unit stores 100. In an embodiment, the plurality of unit stores 100 and the central server 104 are participating in the peer-to-peer network environment. The peer-to-peer network environment includes acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores, transmitting a prediction of quantity of data units required at the one or more unit stores, replenishment schedules and route plans which are generated to replenis and deploy the data units at the one or more unit stores requiring a certain quantity of the data units.

The predicted quantity of data units, the replenishment schedules and the route plan are transmitted to the one or more computing devices 106 over the distributed network 102. The one or more computing devices 106 include, but are not limited to computer, Electronic Data Capture (EDC), a mobile phone, a Personal Digital Assistants (PDA), contactless device and other communication devices. In an embodiment, the one or more computing devices 106 are communicatively connected to the plurality of unit stores 100 and the central server 104 over the distributed network 102. The one or more computing devices 106 receive and display the predicted quantity of data units, replenishment schedules and the route plan. One or more users can view the prediction of the quantity of the data units, replenishment schedules for replenishing the data units at the one or more unit stores, and route plans for deploying the predicted quantity of the data units at the one or more unit stores through the one or more computing devices 106. In an embodiment, the prediction of the quantity of the data units, replenishment schedules, and route plans for deploying the predicted quantity of the data units at the one or more unit stores is provided on a display unit (not shown in figure 1) of the one or more unit stores of the plurality of unit stores 100, monetary servers, and non-monetary servers. Figure 2 illustrates a block diagram of central server 104 managing the data units in a plurality of unit stores 100 according to an embodiment of the present disclosure. The central server 104 comprises an acquiring module 202, a pre-processing module 204, a prediction module 206, an optimization module 208 and a route generation module 210. The acquiring module 202 acquires one or more behavioral data associated to the one or more unit stores of the plurality of unit stores 100. The one or more behavioral data comprises usage data, geographical data, financial data and temporal data.

The usage data comprises data relating to data units' deposits, data units' withdrawals, data units' transfer and data units' exchange with respect to the plurality of unit stores, data units supply, data units delivery, and data units consumption.

The data units' deposits are related to depositing of the data units in the one or more unit stores of the plurality of unit stores 100. For example, considering monetary storage units such as ATMs, an amount of Rs. l lakh is deposited at the ATM 1 of a XYZ bank, Rs.50000 is deposited at the ATM 2 of the XYZ bank, and Rs.45000 is deposited at the ATM 67 of the XYZ bank etc. The amount of Rs. l lakh, Rs.50000 and Rs.45000 are referred to as data units which are deposited at the ATM 1, ATM 2 and ATM 67 respectively of the XYZ bank. Another example, considering a bank such as XYZ bank in which a bulk of cash is deposited, then the bulk of cash which is being deposited is referred to as data unit deposits. The data units' withdrawals are amount being withdrawn from the one or more unit stores of the plurality of unit stores 100. For example, considering a predetermined time period of 4 hours within which a total of Rs.50000 is withdrawn from ATM 1 of the XYZ bank, Rs.3000 is withdrawn from ATM 6 of the XYZ bank and Rs.25000 is withdrawn from ATM 12 of the XYZ bank. Withdrawing of Rs.50000, Rs.3000 and Rs.25000 are referred to as data units' withdrawals which are being withdrawn from ATM 1, ATM 6 and ATM 12 respectively of the XYZ bank.

The data units transfer is related to transfer a certain amount of data units to the one or more unit stores of the plurality of unit stores 100. For example, Rs.50000 is transferred to ATM 1, and Rs.20000 is transferred to ATM 6 etc. Transferring of Rs.50000 and Rs.20000 to ATM 1 and ATM 6 respectively is referred to as data units transfer.

The data units exchange is related to Forex such as exchanging the data unit from one form of currency to another form of currency. For example, considering the monetary resources, exchanging data units of dollars for rupee currency is referred to as data units' exchange.

The data units supply is related to supply of data units to the one or more unit stores of the plurality of unit stores 100. For example, considering the non-monetary resources such as electronic appliances associated to commercial establishment, supplying a bulk of electronic appliances to a branch of the commercial establishment is referred to as data unit supply. The data units' delivery is related to delivery of data units to the one or more unit stores. For example, considering the non-monetary resources, delivery of electronic appliances to branch 1, branch 5 etc. of some ABC enterprise is referred to as data units' delivery.

