CN103258388A - Automatic transaction device, server and method for predicting quantity demanded of cash - Google Patents
Automatic transaction device, server and method for predicting quantity demanded of cash Download PDFInfo
- Publication number
- CN103258388A CN103258388A CN2012100363909A CN201210036390A CN103258388A CN 103258388 A CN103258388 A CN 103258388A CN 2012100363909 A CN2012100363909 A CN 2012100363909A CN 201210036390 A CN201210036390 A CN 201210036390A CN 103258388 A CN103258388 A CN 103258388A
- Authority
- CN
- China
- Prior art keywords
- transaction record
- random
- prediction
- automatic trading
- trading apparatus
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses an automatic transaction device. The automatic transaction device comprises a storage part used for storing historical transaction records of the automatic transaction device; an optimal threshold confirming part used for confirming an optimal threshold of an index used for removing random transaction records; a data cleaning part used for removing random transaction records with the value of the indexes outside a defined range of the optimal threshold from the historical transaction records within an appointed time section, and a statistics predicting part used for counting the historical transaction records after the random transaction records are removed and predicting the quantity demanded of cash within a period of time corresponding to the appointed period of time.
Description
Technical field
The method that the present invention relates to a kind of automatic trading apparatus that in banking industry, uses and connected server and be used for prediction cash demand amount, more specifically, the method that relates to a kind of automatic trading apparatus and connected server and be used for prediction cash demand amount, can conclude the business at random to the influence of predicted value by removing, improve cash demand quantitative statistics and accuracy of predicting.
Background technology
Automatic trading apparatus is widely used in bank's financial industry relevant with other, as a kind of self-help terminal equipment, is financial services such as the user provides deposit, withdraws the money, transfers accounts, paying, purchase payment.Automatic trading apparatus has improved the efficiency of operation of bank, has reduced the situation of bank counter queuing transacting business, for bank has saved great deal of labor, also makes user's transacting business more convenient simultaneously.
The banknote of the staff that general automatic cash deposit and withdrawal device (that is, automatic trading apparatus) needs bank filling some in the banknote box of this device makes device rich desirable, with the normal operation of assurance device, and improves the service efficiency of device.
Filling out in the paper money scheme in the past, bank clerk rule of thumb is summarised in the banknote that needs to insert how much quantity in the certain hour section with historical data, also has by computer program to realize filling out cash amount calculating and forecast method and system.For example, in the Japanese publication that is entitled as " automatic trading apparatus " (spy opens flat 9-153167), proposed on the basis of historical transaction record, influence the environmental information of automatic trading apparatus according to date, week, wage day etc., predict the trading volume of automatic trading apparatus, thereby improve the fund utilization rate of bank.
In the automatic trading apparatus actual motion, some transaction is at random.Here, refer to that at random transaction has not regulation and periodicity, and this user's behavior can not repeat in the future.Still deposit 100,000 yuan because of cause specific as certain user common amount deposited on certain automatic trading apparatus in certain transaction all less than 10,000 yuan, current operation being regarded as once concluding the business at random.Though technique known has been introduced the predicted value that parameters such as historical data and date, week are revised automatic trading apparatus, consider to conclude the business at random to the influence of predicted value.Transaction can not repeat because the amount of money and time have uncertainty at random, thereby has caused the cash demand amount that gets according to the historical data statistics can not embody regularity, and then makes based on the resulting predicted value of historical data also inaccurate.
Therefore, the method that needs a kind of novel automatic trading apparatus and server and be used for prediction cash demand amount improves cash demand quantitative statistics and accuracy of predicting.The cash demand amount of the automatic trading apparatus here comprises withdraws the money demand and deposit demand, the common automatic trading apparatus that can circulate for banknote in the paper money case, and the cash amount that needs to add in automatic trading apparatus is that the total amount of withdrawing the money deducts the deposit total amount.
