CN104778532A - Intelligent calling center management system and intelligent scheduling control method - Google Patents
Intelligent calling center management system and intelligent scheduling control method Download PDFInfo
- Publication number
- CN104778532A CN104778532A CN201510109424.6A CN201510109424A CN104778532A CN 104778532 A CN104778532 A CN 104778532A CN 201510109424 A CN201510109424 A CN 201510109424A CN 104778532 A CN104778532 A CN 104778532A
- Authority
- CN
- China
- Prior art keywords
- telephone traffic
- year
- data
- traffic
- forecast
- 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
Landscapes
- Telephonic Communication Services (AREA)
Abstract
An intelligent scheduling control method of a telephone traffic center comprises the following steps of forecasting telephone traffic, calculating required manpower according to the forecast telephone traffic, and carrying out scheduling according to the required manpower and a scheduling constraint condition. A method of forecasting the telephone traffic comprises the steps of selecting a forecasting time range of telephone traffic service, extracting history data according to a forecasting date, analyzing and cleaning the extracted history data, forecasting daily telephone traffic within the forecasting date by a trend regression method, forecasting period telephone traffic within the forecasting date by a fuzzy neural network method, carrying out smoothness adjustment of the telephone traffic according to the forecast daily telephone traffic and the period telephone traffic, calculating the particular telephone traffic of each time point according to a duty ratio of each time point as corrected forecast telephone traffic, and correcting the forecast telephone traffic of the time points according to significant factors influencing the telephone traffic, wherein the telephone traffic of a special time period can be adjusted according to unpredictable emergencies and human experience for the period telephone traffic within the forecasting date.
Description
Technical field
The present invention relates to field, call center, particularly relate to a kind of intelligent call center management system and smart shift scheduling control method.
Background technology
Along with the high speed development of China's economic, call center's industry have also been obtained develop rapidly at home in recent years, and the quantity of various types of calls center and practitioner constantly increases.The ultimate aim of call center's operation is " excellent service, high-quality, low cost ", and personnel cost is the key of call center's operation cost, and agreeing with of pursuit personnel and telephone traffic is the eternal theme in call center.Call center's field management is a dynamic management process, need the work efficiency of call center management personnel control service quality and employee, and according to the situation that scene, call center occurs, timely reply also takes necessary measure, the generation of potential problems is avoided, the continuity of Deterministic service and quality while solving existing issue.The arranging an order according to class and grade of call center be operated in aspire after perfection answer curve, balanced service level while, also will tackle marketing activity, the accidents such as sending short messages in groups, personnel's increase and decrease are on the impact of telephone traffic.For this reason, arrange an order according to class and grade on the basis in the face of unpredictable event in call center, set up the shift report of relative rule, take into account the strategy of arranging an order according to class and grade of degree of recognition in many ways, be the important topic that large-scale call center overcomes difficult point of arranging an order according to class and grade always.The class monitor and group leader of the many call centers of Present Domestic, at the scene in management process, manages by personal experience mostly.Rely on personal experience to carry out field management predictive ability weakness, often can only accomplish reply afterwards, and fail effectively to accomplish obviate, service level also cannot be protected.Therefore how to design and can increase work efficiency, the scientific and reasonable scheduling method that can meet individual requirements again and system are the art problem demanding prompt solutions.
Summary of the invention
The object of this invention is to provide a kind of intelligent call center management system and smart shift scheduling control method, for solving the problems of the technologies described above.
A kind of intelligent call center control system, comprises, call center's telephone traffic system, human resource system, smart shift scheduling control system, call center's operation management system, e customer service system;
Described call center telephone traffic system is used for seat representative and answers and dial subscriber phone, the service business that process is actual, as handling of consulting and new business, and stores history traffic data;
Described human resource system, for managing the human resources of whole call center, comprises personnel's register, organizational structure, labour contract information;
Described call center operation management system is used for whole call center management, comprises the work attendance of personnel, wages, service quality quality inspection, training examination, performance, integration, traffic statistic analysis;
Described e customer service system is used for telephonist and is carried out shift report inquiry, performance pay inquiry, professional knowledge exercise Self-Test Practice by mobile phone A PP, asked for leave and take off;
The available human resources that the history traffic data that described smart shift scheduling control system stores in conjunction with call center's telephone traffic system, human resource system store, the smart shift scheduling realizing telephone traffic center controls.
Telephone traffic center smart shift scheduling control method of the present invention, comprises the steps:
The available human resources that the history traffic data that S0, receipt of call center telephone traffic system store, human resource system store;
S1, carry out traffic forecast;
S2, calculate the manpower of needs according to predicted traffic meter;
S3, to arrange an order according to class and grade according to required manpower and constraint condition of arranging an order according to class and grade;
The concrete grammar carrying out traffic forecast comprises the steps:
The time range of S1.1, selected traffic forecast;
S1.2, according to forecast date extract historical data, historical data comprises request number of times, talk times, talk client number;
S1.3, to extract historical data analyze and clean;
S1.4, carry out the prediction of the telephone traffic of day in forecast date by the trend Return Law;
S1.5, carry out the prediction of period telephone traffic in forecast date by fuzzy neural network method;
S1.6, the period telephone traffic predicted according to day telephone traffic a and the step S1.5 of step S1.4 prediction, carry out the stationarity adjustment of telephone traffic;
S1.7, according to affecting the significant factor of telephone traffic as seasonal factor, festivals or holidays the factor, a day factor of entering an item of expenditure in the accounts, the time point telephone traffic of marketing factor correction prediction;
Period telephone traffic in S1.8, forecast date can according to unpredictable accident and the telephone traffic of artificial experience adjustment special period.
Described S1.3, to the historical data method of analyzing and cleaning extracted be:
S1.31, empty Data-parallel language, there will be temporary derangement unavoidably and cause the data of part-time point not have typing in system, cleaning can increase corresponding time point, and the data acknowledgment number of every day is consistent;
0 data in S1.32, system are mostly abnormal datas, do smoothing processing according to the data near 0 data;
S1.33, abnormal high point and abnormal low spot data processing, do stationarity according to the identical time data of history to each time point data and judge, if abnormal high point or abnormal low spot, then process;
S1.34, incident data are cleaned, and coverage and factor of influence according to configuring accident repair historical data;
S1.35, the end of the month data correction, be 28,29,30, No. 31 different months according to being divided into the end of the month, the end of the month of historical data also moved to 28,29,30, No. 31;
S1.36, obtain cleaning rear data, for traffic forecast below.