The data units' consumption is related to using the data units from the one or more unit stores of the plurality of unit stores 100. For example, 500 electronic appliances such as mobile phones are assumed to be purchased from branch 1 of the ABC enterprise. Purchasing electronic appliances from some unit store such as branch 1 of some establishment such as ABC enterprise is referred to as data units' consumption.

The geographical data comprises location data of the one or more unit stores of the plurality of unit stores 100. For example, considering monetary storage units such as ATMs have monetary resources as data units associated to single establishment such as XYZ bank. Each of the monetary storage units is located in some location. Each of such monetary storage units comprises location information of itself. For example, ATM 1 is located in 'abc' location; ATM 4 is located 'HIJ' location etc. 'abc' location and 'HIJ' location is the location data of the ATM 1 and ATM 4 respectively.

The financial data comprises a maximum limit of the plurality of unit stores 100 to contain the monetary resources and the non-monetary resources. In an embodiment, the financial data comprises number of monetary resources and non-monetary resources which can be supplied, delivered, offered, consumed and transferred. The maximum limit is the maximum amount of monetary resources and the non-monetary resources that could be held by each of the plurality of the unit stores 100. For example, considering monetary storage units such as branches of a XYZ bank, where branch 1 has a limitation to hold Rs.lcrore as the maximum limit amount, branch 2 has a limitation to hold Rs.5crores as the maximum limit amount etc. Therefore, Rs. lcrore and Rs.5crores are the maximum limit of the branch 1 and branch 2 respectively. Another example, considering the nonmonetary storage units, branch 'XXX' of mobile appliances has a limitation to hold 500 mobile appliances for selling. Likewise, branch 'YYY' of mobile appliances has a limitation to hold 1000 mobile appliances for selling. Limitations of holding 500 and 1000 mobile appliances at branch 'XXX' and 'YYY' are referred to as maximum limit of branch 'XXX' and 'YYY', where branch 'XXX' and 'YYY' are the one or more unit stores of the plurality of stores 100.

The temporal data comprises time-series variables related to the plurality of unit stores 100. The time-series variables related to the plurality of the unit stores 100 include, but do not limit to, trend, seasonality, lag, intermittence, correlations and variance of the one or more unit stores. The trend is related to behavior of usage of the one or more unit stores over a period of time. Seasonality is related to usage trends of the one or more unit stores during different periods. In an embodiment, seasonality includes, but does not limit to, festive period, holidays, weather conditions and other related factors. Lag is related to delay of the one or more unit stores in providing services/operations. Intermittence is unsteadiness of the one or more unit stores over a period of time for providing operations Correlations is the way the one or more unit stores are communicating with each other for providing services/operations. Variance is related to variations in the one or more behavioral data of the one or more unit stores involved in providing services/operations.

Referring back to Figure 2, in an embodiment, the one or more behavioral data are acquired at predetermined intervals of time by the acquiring module 202. For example, the one or more behavioral data are acquired over a period of one week, two weeks, or a month. In an embodiment, the one or more behavioral data is either clustered together or segmented from one another using ways including, but not limiting to, k-Means, Random clustering and Support Vector Clustering. In an embodiment, the plurality of unit stores 100 are monitored in real-time to identify variations in the one or more behavioral data associated to the one or more unit stores of the plurality of unit stores 100. If there is any variation in the one or more behavioral data, then alerts are initiated by the central server 104. The initiated alerts are transmitted either to plurality of the unit stores 100 or the one or more computing devices 106. The initiated alerts are provided to the display unit 212.