Summary of the invention
In order to solve above-mentioned technical task the present invention has been proposed.Therefore, the method that the purpose of this invention is to provide a kind of automatic trading apparatus and server and be used for prediction cash demand amount can be concluded the business to the influence of predicted value at random by removing, and improves cash demand quantitative statistics and accuracy of predicting.
To achieve these goals, according to the present invention, proposed a kind of automatic trading apparatus, having comprised: storage part, for the historical transaction record of storage automatic trading apparatus; The optimal threshold determination portion is used for being identified for removing the optimal threshold of the index of transaction record at random; Data cleansing portion is used for removing the at random transaction record of finger target value described in the historical transaction record in the fixed time section beyond the confining spectrum of described optimal threshold; And statistical forecast portion, be used for the historical transaction record of removing behind the transaction record is at random added up, and the prediction time period interior cash demand amount corresponding with the fixed time section.
Preferably, described the index of transaction record comprises be used to removing at random: the trading frequency in trading volume, exchange hour and the trading frequency statistical form in the transaction record, wherein, described trading volume comprises the credit transaction amount and the trading volume of withdrawing the money.
Preferably, described trading frequency statistical form also is stored in the described storage part.
Preferably, the threshold value of the described index of described optimal threshold determination portion initialization; Remove the transaction record beyond threshold value defines in the original transaction record; The demand of the past period is added up and predicted to transaction record behind the transaction record beyond utilization removal threshold value defines, obtains the historical precision of prediction of the past period; Threshold value is adjusted by the unit step-length; Remove threshold value with the threshold value after adjusting and define transaction at random in addition, calculate new historical precision of prediction; Circulation is carried out threshold value adjustment and precision of prediction and is calculated, and till the border that threshold value arrives the value of described index is maximal value or minimum value, the highest threshold value of precision of prediction that obtains in the prediction so repeatedly is defined as described optimal threshold.
Preferably, described statistical forecast portion utilizes time series predicting model, Regression Forecast, grey method, machine learning predicted method to predict the cash demand amount.
In addition, according to the present invention, also proposed a kind of method that is used to automatic trading apparatus prediction cash demand amount, having comprised: be identified for removing the optimal threshold of the index of transaction record at random; Refer to the at random transaction record of target value beyond the confining spectrum of described optimal threshold described in the historical transaction record of the automatic trading apparatus in the removal fixed time section; And the historical transaction record of removing behind the transaction record at random added up, and the cash demand amount in prediction time period corresponding with the fixed time section.
In addition, according to the present invention, also proposed a kind of server that links to each other with automatic trading apparatus, having comprised: acquisition unit, for the historical transaction record that obtains automatic trading apparatus from automatic trading apparatus; The optimal threshold determination portion is used for being identified for removing the optimal threshold of the index of transaction record at random; Data cleansing portion is used for removing the at random transaction record of finger target value described in the historical transaction record in the fixed time section beyond the confining spectrum of described optimal threshold; And statistical forecast portion, be used for the historical transaction record of removing behind the transaction record is at random added up, and the prediction time period interior cash demand amount corresponding with the fixed time section.
This shows the technique known influence to predicted value of not considering to conclude the business at random.And cash forecast device of the present invention is concluded the business to the influence of predicted value at random by removing, and has improved precision of prediction.
Particularly, according to the present invention, extract transaction log or the transaction statistics of automatic trading apparatus, by for being used for removing the index of concluding the business at random optimal threshold being set, the transaction record of desired value outside the confining spectrum of optimal threshold removed from the transaction record set as transaction record at random, added up and predict with removing transaction record set behind the transaction record at random.So-called index of concluding the business at random for removal comprises: the attributes such as trading frequency in the trading volume in the transaction record (comprising the credit transaction amount and the trading volume of withdrawing the money), exchange hour and the trading frequency statistical form.The setting of optimal threshold or deterministic process are: the threshold value of this index of initialization; Remove the transaction record beyond threshold value defines in the original historical transaction record; With the demand of the transaction record statistical forecast the past period behind the transaction record of removal threshold value beyond defining, obtain the historical precision of prediction of the past period; Threshold value is adjusted by the unit step-length; Remove transaction at random with the threshold value after adjusting, calculate new historical precision of prediction; Circulation is carried out the threshold value adjustment and is predicted, till the border that threshold value arrives the value of this index is maximal value or minimum value, the highest threshold value of precision that obtains in the prediction repeatedly is defined as described optimal threshold.