The method that the trend Return Law in described step S1.4 carries out the telephone traffic of day in forecast date is:
S1.41, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client logarithmic data on year-on-year basis, calculate talk client number increasing law, and carry out the prediction of the talk client number in forecast date;
S1.42, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, talk times, calculates customers dial frequency increasing law, and carries out the prediction of the customers dial frequency in forecast date;
S1.43, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, request number of times, calculates talk client accounting increasing law, and carries out the prediction of the talk client accounting in forecast date;
S1.44, day traffic data prediction, the request number of times 1=talk client number * customers dial frequency, request number of times 2=talk client number/customers dial frequency accounting, request number of times=(request number of times 1+ request number of times 2)/2, just can obtain the day telephone traffic predicted according to above-mentioned three formula.
In described step S1.5 by the method that fuzzy neural network method carries out period telephone traffic in forecast date be:
S1.51, according to the history telephone traffic of nearly a year, with three months for time gradient, with the traffic data of the time point of first trimester be network input, four month some traffic data is that network exports, training data is the historical data of nearly a year, the historical data of predicted data position nearly half a year;
S1.52, use training data Training Fuzzy Neural Networks, the Output rusults according to neural network can determine a moon periodic law, sky periodic law, and every day each time point base unit weight;
S1.53, predicted data is brought into the fuzzy neural network trained, obtains the time period internal traffic data in forecast date;
S1.54, the period telephone traffic obtained in forecast date.
The method of carrying out arranging an order according to class and grade according to required manpower, constraint condition in step S3 is:
S3.1, choice for use order of classes or grades at school type, existing order of classes or grades at school and the order of classes or grades at school automatically generated;
S3.2, formulation wheel turn rule, and the constraint condition of wheel turn rule is: the number of days of monthly having a rest, and man-hour is balanced, order of classes or grades at school hommization linking etc.;
S3.3, the personnel participating in arranging an order according to class and grade are brought into wheel turn rule in forecast date, determine the number of the working of each order of classes or grades at school every day;
S3.4, genetic algorithm carry out order of classes or grades at school appointment;
S3.5, when the population meeting above-mentioned termination rules, by exporting the individuality of fitness optimum, according to the coding rule of individuality, order of classes or grades at school being assigned to concrete seat personnel, generating initial shift report;
S3.6, shift report analysis, carry out the analysis of manpower degree of fitting and seat personnel satisfaction to result of arranging an order according to class and grade, directly export shift report if meet; If do not meet, the adjustment of two kinds of modes will be carried out;
Mode one: manually adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, by the visual adjustment order of classes or grades at school of the mode of sound of laughing figure;
Mode two: automatically adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, automatically adjusts order of classes or grades at school;
S3.7, output shift report, end of arranging an order according to class and grade.
Described S3.4, genetic algorithm carry out order of classes or grades at school appointment, and the process of genetic algorithm is:
Initial population is generated according to described constraint condition.In this step, the random individuality meeting some constraint condition that produces forms initial population, and the present invention is the individuality composition initial population that random generation meets some constraint condition;
Calculate ideal adaptation degree according to required manpower, constraint condition, have employed period prediction manpower in the present embodiment and individual fitness evaluated by actual degree of fitting of arranging an order according to class and grade between manpower;
Judge whether population meets termination rules.Described termination rules can exceed certain value for working as algorithm iteration number of times, or continuous X iteration ideal adaptation degree is without improvement, or exceedes certain time interval T working time, then stop;
When not meeting termination rules, by selection, intersection, variation, defect individual genetic manipulation, adjustment being compared to described ideal adaptation degree, upgrading initial population until the population upgraded meets termination rules;
In embodiments of the present invention, what select operation to adopt is roulette selection algorithm, and each ideal adaptation degree is converted into selected probability in proportion.Ideal adaptation degree is larger, and selected probability is also larger;
Interlace operation is divided into groups by section by the individuality after selecting, and from every group, Stochastic choice intersects starting point, intersects, and calculate the change of the Population adaptation angle value after intersecting to carrying out intersection two individualities from point of crossing to this section of end point;
Mutation operation adopts the variation of segmentation single-point, and in each section, Stochastic choice gene is for making a variation, and adopts TSP question algorithm, and calculates the change of the population's fitness after variation;
Defect individual genetic manipulation is by the individuality of fitness optimum in current population, does not participate in crossover and mutation, directly puts in the population next time upgraded, thus the possibility that the individuality avoiding fitness optimum is eliminated.
Beneficial effect of the present invention is, by management application of arranging an order according to class and grade of the present invention, can effectively arrange an order according to class and grade according to telephone traffic accurately, the shift report obtained can make seat representative in place reach optimum matching with the distribution of call request at that time, utilize resource of attending a banquet to greatest extent, avoid the wasting of resources when telephone traffic demand is less, the service level of call center can be ensured when telephone traffic demand is more.In addition, seat personnel individual demand can be met in the process of arranging an order according to class and grade, ensure the fairness of arranging an order according to class and grade, improve the work efficiency of seat personnel.And utilize intelligent shift arrangement system of the present invention and method, arrange an order according to class and grade each time and all manage separately as a version, the version of different editions or different times can compare, copies and share, and is convenient to historical query and experience management, further increases the efficiency of work.
Below in conjunction with accompanying drawing, intelligent call center management system of the present invention and smart shift scheduling control method are described further.
Accompanying drawing explanation
Fig. 1 is intelligent call center control system schematic diagram;
Fig. 2 is smart shift scheduling control method process flow diagram;
Fig. 3 is the traffic forecast process flow diagram based on trend recurrence and fuzzy neural network;
Fig. 4 is data cleansing process flow diagram;
Fig. 5 is trend Return Law traffic forecast process flow diagram;
Fig. 6 is fuzzy neural network method traffic forecast process flow diagram;
Fig. 7 is the smart shift scheduling process flow diagram based on genetic algorithm;
Fig. 8 is period telephone traffic schematic diagram in fuzzy neural network method forecast date;
Fig. 9 is Sigmoid function curve diagram.