After acquiring the one or more behavioral data, the pre-processing module 204 processes the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores 100 to obtain one or more transformed data pertaining to the acquired one or more behavioral data. In an embodiment, the processing of the acquired one or more behavioral data comprises one or more functions including, but not limiting to, cleansing the acquired one or more behavioral data, converting the acquired one or more behavioral data into one or more predefined formats and uploading the acquired one or more behavioral data into a predefined data model. In an embodiment, the cleansing of the acquired one or more behavioral data comprises identifying duplicate data, missing data and invalid data. In an embodiment, the pre-processing module 204 transforms raw data into known formats compatible for time-series analysis, classification and regression analysis and clustering and segmentation. Also, the pre-processing module 204 processes outliers using Box Plot approach and Local Outlier Factor approach. In an embodiment, the outliers are extremely high or low values that may occur in any transactions. For example, the outliers refer to either extremely high amount dispensed by data unit stores or unusually low amount consumed by any unit store. This indicates that that event has to be taken separately and studied for further action. The prediction module 206 predicts a quantity of the data units required at the one or more unit stores of the plurality of unit stores 100 based on the obtained one or more transformed data. For example, consider three monetary storage units such as ATMs, say ATM 1, ATM 2, and ATM 3. From the one or more behavioral data of each of the ATM 1, ATM 2 and ATM 3 over the period of 1 week, it is analyzed that, ATM 1 and ATM 2 are regular in use whereas ATM 3 is holding idle data units over the entire 1 week i.e. idle cash which is the monetary resources. Based on the one or more behavioral data which is transformed into the one or more transformed data pertaining to the ATM 1, ATM 2 and ATM 3, the quantity of the data units required by the ATM 1 and ATM 2 is predicted. Particularly, the amount of cash required by the ATM 1 and ATM 2 is predicted so that the idle cash from ATM 3 is used towards requirement of the ATM 1 and ATM 2. In an embodiment, the prediction module 206 predicts the quantity of the data units' requirement at each unit level such as how and when an amount of data units is required on basis of predetermined intervals, for example, hourly, daily, weekly, monthly basis etc. In an embodiment, the prediction module 206 involves existing models such as Cashpirin model plans for probabilistic data units demand, for example, cash demand. The prediction module 206 comprises types of events which are used to predict on requirements of the one or more unit stores based on the one or more behavioral data of the one or more unit stores of the plurality of unit stores 100. The types of events includes, but does not limit to, Known-Known which is based on regular patterns of the one or more behavioral data, Known-Unknown which is extreme demand due to known scenarios but unknown while planning, and Unknown-Unknown which is extreme due to scenarios unknown while planning. In an embodiment, the planning for Known-Known event is disclosed which includes two types of predictive models such as machine learning based as well as time- series based. The machine learning based predictive models learns the data units usage, for example, cash usage via approaches including, but not limited to, classification and regression approaches, Na^'ive Bayes, Decision Tree, Neural Net, Logistic Regression and Support Vector Machine. Time series approach comprises techniques including, but not limited to, Double Exponential Smoothing, Holt Winters, AutoRegressive Integrated Moving Average (ARIMA), Decomposition Approach, Generalized AutoRegressive Conditional Heteroskedasticity (GARCH), Croston's approach and state space models such as Kalman Filter.

The replenishment schedule comprises formulating a plan for providing optimized level of cash to ATMs, branches, operators etc. After performing the prediction, the optimization module 208 generates replenishment schedules for the one or more unit stores. The replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores 100. The replenishment schedules comprise the quantity of data units, time interval for replenishing the quantity of data units at the one or more unit stores 100 and denominations of the quantity of the data units to replenish. For example, based on prediction, it is predicted that ATM 1 requires Rs.50000, ATM 2 requires Rs.20000. Based on the one or more behavioral data, it is predicted that ATM 3 is holding the idle cash which can be used towards the requirements of the ATM 1 and ATM 2. Based on the prediction, replenishment schedules for replenishing the predicted quantity i.e. Rs.50000 and Rs.20000 is generated which includes the quantity i.e. Rs.50000 and Rs.20000 for ATM 1 and ATM 2 respectively. Time at which the amount of Rs.50000 and Rs.20000 are required at the ATM 1 and ATM 2 respectively from ATM 3 is included in the replenishment schedules. For example, it is predicted by prediction that ATM 1 requires an amount of Rs.50000 at 14:00 hours and ATM 2 requires an amount of Rs.20000 at 11 :00 hours from ATM 3. Then, replenishment includes the time values i.e. 14:00 hours predicted for ATM 1 and l l :00hours predicted for ATM 2 for replenishing the requirements of the cash. Denominations of the data units involve the divisions of the data units, for example, ATM 1 requires Rs.50000 in 500s and 1000s currencies denominations. In an embodiment, the denomination replenishment is generated based on a user defined denomination preference index for a particular unit store including an underlying Linear Programming (LP) that maximizes the preference index. In an exemplary embodiment, a Greedy Knapsack algorithm is also implemented to create the denomination distribution. In an embodiment, the optimization module 208 includes inventory control systems including, but not limiting to, continuous r, Q policy and periodic R, S policy which decides when to trigger replenishment and how much to replenish. The optimization module 208 models the data unit demand distribution in ways including, but not limited to, normal distribution, Poisson distribution, Negative Binomial and Gamma distribution. The optimization module 208 performs searching method including, but not limiting to, Mixed Integer Programming such as Linear Programming (LP) Relaxation and Branch and Bound as well as evolutionary approaches such as Genetic Algorithm, Simulated Annealing and Tabu Search. The searching methods are performed in order to proceed from one solution to other candidate solution which evaluates the constraints and eventually throws best solution satisfying all constraints. For example, considering Vehicle Route Planning method, where all the possible routes covering the nodes to be travelled are list of candidate solutions and that is the starting point of VRP algorithm. Then the method starts picking the best route based on inputs and constraints to generate best route plan for cash pickup and cash dropping. In an embodiment, the replenishment schedules for replenishing the predicted quantity of data units is performed in levels including, but not limited to, single echelon level and multi- echelon level which are modeled based on stochastic inventory model.