By optimal threshold is set, remove the transaction record at random in the transaction record, can improve precision of prediction.Load cash with this prediction mode prediction and for automatic trading apparatus, can improve the operational efficiency of automatic trading apparatus, avoided scarce paper money or surpassed required banknote putting into automatic trading apparatus, can improve satisfaction and the bank capital utilization factor of bank-user.
Description of drawings
Fig. 1 shows the automatic trading apparatus of first embodiment of the invention and the synoptic diagram of server.
The automatic trading apparatus that Fig. 2 shows first embodiment of the invention carries out the synoptic diagram of the workflow of cash demand prediction.
Fig. 3 shows the optimal threshold of the automatic trading apparatus service index of first embodiment of the invention and removes the synoptic diagram of the process of transaction at random.
Fig. 4 shows the synoptic diagram of the transaction statistical form of storing in the server of first embodiment of the invention.
Fig. 5 shows the synoptic diagram of the trading record sheet of storing in the server of first embodiment of the invention.
Fig. 6 shows the synoptic diagram of the trading frequency statistical form of storing in the server of first embodiment of the invention.
Fig. 7 shows the synoptic diagram of process of index optimal threshold of an automatic trading apparatus of calculating of first embodiment of the invention.
Fig. 8 shows the synoptic diagram of process of deposit amount optimal threshold of an automatic trading apparatus of calculating of first embodiment of the invention.
Fig. 9 shows the synoptic diagram of process of trading frequency optimal threshold of an automatic trading apparatus of calculating of first embodiment of the invention.
Embodiment
The preferred embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 shows the automatic trading apparatus of first embodiment of the invention and the synoptic diagram of server.
According to the flow process of cash demand of the present invention prediction as shown in Figure 2.In step 202, by importing in the module 113 importings transaction log record table as shown in Figure 5.Information such as device numbering, exchange hour, action type, bank's card number, dealing money and operating result have been comprised in the transaction log record table.In step 203, invalid record or error logging that data cleansing module 116 is removed in the historical transaction record.In step 204, statistical module 114 is according to the historical transactional information of automatic trading apparatus, the deposit total amount of statistical unit time (hour, day) and the total amount and being saved in the transaction statistical form in the data memory module 124 of withdrawing the money.Transaction statistical form as shown in Figure 4 comprise device numbering, date, hour, the total amount of withdrawing the money, deposit total amount, may the amount of withdrawing the money and may deposit amount (and not shown).After step 204, transaction in the statistical form may the amount of withdrawing the money and may the deposit amount be defaulted as 0.In step 205, operating personnel import the numbering of the automatic trading apparatus that needs the forecast demand amount and the data such as time of prediction by keyboard 122 input equipments such as grade.In step 206, demand forecast module 116 is according to numbering, predicted time and the revised statistics prediction cash demand amount of the automatic trading apparatus of given parameter.Demand forecast module 116 can adopt multiple Forecasting Methodology, as time series predicting model, Regression Forecast, grey method, machine learning predicted method.The input variable that relates in the forecast model comprises: the time, whether be festivals or holidays, whether be special day, statistical demand amount, weather, economic indexs etc. such as wage granting.The data that comprise input variable can be generated by statistical module, also can generate in prediction module.Forecasting process generally speaking is: the historical data that will comprise above-mentioned input variable joins trains in the forecast model or calculates, to determine the parameter of forecast model; Bring the prediction input variable into the model after the training then, i.e. the data of step 205 input, and model calculates the forecast demand amount.In step 207, cash demand predicts the outcome and is saved.
