CN104378515A - Method for forecasting telephone traffic of call centers - Google Patents
Method for forecasting telephone traffic of call centers Download PDFInfo
- Publication number
- CN104378515A CN104378515A CN201410736394.7A CN201410736394A CN104378515A CN 104378515 A CN104378515 A CN 104378515A CN 201410736394 A CN201410736394 A CN 201410736394A CN 104378515 A CN104378515 A CN 104378515A
- Authority
- CN
- China
- Prior art keywords
- traffic
- data
- day
- telephone traffic
- telephone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000003203 everyday effect Effects 0.000 claims description 51
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 29
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 5
- 238000011282 treatment Methods 0.000 claims description 4
- 230000002354 daily effect Effects 0.000 claims description 3
- 239000002773 nucleotide Substances 0.000 claims description 3
- 125000003729 nucleotide group Chemical group 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 2
- 230000003442 weekly effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 241001672694 Citrus reticulata Species 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 235000021167 banquet Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for forecasting telephone traffic of call centers. The method includes steps of importing, extracting, processing and analyzing data; forecasting integral telephone traffic in each month; forecasting daily telephone traffic; forecasting hourly telephone traffic. The method has the advantages that the tendency of the integral telephone traffic, the daily telephone traffic and the hourly telephone traffic in future months can be accurately forecast, and accordingly scientific and effective data support can be provided for scheduling management and operation management of the call centers.
Description
Technical field
The present invention relates to telecommunication path field.
Background technology
Call center is the Important Platform of enterprise and trade connection.Enterprise can be offering customers service by setting up call center more convenient, fast, neatly, solves the problem of user's consulting, thus effectively improves the service experience of user.According to customer quantity and market scale, set up the Call Center Platform that can meet client's demand, and use scientific and efficient platform management theory to manage, be even more important in the middle of modern customer service industry.
At present, telecommunications industry customer group is huge.For adapting to business demand, domestic three run greatly commercial city establishes large-scale Call Center Platform.But the lack of control data supporting of Call Center Platform, relies on individual's experience accumulation for many years mostly, to the understanding of manpower recruitment, management of arranging an order according to class and grade, service level guarantee, the aspect such as utilance and man-hour management of attending a banquet shortage science.Easily cause and waste, in the embarrassment that traffic busy service level cannot ensure again at the manpower of traffic idle.This reduces customer service to a great extent and experiences, and adds operation cost of enterprises.Therefore, the traffic forecast system of systematic science, manpower Workforce Management system are even more important in the middle of customer calling center operation management.
Summary of the invention
The object of the present invention is to provide a kind of call center telephone traffic prediction method, can calculate to a nicety the moon in future entirety, every day, telephone traffic trend per hour.
The technical scheme realizing above-mentioned purpose is:
A kind of call center telephone traffic prediction method, comprises the following steps:
A, imports database respectively by history traffic data every day, history traffic data per hour, is quantized by the day regular data of history burst, failure date, obtains telephone traffic exception table;
B, gather history monthly traffic data, operate time sequence algorithm simulates the moon overall traffic data of next month, in conjunction with described telephone traffic exception table and next month sending short messages in groups, the factor impact such as festivals or holidays, draw next month the moon entirety traffic forecast value;
C, according to history traffic data every day, carries out successively rejecting all exponential effect and moving weighted average, obtains traffic data every day of next month, and the moon in conjunction with next month, overall traffic forecast value corrected, and obtained the traffic forecast value of every day next month;
D, according to history traffic data per hour, isolate the factor that each affects telephone traffic, set up neural network model, each factor variable in the middle of predetermined period is needed by input, obtain traffic data hourly, in conjunction with the traffic forecast value of every day, obtain traffic forecast value hourly;
In above-mentioned call center's telephone traffic prediction method, also comprise:
E, contrasts described telephone traffic exception table, revises each traffic forecast value obtained.
In above-mentioned call center's telephone traffic prediction method, described step a comprises:
History every day, traffic data hourly are imported in database respectively;
History burst every day, fault log data are imported in database;
The abnormal data of burst, failure date is carried out quantification treatment, obtains telephone traffic exception table.
