WO2017084385A1 - 一种自助设备节能控制方法和装置 - Google Patents

一种自助设备节能控制方法和装置 Download PDF

Info

Publication number
WO2017084385A1
WO2017084385A1 PCT/CN2016/092306 CN2016092306W WO2017084385A1 WO 2017084385 A1 WO2017084385 A1 WO 2017084385A1 CN 2016092306 W CN2016092306 W CN 2016092306W WO 2017084385 A1 WO2017084385 A1 WO 2017084385A1
Authority
WO
WIPO (PCT)
Prior art keywords
self
service device
time
sample information
preset
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.)
Ceased
Application number
PCT/CN2016/092306
Other languages
English (en)
French (fr)
Inventor
韩小平
郑家春
肖铮
何进君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GRG Banking Equipment Co Ltd
Original Assignee
GRG Banking Equipment Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GRG Banking Equipment Co Ltd filed Critical GRG Banking Equipment Co Ltd
Priority to RU2018121253A priority Critical patent/RU2697640C1/ru
Priority to EP16865563.7A priority patent/EP3379432A4/en
Priority to HK19101141.5A priority patent/HK1258733A1/zh
Priority to US15/772,061 priority patent/US10394302B2/en
Publication of WO2017084385A1 publication Critical patent/WO2017084385A1/zh
Anticipated expiration legal-status Critical
Priority to ZA2018/03392A priority patent/ZA201803392B/en
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/30—Circuit design
    • G06F30/36—Circuit design at the analogue level
    • G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
    • G07F19/20—Automatic teller machines [ATMs]
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
    • G07F19/20—Automatic teller machines [ATMs]
    • G07F19/206—Software aspects at ATMs
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
    • G07F19/20—Automatic teller machines [ATMs]
    • G07F19/209—Monitoring, auditing or diagnose of functioning of ATMs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation

Definitions

  • the present invention relates to the field of self-service devices, and in particular, to a self-service device energy-saving control method and apparatus.
  • ATM equipment is one of the important applications.
  • ATM refers to a small machine set up by banks in different locations, allowing users to implement self-service deposit, withdrawal, transfer and other counter services through bank cards.
  • the emergence of ATM equipment makes it unnecessary for users to carry out the cumbersome operations such as taking the number and counter processing when handling this part of the business, and also reduces the pressure on the counter staff, saving time and improving efficiency.
  • the sleep interval of current ATM devices is fixed, and the length of time is set by the bank or ATM equipment manufacturer.
  • the length of time is set by the bank or ATM equipment manufacturer.
  • the device When the device is set to sleep for a long time, when the service is relatively deserted (such as the early morning), the ATM device does not enter the sleep state for a long time, and the power consumption will be greatly increased.
  • the embodiment of the invention provides a self-service device energy-saving control method and device, which can solve the problem that the sleep interval is too short when the user volume is large, the self-service device repeatedly sleeps, and the sleep interval is too long when the user traffic is small. The problem of wasting resources.
  • sample information to be learned from the historical data used by the self-service device user, where the sample information is a quantity of users using different time periods of the self-service device for a period of time;
  • the updated Bayesian prior probability model is used to predict the amount of users in each time period in the preset time period, and the predicted user amount of the self-service device is obtained;
  • the Bayesian prior probability model is obtained by the following steps:
  • a Bayesian prior probability model is obtained according to Bayes' rule and the prior sample information.
  • the sample information to be learned is updated to the a priori sample information each time the sample information to be learned is acquired.
  • the Bayesian prior probability model P(x s ) is:
  • Dir( ⁇ 1 , ⁇ 2 , . . . , ⁇ s ) is a Dirichlet distribution
  • s represents the number of time periods in a period of time
  • x s represents the amount of users corresponding to the sample information in the s time period
  • ⁇ s represents the amount of sample information in the s time period
  • the updated model of the Bayesian prior probability P '(x s) of:
  • x s s represents an amount of user information corresponding to the sample period at.
  • the dormant interval of the self-service device is adjusted according to the predicted user amount, and the dormancy state of the self-service device corresponding to the dormant interval time is also adjusted. state.
  • adjusting, according to the predicted user quantity, the sleep interval time of the self-service device and the sleep state of the self-service device corresponding to the sleep interval time specifically:
  • adjusting, according to the average idle time, the sleep interval of the self-service device and the sleep state of the self-service device corresponding to the sleep interval include:
  • Controlling the self-service if the average idle time is greater than or equal to a preset first time threshold and less than a preset second time threshold, and the self-service device is not used within a preset first sleep interval The device enters a shallow sleep state. In the shallow sleep state, the screen of the self-service device is turned off but the main device is kept running normally;
  • the self-service device If the average idle time is greater than a preset second time threshold, and the self-service device is not used within a preset first sleep interval time, controlling the self-service device to enter a shallow sleep state, and when When the time when the self-service device enters the shallow sleep state exceeds the preset second sleep interval time, the self-service device is controlled to enter a deep sleep state, and the screen of the self-service device is turned off and the main device enters the lowest power consumption in the deep sleep state. Operating status.
  • adjusting, according to the average idle time, the sleep interval time of the self-service device and the sleep state of the self-service device corresponding to the sleep interval time further includes:
  • the self-service device is controlled to enter a deep sleep state.
  • sample information obtaining module for obtaining learning from historical data used by self-service device users Sample information, which is the amount of users using different time periods of the self-service device for a period of time;
  • a learning module configured to learn the sample information to be learned according to a preset Bayesian prior probability model, and obtain a learning result
  • An update module configured to update the Bayesian prior probability model according to the learning result
  • the user quantity prediction module is configured to predict the user quantity of each time period in the preset time period by using the updated Bayesian prior probability model to obtain the predicted user quantity of the self-service device;
  • a sleep adjustment module configured to adjust a sleep interval of each time period of the self-service device according to the predicted user amount.
  • the sample information to be learned is obtained from historical data used by the user of the self-service device, and the sample information is a quantity of users using different time periods of the self-service device for a period of time; a Bayesian prior probability model for learning the sample information to be learned to obtain a learning result; then, updating the Bayesian prior probability model according to the learning result; and further, using the updated The Bayesian prior probability model predicts the amount of users in each time period in the preset time period to obtain the predicted user amount of the self-service device; finally, adjusts the sleep time of the self-service device according to the predicted user amount. Intervals.
  • the self-learned Bayesian prior probability model is used to predict the amount of users, and the sleep interval of each time period of the self-service device is adjusted according to the obtained predicted user amount, and the self-service equipment time can be reasonably set according to requirements.
  • the sleep interval of the segment avoids the sleep interval being too short when the user volume is large, the self-service device repeatedly sleeps, and the sleep interval is too long when the user traffic is small, resulting in waste of resources.
  • FIG. 1 is a flowchart of an embodiment of a self-service device energy-saving control method according to an embodiment of the present invention
  • FIG. 2 is a flowchart of another embodiment of a self-service device energy-saving control method according to an embodiment of the present invention
  • FIG. 3 is a structural diagram of an embodiment of a self-service device energy-saving control device according to an embodiment of the present invention
  • FIG. 4 is a structural diagram of another embodiment of a self-service device energy-saving control apparatus according to an embodiment of the present invention.
  • the embodiment of the invention provides a self-service device energy-saving control method and device, which is used to solve the problem that the sleep interval is too short when the user volume is large, the self-service device repeatedly sleeps, and the sleep interval is too long when the user traffic is small. , causing waste of resources.
  • an embodiment of a self-service device energy-saving control method includes:
  • the sample information to be learned is obtained from historical data used by the self-service device user, and the sample information is the amount of users using different time periods of the self-service device for a period of time.
  • the sample information to be learned may be learned according to a preset Bayesian prior probability model, and the learning result is obtained.
  • the Bayesian prior probability model After learning the sample information to be learned according to the preset Bayesian prior probability model, and obtaining the learning result, the Bayesian prior probability model may be updated according to the learning result.
  • the updated Bayesian prior probability model may be used to predict the amount of users in each time period in the preset time period, and the self-service device is obtained. The predicted user volume.
  • the self-service device time can be adjusted according to the predicted user amount.
  • the sleep interval of the segment After the updated Bayesian prior probability model is used to predict the amount of users in each time period in the preset time period, and after obtaining the predicted user amount of the self-service device, the self-service device time can be adjusted according to the predicted user amount.
  • the sleep interval of the segment After the updated Bayesian prior probability model is used to predict the amount of users in each time period in the preset time period, and after obtaining the predicted user amount of the self-service device, the self-service device time can be adjusted according to the predicted user amount.
  • the sleep interval of the segment After the updated Bayesian prior probability model is used to predict the amount of users in each time period in the preset time period, and after obtaining the predicted user amount of the self-service device, the self-service device time can be adjusted according to the predicted user amount.
  • the sleep interval of the segment After the updated Bayesian prior probability model is used to predict the amount of users in each time period in the preset time period, and
  • the sample information to be learned is obtained from the historical data used by the user of the self-service device, and the sample information is the amount of users using different time periods of the self-service device for a period of time; and then, according to the preset Bayes
  • the prior probability model learns the sample information to be learned, and obtains the learning result.
  • the Bayesian prior probability model is updated according to the learning result; and then, the updated Bayesian prior is used.
  • the probability model predicts the amount of users in each time period in the preset time period to obtain the predicted user amount of the self-service device.
  • the sleep interval time of each self-service device is adjusted according to the predicted user amount.
  • the self-learned Bayesian prior probability model is used to predict the amount of users, and the sleep interval of each time period of the self-service device is adjusted according to the obtained predicted user amount, and the self-service devices can be reasonably set according to requirements.
  • the sleep interval is avoided when the number of users is too large, and the sleep interval is too short.
  • the self-service device repeatedly starts to sleep, and when the user traffic is small, the sleep interval is too long, resulting in waste of resources.
  • FIG. 2 another embodiment of the self-service energy-saving control method in the embodiment of the present invention includes:
  • the sample information to be learned may be obtained from the historical data used by the self-service device user, and the sample information is the amount of users using different time periods of the self-service device for a period of time. It can be understood that, that is, a user who can obtain the sample information to be learned between the time point when the user starts using the self-service device and the time point when the user starts using the self-service device can be acquired for a period of time (in an integer multiple of 24 hours). The amount, and the amount of users of the sample information to be learned are sorted by time period, and the sampled information to be learned is obtained; wherein each time period can be one hour or two hours or longer.
  • the following is an hour to treat the learning sample information and the prior sample information as a time period. For example:
  • sample information D 1 to be learned after being sorted is:
  • s represents the first time period
  • s 1, 2, ..., 12.
  • the sorted a priori sample information D is:
  • s represents the first time period
  • s 1, 2, ..., 12.
  • the sample information to be learned may be learned according to a preset Bayesian prior probability model, and the learning result is obtained.
  • Bayesian prior probability model can be preprocessed by the following steps:
  • the sample information to be learned may be updated to the a priori sample information.