The detail flowchart that the data cleansing module 115 of step 203 is removed transaction data at random as shown in Figure 3.In step 301, calculate the optimal threshold that is used for removing the index of concluding the business at random.In step 302, the optimal threshold of service index, the transaction record beyond the confining spectrum of removal threshold value.In step 303, use the transaction record data remove behind the transaction record at random to predict, and calculate precision of prediction.Precision of prediction is represented the degree that forecast demand amount and actual demand amount are consistent.Demand precision of prediction computing method in a period of time are as follows: suppose to have during this period of time N the unit interval (as N days), the forecast demand amount of obtaining each unit interval deduct the actual demand amount difference square; The above-mentioned N that calculates amount summation; N-1 is precision of prediction divided by the above-mentioned result who calculates.Last bearing reaction the degree of the realistic demand of premeasuring.The result is more big, and premeasuring and actual amount more meet, and namely precision of prediction is more high; Otherwise the result is more little, and precision of prediction is more low.Except the method for above-mentioned computational accuracy, also can replace with other precision of prediction Calculation Method, but need adopt identical precision of prediction computing method to every table apparatus.In step 304, if precision of prediction then recomputates the index optimal threshold less than acceptable scope; Otherwise continue to use this optimal threshold to remove transaction at random.This acceptable scope has different settings according to different banks, the device of different location.
The detailed process of the index optimal threshold of an automatic trading apparatus of calculating of step 301 as shown in Figure 7.In step 701, threshold value to index is carried out initialization, here the mean value of this index is set to initial value in the historical transaction record of this device or the statistical form, also can the historical transaction record of this device in or maximal value or the minimum value of this index value of statistical form be set to initial value.In step 702, from the original transaction record of this device, remove the confining spectrum transaction record in addition of threshold value.Beyond confining spectrum, refer to greater than threshold value or less than threshold value.In step 703, with the record data behind the transaction record beyond the confining spectrum of removing threshold value, predict this device the past period demand.Calculate this device past consensus forecast precision P during this period of time.In step 704, adjust the size of threshold value by the least unit of threshold value.In step 705, from the original transaction record of this device, remove amended threshold value confining spectrum transaction record in addition.In step 706, with the record data after removing, predict same time in the past demand.Calculate past consensus forecast precision P ' during this period of time.In step 707, compare the size of P ' and P.If P ' greater than P be amended threshold value accuracy of predicting greater than original initial value precision of prediction, then enter step 708; Otherwise enter step 709.In step 708, setting allows P equal P ' and is about to represent that current optimal threshold is set to amended threshold value.In step 709, whether judgment threshold has exceeded the scope of this index value.The scope of the value of index refers to the historical record of this this device or the value before statistical form middle finger target minimum value and the maximal value.If go beyond the scope, then enter step 710; Otherwise, entering step 704, circulation is made amendment threshold ratio than precision.In step 710, preservation P is the optimal threshold at this index of this device.
Fig. 8 has provided the object lesson of Fig. 7, calculates the optimal threshold that a certain device deposit figureofmerit is removed.In step 801, deposit figureofmerit threshold value is carried out initialization.Here the device that is set to field 501 in the trading record sheet shown in Figure 5 is numbered the action type of this device numbering, field 502 and is the mean value of field 502 amount of money of all records of deposit.In step 802, be that field 501 devices are numbered in this device numbering, field 502 action types all records for deposit the trading record sheet shown in Figure 5 from the original transaction record of this device, remove the amount of money greater than the transaction record of threshold value.In step 803, with the record data of removing this device of the amount of money after greater than the transaction record of threshold value, by demand forecast module 206, predict that this device goes over 1 month demand.Calculate the consensus forecast precision P in past 1 month of this device.In step 804, be that least unit increases threshold value with 100 yuan.In step 805, from the original transaction record of this device, remove the transaction record greater than amended threshold value.In step 806, usefulness is removed the record data after the operation, and prediction is 1 month demand in the past.Calculate past consensus forecast precision P ' during this period of time.In step 707, compare the size of P ' and P.If P ' greater than P be amended threshold value accuracy of predicting greater than original initial value precision of prediction, then enter step 808; Otherwise enter step 809.In step 808, setting allows P equal P ', is about to represent that current optimal threshold is set to amended threshold value.In step 809, whether judgment threshold has exceeded minimum value or the maximal value of this index value.If go beyond the scope, then enter step 810; Otherwise, enter step 804, circulate and make amendment threshold value and compare precision.In step 810, preserve P for being used for the optimal threshold that this device deposit figureofmerit is removed.