Embodiment
As shown in Figure 1, intelligent call center control system comprises call center's telephone traffic system, human resource system, smart shift scheduling control system, call center's operation management system, e customer service system; Wherein call center's telephone traffic system is used for seat representative and answers and dial subscriber phone, the service business that process is actual, as handling of consulting and new business, and stores history traffic data; Human resource system, for managing the human resources of whole call center, comprises the information such as personnel's register, organizational structure, labour contract; Call center's operation management system is used for whole call center management, comprises the work attendance of personnel, wages, service quality quality inspection, training examination, performance, integration, traffic statistic analysis etc.; E customer service system is used for telephonist and is carried out shift report inquiry, performance pay inquiry, professional knowledge exercise Self-Test Practice by mobile phone A PP, asked for leave and take off; And what play decisive role in whole intelligent call center control system is exactly smart shift scheduling control system, the available human resources that the history traffic data that smart shift scheduling control system stores in conjunction with call center's telephone traffic system, human resource system store, thus the smart shift scheduling realizing telephone traffic center controls, realize the scheduling the most efficiently to whole telephone traffic center telephonist and utilization.
In intelligent call center control system, a kind of outstanding management process of arranging an order according to class and grade should comprise traffic forecast accurately, fine-grained period manpower prediction, the shift report that dirigibility is better and practicality is higher.The invention provides new management method of arranging an order according to class and grade, the shift report of discharging can make the distribution of telephonist in place and call request at that time reach optimum matching, utilize human resources to greatest extent, avoid the wasting of resources when telephone traffic demand is less, the service level of call center can be ensured when telephone traffic demand is more.In addition, in the process of arranging an order according to class and grade, consider the requirements such as seat personnel individual demand, fairness, comfort level, maximize and meet seat personnel individual demand, ensure the fairness of arranging an order according to class and grade, improve the work efficiency of seat personnel.
As shown in Figure 2, smart shift scheduling control system carries out the method for telephone traffic center smart shift scheduling control, comprises the steps:
The available human resources that the history traffic data that S0, receipt of call center telephone traffic system store, human resource system store;
S1, carry out traffic forecast;
S2, calculate the manpower of needs according to predicted traffic meter;
S3, to arrange an order according to class and grade according to required manpower and constraint condition of arranging an order according to class and grade.
As shown in Figure 3, the concrete grammar carrying out traffic forecast comprises the steps:
The time range of S1.1, selected traffic forecast;
S1.2, according to forecast date extract historical data, historical data comprises request number of times, talk times, talk client number.
S1.3, to extract historical data analyze and clean;
S1.4, carry out the prediction of the telephone traffic of day in forecast date by the trend Return Law;
S1.5, carry out the prediction of period telephone traffic in forecast date by fuzzy neural network method;
S1.6, the period telephone traffic predicted according to day telephone traffic a and the step S1.5 of step S1.4 prediction, carry out the stationarity adjustment of telephone traffic, the accounting of telephone traffic in whole day telephone traffic of each time point and the day telephone traffic b of whole day in forecast date in calculation procedure S1.5, ask for the mean value of a and b as the day traffic forecast data revised, the concrete telephone traffic of each time point is calculated, as the telephone traffic revising prediction according to time point accounting;
S1.7, according to affecting the significant factor of telephone traffic as seasonal factor, festivals or holidays the factor, a day factor of entering an item of expenditure in the accounts, the marketing factor etc. revises the time point telephone traffic of prediction in step 7;
The significant factor affecting telephone traffic is determined by two kinds of methods:
Method 1: the significant factor affecting telephone traffic according to the gerentocratic experience configuration of telephone traffic center.
Method 2: automatically calculate the significant factor affecting telephone traffic, factor values=((same ratio telephone traffic-last month) last month same ratio+(same ratio telephone traffic-last year)/last year same ratio)/2.
Period telephone traffic in S1.8, forecast date according to unpredictable accident and the telephone traffic of artificial experience adjustment special period, to meet the high-precision requirement to traffic forecast, can terminate to this prediction.
As shown in Figure 4, in step S1.3, the method that the historical data extracted is analyzed and cleaned is specially:
S1.31, empty Data-parallel language, there will be temporary derangement unavoidably and cause the data of part-time point not have typing in system, cleaning can increase corresponding time point, and the data acknowledgment number of every day is consistent;
0 data in S1.32, system are mostly abnormal datas, do smoothing processing according to the data near 0 data;
S1.33, abnormal high point and abnormal low spot data processing, do stationarity according to the identical time data of history to each time point data and judge, if abnormal high point or abnormal low spot, then process;
S1.34, incident data are cleaned, and coverage and factor of influence according to configuring accident repair historical data;
S1.35, the end of the month data correction, be 28,29,30, No. 31 different months according to being divided into the end of the month, the end of the month of historical data also moved to 28,29,30, No. 31;
S1.36, obtain cleaning rear data, for traffic forecast below.
As shown in Figure 5, the method that the trend Return Law in step S1.4 carries out the telephone traffic of day in forecast date is:
S1.41, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client logarithmic data on year-on-year basis, calculate talk client number increasing law, and carry out the prediction of the talk client number in forecast date;
S1.42, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, talk times, calculates customers dial frequency increasing law, and carries out the prediction of the customers dial frequency in forecast date;
S1.43, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, request number of times, calculates talk client accounting increasing law, and carries out the prediction of the talk client accounting in forecast date;
S1.44, day traffic data prediction, the request number of times 1=talk client number * customers dial frequency, request number of times 2=talk client number/customers dial frequency accounting, request number of times=(request number of times 1+ request number of times 2)/2, just can obtain the day telephone traffic predicted according to above-mentioned three formula.
As shown in Figure 6, in step S1.5 by the method that fuzzy neural network method carries out period telephone traffic in forecast date be:
S1.51, according to the history telephone traffic of nearly a year, with three months for time gradient, with the traffic data of the time point of first trimester be network input, four month some traffic data is that network exports, training data is the historical data of nearly a year, the historical data of predicted data position nearly half a year;
S1.52, use training data Training Fuzzy Neural Networks, the Output rusults according to neural network can determine a moon periodic law, sky periodic law, and every day each time point base unit weight;
S1.53, predicted data is brought into the fuzzy neural network trained, obtains the time period internal traffic data in forecast date;
S1.54, the period telephone traffic obtained in forecast date.