  • the Bayesian prior probability model can be updated according to the learning result.
  • the organized sample information to be learned is learned; the interval between the learned sample information to be learned may be one or two days or longer, which It depends on the usage of the self-service equipment at the site.
  • the Bayesian prior probability is used to describe the process of learning the sample information to be learned in detail:
  • the pre-arranged a priori sample information obtained as illustrated in step 201 can obtain the total number of prior sample information n:
  • Dir( ⁇ 1 , ⁇ 2 , . . . , ⁇ s ) is a Dirichlet distribution
  • s represents the number of time periods in a day
  • x s represents the amount of users corresponding to the sample information in the s time period
  • ⁇ s represents the amount of sample information in the s time period
  • Bayesian prior probability P (x s) as x s profile, P (x s
  • Dir( ⁇ 1 + ⁇ 1 , ⁇ 2 + ⁇ 2 ,..., ⁇ s + ⁇ s ) gives the Bayesian prior probability P′(x s ) after learning:
  • the total number of a priori sample information after sorting is also updated to
  • the updated Bayesian prior probability model may be used to predict the amount of users in each time period in the preset time period, and the self-service device is obtained.
  • the predicted user volume The following will be described in detail:
  • the updated Bayesian prior probability is used to predict the amount of users in each time period in a period of time, and the period of time may be based on the learning interval of the collated sample information to be learned. Depending on the time.
  • the probability prediction of the user appearing in each time period of the second day is predicted, and the amount of users using the self-service device in each time period is predicted.
  • the Bayesian prior probability model is updated according to the Bayesian prior probability P′(x s ) after learning, and the updated Bayesian prior probability model P(x s ) is obtained as:
  • x' s is merged into x s to become a priori sample information, and when the time is two hours as a time period, 24 of the above formula will become 12.
  • the user amount of the self-service device can be predicted by the user in the sth time period, and the user amount y of the user using the ATM device in the s time period is:
  • n is the total number of samples after the update, that is, the total number of self-service devices is used
  • P(x s ) is the updated Bayesian prior probability model, and all the users who use the self-service device in the S time period can be obtained.
  • the total duration of use of the self-service device by all users can be obtained.
  • the average duration of the user's use of the self-service device can be calculated according to the total duration.
  • the total duration of the predicted usage may be obtained according to the predicted user amount and the average duration.
  • the total duration may be used according to the prediction to calculate the usage between the two self-service devices in the preset time period. Average idle time.
  • the sleep interval time and the sleep of each time period of the self-service device may be adjusted according to the average idle time. status.
  • adjusting the sleep interval and the sleep state of the self-service device in each time period according to the average idle time may specifically include:
  • the self-service device is controlled not to enter a sleep state
  • the self-service device is controlled. Entering the shallow sleep state, the screen of the self-service device is turned off in the shallow sleep state but the main device is kept running normally;
  • the self-service device is controlled to enter a shallow sleep state, and when the self-service device When the time of entering the shallow sleep state exceeds the preset second sleep interval time, the self-service device is controlled to enter the deep sleep state, and the screen of the self-service device is turned off and the main device enters the lowest power consumption operation state in the deep sleep state.
  • the self-service device is controlled to enter a deep sleep state.
  • the device When the average idle time before a user uses the self-service device in the x s time period and the next user comes to use the self-service device is less than 5 minutes, the device does not prepare to go to sleep.
  • the average idle time before a user uses the self-service device in the x s time period and the next user comes to use the self-service device is greater than 5 minutes and less than 30 minutes, no user uses the self-service device within 3 minutes of the adjusted sleep interval. It will be adjusted to a shallow sleep state, the screen of the self-service device is turned off, and the main device is kept running normally, such as a CPU.
  • the average idle time before a user uses the self-service device after the user has finished using the self-service device in the x s time period is greater than 30 minutes
  • no user using the self-service device within 3 minutes of the adjusted sleep interval will be adjusted to In the shallow sleep state, the screen of the self-service device is turned off, and the main device is kept running normally.
  • the adjusted sleep interval is 10 minutes
  • the self-service device will enter deep sleep, and the main device will enter the lowest power consumption state.
  • the usage rate of the self-service device is extremely low.
  • the user can directly adjust to the deep sleep state within 3 minutes of the adjusted sleep interval, so that it can be guaranteed to be used by the user.
  • the self-service device is used, the device can be quickly started to ensure the user's experience and energy saving effect.
  • the invention learns the sample information of the learning by the Bayesian prior probability, obtains the learning result, updates the Bayesian prior experience according to the learning result, and then predicts each time period of the day through the updated Bayesian prior experience.
  • the sleep mode of the self-service device and the time of entering the sleep are adjusted, and the sleep interval is extended when the number of users is large, thereby preventing the device from being started multiple times.
  • Reduce equipment failure probability and maintenance cost shorten the interval between device sleep when user traffic is low, reduce resource waste, and save costs.
  • an embodiment of the self-service energy-saving control device in the embodiment of the present invention includes:
  • the sample information obtaining module 301 is configured to obtain sample information to be learned from the historical data used by the self-service device user, where the sample information is a quantity of users using different time periods of the self-service device for a period of time;
  • the learning module 302 is configured to learn the sample information to be learned according to a preset Bayesian prior probability model, and obtain a learning result;
  • An update module 303 configured to update the Bayesian prior probability model according to the learning result
  • the user quantity prediction module 304 is configured to predict the user quantity of each time period in the preset time period by using the updated Bayesian prior probability model to obtain the predicted user quantity of the self-service device;
  • a sleep adjustment module 305 configured to adjust the self-service device time according to the predicted user amount The sleep interval of the segment.
  • the sample information obtaining module 301 obtains sample information to be learned from the historical data used by the self-service device user, where the sample information is the amount of users using different time periods of the self-service device for a period of time; the learning module 302 The sample information to be learned is learned according to a preset Bayesian prior probability model to obtain a learning result; the update module 303 updates the Bayesian prior probability model according to the learning result; the user amount prediction module 304 adopts The updated Bayesian prior probability model predicts the amount of users in each time period in the preset time period to obtain the predicted user amount of the self-service device; finally, the sleep adjustment module 305 adjusts the self-service device according to the predicted user amount. The sleep interval for each time period.
  • the self-learned Bayesian prior probability model is used to predict the amount of users, and the sleep interval of each time period of the self-service device is adjusted according to the obtained predicted user amount, and the self-service devices can be reasonably set according to requirements.
  • the sleep interval is avoided when the number of users is too large, and the sleep interval is too short.
  • the self-service device repeatedly starts to sleep, and when the user traffic is small, the sleep interval is too long, resulting in waste of resources.
  • FIG. 4 another embodiment of the self-service energy-saving control device in the embodiment of the present invention includes:
  • the sample information obtaining module 401 is configured to obtain sample information to be learned from the historical data used by the user of the self-service device, where the sample information is different time periods used by different users in the day;
  • the learning module 402 is configured to learn the sample information to be learned according to a preset Bayesian prior probability model, and obtain a learning result;
  • An update module 403, configured to update the Bayesian prior probability model according to the learning result
  • the user quantity prediction module 404 is configured to predict the user quantity of each time period in the preset time period by using the updated Bayesian prior probability model to obtain the predicted user quantity of the self-service device;
  • the sleep adjustment module 405 is configured to adjust a sleep interval of each self-service device according to the predicted user amount.
  • the sleep adjustment module 405 is further configured to adjust according to the predicted user amount.
  • the sleep adjustment module 405 may specifically include:
  • the total duration acquisition unit 4051 is configured to obtain a total duration of time that all users use the self-service device;
  • the average duration acquisition unit 4052 is configured to calculate, according to the total duration, an average duration of the user using the self-service device each time;
  • the usage time acquisition unit 4053 is configured to obtain a total duration of prediction use according to the predicted user amount and the average duration;
  • the idle time calculation unit 4054 is configured to calculate, according to the prediction, the total idle time between two adjacent use of the self-service devices in the preset time period;
  • the adjusting unit 4055 is configured to adjust the sleep interval time and the sleep state of the self-service device for each time period according to the average idle time.
  • the adjusting unit 4055 may specifically include:
  • the first control subunit 0551 is configured to control the self-service device not to enter a sleep state if the average idle time is less than a preset first time threshold;
  • the second control sub-unit 0552 is configured to: if the average idle time is greater than or equal to a preset first time threshold and less than a preset second time threshold, and the self-service device is not used within a preset first time limit, Controlling the self-service device to enter a shallow sleep state, in which the screen of the self-service device is turned off but the main device is kept running normally;
  • the third control sub-unit 0553 is configured to control the self-service device to enter a shallow sleep state if the average idle time is greater than a preset second time threshold, and the self-service device is not used within a preset first time limit. And when the self-service device enters the shallow sleep state for more than a preset second time limit, the self-service device is controlled to enter a deep sleep state, and the screen of the self-service device is turned off and the main device enters a minimum power consumption operation in the deep sleep state. status;
  • the fourth control sub-unit 0554 is configured to control the self-service device to enter a deep sleep state if the current real time is within a preset time range and the self-service device is not used within a preset third time limit.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • General Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Data Mining & Analysis (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Optimization (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Facsimiles In General (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Architecture (AREA)
  • Air Conditioning Control Device (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