After generating the replenishment schedules, the route generation module 210 generates at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores (1, 2, ...., n) based on the generated replenishment schedules. The route plan comprises a route through which the data units are deployed at the one or more unit stores 100. For example, for deploying Rs.50000 and Rs.20000 to ATM 1 and ATM 2 from ATM 3 respectively, the route plan joining the ATM 3 to ATM 1 and ATM 3 to ATM 2 is generated. Through generated route plans the data units are deployed towards requirement of the ATM 1 and ATM 2. The route pans are generated to minimize the transportation delays, losses and maximize efficiency. In an embodiment, a shortest route plans is generated by the route generation module 210. In an embodiment, the route generation module 210 includes roster generation which is a recommender system based on operations including, but not limiting to, a stochastic inventory route planning, single echelon stochastic supply chain optimization and multi echelon stochastic supply chain optimization. The stochastic inventory route planning approach minimizes the idle data units holding and transportation simultaneously based on the generated replenishment schedules. In addition, an itinerary for data units' pickup for supply and data unit replenishment is also generated. The supply chain optimization approach comprises modeling lead time data unit, for example cash, demand distribution and generating optimal policies for the inventory control system. Emergency and extreme events module (not shown in figure 2) is included in the route generation module 210 to handle the extreme event, Unknown-Unknown and consequently plans emergency orders through an agent based model with underlying rule based decision model. The agent based model includes two types namely, sense agent and respond agent. The sense agents are informed extreme events (for example, a strike) and state variable (for example, trend in transactional volume) which triggers the respond agent towards emergency replenishments. In an embodiment, for managing data units, for example Forex, the route generation module 210 utilizes a plurality of optimization ways including, but not limited to, Vehicle Routing Problem (VRP), Inventory Allocation Problem, and Travelling Sales Person (TSP). The display unit 212 of the one or more computing devices 106 receives and displays the one or more behavioral data, prediction of the quantity of data units, replenishment schedules and route plans.

Figure 3 shows an exemplary flowchart illustrating a method for managing data units in the plurality of unit stores 100 according to an embodiment of the present disclosure. At step 302, the one or more behavioral data associated to one or more unit stores of the plurality of unit stores 100 are acquired by the acquiring module 202 of the central server 104. At step 304, the pre-processing module 204 pre-processes the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores 100 to obtain the one or more transformed data pertaining to the acquired one or more behavioral data. At step 306, the prediction module 206 predicts the quantity of the data units required at the one or more unit stores of the plurality of unit stores 100 based on the obtained one or more transformed data. At step 310, the optimization module 208 generates the replenishment schedules for the one or more unit stores. The replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores 100. At step 310, the route generation module 210 generates at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores 100 based on the generated replenishment schedules.