Fig. 9 has provided another object lesson of Fig. 7, calculates the optimal threshold that a certain device trading frequency index is removed.In step 901, the trading frequency metrics-thresholds is carried out initialization.Here the device that is set to field 601 in the trading frequency statistical form shown in Figure 6 is numbered the minimum value of field 603 transaction of all records of this device numbering.In step 902, be that field 501 devices are numbered in all records of this device numbering the trading record sheet shown in Figure 5 from the original transaction record of this device, remove card number and be in the statistical form transaction record less than all card numbers of threshold value.Wherein, the trading frequency statistical form is generated by statistical module 114.In step 903, with the record data of carrying out this device after above-mentioned removal is operated, predict this device 1 month demand in the past.Calculate the consensus forecast precision P in past 1 month of this device.In step 904, be that least unit increases threshold value with 1 time.In step 905, from the raw readings of this device, remove card number and be in the statistical form transaction record less than all card numbers of revising threshold value.In step 906, with the record data of carrying out after above-mentioned removal is operated, prediction is 1 month demand in the past.Calculate past consensus forecast precision P ' during this period of time.In step 907, compare the size of P ' and P.If P ' greater than P be amended threshold value accuracy of predicting greater than original initial value precision of prediction, then enter step 908; Otherwise enter step 909.In step 908, setting allows P equal P ', is about to represent that current optimal threshold is set to amended threshold value.In step 909, whether judgment threshold has exceeded minimum value or the maximal value of this index value.If go beyond the scope, then enter step 910; Otherwise, enter step 904, circulate and make amendment threshold value and compare precision.In step 910, preserve P for being used for the optimal threshold that this device trading frequency is removed.
According to the present invention, by optimal threshold is set, remove the transaction record at random in the transaction record, can improve precision of prediction.Load cash with this prediction mode prediction and for automatic trading apparatus, can improve the operational efficiency of automatic trading apparatus, avoided scarce paper money or surpassed required banknote putting into automatic trading apparatus, can improve satisfaction and the bank capital utilization factor of bank-user.
Those skilled in the art are to be understood that, module in the server disclosed in this invention can be under the situation that does not depart from essence of the present invention, can be installed in the automatic trading apparatus, independently be finished correction and the prediction of cash demand amount of the present invention by automatic trading apparatus.
Although below show the present invention in conjunction with the preferred embodiments of the present invention, one skilled in the art will appreciate that under the situation that does not break away from the spirit and scope of the present invention, can carry out various modifications, replacement and change to the present invention.Therefore, the present invention should not limited by above-described embodiment, and should be limited by claims and equivalent thereof.
Claims (7)
1. automatic trading apparatus comprises:
Storage part is for the historical transaction record of storage automatic trading apparatus;
The optimal threshold determination portion is used for being identified for removing the optimal threshold of the index of transaction record at random;
Data cleansing portion is used for removing the at random transaction record of finger target value described in the historical transaction record in the fixed time section beyond the confining spectrum of described optimal threshold; And
Statistical forecast portion is used for the historical transaction record of removing behind the transaction record is at random added up, and the prediction time period interior cash demand amount corresponding with the fixed time section.