一种自助设备节能控制方法和装置，用于解决在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的问题。本方法包括：从自助设备用户使用的历史数据中获取待学习的样本信息（101）；根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果（102）；根据所述学习结果对所述贝叶斯先验概率模型进行更新（103）；采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量（104）；根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间（105）。

Description

一种自助设备节能控制方法和装置
本申请要求于2015年11月16日提交中国专利局、申请号为201510789025.9、发明名称为“一种自助设备节能控制方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及自助设备技术领域，尤其涉及一种自助设备节能控制方法和装置。
背景技术
随着社会的飞速发展，科技被运用于各行各业，包括金融领域。ATM设备便是其中的一个重要的应用。ATM是指银行在不同地点设置的一种小型机器，让用户通过银行卡实现自助存款、取款、转账等柜台服务。ATM设备的出现，使得用户在办理这部分业务时不必再进行取号、柜台办理等繁琐操作，同时也减少了柜台人员的压力，节省了时间也提高了效率。
但是数量庞大的ATM设备带来的耗能问题也给银行带来了较大的负担，目前的ATM设备的休眠间隔时间都是固定的，时间的长短是由银行或者ATM设备厂商设置，在无人使用设备时间较短时设置休眠，在业务较为繁忙的时段就可能存在频繁休眠和启动，给ATM设备带来了较大的伤害，增加了设备故障率和维护成本；而若在无人使用设备较长时间设置休眠，则在业务相对冷清的时候(比如凌晨)，ATM设备长时间不进入休眠状态，耗电将会大大增加。
发明内容
本发明实施例提供了一种自助设备节能控制方法和装置，能够解决在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的问题。
本发明实施例提供的一种自助设备节能控制方法，包括：
从自助设备用户使用的历史数据中获取待学习的样本信息，所述样本信息为一段时间内使用所述自助设备的不同时间段的用户量；
根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果；
根据所述学习结果对所述贝叶斯先验概率模型进行更新；
采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量；
根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间。
可选地，所述贝叶斯先验概率模型由以下步骤预处理得到：
对自助设备用户使用的历史数据进行预处理，获取一段时间内使用所述自助设备的不同时间段的用户量作为样本信息；
按照时间段分类对所述样本信息进行整理，得到对应的先验样本信息；
根据贝叶斯法则和所述先验样本信息得到贝叶斯先验概率模型。
可选地，每次在获取到所述待学习的样本信息之后，将所述待学习的样本信息更新至所述先验样本信息。
可选地，所述贝叶斯先验概率模型P(xs)为：
Figure PCTCN2016092306-appb-000001
其中，Dir(α1,α2,…,αs)为狄利克雷分布，s表示一段时间内所述时间段的数量，xs表示在s时间段内所述样本信息对应的用户量，αs表示s时间段内所述样本信息的数量，
Figure PCTCN2016092306-appb-000002
可选地，更新后的所述贝叶斯先验概率模型P′(xs)为：
Figure PCTCN2016092306-appb-000003
其中，更新后的样本信息总数
Figure PCTCN2016092306-appb-000004
x′s为待学习的样本信息中每个时间段的用户量，xs表示在s时间段内所述样本信息对应的用户量。
可选地，根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间的同时，还调节与所述休眠间隔时间对应的所述自助设备的休眠状 态。
可选地，根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态具体包括：
获取所有用户使用所述自助设备的总时长；
根据所述总时长计算得到用户每次使用所述自助设备的平均时长；
根据所述预测用户量和所述平均时长得到预测使用总时长；
根据所述预测使用总时长计算出预设时间段内相邻两次使用所述自助设备之间的平均空闲时间；
根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态。
可选地，根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态具体包括：
若所述平均空闲时间小于预设的第一时间阈值，则控制所述自助设备不进入休眠状态；
若所述平均空闲时间大于或等于预设的第一时间阈值且小于预设的第二时间阈值，且在预设的第一休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入浅度休眠状态，在浅度休眠状态下所述自助设备的屏幕关闭但保持主要设备正常运行；
若所述平均空闲时间大于预设的第二时间阈值，且在预设的第一休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入浅度休眠状态，并且当所述自助设备进入浅度休眠状态的时间超过预设的第二休眠间隔时间时，控制所述自助设备进入深度休眠状态，在深度休眠状态下所述自助设备的屏幕关闭并且其主要设备进入最低功耗运行状态。
可选地，根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态还包括：
若当前现实时间处于预设的时间范围内，且在预设的第三休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入深度休眠状态。
本发明实施例提供的一种自助设备节能控制装置，包括：
样本信息获取模块，用于从自助设备用户使用的历史数据中获取待学 习的样本信息，所述样本信息为一段时间内使用所述自助设备的不同时间段的用户量；
学习模块，用于根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果；
更新模块，用于根据所述学习结果对所述贝叶斯先验概率模型进行更新；
用户量预测模块，用于采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量；
休眠调节模块，用于根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间。
从以上技术方案可以看出，本发明实施例具有以下优点：
本发明实施例中，首先，从自助设备用户使用的历史数据中获取待学习的样本信息，所述样本信息为一段时间内使用所述自助设备的不同时间段的用户量；然后，根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果；接着，根据所述学习结果对所述贝叶斯先验概率模型进行更新；再之，采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量；最后，根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间。在本发明实施例中，利用自学习的贝叶斯先验概率模型预测用户量，并根据得到的预测用户量调节自助设备各个时间段的休眠间隔时间，可以根据需要合理地设置自助设备各个时间段的休眠间隔时间，避免出现在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的情况。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例中一种自助设备节能控制方法一个实施例流程图；
图2为本发明实施例中一种自助设备节能控制方法另一个实施例流程图；
图3为本发明实施例中一种自助设备节能控制装置一个实施例结构图；
图4为本发明实施例中一种自助设备节能控制装置另一个实施例结构图。
具体实施方式
本发明实施例提供了一种自助设备节能控制方法和装置，用于解决在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的问题。
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，下面所描述的实施例仅仅是本发明一部分实施例，而非全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
请参阅图1，本发明实施例中一种自助设备节能控制方法一个实施例包括：
101、从自助设备用户使用的历史数据中获取待学习的样本信息；
首先，从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一段时间内使用该自助设备的不同时间段的用户量。
102、根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；
在从自助设备用户使用的历史数据中获取待学习的样本信息之后，可以根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果。
103、根据该学习结果对该贝叶斯先验概率模型进行更新；
在根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果之后，可以根据该学习结果对该贝叶斯先验概率模型进行更新。
104、采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；
在根据该学习结果对该贝叶斯先验概率模型进行更新之后，可以采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量。
105、根据该预测用户量调节该自助设备各个时间段的休眠间隔时间。
在采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量之后，可以根据该预测用户量调节该自助设备各个时间段的休眠间隔时间。
本实施例中，首先，从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一段时间内使用该自助设备的不同时间段的用户量；然后，根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；接着，根据该学习结果对该贝叶斯先验概率模型进行更新；再之，采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；最后，根据该预测用户量调节该自助设备各个时间段的休眠间隔时间。在本实施例中，利用自学习的贝叶斯先验概率模型预测用户量，并根据得到的预测用户量调节自助设备各个时间段的休眠间隔时间，可以根据需要合理地设置自助设备各个时间段的休眠间隔时间，避免出现在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的情况。