An example is illustrated herein to manage the data units in the plurality of unit stores 100. Considering the plurality of unit stores 100 as the monetary storage units with monetary resources as the data units. The monetary storage units are ATMs and data units are the currency or cash. Considering three ATMs such as ATM 1 located at ABC, ATM 2 location GHI and ATM 3 located at KLM. All three ATMs are associated to an enterprise 'XYZ' bank. Now, the one or more behavioral data including geographical data, usage data and temporal data of each of the ATM 1, ATM 2 and ATM 3 are acquired. Considering, ATM 1 and ATM 2 are in regular usage whereas ATM 3 is maintaining idle cash or currency which are analyzed based on the one or more behavioral data corresponding to the ATM 1 , ATM 2 and ATM 3 respectively. Based on the one or more behavioral data of each of the ATM 1, ATM 2 and ATM 3 respectively, it is predicted that, ATM 1 and ATM 2 are going to incur out of cash or currency at 14:00 hours and 15:00 hours respectively. Therefore, in order to replenish or refill the ATM 1 and ATM 2, the idle cash present in the ATM 3 is used. Particularly, the prediction on requirement of certain amount of cash is performed, for example, Rs.50000 and Rs.20000 is required at ATM 1 and ATM 2 respectively. The cash from ATM 3 is used towards amount Rs.50000 and Rs.20000 at ATM 1 and ATM 2. After the prediction, in order to replenish respective amount of Rs.50000 and Rs.20000 to corresponding ATM 1 and ATM 2, the replenishment schedules is generated. For example, the amount of cash required to be replenished which in this case are Rs.50000 and Rs.20000 for ATM 1 and ATM 2 respectively. Then, time at which the amount of cash is required is also generated as the replenishment schedules, for example, at 14:00 hours ATM 1 is required to be replenished with Rs,50000 and at 15:00 hours ATM 2 is required to be replenished with Rs.20000. In addition, denominations such as Rs.50000 are required in 500s for ATM 1 and Rs.20000 is required in 1000s for ATM 2 is determined. After the replenishment schedule is generated to replenish Rs.50000 in 500s at 14:00 hours for ATM 1 and Rs.20000 in 1000s at 15:00 hours, a route plan is generated through which the cash from ATM 3 to ATM 1 and ATM 3 to ATM 2 are deployed. The one or more behavioral data, prediction, replenishment schedules and route plans are viewed by the user on the one or computing devices 106 or on the display of the ATMs. In an embodiment, the 'XYZ' bank deploys the currencies or cash to the ATMs (ATM1, ATM 2 and ATM 3) towards the requirements of the ATM 1 , ATM 2 and ATM 3 as per replenishment schedules generated based on the one or more behavioral data of the ATMs.

Another example is illustrated herein to manage the data units in the plurality of unit stores 100. Considering the non-monetary storage units such as commercial establishment relate to mobile phones named by "ABC Mobile priority" and data units in the "ABC Mobile priority" are the mobile phones. Considering three branches of the "ABC Mobile priority" such as Branch 1, Branch 2 and Branch 3 where the one or more behavioral data of each of the Branch 1, Branch 2 and Branch 3 are acquired. Considering, Branch 1 and Branch 2 are regularly providing services such as selling the mobile phones to customer. Whereas, the Branch 3 comprises mobile phones which are not been sold or supplied or delivered, that means, the Branch 3 possess idle mobile phones. Now, based on the one or more behavioral data of the Branch 1, Branch 2 and Branch 3, it is predicted that, the Branch 1 and Branch 2 are in need or requirement of 500 pieces and 200 pieces of mobile phones respectively. Therefore, to fulfill the requirement of mobile phones at the Branch 1 and Branch 2, the mobile phones from Branch 3 could be used. Hence, the replenishment schedules such as time interval at which the requirements are to refilled, time at which the requirement has to be deployed are generated. Based on the generated replenishment schedule, the mobile phones from Branch 3 are supplied to the Branch 1 and Branch 2.

Aspects of the present disclosure are suitable for use in a variety of distributed computing system environments. In distributed computing environments, tasks may be performed by remote computer devices that are linked through communications networks. Embodiments of the present disclosure may comprise special purpose and/or general purpose computer devices that each may include standard computer hardware such as a central processing unit (CPU) or other processing means for executing computer executable instructions, computer readable media for storing executable instructions, a display or other output means for displaying or outputting information, a keyboard or other input means for inputting information, and so forth. Examples of suitable computer devices include hand- held devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCS, minicomputers, mainframe computers, and the like.