As shown in Figure 8, the history traffic data inputting a year is trained;
Training process, in the past trimestral data prediction four month (here with 5,6, the telephone traffic in traffic forecast August in July), predict the telephone traffic of 08-01:18:00 as gone according to the telephone traffic of 05-01:18:00,06-01:18:00,07-01:18:00;
Suppose that the telephone traffic tendency in continuous time is be level and smooth, so go matching to draw predicted value according to Sigmoid function (continuous and smooth function, with reference to figure 9);
The deviation of predicted value and actual value is empirically recorded (△=forecast-true), and is input in follow-up training, after having trained the historical data of a year, accumulate corresponding experience, be used further to actual traffic forecast.
In Fig. 2 in step S2 according to the method for the manpower of predicted telephone traffic calculating needs be: it is on the basis of the telephone traffic of prediction that demand manpower calculates, personnel's number of each time point needs under predicting various situation according to the different parameters of user's input.Wherein, canonical parameter comprises: the artificial percent of call completed that the telephone traffic of prediction, time range, Average Speed of Answer, call are all grown, expected, the attendance rate, the rate of utilization of work hour etc.; Output rusults: the number that each time range needs; Minimum accurate 15 minutes of time period, the linear formula of method of employing.
As shown in Figure 7, the method for carrying out arranging an order according to class and grade according to required manpower, constraint condition in the step S3 in Fig. 2 is:
S3.1, choice for use order of classes or grades at school type, existing order of classes or grades at school and the order of classes or grades at school automatically generated.Existing order of classes or grades at school is through accumulated time and gets off the order of classes or grades at school of empirical, automatic generation order of classes or grades at school is the order of classes or grades at school automatically produced according to the constraint condition system of order of classes or grades at school, constraint condition comprises: the duration of order of classes or grades at school, the number of each order of classes or grades at school class section, the duration of each half section, the time interval between class's section of each order of classes or grades at school, Chinese meal, dinner meal time and dining holding time, the ratio etc. of cruel class;
S3.2, formulation wheel turn rule, and the constraint condition of wheel turn rule is: the number of days of monthly having a rest, and man-hour is balanced, order of classes or grades at school hommization linking etc.;
S3.3, the personnel participating in arranging an order according to class and grade are brought into wheel turn rule in forecast date, determine the number of the working of each order of classes or grades at school every day.
S3.4, genetic algorithm carry out order of classes or grades at school appointment, and the process of genetic algorithm is:
Initial population is generated according to described constraint condition.In this step, the random individuality meeting some constraint condition that produces forms initial population, and the present invention is the individuality composition initial population that random generation meets some constraint condition.
Ideal adaptation degree is calculated according to required manpower, constraint condition.Have employed period prediction manpower in the present embodiment and individual fitness evaluated by actual degree of fitting of arranging an order according to class and grade between manpower.
Judge whether population meets termination rules.Described termination rules can exceed certain value for working as algorithm iteration number of times, or continuous X iteration ideal adaptation degree is without improvement, or exceedes certain time interval T working time, then stop.
When not meeting termination rules, by selection, intersection, variation, defect individual genetic manipulation, adjustment being compared to described ideal adaptation degree, upgrading initial population until the population upgraded meets termination rules.
In embodiments of the present invention, what select operation to adopt is roulette selection algorithm, and each ideal adaptation degree is converted into selected probability in proportion.Ideal adaptation degree is larger, and selected probability is also larger.
Interlace operation is divided into groups by section by the individuality after selecting, and from every group, Stochastic choice intersects starting point, intersects, and calculate the change of the Population adaptation angle value after intersecting to carrying out intersection two individualities from point of crossing to this section of end point.
Mutation operation adopts the variation of segmentation single-point, and in each section, Stochastic choice gene is for making a variation, and adopts TSP question algorithm, and calculates the change of the population's fitness after variation.
Defect individual genetic manipulation is by the individuality of fitness optimum in current population, does not participate in crossover and mutation, directly puts in the population next time upgraded, thus the possibility that the individuality avoiding fitness optimum is eliminated.
S3.5, when the population meeting above-mentioned termination rules, by exporting the individuality of fitness optimum, according to the coding rule of individuality, order of classes or grades at school being assigned to concrete seat personnel, generating initial shift report.
S3.6, shift report analysis, carry out the analysis of manpower degree of fitting and seat personnel satisfaction to result of arranging an order according to class and grade, directly export shift report if meet; If do not meet, the adjustment of two kinds of modes will be carried out.
Mode one: manually adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, by the visual adjustment order of classes or grades at school of the mode of sound of laughing figure.
Mode two: automatically adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, automatically adjusts order of classes or grades at school.
S3.7, output shift report, end of arranging an order according to class and grade.
One day telephone traffic of such as 2015-03-06 and manpower requirement as:
Genetic algorithm illustrates:
| Time | … | 7:00 | 7:30 | 8:00 | 8:300 | 9:00 | 9:300 | 10:00 | 10:30 | 11:00 | 11:30 | 12:00 | 12:30 | … |
| Telephone traffic | … | 362 | 362 | 482 | 542 | 902 | 902 | 842 | 782 | 662 | 602 | 482 | 482 | … |
| Manpower requirement | … | 6 | 6 | 8 | 9 | 15 | 15 | 14 | 13 | 11 | 10 | 8 | 8 | … |
Table 1 telephone traffic is corresponding with manpower requirement to be shown
If the selectable order of classes or grades at school of Zhang San 2015-03-06 is as shown in table 2:
Table 2 order of classes or grades at school table
Using order of classes or grades at school as individuality, according to numbering, order of classes or grades at school is encoded
Such as: genotype evening=5, little night=6
Stochastic choice 3 groups of order of classes or grades at school, are assumed to be early 1, early 2, in 2
Evaluation function:
Select respectively early 1 (each time point of 07:00 ~ 11:00 and the 12:00 ~ 17:00 number of arranging an order according to class and grade increases by 1), early 2, in 2 calculate degree of fitting, then get minimum Min (N),
According to the working order of classes or grades at school obtained Zhang San above and should select.
By that analogy, by evaluation function, calculate the working order of classes or grades at school that all personnel should select, to reach overall optimum.