为便于理解，下面对本发明实施例中的一种自助设备节能控制方法进行详细描述，请参阅图2，本发明实施例中一种自助设备节能控制方法另一个实施例包括：
201、从自助设备用户使用的历史数据中获取待学习的样本信息；
首先，可以从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一段时间内使用该自助设备的不同时间段的用户量。可以理解的是，也即，可以获取一段时间(是以24小时为整数倍)内用户开始使用该自助设备的时间点至结束使用该自助设备的时间点之间作为待学习样本信息的一个用户量，并将待学习样本信息的用户量按时间段进行整理，得到整理后的待学习样本信息；其中每个时间段可以为一小时或两小时或更长的时间。
以下是以一个小时作为一个时间段对待学习样本信息和先验样本信息进行整理，举例说明：
即得到整理后的待学习样本信息D1为：
D1＝{x′1,x′2,…,x′s}；
其中，s表示第几时间段，s取值范围为s≤24且s能被24整除；当以一个小时作为一个时间段时，s取值：s＝1,2，…，24；x′s表示该时间段待学习样本信息的用户量，并且x′s＝0,1,2，…m。
而当以两个小时作为一个时间段对待学习样本信息进行整理时，s取值：s＝1,2，…，12。
得到整理后的先验样本信息D为：
D＝{x1,x2,…,xs}；
其中，s表示第几时间段，s取值范围为s≤24且s能被24整除；当以一个小时为一个时间段时，s取值：s＝1,2，…，24；xs表示该时间段先验样本信息的用户量并且xs＝0,1,2，…m；
当以两个小时作为一个时间段对先验样本信息进行整理时，s取值：s＝1,2，…，12。
202、根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；
在从自助设备用户使用的历史数据中获取待学习的样本信息之后，可以根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果。
需要说明的是，该贝叶斯先验概率模型可以由以下步骤预处理得到：
A、对自助设备用户使用的历史数据进行预处理，获取一天时间内不同用户使用该自助设备的不同时间段作为样本信息；
B、按照时间段分类对该样本信息进行整理，得到对应的先验样本信息；
C、根据贝叶斯法则和该先验样本信息得到贝叶斯先验概率模型。
需要注意的是，每次在获取到该待学习的样本信息之后，还可以将该待学习的样本信息更新至该先验样本信息。
203、根据该学习结果对该贝叶斯先验概率模型进行更新；
在得到学习结果之后，可以根据该学习结果对该贝叶斯先验概率模型进行更新。
需要说明的是，根据贝叶斯先验概率，对整理后的待学习样本信息进行学习；对整理后的待学习样本信息进行学习的间隔时间可以为一天或两天或更长的时间，这需要根据该网点的自助设备的使用量情况而定。
举例说明，假设时间间隔为一天，采用贝叶斯先验概率，对整理后的待学习样本信息进行学习的过程进行详细说明：
如步骤201中举例说明的获取的整理后先验样本信息，可得先验样本信息总数n：
Figure PCTCN2016092306-appb-000005
其中，当以两个小时作为一个时间段时上式的24将变为12。
则有各个时间段ATM设备用户量的贝叶斯先验概率P(xs)有：
Figure PCTCN2016092306-appb-000006
其中，当以两个小时作为一个时间段时上式的24将变为12。
由于使用自助设备的用户是连续多变的，则每个时间段的贝叶斯先验概率模型P(xs)服从狄利克雷分布为Dir(α1,α2,…,αs)，则有：
Figure PCTCN2016092306-appb-000007
其中，Dir(α1,α2,…,αs)为狄利克雷分布，s表示一天时间内所述时间段的数量，xs表示在s时间段内所述样本信息对应的用户量，αs表示s时间段内所述样本信息的数量，
Figure PCTCN2016092306-appb-000008
那么先验样本的概率P(D)为：
P(D)＝∫P(xs)P(D|xs)dxs；
即，对待学习样本信息进行学习，由贝叶斯公式得：
Figure PCTCN2016092306-appb-000009
其中P(xs)为xs的贝叶斯先验概率分布，P(xs|D)为xs的贝叶斯后验概率分布，将P(xs|D)转换为狄利克雷分布Dir(α1+β1,α2+β2,…,αs+βs)，即可得学习后的贝叶斯先验概率P′(xs)：
Figure PCTCN2016092306-appb-000010
其中，当以两个小时作为一个时间段时上式的24将变为12；β1，β2，…，βs为整理后的待学习样本信息中x′s时间段狄利克雷分布，x′s为更新样本中每个时间段的用户量，x′s＝0,1,2,…,m；采用学习后的贝叶斯先验概率去更新原来的贝叶斯先验概率；
整理后的先验样本信息总数n也更新为
Figure PCTCN2016092306-appb-000011
其中，当以两个小时作为一个时间段时上式的24将变为12。
204、采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；
在根据该学习结果对该贝叶斯先验概率模型进行更新之后，可以采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量。下面将进行详细说明：
采用更新后的贝叶斯先验概率对一段时间内各个时间段的用户量进行预测，其中的一段时间可以根据对整理后的待学习样本信息的学习间隔时 间而定。
以下是对第二天预测各个时间段的用户量进行详细说明：
根据更新后贝叶斯先验概率做出第二天的各个时间段的用户出现的概率预测，预测出各个时间段使用自助设备的用户量。
则根据学习后的贝叶斯先验概率P′(xs)对贝叶斯先验概率模型进行进行更新，获取更新后贝叶斯先验概率模型P(xs)为：
Figure PCTCN2016092306-appb-000012
其中，将x′s融到xs中，成为先验样本信息，当以两个小时作为一个时间段时上式的24将变为12。
即可预测出第s时间段的用户使用自助设备的用户量，则第s时间段的用户的使用ATM设备的用户量y为：
y＝P(xs)·n；
n为更新后样本总数，即为使用自助设备的总数，P(xs)为更新后的贝叶斯先验概率模型，即可得到所有在第S时间段用户使用该自助设备的用户量。
205、获取所有用户使用该自助设备的总时长；
在得到该自助设备的预测用户量之后，可以获取所有用户使用该自助设备的总时长。
206、根据该总时长计算得到用户每次使用该自助设备的平均时长；
在获取所有用户使用该自助设备的总时长之后，可以根据该总时长计算得到用户每次使用该自助设备的平均时长。
207、根据该预测用户量和该平均时长得到预测使用总时长；
在根据该总时长计算得到用户每次使用该自助设备的平均时长之后，可以根据该预测用户量和该平均时长得到预测使用总时长。
208、根据该预测使用总时长计算出预设时间段内相邻两次使用该自助设备之间的平均空闲时间；
在根据该预测用户量和该平均时长得到预测使用总时长之后，可以根据该预测使用总时长计算出预设时间段内相邻两次使用该自助设备之间的 平均空闲时间。
209、根据该平均空闲时间调节该自助设备各个时间段的休眠间隔时间和该休眠状态。
在根据该预测使用总时长计算出预设时间段内相邻两次使用该自助设备之间的平均空闲时间之后，可以根据该平均空闲时间调节该自助设备各个时间段的休眠间隔时间和该休眠状态。
需要说明的是，根据该平均空闲时间调节该自助设备各个时间段的休眠间隔时间和该休眠状态具体可以包括：
1、若该平均空闲时间小于预设的第一时间阈值，则控制该自助设备不进入休眠状态；
2、若该平均空闲时间大于或等于预设的第一时间阈值且小于预设的第二时间阈值，且在预设的第一休眠间隔时间内该自助设备未被使用，则控制该自助设备进入浅度休眠状态，在浅度休眠状态下该自助设备的屏幕关闭但保持主要设备正常运行；
3、若该平均空闲时间大于预设的第二时间阈值，且在预设的第一休眠间隔时间内该自助设备未被使用，则控制该自助设备进入浅度休眠状态，并且当该自助设备进入浅度休眠状态的时间超过预设的第二休眠间隔时间时，控制该自助设备进入深度休眠状态，在深度休眠状态下该自助设备的屏幕关闭并且其主要设备进入最低功耗运行状态。
4、若当前现实时间处于预设的时间范围内，且在预设的第三休眠间隔时间内该自助设备未被使用，则控制该自助设备进入深度休眠状态。
为便于理解，举例详细说明如下：
当预测xs时间段内一个用户使用完毕自助设备后到下个用户前来使用自助设备前的平均空闲时间小于5分钟时，设备不做进入休眠准备。
当预测xs时间段内一个用户使用完毕自助设备后到下个用户前来使用自助设备前的平均空闲时间大于5分钟小于30分钟时，在调整的休眠间隔时间3分钟内没有用户使用自助设备将调整为浅度休眠状态，自助设备的屏幕关闭，保持主要设备正常运行，如CPU等。
当预测xs时间段内一个用户使用完毕自助设备后到下个用户前来使用自助设备前的平均空闲时间大于30分钟时，在调整的休眠间隔时间3分钟内没有用户使用自助设备将调整为浅度休眠状态，自助设备的屏幕关闭，保持主要设备正常运行，调整的休眠间隔时间10分钟后自助设备将进入深度休眠，主要的设备也将进入最低功耗运行状态。
如在深夜11点到凌晨6点之间，自助设备的使用率极低，在调整的休眠间隔时间3分钟内无用户使用自助设备可直接调整为深度休眠状态，这样既能保证当有用户使用自助设备时能快速启动设备，保证用户的使用体验感，又能达到节能的效果。
本发明通过贝叶斯先验概率对待学习的样本信息进行学习，获取学习结果，根据学习结果更新贝叶斯先验经验，然后通过更新后的贝叶斯的先验经验预测当天每个时间段使用该自助设备的用户量，根据更新后贝叶斯先验经验的预测结果，调整自助设备的休眠模式和进入休眠的时间，在用户量较多的时候延长休眠间隔时间，防止设备多次启动，降低设备故障概率和维护成本，在用户流量较少时缩短设备休眠的间隔时间，减少资源浪费，节约成本。
上面主要对一种自助设备节能控制方法进行描述，下面将详细描述一种自助设备节能控制装置，请参阅图3，本发明实施例中一种自助设备节能控制装置一个实施例包括：
样本信息获取模块301，用于从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一段时间内使用该自助设备的不同时间段的用户量；
学习模块302，用于根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；
更新模块303，用于根据该学习结果对该贝叶斯先验概率模型进行更新；
用户量预测模块304，用于采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；
休眠调节模块305，用于根据该预测用户量调节该自助设备各个时间 段的休眠间隔时间。