In above-mentioned call center's telephone traffic prediction method, described step b comprises:
Gather the history moon monthly overall traffic data;
If the moon, overall traffic data existed great exception or Important Adjustment, adopt the smoothing process of rolling average;
The moon overall traffic data operate time sequence nucleotide sequence algorithm simulation is gone out to the trend of annual traffic capacity, obtain the moon overall telephone traffic of next month;
In conjunction with next month sending short messages in groups, the factor impact such as festivals or holidays, draw next month the moon entirety traffic forecast value.
In above-mentioned call center's telephone traffic prediction method, described step c comprises:
The abnormal data of fault and burst will be there is, smoothing process in units of sky;
Try to achieve weekly all several all indexes, then the telephone traffic of every day is divided by all indexes of correspondence, obtains level and smooth telephone traffic every day rejecting all exponential effect;
Moving weighted average is carried out to telephone traffic every day after process, obtains the traffic value of the every day of next month;
The traffic value obtained by moving weighted average is multiplied by corresponding all indexes, obtains the traffic forecast value of every day;
In conjunction with the traffic forecast value of moon entirety, the traffic forecast value of every day is revised, obtain final traffic forecast value every day.
In above-mentioned call center's telephone traffic prediction method, described steps d comprises:
By hour in units of will there is the abnormal data of fault and burst, smoothing process;
Isolate each factor, comprising: whether the account phase, month, when per medio, hour, several, festivals or holidays in week and sending short messages in groups, be treated to a wide table;
Set up neural network model, obtain telephone traffic with whether the account phase, month, when per medio, week are several, hour, the relation of festivals or holidays and each factor of sending short messages in groups;
Using several in month, date, the week that will predict, hour, sending short messages in groups and festivals or holidays each factor as input layer, utilize the neural network model that establishes to obtain the predicted value of corresponding time;
According to the traffic forecast value of every day, traffic forecast value hourly is revised, obtain final traffic forecast value hourly.
In above-mentioned call center's telephone traffic prediction method, described history traffic data every day comprises the traffic data of nearest 2 year every day; Described history telephone traffic per hour comprises nearest 1 year traffic data hourly.
In above-mentioned call center's telephone traffic prediction method, the daily data of described history burst, failure date comprise: telephone traffic catastrophic failure data, telephone traffic sending short messages in groups data and festivals or holidays data.
The invention has the beneficial effects as follows: the present invention take historical data as object, by a series of extraction, analysis, treatment step, can be calculated to a nicety following moon entirety, every day, telephone traffic trend per hour, thus provide scientific and effective data supporting for arrange an order according to class and grade management, operation management of the heart in a call.
Accompanying drawing explanation
Fig. 1 is the overall flow figure of call center of the present invention telephone traffic prediction method;
Fig. 2 is the flow chart of the importing of data in the present invention, extraction, process and analytical procedure;
Fig. 3 is the flow chart of monthly overall traffic forecast step in the present invention;
Fig. 4 be in the present invention every day traffic forecast step flow chart;
Fig. 5 is the flow chart of traffic forecast step per hour in the present invention.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.
Refer to Fig. 1, call center of the present invention telephone traffic prediction method, comprises the following steps:
Step S0, history data collection, form derive step: by collecting history traffic data, comprise the traffic data of nearest 2 year every day, nearest 1 year traffic data hourly, day regular data (the telephone traffic catastrophic failure data of history burst, failure date, telephone traffic sending short messages in groups data, festivals or holidays the information such as data).
Step S1, the importing of data, extraction, process and analytical procedure: by the traffic data of history every day collected, traffic data hourly imports database respectively, and the daily record datas such as fault burst, telephone traffic adjustment, sending short messages in groups, festivals or holidays are imported database, by contrast traffic data under normal circumstances, thus the impacts of factor on telephone traffic such as complete paired fault burst, festivals or holidays, sending short messages in groups quantize, generate telephone traffic exception table.Particularly, refer to Fig. 2, comprise step as follows:
Step S11, imports in database respectively by history every day, traffic data hourly.
Step S12, imports history burst every day, fault log data in database.
Step S13, carries out quantification treatment by the abnormal data of burst, failure date, obtains telephone traffic exception table.