In the actual execution of shift report, shift report support is revised dynamically, with satisfied operation target and seat personnel individual demand.According to the actual conditions of human resources, support as asked for leave, change shifts, work overtime, the class of tune, put and stop, go to work in advance, come off duty in advance, mend class's business adjustment applications such as class, adjust arranging an order according to class and grade and optimize, and the situation of the arranged time of having a rest of the form record seat personnel of bankbook is stopped with labor, meet flexibility and the individual requirement of shift report.
In the present invention, can according to required manpower and constraint condition, the most suitable order of classes or grades at school of seat personnel is assigned to by intelligent algorithm, the manpower of arranging an order according to class and grade obtained is made to reach higher degree of fitting with prediction manpower, thus optimum matching traffic request and human resources, reach distributing rationally of human resources, meet again the constraint condition of individual demand, fairness, comfort level, therefore the present invention more can meet the requirement of management of arranging an order according to class and grade.
By management application of arranging an order according to class and grade of the present invention, can effectively arrange an order according to class and grade according to telephone traffic accurately, the shift report obtained can make seat representative in place reach optimum matching with the distribution of call request at that time, utilize resource of attending a banquet to greatest extent, avoid the wasting of resources when telephone traffic demand is less, the service level of call center can be ensured when telephone traffic demand is more.In addition, seat personnel individual demand can be met in the process of arranging an order according to class and grade, ensure the fairness of arranging an order according to class and grade, improve the work efficiency of seat personnel.And utilize intelligent shift arrangement system of the present invention and method, arrange an order according to class and grade each time and all manage separately as a version, the version of different editions or different times can compare, copies and share, and is convenient to historical query and experience management, further increases the efficiency of work.
Above-described embodiment is only be described the preferred embodiment of the present invention; not scope of the present invention is limited; under not departing from the present invention and designing the prerequisite of spirit; the various distortion that those of ordinary skill in the art make technical scheme of the present invention and improvement, all should fall in protection domain that claims of the present invention determines.
Claims (7)
1. an intelligent call center control system, comprises, call center's telephone traffic system, human resource system, smart shift scheduling control system, call center's operation management system, e customer service system;
Described call center telephone traffic system is used for seat representative and answers and dial subscriber phone, the service business that process is actual, as handling of consulting and new business, and stores history traffic data;
Described human resource system, for managing the human resources of whole call center, comprises personnel's register, organizational structure, labour contract information;
Described call center operation management system is used for whole call center management, comprises the work attendance of personnel, wages, service quality quality inspection, training examination, performance, integration, traffic statistic analysis;
Described e customer service system is used for telephonist and is carried out shift report inquiry, performance pay inquiry, professional knowledge exercise Self-Test Practice by mobile phone A PP, asked for leave and take off;
The available human resources that the history traffic data that described smart shift scheduling control system stores in conjunction with call center's telephone traffic system, human resource system store, the smart shift scheduling realizing telephone traffic center controls.
2. intelligent call center control system according to claim 1, is characterized in that, smart shift scheduling control system carries out the method for telephone traffic center smart shift scheduling control, comprises the steps:
The available human resources that the history traffic data that S0, receipt of call center telephone traffic system store, human resource system store;
S1, carry out traffic forecast;
S2, calculate the manpower of needs according to predicted traffic meter;
S3, to arrange an order according to class and grade according to required manpower and constraint condition of arranging an order according to class and grade;
The concrete grammar carrying out traffic forecast comprises the steps:
The time range of S1.1, selected traffic forecast;
S1.2, according to forecast date extract historical data, historical data comprises request number of times, talk times, talk client number;
S1.3, to extract historical data analyze and clean;
S1.4, carry out the prediction of the telephone traffic of day in forecast date by the trend Return Law;
S1.5, carry out the prediction of period telephone traffic in forecast date by fuzzy neural network method;
S1.6, the period telephone traffic predicted according to day telephone traffic a and the step S1.5 of step S1.4 prediction, carry out the stationarity adjustment of telephone traffic;
S1.7, according to affecting the significant factor of telephone traffic as seasonal factor, festivals or holidays the factor, a day factor of entering an item of expenditure in the accounts, the time point telephone traffic of marketing factor correction prediction;
Period telephone traffic in S1.8, forecast date can according to unpredictable accident and the telephone traffic of artificial experience adjustment special period.
3. telephone traffic center smart shift scheduling control method according to claim 2, is characterized in that, described S1.3, to the historical data method of analyzing and cleaning extracted is:
S1.31, empty Data-parallel language, there will be temporary derangement unavoidably and cause the data of part-time point not have typing in system, cleaning can increase corresponding time point, and the data acknowledgment number of every day is consistent;
0 data in S1.32, system are mostly abnormal datas, do smoothing processing according to the data near 0 data;
S1.33, abnormal high point and abnormal low spot data processing, do stationarity according to the identical time data of history to each time point data and judge, if abnormal high point or abnormal low spot, then process;
S1.34, incident data are cleaned, and coverage and factor of influence according to configuring accident repair historical data;
S1.35, the end of the month data correction, be 28,29,30, No. 31 different months according to being divided into the end of the month, the end of the month of historical data also moved to 28,29,30, No. 31;
S1.36, obtain cleaning rear data, for traffic forecast below.
4. telephone traffic center smart shift scheduling control method according to claim 3, is characterized in that, the method that the trend Return Law in described step S1.4 carries out the telephone traffic of day in forecast date is:
S1.41, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client logarithmic data on year-on-year basis, calculate talk client number increasing law, and carry out the prediction of the talk client number in forecast date;
S1.42, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, talk times, calculates customers dial frequency increasing law, and carries out the prediction of the customers dial frequency in forecast date;
S1.43, according to last month corresponding in forecast date on year-on-year basis, the month before last on year-on-year basis with same month last year on year-on-year basis, last month last year talk client number on year-on-year basis, request number of times, calculates talk client accounting increasing law, and carries out the prediction of the talk client accounting in forecast date;
S1.44, day traffic data prediction, the request number of times 1=talk client number * customers dial frequency, request number of times 2=talk client number/customers dial frequency accounting, request number of times=(request number of times 1+ request number of times 2)/2, just can obtain the day telephone traffic predicted according to above-mentioned three formula.