本实施例中，首先，样本信息获取模块301从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一段时间内使用该自助设备的不同时间段的用户量；学习模块302根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；更新模块303根据该学习结果对该贝叶斯先验概率模型进行更新；用户量预测模块304采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；最后，休眠调节模块305根据该预测用户量调节该自助设备各个时间段的休眠间隔时间。在本实施例中，利用自学习的贝叶斯先验概率模型预测用户量，并根据得到的预测用户量调节自助设备各个时间段的休眠间隔时间，可以根据需要合理地设置自助设备各个时间段的休眠间隔时间，避免出现在用户量较多的时候休眠间隔时间过短，自助设备反复休眠启动，而在用户流量较少时休眠间隔时间过长，造成资源浪费的情况。
为便于理解，下面对本发明实施例中的一种自助设备节能控制装置进行详细描述，请参阅图4，本发明实施例中一种自助设备节能控制装置另一个实施例包括：
样本信息获取模块401，用于从自助设备用户使用的历史数据中获取待学习的样本信息，该样本信息为一天时间内不同用户使用该自助设备的不同时间段；
学习模块402，用于根据预设的贝叶斯先验概率模型对该待学习的样本信息进行学习，得到学习结果；
更新模块403，用于根据该学习结果对该贝叶斯先验概率模型进行更新；
用户量预测模块404，用于采用更新后的该贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到该自助设备的预测用户量；
休眠调节模块405，用于根据该预测用户量调节该自助设备各个时间段的休眠间隔时间。
本实施例中，该休眠调节模块405还可以用于根据该预测用户量调节 该自助设备各个时间段的休眠间隔时间和该休眠状态。
本实施例中，该该休眠调节模块405具体可以包括：
总时长获取单元4051，用于获取所有用户使用该自助设备的总时长；
平均时长获取单元4052，用于根据该总时长计算得到用户每次使用该自助设备的平均时长；
使用时长获取单元4053，用于根据该预测用户量和该平均时长得到预测使用总时长；
空闲时间计算单元4054，用于根据该预测使用总时长计算出预设时间段内相邻两次使用该自助设备之间的平均空闲时间；
调节单元4055，用于根据该平均空闲时间调节该自助设备各个时间段的休眠间隔时间和该休眠状态。
本实施例中，该调节单元4055具体可以包括：
第一控制子单元0551，用于若该平均空闲时间小于预设的第一时间阈值，则控制该自助设备不进入休眠状态；
第二控制子单元0552，用于若该平均空闲时间大于或等于预设的第一时间阈值且小于预设的第二时间阈值，且在预设的第一时限内该自助设备未被使用，则控制该自助设备进入浅度休眠状态，在浅度休眠状态下该自助设备的屏幕关闭但保持主要设备正常运行；
第三控制子单元0553，用于若该平均空闲时间大于预设的第二时间阈值，且在预设的第一时限内该自助设备未被使用，则控制该自助设备进入浅度休眠状态，并且当该自助设备进入浅度休眠状态的时间超过预设的第二时限时，控制该自助设备进入深度休眠状态，在深度休眠状态下该自助设备的屏幕关闭并且其主要设备进入最低功耗运行状态；
第四控制子单元0554，用于若当前现实时间处于预设的时间范围内，且在预设的第三时限内该自助设备未被使用，则控制该自助设备进入深度休眠状态。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的 对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，该单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技 术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种自助设备节能控制方法，其特征在于，包括：
    从自助设备用户使用的历史数据中获取待学习的样本信息，所述样本信息为一段时间内使用所述自助设备的不同时间段的用户量；
    根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果；
    根据所述学习结果对所述贝叶斯先验概率模型进行更新；
    采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量；
    根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间。
  2. 根据权利要求1所述的方法，其特征在于，所述贝叶斯先验概率模型由以下步骤预处理得到：
    对自助设备用户使用的历史数据进行预处理，获取一段时间内使用所述自助设备的不同时间段的用户量作为样本信息；
    按照时间段分类对所述样本信息进行整理，得到对应的先验样本信息；
    根据贝叶斯法则和所述先验样本信息得到贝叶斯先验概率模型。
  3. 根据权利要求2所述的方法，其特征在于，每次在获取到所述待学习的样本信息之后，将所述待学习的样本信息更新至所述先验样本信息。
  4. 根据权利要求1所述的方法，其特征在于，所述贝叶斯先验概率模型P(xs)为：
    Figure PCTCN2016092306-appb-100001
    其中，Dir(α1,α2,…,αs)为狄利克雷分布，s表示一段时间内所述时间段的数量，xs表示在s时间段内所述样本信息对应的用户量，αs表示s时间段内所述样本信息的数量，
    Figure PCTCN2016092306-appb-100002
  5. 根据权利要求4所述的方法，其特征在于，更新后的所述贝叶斯先验概率模型P′(xs)为：
    Figure PCTCN2016092306-appb-100003
    其中，更新后的样本信息总数
    Figure PCTCN2016092306-appb-100004
    x′s为待学习的样本信息中每个时间段的用户量，xs表示在s时间段内所述样本信息对应的用户量。
  6. 根据权利要求1所述的方法，其特征在于，根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间的同时，还调节与所述休眠间隔时间对应的所述自助设备的休眠状态。
  7. 根据权利要求6所述的方法，其特征在于，根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态具体包括：
    获取所有用户使用所述自助设备的总时长；
    根据所述总时长计算得到用户每次使用所述自助设备的平均时长；
    根据所述预测用户量和所述平均时长得到预测使用总时长；
    根据所述预测使用总时长计算出预设时间段内相邻两次使用所述自助设备之间的平均空闲时间；
    根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态。
  8. 根据权利要求7所述的方法，其特征在于，根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态具体包括：
    若所述平均空闲时间小于预设的第一时间阈值，则控制所述自助设备不进入休眠状态；
    若所述平均空闲时间大于或等于预设的第一时间阈值且小于预设的第二时间阈值，且在预设的第一休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入浅度休眠状态，在浅度休眠状态下所述自助设备的屏幕关闭但保持主要设备正常运行；
    若所述平均空闲时间大于预设的第二时间阈值，且在预设的第一休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入浅度休眠状态，并且当所述自助设备进入浅度休眠状态的时间超过预设的第二休眠间隔时间时，控制所述自助设备进入深度休眠状态，在深度休眠状态下所述自助设备的屏幕关闭并且其主要设备进入最低功耗运行状态。
  9. 根据权利要求8所述的方法，其特征在于，根据所述平均空闲时间调节所述自助设备各个时间段的休眠间隔时间和与所述休眠间隔时间对应的所述自助设备的休眠状态还包括：
    若当前现实时间处于预设的时间范围内，且在预设的第三休眠间隔时间内所述自助设备未被使用，则控制所述自助设备进入深度休眠状态。
  10. 一种自助设备节能控制装置，其特征在于，包括：
    样本信息获取模块，用于从自助设备用户使用的历史数据中获取待学习的样本信息，所述样本信息为一段时间内使用所述自助设备的不同时间段的用户量；
    学习模块，用于根据预设的贝叶斯先验概率模型对所述待学习的样本信息进行学习，得到学习结果；
    更新模块，用于根据所述学习结果对所述贝叶斯先验概率模型进行更新；
    用户量预测模块，用于采用更新后的贝叶斯先验概率模型对预设时间段内各个时间段的用户量进行预测，得到所述自助设备的预测用户量；
    休眠调节模块，用于根据所述预测用户量调节所述自助设备各个时间段的休眠间隔时间。
PCT/CN2016/092306 2015-11-16 2016-07-29 一种自助设备节能控制方法和装置 Ceased WO2017084385A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
RU2018121253A RU2697640C1 (ru) 2015-11-16 2016-07-29 Способ и устройство энергосберегающего управления для оборудования самообслуживания
EP16865563.7A EP3379432A4 (en) 2015-11-16 2016-07-29 Self-service equipment energy saving control method and device
HK19101141.5A HK1258733A1 (zh) 2015-11-16 2016-07-29 一种自助设备节能控制方法和装置
US15/772,061 US10394302B2 (en) 2015-11-16 2016-07-29 Self-service equipment energy saving control method and device
ZA2018/03392A ZA201803392B (en) 2015-11-16 2018-05-22 Self-service equipment energy saving control method and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510789025.9 2015-11-16
CN201510789025.9A CN105468823B (zh) 2015-11-16 2015-11-16 一种自助设备节能控制方法和装置