Step S2, monthly overall traffic forecast step: gather history monthly traffic data, operate time sequence algorithm, obtains the moon overall traffic data of next month, then take into full account next month note burst, festivals or holidays and etc. factor impact, obtain the traffic value of entirety next month.Particularly, refer to Fig. 3, comprise step as follows:
Step S21, gathers the history moon monthly overall traffic data, comprises the time series data of nearly 2 years.
Step S22, if the moon overall traffic data there is great exception or Important Adjustment, adopt the smoothing process of rolling average.
Step S23, to the moon overall traffic data operate time sequence nucleotide sequence algorithm (importing in clementine by moon overall data), simulates the trend of annual traffic capacity, obtains the moon overall telephone traffic of next month.
Step S24, in conjunction with the impact of burst next month, failure date in telephone traffic exception table, obtains overall traffic forecast value Y (m) of the final moon.
Step S3, every day traffic forecast step: according to the traffic data of history every day, reject all exponential effect, and use moving weighted average method, then the moon overall telephone traffic trend in conjunction with next month corrects, thus obtains the traffic forecast value of the every day of next month.Particularly, refer to Fig. 4, comprise step as follows:
Step S31, the smoothing process of abnormal data that will significant trouble and great burst be there is in units of sky.Processing mode is: if exceed 20% of the mean value on nearly three months corresponding dates, with Y (m, d)=0.5*Y (m-1, d)+0.3*Y (m-2, d)+0.2Y (m-3, d) replace, wherein: Y (m, d) represents the traffic data of m month d day.
Step S32, with nearest trimestral traffic data, weeds out and is greater than 3/4 quantile part, try to achieve all indexes w (j), then the telephone traffic of every day is divided by all indexes of correspondence, thus rejects week several impact on telephone traffic, obtains the level and smooth traffic data of rejecting all exponential effect.
Week index: W (j)=P (j) * 7/ (P (1)+P (2)+P (3)+...+P (7)), wherein P (j) represents and weeded out with nearest three months the telephone traffic average that the data being greater than 3/4 quantile part try to achieve all a few correspondences.
Step S33, by telephone traffic every day after process, by nearly trimestral data, carries out moving weighted average according to the corresponding date, obtains traffic value Y1 (m, d) of the every day of next month.
Step S34, traffic value Y1 (m, d) weighted average obtained, is multiplied by corresponding all index W (j), obtains the traffic forecast value Y2 (m, d) of every day.
Step S35, according to traffic forecast value Y (m) of moon entirety, revises the traffic forecast value of the every day obtained, and obtains final traffic forecast value every day.Revise as follows: Y (m, d)=Y2 (m, d)/(Y2 (m, 1)+Y2 (m, 2)+... + Y2 (m, 30)) * Y (m).
Step S4, traffic forecast step per hour: according to nearest three months telephone traffics hourly, isolate the factor that each affects telephone traffic, set up neural network model, need each factor variable in the middle of predetermined period by input, thus obtain traffic forecast value hourly.Particularly, refer to Fig. 5, comprise step as follows:
Step S41, by hour in units of will exist fault burst abnormal data, smoothing process;
Step S42, isolate each factor, comprising: whether the account phase, month, when per medio, hour, several, festivals or holidays in week and sending short messages in groups, be treated to a wide table.
Step S43, by the wide table data importing handled well in spss clementine, sets up neural network model, obtain telephone traffic with whether the account phase, month, when per medio, week are several, hour, the relation of festivals or holidays and each factor of sending short messages in groups.
Step S44, using several for month, date, the week that will predict, hour, sending short messages in groups type, festivals or holidays etc. the factor as input layer, utilize the neural network model established, thus obtain the predicted value of corresponding time.
Step S45, according to the traffic forecast value of every day, revises traffic forecast value hourly, obtains final traffic forecast value hourly.Revise as follows: Y (m, d, h)=Y (m, d, h)/(Y (m, d, 1)+Y (m, d, 2)+... + Y (m, d, 24)) * Y (m, d), wherein Y (m, d, h) traffic data when representing m month d day h.
Step S5, telephone traffic correction set-up procedure: after the telephone traffic obtained by algorithm, in conjunction with various sending short messages in groups and most common failure emergency case, and contrast telephone traffic exception table, revises each traffic forecast value obtained in time.