5. telephone traffic center smart shift scheduling control method according to claim 4, is characterized in that, in described step S1.5 by the method that fuzzy neural network method carries out period telephone traffic in forecast date is:
S1.51, according to the history telephone traffic of nearly a year, with three months for time gradient, with the traffic data of the time point of first trimester be network input, four month some traffic data is that network exports, training data is the historical data of nearly a year, the historical data of predicted data position nearly half a year;
S1.52, use training data Training Fuzzy Neural Networks, the Output rusults according to neural network can determine a moon periodic law, sky periodic law, and every day each time point base unit weight;
S1.53, predicted data is brought into the fuzzy neural network trained, obtains the time period internal traffic data in forecast date;
S1.54, the period telephone traffic obtained in forecast date.
6. telephone traffic center smart shift scheduling control method according to claim 5, is characterized in that, the method for carrying out arranging an order according to class and grade according to required manpower, constraint condition in described step S3 is:
S3.1, choice for use order of classes or grades at school type, existing order of classes or grades at school and the order of classes or grades at school automatically generated;
S3.2, formulation wheel turn rule, and the constraint condition of wheel turn rule is: the number of days of monthly having a rest, and man-hour is balanced, order of classes or grades at school hommization linking etc.;
S3.3, the personnel participating in arranging an order according to class and grade are brought into wheel turn rule in forecast date, determine the number of the working of each order of classes or grades at school every day;
S3.4, genetic algorithm carry out order of classes or grades at school appointment;
S3.5, when the population meeting above-mentioned termination rules, by exporting the individuality of fitness optimum, according to the coding rule of individuality, order of classes or grades at school being assigned to concrete seat personnel, generating initial shift report;
S3.6, shift report analysis, carry out the analysis of manpower degree of fitting and seat personnel satisfaction to result of arranging an order according to class and grade, directly export shift report if meet; If do not meet, the adjustment of two kinds of modes will be carried out;
Mode one: manually adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, by the visual adjustment order of classes or grades at school of the mode of sound of laughing figure;
Mode two: automatically adjust, the telephone traffic of fine setting period every day, system adjusts period number demand automatically, automatically adjusts order of classes or grades at school;
S3.7, output shift report, end of arranging an order according to class and grade.
7. telephone traffic center smart shift scheduling control method according to claim 6, it is characterized in that, described S3.4, genetic algorithm carry out order of classes or grades at school appointment, and the process of genetic algorithm is:
Generate initial population according to described constraint condition, in this step, the random individuality meeting some constraint condition that produces forms initial population, and the present invention produces the individuality composition initial population meeting some constraint condition at random;
Calculate ideal adaptation degree according to required manpower, constraint condition, have employed period prediction manpower in the present embodiment and individual fitness evaluated by actual degree of fitting of arranging an order according to class and grade between manpower;
Judge whether population meets termination rules, described termination rules can exceed certain value for working as algorithm iteration number of times, or continuous X iteration ideal adaptation degree is without improvement, or exceedes certain time interval T working time, then stop;
When not meeting termination rules, by selection, intersection, variation, defect individual genetic manipulation, adjustment being compared to described ideal adaptation degree, upgrading initial population until the population upgraded meets termination rules;
In embodiments of the present invention, what select operation to adopt is roulette selection algorithm, and each ideal adaptation degree is converted into selected probability in proportion, and ideal adaptation degree is larger, and selected probability is also larger;
Interlace operation is divided into groups by section by the individuality after selecting, and from every group, Stochastic choice intersects starting point, intersects, and calculate the change of the Population adaptation angle value after intersecting to carrying out intersection two individualities from point of crossing to this section of end point;
Mutation operation adopts the variation of segmentation single-point, and in each section, Stochastic choice gene is for making a variation, and adopts TSP question algorithm, and calculates the change of the population's fitness after variation;
Defect individual genetic manipulation is by the individuality of fitness optimum in current population, does not participate in crossover and mutation, directly puts in the population next time upgraded, thus the possibility that the individuality avoiding fitness optimum is eliminated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510109424.6A CN104778532A (en) | 2015-03-12 | 2015-03-12 | Intelligent calling center management system and intelligent scheduling control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510109424.6A CN104778532A (en) | 2015-03-12 | 2015-03-12 | Intelligent calling center management system and intelligent scheduling control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104778532A true CN104778532A (en) | 2015-07-15 |
Family
ID=53619983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510109424.6A Pending CN104778532A (en) | 2015-03-12 | 2015-03-12 | Intelligent calling center management system and intelligent scheduling control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104778532A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105704335A (en) * | 2016-03-02 | 2016-06-22 | 重庆大学 | Predictive form calling-out algorithm based on dynamic statistics process, switch dialing method and device |
| CN106529144A (en) * | 2016-10-27 | 2017-03-22 | 上海览海在线健康管理有限公司 | Method and system for intelligent scheduling in online medical process |