Publications (1)

Publication Number Publication Date
WO2017084385A1 true WO2017084385A1 (zh) 2017-05-26

Family

ID=55606519

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/092306 Ceased WO2017084385A1 (zh) 2015-11-16 2016-07-29 一种自助设备节能控制方法和装置

Country Status (8)

Country Link
US (1) US10394302B2 (zh)
EP (1) EP3379432A4 (zh)
CN (1) CN105468823B (zh)
CL (1) CL2018001293A1 (zh)
HK (1) HK1258733A1 (zh)
RU (1) RU2697640C1 (zh)
WO (1) WO2017084385A1 (zh)
ZA (1) ZA201803392B (zh)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105468823B (zh) 2015-11-16 2019-01-25 广州广电运通金融电子股份有限公司 一种自助设备节能控制方法和装置
CN106527664B (zh) * 2016-11-07 2020-10-30 东软集团股份有限公司 自助终端节能控制方法及装置
CN107577522B (zh) * 2017-09-30 2020-04-21 Oppo广东移动通信有限公司 应用控制方法、装置、存储介质以及电子设备
CN109947497B (zh) * 2017-12-20 2021-06-08 Oppo广东移动通信有限公司 应用程序预加载方法、装置、存储介质及移动终端
CN109179101A (zh) * 2018-09-07 2019-01-11 平安科技（深圳）有限公司 电梯控制方法、装置、计算机设备及计算机可读存储介质
CN109725616B (zh) * 2018-12-29 2020-10-30 广州远联物流服务有限公司 一种基于智能仓库的无人搬运车调度方法及装置
CN111240459B (zh) * 2020-01-08 2021-05-28 珠海全志科技股份有限公司 片上系统功耗管理方法、计算机装置及计算机可读存储介质
CN112233343A (zh) * 2020-10-19 2021-01-15 中国工商银行股份有限公司 自助终端设备业务数据处理方法及装置
CN114521005B (zh) * 2020-11-20 2025-01-28 中兴通讯股份有限公司 基站节能的控制方法和装置、计算机可读存储介质
CN116345536B (zh) * 2023-02-08 2024-02-02 广东电网有限责任公司佛山供电局 一种配电变压器的有载在线调压方法及装置
CN117095496A (zh) * 2023-09-05 2023-11-21 中国银行股份有限公司 Atm机管理系统及控制方法、节能atm机及控制方法
CN117409516B (zh) * 2023-12-15 2024-03-22 杭银消费金融股份有限公司 一种自助终端的节能控制方法以及自助终端

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102662325A (zh) * 2012-05-04 2012-09-12 重庆邮电大学 一种改进自适应学习树电源管理方法
CN103490956A (zh) * 2013-09-22 2014-01-01 杭州华为数字技术有限公司 基于业务量预测的自适应节能控制方法及设备、系统
WO2014117861A1 (en) * 2013-02-01 2014-08-07 Telecom Italia S.P.A. Automatic system for controlling appliances
CN104093197A (zh) * 2014-07-17 2014-10-08 中国联合网络通信集团有限公司 一种移动互联网中的设备节能方法及系统
CN105468823A (zh) * 2015-11-16 2016-04-06 广州广电运通金融电子股份有限公司 一种自助设备节能控制方法和装置