Claims (8)
1. call center's telephone traffic prediction method, is characterized in that, comprises the following steps:
A, imports database respectively by history traffic data every day, history traffic data per hour, is quantized by the day regular data of history burst, failure date, obtains telephone traffic exception table;
B, gather history monthly traffic data, operate time sequence algorithm simulates the moon overall traffic data of next month, in conjunction with described telephone traffic exception table and next month sending short messages in groups, the factor impact such as festivals or holidays, draw next month the moon entirety traffic forecast value;
C, according to history traffic data every day, carries out successively rejecting all exponential effect and moving weighted average, obtains traffic data every day of next month, and the moon in conjunction with next month, overall traffic forecast value corrected, and obtained the traffic forecast value of every day next month;
D, according to history traffic data per hour, isolate the factor that each affects telephone traffic, set up neural network model, each factor variable in the middle of predetermined period is needed by input, obtain traffic data hourly, then in conjunction with the traffic forecast value of every day, obtain traffic forecast value hourly.
2. call center according to claim 1 telephone traffic prediction method, is characterized in that, also comprise:
E, contrasts described telephone traffic exception table, revises each traffic forecast value obtained.
3. call center according to claim 1 telephone traffic prediction method, is characterized in that, described step a comprises:
History every day, traffic data hourly are imported in database respectively;
History burst every day, fault log data are imported in database;
The abnormal data of burst, failure date is carried out quantification treatment, obtains telephone traffic exception table.
4. call center according to claim 1 telephone traffic prediction method, is characterized in that, described step b comprises:
Gather the history moon monthly overall traffic data;
If the moon, overall traffic data existed great exception or Important Adjustment, adopt the smoothing process of rolling average;
The moon overall traffic data operate time sequence nucleotide sequence algorithm simulation is gone out to the trend of annual traffic capacity, obtain the moon overall telephone traffic of next month;
In conjunction with next month sending short messages in groups, the factor impact such as festivals or holidays, draw next month the moon entirety traffic forecast value.
5. call center according to claim 1 telephone traffic prediction method, is characterized in that, described step c comprises:
The abnormal data of fault and burst will be there is, smoothing process in units of sky;
Try to achieve weekly all several all indexes, then the telephone traffic of every day is divided by all indexes of correspondence, obtains level and smooth telephone traffic every day rejecting all exponential effect;
Moving weighted average is carried out to telephone traffic every day after process, obtains the traffic value of the every day of next month;
The traffic value obtained by moving weighted average is multiplied by corresponding all indexes, obtains the traffic forecast value of every day;
In conjunction with the traffic forecast value of moon entirety, the traffic forecast value of every day is revised, obtain final traffic forecast value every day.
6. call center according to claim 1 telephone traffic prediction method, is characterized in that, described steps d comprises:
By hour in units of will there is the abnormal data of fault and burst, smoothing process;
Isolate each factor, comprising: whether the account phase, month, when per medio, hour, several, festivals or holidays in week and sending short messages in groups, be treated to a wide table;
Set up neural network model, obtain telephone traffic with whether the account phase, month, when per medio, week are several, hour, the relation of festivals or holidays and each factor of sending short messages in groups;
Using several in month, date, the week that will predict, hour, sending short messages in groups and festivals or holidays each factor as input layer, utilize the neural network model that establishes to obtain the predicted value of corresponding time;
According to the traffic forecast value of every day, traffic forecast value hourly is revised, obtain final traffic forecast value hourly.
7. call center according to claim 1 telephone traffic prediction method, is characterized in that, described history traffic data every day comprises the traffic data of nearest 2 year every day; Described history telephone traffic per hour comprises nearest 1 year traffic data hourly.