2. automatic trading apparatus according to claim 1, wherein,
Described the index of transaction record comprises be used to removing at random: the trading frequency in trading volume, exchange hour and the trading frequency statistical form in the transaction record, wherein, described trading volume comprises the credit transaction amount and the trading volume of withdrawing the money.
3. automatic trading apparatus according to claim 1, wherein, described trading frequency statistical form also is stored in the described storage part.
4. automatic trading apparatus according to claim 1, wherein,
The threshold value of the described index of described optimal threshold determination portion initialization; Remove the transaction record beyond threshold value defines in the original transaction record; The demand of the past period is added up and predicted to transaction record behind the transaction record beyond utilization removal threshold value defines, obtains the historical precision of prediction of the past period; Threshold value is adjusted by the unit step-length; Remove threshold value with the threshold value after adjusting and define transaction at random in addition, calculate new historical precision of prediction; Circulation is carried out threshold value adjustment and precision of prediction and is calculated, and till the border that threshold value arrives the value of described index is maximal value or minimum value, the highest threshold value of precision of prediction that obtains in the prediction so repeatedly is defined as described optimal threshold.
5. automatic trading apparatus according to claim 1, wherein,
Described statistical forecast portion utilizes time series predicting model, Regression Forecast, grey method, machine learning predicted method to predict the cash demand amount.
6. method that is used to automatic trading apparatus prediction cash demand amount comprises:
Be identified for removing the optimal threshold of the index of transaction record at random;
Refer to the at random transaction record of target value beyond the confining spectrum of described optimal threshold described in the historical transaction record of the automatic trading apparatus in the removal fixed time section; And
The historical transaction record of removing behind the transaction record is at random added up, and the cash demand amount in prediction time period corresponding with the fixed time section.
7. server that links to each other with automatic trading apparatus comprises:
Acquisition unit is for the historical transaction record that obtains automatic trading apparatus from automatic trading apparatus;
The optimal threshold determination portion is used for being identified for removing the optimal threshold of the index of transaction record at random;
Data cleansing portion is used for removing the at random transaction record of finger target value described in the historical transaction record in the fixed time section beyond the confining spectrum of described optimal threshold; And
Statistical forecast portion is used for the historical transaction record of removing behind the transaction record is at random added up, and the prediction time period interior cash demand amount corresponding with the fixed time section.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210036390.9A CN103258388B (en) | 2012-02-17 | 2012-02-17 | Automatic trading apparatus and server and the method for predicting cash demand amount |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210036390.9A CN103258388B (en) | 2012-02-17 | 2012-02-17 | Automatic trading apparatus and server and the method for predicting cash demand amount |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103258388A true CN103258388A (en) | 2013-08-21 |
CN103258388B CN103258388B (en) | 2015-09-02 |
Family
ID=48962271
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210036390.9A Expired - Fee Related CN103258388B (en) | 2012-02-17 | 2012-02-17 | Automatic trading apparatus and server and the method for predicting cash demand amount |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103258388B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424598A (en) * | 2013-09-06 | 2015-03-18 | 株式会社日立制作所 | Cash demand quantity predicating device and method |