The methodology disclosed in the present disclosure will be described in the general context of computer-executable instructions, such as program modules, that are executed by a personal computer or a server. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. Typically the functionality of the program modules may be combined or distributed as desired in various environments.

The described operations may be implemented as a method, system or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof. The described operations may be implemented as code maintained in a "non-transitory computer readable medium", where a processing unit may read and execute the code from the computer readable medium. The processing unit is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable medium may comprise media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD-ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, firmware, programmable logic, etc.), etc. We suggest further stating in the specification that non-transitory computer-readable media comprise all computer-readable media except for a transitory. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific Integrated Circuit (ASIC), etc.). Still further, the code implementing the described operations may be implemented in "transmission signals", where transmission signals may propagate through space or through a transmission media, such as an optical fiber, copper wire, etc. The transmission signals in which the code or logic is encoded may further comprise a wireless signal, satellite transmission, radio waves, infrared signals, Bluetooth, etc. The transmission signals in which the code or logic is encoded is capable of being transmitted by a transmitting station and received by a receiving station, where the code or logic encoded in the transmission signal may be decoded and stored in hardware or a non-transitory computer readable medium at the receiving and transmitting stations or devices. An "article of manufacture" comprises non-transitory computer readable medium, hardware logic, and/or transmission signals in which code may be implemented. A device in which the code implementing the described embodiments of operations is encoded may comprise a computer readable medium or hardware logic. Of course, those skilled in the art will recognize that many modifications may be made to this configuration without departing from the scope of the invention, and that the article of manufacture may comprise suitable information bearing medium known in the art.

The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise. The terms "including", "comprising", "having" and variations thereof mean "including but not limited to", unless expressly specified otherwise.

The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise.

The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise. Devices that are in communication with each other need not be in continuous communication with each other, unless expressly specified otherwise. In addition, devices that are in communication with each other may communicate directly or indirectly through one or more intermediaries.

Further, although process steps, method steps, algorithms or the like may be described in a sequential order, such processes, methods and algorithms may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously. When a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself. The illustrated operations of figure 3 show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified or removed. Moreover, steps may be added to the above described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

The foregoing description of various embodiments of the invention has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the invention be limited not by this detailed description, but rather by the claims appended hereto. The above specification, examples and data provide a complete description of the manufacture and use of the composition of the invention. Since many embodiments of the invention can be made without departing from the spirit and scope of the invention, the invention resides in the claims hereinafter appended. Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims. With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity.

In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Reference Table: iReference Numerals ^Description

Plurality of Unit Stores !IOO (100 (1), 100 (2), ..- 100 (n))

^Distributed Network 102 iCentral Server 104

Computing Devices Π 06

^Acquiring Module 202 iPre-processing Module 204 iPrediction Module 206

^Optimization Module 208 iRoute Generation Module 210 iDisplay Unit 212

Claims

CLAIMS:

1. A method for managing data units in a plurality of unit stores, said method comprising acts of:

acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores by an acquiring module configured in a central server, wherein the central server is communicatively connected to the plurality of unit stores over a distributed network;

pre-processing, by a pre-processing module configured in the central server, the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data;

predicting, by a prediction module configured in the central server, a quantity of the data units required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data;

generating replenishment schedules for the one or more unit stores by an optimization module configured in the central server, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores; and

generating, by a route generation module configured in the central server, at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

2. The method as claimed in claim 1, wherein the data units are selected from at least one of monetary resources and non-monetary resources.

3. The method as claimed in claim 2, wherein the plurality of unit stores is selected from at least one of a monetary storage unit and a non-monetary storage unit, said monetary storage unit and non-monetary storage unit store the monetary resources and the nonmonetary resources respectively.

4. The method as claimed in claim 1 , wherein the one or more behavioral data associated to the one or more unit stores of the plurality of unit stores comprises at least one of a usage data, a geographical data, a financial data and a temporal data.

5. The method as claimed in claim 4, wherein the usage data of the plurality of unit stores comprises data relating to data units' deposits, data units' withdrawals, data units transfer, data units' exchange with respect to the plurality of unit stores, data units supply, data units delivery, and data units consumption.