8. call center according to claim 1 telephone traffic prediction method, is characterized in that, the daily data of described history burst, failure date comprise: telephone traffic catastrophic failure data, telephone traffic sending short messages in groups data and festivals or holidays data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410736394.7A CN104378515A (en) | 2014-12-04 | 2014-12-04 | Method for forecasting telephone traffic of call centers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410736394.7A CN104378515A (en) | 2014-12-04 | 2014-12-04 | Method for forecasting telephone traffic of call centers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104378515A true CN104378515A (en) | 2015-02-25 |
Family
ID=52557155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410736394.7A Pending CN104378515A (en) | 2014-12-04 | 2014-12-04 | Method for forecasting telephone traffic of call centers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104378515A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847598A (en) * | 2016-04-05 | 2016-08-10 | 浙江远传信息技术股份有限公司 | Method and device for call center multifactorial telephone traffic prediction |
| CN105979538A (en) * | 2016-07-19 | 2016-09-28 | 浪潮软件集团有限公司 | An analysis method for lost traffic and flow during cell outage |
| CN106547481A (en) * | 2016-09-29 | 2017-03-29 | 浙江宇视科技有限公司 | A kind of data method for pre-distributing and equipment |
| CN106713677A (en) * | 2016-05-24 | 2017-05-24 | 国家电网公司客户服务中心 | Prediction method for incoming call traffic of power client service center |
| CN107426450A (en) * | 2017-07-05 | 2017-12-01 | 北京辰安信息科技有限公司 | A kind of method and device for calculating the busy degree in call center |
| CN107992988A (en) * | 2017-10-18 | 2018-05-04 | 阿里巴巴集团控股有限公司 | The personnel of client service center have holidays by turns management-control method and device |
| CN108076235A (en) * | 2016-11-14 | 2018-05-25 | 中国移动通信集团公司 | A kind of abandon percentage Forecasting Methodology and server |
| CN108268967A (en) * | 2017-01-04 | 2018-07-10 | 北京京东尚科信息技术有限公司 | A kind of method and system of traffic forecast |
| CN110430328A (en) * | 2019-06-26 | 2019-11-08 | 深圳市跨越新科技有限公司 | Call center's telephone traffic prediction method and system based on LightGBM model |
| CN112016761A (en) * | 2020-09-08 | 2020-12-01 | 平安科技（深圳）有限公司 | Emergency call volume prediction method, emergency call volume prediction device, terminal and storage medium |
| CN112446556A (en) * | 2021-01-27 | 2021-03-05 | 电子科技大学 | Communication network user calling object prediction method based on expression learning and behavior characteristics |
| CN113723665A (en) * | 2021-07-20 | 2021-11-30 | 山东环维通讯科技有限公司 | Call center telephone traffic prediction method and equipment and device with same |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1657899A1 (en) * | 2004-11-12 | 2006-05-17 | Empirix Inc. | Testing using asynchronous automated virtual agent behaviour |
| CN101132447A (en) * | 2007-08-13 | 2008-02-27 | 中国移动通信集团安徽有限公司 | A hotline call prediction method for a large call center |
| CN101541030A (en) * | 2009-05-06 | 2009-09-23 | 华为技术有限公司 | Method for predicting data based on support vector machine and equipment thereof |
-
2014
- 2014-12-04 CN CN201410736394.7A patent/CN104378515A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1657899A1 (en) * | 2004-11-12 | 2006-05-17 | Empirix Inc. | Testing using asynchronous automated virtual agent behaviour |
| CN101132447A (en) * | 2007-08-13 | 2008-02-27 | 中国移动通信集团安徽有限公司 | A hotline call prediction method for a large call center |
| CN101541030A (en) * | 2009-05-06 | 2009-09-23 | 华为技术有限公司 | Method for predicting data based on support vector machine and equipment thereof |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847598A (en) * | 2016-04-05 | 2016-08-10 | 浙江远传信息技术股份有限公司 | Method and device for call center multifactorial telephone traffic prediction |
| CN105847598B (en) * | 2016-04-05 | 2017-04-19 | 浙江远传信息技术股份有限公司 | Method for call center multifactorial telephone traffic prediction |
| CN106713677A (en) * | 2016-05-24 | 2017-05-24 | 国家电网公司客户服务中心 | Prediction method for incoming call traffic of power client service center |
| CN105979538A (en) * | 2016-07-19 | 2016-09-28 | 浪潮软件集团有限公司 | An analysis method for lost traffic and flow during cell outage |
| CN106547481A (en) * | 2016-09-29 | 2017-03-29 | 浙江宇视科技有限公司 | A kind of data method for pre-distributing and equipment |