CN104794536A (en) * | 2015-04-15 | 2015-07-22 | 江苏林洋电子股份有限公司 | Method for predicting clearing maintenance time of self-help electricity selling terminal |
CN105205945A (en) * | 2015-10-09 | 2015-12-30 | 昆山古鳌电子机械有限公司 | Automatic trading device, server and method used for predicting cash demands of clients |
CN106156122A (en) * | 2015-04-07 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Transaction Information acquisition methods and device |
CN107609974A (en) * | 2017-09-26 | 2018-01-19 | 北京福布罗科技有限公司 | Method for testing pressure and device |
CN107798057A (en) * | 2017-09-05 | 2018-03-13 | 平安科技(深圳)有限公司 | transaction data processing method, device, storage medium and computer equipment |
CN108230140A (en) * | 2017-12-29 | 2018-06-29 | 阿里巴巴集团控股有限公司 | The method and apparatus of pushed information, the method and apparatus for determining input default value |
CN108665650A (en) * | 2017-03-27 | 2018-10-16 | 深圳怡化电脑股份有限公司 | Data processing method, finance device and server for saving the time of withdrawing the money |
CN110197374A (en) * | 2018-06-15 | 2019-09-03 | 腾讯科技(深圳)有限公司 | Transaction intercepts control method and device |
CN110400021A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Bank outlets' cash dosage prediction technique and device |
WO2020001114A1 (en) * | 2018-06-29 | 2020-01-02 | 阿里巴巴集团控股有限公司 | Data prefill method, device and equipment |
CN111341040A (en) * | 2020-03-28 | 2020-06-26 | 江西财经职业学院 | Financial self-service equipment and management system thereof |
CN111612991A (en) * | 2020-06-05 | 2020-09-01 | 中国银行股份有限公司 | ATM maintenance method and device |
CN111708768A (en) * | 2020-05-20 | 2020-09-25 | 广州中智融通金融科技有限公司 | Cash dispatching method, system and storage medium for automatic teller machine |
WO2020258994A1 (en) * | 2019-06-24 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Node data prediction method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0753524A2 (en) * | 1995-07-11 | 1997-01-15 | Fujitsu Limited | Remaining money management system |
JPH09153167A (en) * | 1995-12-01 | 1997-06-10 | Hitachi Ltd | Automated teller machine |
CN102081784A (en) * | 2009-11-30 | 2011-06-01 | 株式会社匠技研 | Cash-replenishment planning support system and cash-replenishment planning support method |
CN102231216A (en) * | 2011-06-27 | 2011-11-02 | 中国建设银行股份有限公司 | Cash management method and system for self-service equipment |
CN102306366A (en) * | 2011-07-11 | 2012-01-04 | 迈普通信技术股份有限公司 | Method for determining money configuring data of automatic teller machine |
-
2012
- 2012-02-17 CN CN201210036390.9A patent/CN103258388B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0753524A2 (en) * | 1995-07-11 | 1997-01-15 | Fujitsu Limited | Remaining money management system |
JPH09153167A (en) * | 1995-12-01 | 1997-06-10 | Hitachi Ltd | Automated teller machine |
CN102081784A (en) * | 2009-11-30 | 2011-06-01 | 株式会社匠技研 | Cash-replenishment planning support system and cash-replenishment planning support method |
CN102231216A (en) * | 2011-06-27 | 2011-11-02 | 中国建设银行股份有限公司 | Cash management method and system for self-service equipment |
CN102306366A (en) * | 2011-07-11 | 2012-01-04 | 迈普通信技术股份有限公司 | Method for determining money configuring data of automatic teller machine |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424598A (en) * | 2013-09-06 | 2015-03-18 | 株式会社日立制作所 | Cash demand quantity predicating device and method |
CN106156122A (en) * | 2015-04-07 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Transaction Information acquisition methods and device |
CN104794536A (en) * | 2015-04-15 | 2015-07-22 | 江苏林洋电子股份有限公司 | Method for predicting clearing maintenance time of self-help electricity selling terminal |
CN104794536B (en) * | 2015-04-15 | 2018-02-23 | 江苏林洋能源股份有限公司 | A kind of Forecasting Methodology of the clear maintenance time of self-help electric-selling terminal |
CN105205945A (en) * | 2015-10-09 | 2015-12-30 | 昆山古鳌电子机械有限公司 | Automatic trading device, server and method used for predicting cash demands of clients |
CN108665650A (en) * | 2017-03-27 | 2018-10-16 | 深圳怡化电脑股份有限公司 | Data processing method, finance device and server for saving the time of withdrawing the money |
CN107798057A (en) * | 2017-09-05 | 2018-03-13 | 平安科技(深圳)有限公司 | transaction data processing method, device, storage medium and computer equipment |