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7689521B2 (en) * 2001-06-28 2010-03-30 Microsoft Corporation Continuous time bayesian network models for predicting users' presence, activities, and component usage
US7222245B2 (en) * 2002-04-26 2007-05-22 Hewlett-Packard Development Company, L.P. Managing system power based on utilization statistics
US7174468B2 (en) * 2002-08-01 2007-02-06 Texas Instruments Incorporated Methodology for coordinating and tuning application power
US20040064731A1 (en) * 2002-09-26 2004-04-01 Nguyen Timothy Thien-Kiem Integrated security administrator
US20040064531A1 (en) 2002-10-01 2004-04-01 Wisner Steven P. System and process for projecting hardware requirements for a web site
CN1700146A (zh) * 2004-05-20 2005-11-23 宏碁股份有限公司 用于计算机系统的省电方法及相关计算机系统
US7428521B2 (en) * 2005-06-29 2008-09-23 Microsoft Corporation Precomputation of context-sensitive policies for automated inquiry and action under uncertainty
US20080033786A1 (en) * 2006-08-04 2008-02-07 General Electric Company Power generation mix forecasting modeling method
JP2009140052A (ja) * 2007-12-04 2009-06-25 Konica Minolta Business Technologies Inc 電源管理システムおよび電源管理方法
US8281166B2 (en) * 2008-03-10 2012-10-02 Virdiem Corporation System and method for computer power control
US8227936B1 (en) 2008-07-31 2012-07-24 Bank Of America Corporation Cash handling device having integrated uninterruptible power supply
CN102012735B (zh) * 2009-09-07 2013-10-23 三竹资讯股份有限公司 移动装置的电源管理方法
US20110252252A1 (en) * 2010-04-12 2011-10-13 Xerox Corporation System and method for identifying and reducing power consumption based on an inactivity period
JP2011253311A (ja) * 2010-06-01 2011-12-15 Pfu Ltd 情報処理装置、モード制御方法およびモード制御用プログラム
US9535895B2 (en) * 2011-03-17 2017-01-03 Amazon Technologies, Inc. n-Gram-based language prediction
CN104394583B (zh) 2011-06-24 2018-07-13 华为技术有限公司 节省功耗的方法及站点设备
KR101593344B1 (ko) * 2011-11-10 2016-02-18 엠파이어 테크놀로지 디벨롭먼트 엘엘씨 이력 플레이어 데이터를 이용한 추론적인 렌더링
CN102625425B (zh) * 2012-02-29 2015-06-17 电子科技大学 一种事件自适应的传感器节点
CN102662748A (zh) * 2012-03-14 2012-09-12 广州广电运通金融电子股份有限公司 自助终端服务模式的切换装置
US9317842B2 (en) * 2012-04-10 2016-04-19 Bank Of America Corporation Dynamic allocation of video resources
SG195395A1 (en) * 2012-05-07 2013-12-30 Accenture Global Services Ltd Location-based cognitive and predictive communication system
CN102869079B (zh) * 2012-09-20 2015-04-15 电子科技大学 一种自适应调整终端节点定时休眠周期的方法
US9471080B2 (en) * 2013-10-21 2016-10-18 Restore Nv Portfolio managed, demand-side response system
CN104298881B (zh) * 2014-10-15 2017-11-17 南通大学 一种基于贝叶斯网络模型的公交环境动态变化预报方法
CN104794536B (zh) * 2015-04-15 2018-02-23 江苏林洋能源股份有限公司 一种自助售电终端的清机维护时间的预测方法
US9894400B2 (en) * 2015-05-12 2018-02-13 Roku, Inc. Profile driven communication polling for remote control
US9705327B2 (en) * 2015-07-14 2017-07-11 Restore Nv Self-learning, real-time, data-driven power metering system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102662325A (zh) * 2012-05-04 2012-09-12 重庆邮电大学 一种改进自适应学习树电源管理方法
WO2014117861A1 (en) * 2013-02-01 2014-08-07 Telecom Italia S.P.A. Automatic system for controlling appliances
CN103490956A (zh) * 2013-09-22 2014-01-01 杭州华为数字技术有限公司 基于业务量预测的自适应节能控制方法及设备、系统
CN104093197A (zh) * 2014-07-17 2014-10-08 中国联合网络通信集团有限公司 一种移动互联网中的设备节能方法及系统
CN105468823A (zh) * 2015-11-16 2016-04-06 广州广电运通金融电子股份有限公司 一种自助设备节能控制方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3379432A4 *

Also Published As

Publication number Publication date
RU2697640C1 (ru) 2019-08-15
US20180314310A1 (en) 2018-11-01
ZA201803392B (en) 2019-01-30
CN105468823A (zh) 2016-04-06
EP3379432A4 (en) 2018-10-03
EP3379432A1 (en) 2018-09-26
HK1258733A1 (zh) 2019-11-15
CL2018001293A1 (es) 2018-09-28
CN105468823B (zh) 2019-01-25
US10394302B2 (en) 2019-08-27

Similar Documents

Publication Publication Date Title
WO2017084385A1 (zh) 一种自助设备节能控制方法和装置
CN105868004B (zh) 一种基于云计算的业务系统的调度方法及调度装置
CN113748398B (zh) 数据处理与任务调度方法、设备、系统及存储介质
CN101661327A (zh) 一种调节中央处理器主频的方法及装置
CN104754063B (zh) 本地云计算资源调度方法
WO2020253265A1 (zh) 应用于电子设备的数据处理方法、装置、系统、介质
CN109756372B (zh) 一种电信计费系统的弹性伸缩方法及装置
Yurur et al. Adaptive sampling and duty cycling for smartphone accelerometer
CN114727370A (zh) 一种小区节能控制方法、装置、设备及可读存储介质
CN101776946B (zh) 一种基于对象存储系统的功耗控制方法
CN111077976B (zh) 多核心处理器的空闲状态低功耗模式实现方法和处理器
WO2019062409A1 (zh) 后台应用程序管控方法、存储介质及电子设备
CN104050100B (zh) 一种适用于大数据环境的数据流存储管理方法及系统
CN120825824A (zh) 设备连接方法及电子设备
CN113760069A (zh) 温度控制的方法、设备、存储介质及程序产品
US8521855B2 (en) Centralized server-directed power management in a distributed computing system
EP2867790B1 (en) Systems and methods for automatic modification of device configuration values
CN116185619A (zh) 控制方法、装置及电子设备和存储介质
WO2020238326A1 (zh) 处理器的性能状态的调节方法、装置、uefi及存储介质
CN114666223B (zh) 云计算资源池处理方法、装置及可读存储介质
CN116340393A (zh) 数据库饱和度的预测方法、存储介质及数据库系统
CN116669387A (zh) 一种用于数据中心机房的节能方法及装置
CN114963413A (zh) 一种空调的控制方法、装置、设备及存储介质
CN113055212B (zh) 策略的推送方法、策略的执行方法、装置、设备及介质
CN107766105A (zh) 应用清理方法、装置、存储介质及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16865563

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15772061

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2018121253

Country of ref document: RU

Ref document number: 2016865563

Country of ref document: EP