| CN106548274A (en) * | 2016-10-19 | 2017-03-29 | 平安科技（深圳）有限公司 | A kind of personnel's scheduling method and device |
| CN107067109A (en) * | 2017-04-14 | 2017-08-18 | 天津农学院 | A kind of CNG air entraining substations equipment excavated based on aerating record data and personnel depaly optimization method |
| CN107844915A (en) * | 2017-11-29 | 2018-03-27 | 信雅达***工程股份有限公司 | A kind of automatic scheduling method of the call center based on traffic forecast |
| CN107862400A (en) * | 2017-02-20 | 2018-03-30 | 平安科技（深圳）有限公司 | Scheduling method and device |
| 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 |
| CN108076236A (en) * | 2016-11-14 | 2018-05-25 | 平安科技（深圳）有限公司 | Scheduling method and device |
| CN108229776A (en) * | 2016-12-15 | 2018-06-29 | 平安科技（深圳）有限公司 | One kind is arranged an order according to class and grade method of adjustment and device |
| CN108256755A (en) * | 2018-01-09 | 2018-07-06 | 信雅达***工程股份有限公司 | A kind of scheduling method for being competent at more job position requests simultaneously based on single employee |
| CN108551533A (en) * | 2018-03-09 | 2018-09-18 | 平安普惠企业管理有限公司 | A kind of scheduling method that customer service is attended a banquet, storage medium and server |
| CN108734345A (en) * | 2018-05-11 | 2018-11-02 | 携程旅游网络技术（上海）有限公司 | The prediction technique and system of OTA air ticket customer service telephone traffics |
| CN108764699A (en) * | 2018-05-23 | 2018-11-06 | 平安科技（深圳）有限公司 | Scheduling method, server and computer readable storage medium |
| CN109544098A (en) * | 2018-10-19 | 2019-03-29 | 中国平安财产保险股份有限公司 | A kind of smart shift scheduling method, apparatus, storage medium and terminal device |
| CN109886489A (en) * | 2019-02-21 | 2019-06-14 | 上海德启信息科技有限公司 | Configuration system and method applied to transfer resource |
| CN110147905A (en) * | 2019-05-08 | 2019-08-20 | 联想(北京)有限公司 | Information processing method, device, system and storage medium |
| CN110248031A (en) * | 2019-04-19 | 2019-09-17 | 中国联合网络通信集团有限公司 | Management method of arranging an order according to class and grade, device, equipment and the storage medium of customer service system |
| 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 |
| CN110472893A (en) * | 2019-09-06 | 2019-11-19 | 北京谦仁科技有限公司 | Data processing method, data processing equipment, storage medium and electronic equipment |
| WO2019218456A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Job manpower forecasting method and apparatus, and computer device and storage medium |
| CN111147676A (en) * | 2019-12-23 | 2020-05-12 | 广州供电局有限公司 | Intelligent auxiliary agent answering service realization method based on electric power IT service call center |
| CN111246025A (en) * | 2020-02-27 | 2020-06-05 | 大连即时智能科技有限公司 | Man-machine mixed arrangement customer service method and system |
| CN111461744A (en) * | 2020-03-26 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Service providing method, device and equipment |
| CN111461491A (en) * | 2020-03-05 | 2020-07-28 | 浙江工业大学 | Multi-constraint scheduling method for call center |
| CN111614844A (en) * | 2020-05-21 | 2020-09-01 | 携程计算机技术（上海）有限公司 | Method, system, equipment and medium for scheduling of call center |
| CN111754336A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Network scheduling method and device |
| CN113194208A (en) * | 2016-12-30 | 2021-07-30 | 阿菲尼帝有限公司 | Techniques for L3 pairing |
| 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 |
| CN113743640A (en) * | 2020-09-27 | 2021-12-03 | 北京京东振世信息技术有限公司 | Personnel scheduling and scheduling method and device in warehouse |
| CN113807597A (en) * | 2021-09-23 | 2021-12-17 | 中国工商银行股份有限公司 | Network scheduling method, device, equipment and storage medium |
| CN114239906A (en) * | 2021-11-08 | 2022-03-25 | 壹药网科技(上海)股份有限公司 | Human demand prediction method and personnel scheduling system |
| CN114781678A (en) * | 2021-12-30 | 2022-07-22 | 友邦人寿保险有限公司 | Incoming call quantity prediction method, system, terminal and medium based on prediction model |
| US11595522B2 (en) | 2016-12-30 | 2023-02-28 | Afiniti, Ltd. | Techniques for workforce management in a contact center system |
| CN116915915A (en) * | 2023-08-07 | 2023-10-20 | 云南电网有限责任公司 | Scheduling method, device and equipment for call center access terminal agents |
| US11831808B2 (en) | 2016-12-30 | 2023-11-28 | Afiniti, Ltd. | Contact center system |
| CN113194208B (en) * | 2016-12-30 | 2024-06-07 | 阿菲尼帝有限公司 | Techniques for L3 pairing |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297626A (en) * | 2013-05-20 | 2013-09-11 | 杭州远传通信技术有限公司 | Scheduling method and scheduling device |
-
2015
- 2015-03-12 CN CN201510109424.6A patent/CN104778532A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103297626A (en) * | 2013-05-20 | 2013-09-11 | 杭州远传通信技术有限公司 | Scheduling method and scheduling device |
Non-Patent Citations (1)
| Title |
|---|
| 张怡虹: ""G电信公司呼叫中心***优化方案"", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (45)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105704335B (en) * | 2016-03-02 | 2018-12-18 | 重庆大学 | Predictive outbound algorithm, interchanger dialing method and device based on dynamic statistics process |
| CN105704335A (en) * | 2016-03-02 | 2016-06-22 | 重庆大学 | Predictive form calling-out algorithm based on dynamic statistics process, switch dialing method and device |
| CN106548274A (en) * | 2016-10-19 | 2017-03-29 | 平安科技（深圳）有限公司 | A kind of personnel's scheduling method and device |
| CN106529144A (en) * | 2016-10-27 | 2017-03-22 | 上海览海在线健康管理有限公司 | Method and system for intelligent scheduling in online medical process |
| CN108076236A (en) * | 2016-11-14 | 2018-05-25 | 平安科技（深圳）有限公司 | Scheduling method and device |
| CN108229776A (en) * | 2016-12-15 | 2018-06-29 | 平安科技（深圳）有限公司 | One kind is arranged an order according to class and grade method of adjustment and device |
| US11831808B2 (en) | 2016-12-30 | 2023-11-28 | Afiniti, Ltd. | Contact center system |
| CN113194208B (en) * | 2016-12-30 | 2024-06-07 | 阿菲尼帝有限公司 | Techniques for L3 pairing |
| US11595522B2 (en) | 2016-12-30 | 2023-02-28 | Afiniti, Ltd. | Techniques for workforce management in a contact center system |
| CN113194208A (en) * | 2016-12-30 | 2021-07-30 | 阿菲尼帝有限公司 | Techniques for L3 pairing |
| CN107862400A (en) * | 2017-02-20 | 2018-03-30 | 平安科技（深圳）有限公司 | Scheduling method and device |
| CN107067109A (en) * | 2017-04-14 | 2017-08-18 | 天津农学院 | A kind of CNG air entraining substations equipment excavated based on aerating record data and personnel depaly optimization method |
| CN107067109B (en) * | 2017-04-14 | 2020-08-14 | 天津农学院 | CNG (compressed Natural gas) filling substation equipment and personnel configuration optimization method based on filling record data mining |