CN107609974A (en) * | 2017-09-26 | 2018-01-19 | 北京福布罗科技有限公司 | Method for testing pressure and device |
US11087402B2 (en) | 2017-12-29 | 2021-08-10 | Advanced New Technologies Co., Ltd. | Method and device for pushing information and method and device for determining default input value |
CN108230140A (en) * | 2017-12-29 | 2018-06-29 | 阿里巴巴集团控股有限公司 | The method and apparatus of pushed information, the method and apparatus for determining input default value |
WO2019128514A1 (en) * | 2017-12-29 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Method and device for pushing information and method and device for determining default input value |
CN110197374A (en) * | 2018-06-15 | 2019-09-03 | 腾讯科技(深圳)有限公司 | Transaction intercepts control method and device |
CN110197374B (en) * | 2018-06-15 | 2024-02-20 | 腾讯科技(深圳)有限公司 | Transaction interception control method and device |
WO2020001114A1 (en) * | 2018-06-29 | 2020-01-02 | 阿里巴巴集团控股有限公司 | Data prefill method, device and equipment |
WO2020258994A1 (en) * | 2019-06-24 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Node data prediction method and device |
CN110400021A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Bank outlets' cash dosage prediction technique and device |
CN110400021B (en) * | 2019-07-31 | 2022-03-25 | 中国工商银行股份有限公司 | Bank branch cash usage prediction method and device |
CN111341040A (en) * | 2020-03-28 | 2020-06-26 | 江西财经职业学院 | Financial self-service equipment and management system thereof |
CN111708768A (en) * | 2020-05-20 | 2020-09-25 | 广州中智融通金融科技有限公司 | Cash dispatching method, system and storage medium for automatic teller machine |
CN111612991A (en) * | 2020-06-05 | 2020-09-01 | 中国银行股份有限公司 | ATM maintenance method and device |
Also Published As
Publication number | Publication date |
---|---|
CN103258388B (en) | 2015-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103258388B (en) | Automatic trading apparatus and server and the method for predicting cash demand amount | |
Raberto et al. | Debt, deleveraging and business cycles: An agent-based perspective | |
US6725210B1 (en) | Process database entries to provide predictions of future data values | |
Cincotti et al. | Macroprudential policies in an agent-based artificial economy | |
CN104424598A (en) | Cash demand quantity predicating device and method | |
Han et al. | Multicriteria financial portfolio risk management for international projects | |
Simutis et al. | Optimization of cash management for ATM network | |
CN108932585A (en) | A kind of trade company's operation management method and its equipment, storage medium, electronic equipment | |
Gowrisankaran et al. | Entry and pricing in a differentiated products industry: Evidence from the ATM market | |
CN104584051A (en) | Novel systems and processes for enhanced microlending | |
CN109740792A (en) | Data predication method, system, terminal and computer storage medium | |
Ekinci et al. | Optimal ATM replenishment policies under demand uncertainty | |
CN110348902A (en) | A kind of acquisition device and method of tobacco retail terminal sales information | |
US20140310088A1 (en) | Early Payment Rewards System and Method | |
CN1971610A (en) | System and method for evaluating bank lending risks | |
CN101221680A (en) | System and method for implementing minimum and maximum amount repayment of individual loan | |
Norawati et al. | The effectiveness of the determinants of banking credit growth | |
Balasubramanian et al. | Inventory management for mobile money agents in the developing world | |
RU158417U1 (en) | INVESTMENT RISK MODELING SYSTEM FOR MINING ENTERPRISES | |
Barbone et al. | Public finances and economic transition | |
CN102800159B (en) | Automatic transaction device and method for predicating cash demanded quantity | |
CN108256667A (en) | Asset data processing method, device, storage medium and computer equipment | |
WO2013102917A2 (en) | A c omputer implemented system for management and optimization of financial accounts and financial obligations of a user | |
Ilagan et al. | A scheduling model for full maintenance of automated teller machines | |
CN111626572A (en) | Digital intelligent wind control method and related product |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150902 Termination date: 20200217 |