6. The method as claimed in claim 4, wherein the geographical data comprises location data of the plurality of unit stores.

7. The method as claimed in claim 4, wherein the financial data comprises a maximum limit of the plurality of unit stores to contain the monetary resources and the nonmonetary resources.

8. The method as claimed in claim 4, wherein the temporal data comprises time-series variables related to the plurality of unit stores.

9. The method as claimed in claim 1, wherein the one or more behavioral data are acquired at predetermined intervals of time.

10. The method as claimed in claim 1, wherein the pre-processing of the acquired one or more behavioral data comprises at least one of cleansing the acquired one or more behavioral data, converting the acquired one or more behavioral data into one or more predefined formats and uploading the acquired one or more behavioral data into a predefined data model.

11. The method as claimed in claim 10, wherein the cleansing of the acquired one or more behavioral data comprises identifying duplicated data, missing data and invalid data.

12. The method as claimed in claim 1, wherein the replenishment schedules comprises the quantity of data units, time for replenishing the quantity data units at the one or more unit stores and denominations of the quantity of the data units to replenish.

13. The method as claimed in claim 1, wherein the at least one route plan comprises a route through which the data units are deployed at the one or more unit stores.

14. The method as claimed in claim 1 further comprises real-time monitoring of plurality of unit stores to identify variations in the one or more behavioral data associated to the one or more unit stores.

15. The method as claimed in claim 14, wherein initiating alerts when the variations in the one or more behavioral data are identified.

16. A system for managing data units in real-time, said system comprising:

a plurality of unit stores comprising data units;

a central server communicatively connected to the plurality of unit stores over a distributed network, said central server comprising:

an acquiring module to acquire one or more behavioral data associated to one or more unit stores of the plurality of unit stores;

a pre-processing module to pre-process the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data;

a prediction module to predict a quantity of the data units required at one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data;

an optimization module to generate replenishment schedules for the one or more unit stores, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores; and

a route generation module to generate at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

17. The system as claimed in claim 16, wherein the pre-processing module performs at least one of cleansing the acquired one or more behavioral data, converting the acquired one or more behavioral data into one or more predefined formats and uploading the acquired one or more behavioral data into a predefined data model.

18. The system as claimed in claim 16, wherein data units are selected from at least one of monetary resources and non-monetary resources.

19. The system as claimed in claim 16, wherein the plurality of unit stores is selected from at least one of a monetary storage unit and non-monetary storage unit, said monetary storage unit and non-monetary storage unit store the monetary resources and the nonmonetary resources respectively.

20. The system as claimed in claim 16 comprises one or more computing devices communicatively connected to the plurality of unit stores and the central server over the distributed network for receiving data, transmitting data and displaying the predicted quantity of data units, replenishment schedules and the route plan.

21. The system as claimed in claim 20, wherein the one or more computing devices are selected from at least one of computer, Electronic Data Capture (EDC), a mobile phone, a Personal Digital Assistants (PDA), contactless device and other communication devices.

22. A non-transitory computer readable medium including operations stored thereon that for real-time managing data units in a plurality of unit stores which is processed by a central server which is communicatively connected to the plurality of unit stores over a distributed network by performing the acts of:

acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores;

pre-processing the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data;

predicting a quantity of the data units required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data; and generating replenishment schedules for the one or more unit stores, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores; and

generating at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.

23. A computer program for real-time managing data units in a plurality of unit stores, said computer program comprising code segment for acquiring one or more behavioral data associated to one or more unit stores of the plurality of unit stores; code segment for pre-processing the acquired one or more behavioral data associated to the one or more unit stores of the plurality of unit stores to obtain one or more transformed data pertaining to the acquired one or more behavioral data; code segment for predicting a quantity of the data units required at the one or more unit stores of the plurality of unit stores based on the obtained one or more transformed data; code segment generating replenishment schedules for the one or more unit stores, wherein the replenishment schedules are generated for replenishing the predicted quantity of the data units at the one or more unit stores, and code segment for generating at least one route plan to deploy the predicted quantity of the data units at the one or more unit stores of the plurality of unit stores based on the generated replenishment schedules.