| 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 |
| CN107844915A (en) * | 2017-11-29 | 2018-03-27 | 信雅达***工程股份有限公司 | A kind of automatic scheduling method of the call center based on traffic forecast |
| CN107844915B (en) * | 2017-11-29 | 2021-01-01 | 信雅达***工程股份有限公司 | Automatic scheduling method of call center based on traffic prediction |
| CN108256755A (en) * | 2018-01-09 | 2018-07-06 | 信雅达***工程股份有限公司 | A kind of scheduling method for being competent at more job position requests simultaneously based on single employee |
| CN108551533A (en) * | 2018-03-09 | 2018-09-18 | 平安普惠企业管理有限公司 | A kind of scheduling method that customer service is attended a banquet, storage medium and server |
| CN108734345B (en) * | 2018-05-11 | 2021-01-29 | 携程旅游网络技术（上海）有限公司 | OTA air ticket customer service telephone traffic prediction method and system |
| CN108734345A (en) * | 2018-05-11 | 2018-11-02 | 携程旅游网络技术（上海）有限公司 | The prediction technique and system of OTA air ticket customer service telephone traffics |
| WO2019218456A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Job manpower forecasting method and apparatus, and computer device and storage medium |
| CN108764699A (en) * | 2018-05-23 | 2018-11-06 | 平安科技（深圳）有限公司 | Scheduling method, server and computer readable storage medium |
| CN109544098A (en) * | 2018-10-19 | 2019-03-29 | 中国平安财产保险股份有限公司 | A kind of smart shift scheduling method, apparatus, storage medium and terminal device |
| CN109886489A (en) * | 2019-02-21 | 2019-06-14 | 上海德启信息科技有限公司 | Configuration system and method applied to transfer resource |
| CN110248031A (en) * | 2019-04-19 | 2019-09-17 | 中国联合网络通信集团有限公司 | Management method of arranging an order according to class and grade, device, equipment and the storage medium of customer service system |
| CN110147905A (en) * | 2019-05-08 | 2019-08-20 | 联想(北京)有限公司 | Information processing method, device, system and storage medium |
| 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 |
| CN110472893A (en) * | 2019-09-06 | 2019-11-19 | 北京谦仁科技有限公司 | Data processing method, data processing equipment, storage medium and electronic equipment |
| CN111147676A (en) * | 2019-12-23 | 2020-05-12 | 广州供电局有限公司 | Intelligent auxiliary agent answering service realization method based on electric power IT service call center |
| CN111246025A (en) * | 2020-02-27 | 2020-06-05 | 大连即时智能科技有限公司 | Man-machine mixed arrangement customer service method and system |
| CN111461491B (en) * | 2020-03-05 | 2022-04-15 | 浙江工业大学 | Multi-constraint scheduling method for call center |
| CN111461491A (en) * | 2020-03-05 | 2020-07-28 | 浙江工业大学 | Multi-constraint scheduling method for call center |
| CN111461744A (en) * | 2020-03-26 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Service providing method, device and equipment |
| CN111614844A (en) * | 2020-05-21 | 2020-09-01 | 携程计算机技术（上海）有限公司 | Method, system, equipment and medium for scheduling of call center |
| CN111754336B (en) * | 2020-06-28 | 2024-05-24 | 中国银行股份有限公司 | Method and device for scheduling network points |
| CN111754336A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Network scheduling method and device |
| CN113743640A (en) * | 2020-09-27 | 2021-12-03 | 北京京东振世信息技术有限公司 | Personnel scheduling and scheduling method and device in warehouse |
| CN113743640B (en) * | 2020-09-27 | 2023-09-26 | 北京京东振世信息技术有限公司 | Personnel scheduling method and device in warehouse |
| 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 |
| CN113807597A (en) * | 2021-09-23 | 2021-12-17 | 中国工商银行股份有限公司 | Network scheduling method, device, equipment and storage medium |
| CN114239906A (en) * | 2021-11-08 | 2022-03-25 | 壹药网科技(上海)股份有限公司 | Human demand prediction method and personnel scheduling system |
| CN114781678A (en) * | 2021-12-30 | 2022-07-22 | 友邦人寿保险有限公司 | Incoming call quantity prediction method, system, terminal and medium based on prediction model |
| CN116915915B (en) * | 2023-08-07 | 2024-01-12 | 云南电网有限责任公司 | Scheduling method, device and equipment for call center access terminal agents |
| CN116915915A (en) * | 2023-08-07 | 2023-10-20 | 云南电网有限责任公司 | Scheduling method, device and equipment for call center access terminal agents |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778532A (en) | Intelligent calling center management system and intelligent scheduling control method | |
| CN107844915B (en) | Automatic scheduling method of call center based on traffic prediction | |
| CN108551533B (en) | Scheduling method of customer service agents, storage medium and server | |
| CN101729690B (en) | System and method for scheduling shifts | |
| US9734228B2 (en) | Digital analytics system | |
| CN102270363B (en) | Intelligent queuing system | |
| CN111382942B (en) | Replacement flow shop energy efficiency optimization scheduling method integrated with delivery date configuration | |
| CN103297626A (en) | Scheduling method and scheduling device | |
| US20030065548A1 (en) | Dynamic management of helpdesks | |
| CN110110881A (en) | Power customer requirement forecasting analysis method and system | |
| CN106779307A (en) | The data processing method and system of cubic management system | |
| CN108574303A (en) | A kind of multiple-energy-source coordination optimization dispatching method considering peak-frequency regulation demand | |
| CN113361816A (en) | One set of customer service staff scheduling system | |
| CN104424598A (en) | Cash demand quantity predicating device and method | |
| CN101620692A (en) | Method for analyzing customer churn of mobile communication service | |
| CN107563631A (en) | A kind of customer service management platform and its method | |
| CN108256755A (en) | A kind of scheduling method for being competent at more job position requests simultaneously based on single employee | |
| CN106817499A (en) | A kind of resources for traffic dispatching method and forecast dispatching device | |
| CN109919423B (en) | intelligent water affair management method and system based on deep learning | |
| CN110097455B (en) | Bank customer optimal configuration method and device | |
| CN101483531A (en) | Method and system for prediction type account balance alarm | |
| CN113361980A (en) | Big data asset value evaluation system and method | |
| CN109919487A (en) | The calculation method of entry priority under multifactor impact | |
| CN105574668A (en) | Particle swarm optimization algorithm-based call center scheduling method | |
| Green | Job quality in Britain under the Labour government |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150715 |
|
| RJ01 | Rejection of invention patent application after publication |