| CN106547481B (en) * | 2016-09-29 | 2020-04-10 | 浙江宇视科技有限公司 | Data pre-distribution method and equipment |
| CN108076235B (en) * | 2016-11-14 | 2020-10-16 | 中国移动通信集团公司 | Call abandoning rate prediction method and server |
| CN108076235A (en) * | 2016-11-14 | 2018-05-25 | 中国移动通信集团公司 | A kind of abandon percentage Forecasting Methodology and server |
| CN108268967A (en) * | 2017-01-04 | 2018-07-10 | 北京京东尚科信息技术有限公司 | A kind of method and system of traffic forecast |
| CN107426450A (en) * | 2017-07-05 | 2017-12-01 | 北京辰安信息科技有限公司 | A kind of method and device for calculating the busy degree in call center |
| CN107992988A (en) * | 2017-10-18 | 2018-05-04 | 阿里巴巴集团控股有限公司 | The personnel of client service center have holidays by turns management-control method and device |
| CN110430328A (en) * | 2019-06-26 | 2019-11-08 | 深圳市跨越新科技有限公司 | Call center's telephone traffic prediction method and system based on LightGBM model |
| CN110430328B (en) * | 2019-06-26 | 2021-09-03 | 深圳市跨越新科技有限公司 | Method and system for predicting call center telephone traffic based on LightGBM model |
| CN112016761A (en) * | 2020-09-08 | 2020-12-01 | 平安科技（深圳）有限公司 | Emergency call volume prediction method, emergency call volume prediction device, terminal and storage medium |
| CN112446556A (en) * | 2021-01-27 | 2021-03-05 | 电子科技大学 | Communication network user calling object prediction method based on expression learning and behavior characteristics |
| CN112446556B (en) * | 2021-01-27 | 2021-04-30 | 电子科技大学 | Communication network user calling object prediction method based on expression learning and behavior characteristics |
| CN113723665A (en) * | 2021-07-20 | 2021-11-30 | 山东环维通讯科技有限公司 | Call center telephone traffic prediction method and equipment and device with same |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104378515A (en) | Method for forecasting telephone traffic of call centers | |
| CN107844915B (en) | Automatic scheduling method of call center based on traffic prediction | |
| CN101132447A (en) | A hotline call prediction method for a large call center | |
| CN101729690A (en) | System and method for scheduling shifts | |
| CN103095937A (en) | Prediction method for number of seats in call center based on telephone traffic prediction | |
| CN111382911A (en) | High-cabinet personnel scheduling prediction method based on bank outlet business data | |
| CN102654909A (en) | Service level agreement work prioritization system | |
| US11425250B1 (en) | Artificial intelligence based call handling optimization | |
| CN110166641A (en) | Dynamic prediction type intelligence automatic outer call system algorithm | |
| CN108268967A (en) | A kind of method and system of traffic forecast | |
| CN110097455B (en) | Bank customer optimal configuration method and device | |
| JP4684156B2 (en) | Call center business management system and method | |
| CN108053323A (en) | Method, apparatus, computer equipment and the storage medium of service plan generation | |
| CN113449925A (en) | Station area power failure risk level prediction method based on random forest model | |
| CN115860694A (en) | Business expansion process management and control method and system based on instant message technology | |
| CN114169770A (en) | A Power Supply Quality Complaint Early Warning System Considering Personnel Factors | |
| CN110543568B (en) | Financial information consultation reservation service system | |
| CN112511705A (en) | Efficient customer allocation algorithm mechanism | |
| CN117391779A (en) | User data gain feedback method, device, equipment and storage medium | |
| CN115700627A (en) | Scheduling method and device for personnel at bank outlets | |
| US10762434B2 (en) | Method and software for obtaining answers to complex questions based on information retrieved from big data systems | |
| CN117575202A (en) | Power grid customer service three-section personnel scheduling method considering telephone traffic idle-busyness | |
| CN113723665A (en) | Call center telephone traffic prediction method and equipment and device with same | |
| CN114154727B (en) | Information processing method and device and storage medium | |
| CN109858669A (en) | A kind of arrearage based on Information Entropy stops telegram in reply and complains tendency prediction technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150225 |
|
| RJ01 | Rejection of invention patent application after publication |