Dynamic number monitoring, early warning and resource allocation method for service personnel

The number prediction model of the number of people being served constructed through machine learning algorithms solves the problem that traditional service staff configuration methods are difficult to cope with sudden changes in people flow, realizes dynamic number monitoring and resource allocation of service windows, and improves service efficiency and user satisfaction.

CN117689073BActive Publication Date: 2024-11-12TIANJIN UNIV
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202311711682.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2023-12-07
Filing Date
2023-12-13
Publication Date
2024-11-12
Estimated Expiration
2043-12-13

AI Technical Summary

Technical Problem

Traditional service staffing methods are difficult to flexibly respond to sudden changes in people flow, resulting in delayed service response, decreased customer satisfaction, waste of resources and poor work efficiency, and it is difficult to predict future people flow in real time.

Method used

The machine learning algorithm is used to build a prediction model for the number of people being served. By obtaining and analyzing the service window information, the number of people being served in the future schedule is predicted, and whether it exceeds the carrying capacity threshold of the service personnel is dynamically allocated. To minimize the average waiting time.

Benefits of technology

It realizes dynamic number monitoring and resource allocation of service windows, improves service efficiency and user satisfaction, ensures the scientific and rationality of service staffing configuration, and adapts to complex and changeable flow of people.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117689073B_ABST
    Figure CN117689073B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for monitoring, warning and allocating resources for the dynamic number of service personnel, comprising the following steps: obtaining service personnel information, service window information and service personnel information; inputting the trained new service personnel number prediction model to predict the number of new service personnel in a future scheduling cycle of any service window to obtain the number of new service personnel; judging, based on the obtained number of new service personnel, whether the number of service personnel will exceed the current service personnel carrying capacity threshold in any future time period; if so, calculating the number of service personnel that need to be added. The present application realizes the dynamic prediction of the number of service personnel that will be served in each service window. Based on the dynamic prediction results, the predicted number of service personnel in a certain time period in the future and the carrying capacity of the current service personnel are evaluated to ensure the stability of the service personnel arrangement and dynamically allocate the required service personnel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for monitoring, warning and allocating resources of the dynamic number of service personnel. Background Art

[0002] With the rapid development of modern society, various public places, such as hospitals, passenger stations, restaurants, etc., often face a large number of people. In order to meet the service needs of these people, how to effectively configure service personnel has become a key issue. Traditional service staff scheduling methods mostly rely on experience or fixed scheduling patterns, such as scheduling at fixed time periods every day or arranging staff according to holidays and specific events. However, these traditional methods often cannot flexibly respond to sudden changes in passenger flow or unexpected peak periods, resulting in delayed service response, reduced customer satisfaction, waste of resources, and poor work efficiency.

[0003] In addition, most places currently have difficulty predicting future traffic and corresponding service needs in real time when staffing. Although there are some simple prediction methods, such as statistical analysis based on historical data, these methods often fail to predict the complex and changing reality and are difficult to adapt to the rapid changes in traffic patterns.

[0004] Therefore, how to predict the future flow of people in real time and accurately, and dynamically configure service personnel accordingly, predict and control so that when a large number of service personnel are needed, the carrying capacity threshold of the current service personnel will not be exceeded, has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] Therefore, the purpose of the present invention is to provide a dynamic number monitoring, early warning and resource allocation method for service personnel, aiming to monitor and predict the number of service personnel in real time, dynamically optimize the rationality of service personnel configuration, reduce user waiting time, improve overall service efficiency and user satisfaction, and thus provide scientific and reasonable personnel configuration guidance for various service industries.

[0006] In order to achieve the above-mentioned purpose, the present invention provides a method for monitoring the dynamic number of service personnel, early warning and resource allocation, comprising the following steps:

[0007] S1. Obtaining the service personnel information, service window information and service personnel information;

[0008] S2. Input the obtained service personnel information and service personnel information into the trained prediction model for the number of newly added service personnel, and predict the number of newly added service personnel in a future scheduling cycle of any service window to obtain the number of newly added service personnel;

[0009] S3. Determine any future time period based on the number of newly added service personnel Whether the number of service personnel exceeds the current service personnel carrying capacity threshold;

[0010] S4. If the number of service personnel exceeds the current service personnel carrying capacity threshold, the number of service personnel that needs to be added is calculated.

[0011] Further preferably, in S2, the model for predicting the number of newly added service personnel is constructed using a machine learning algorithm, with the service personnel data and service window data in historical data as input, and the number of newly added service personnel in a future scheduling cycle of the service window as output for training.

[0012] Further preferably, in S2, the number of newly added service personnel in a future scheduling cycle of any service window is predicted to obtain the number of newly added service personnel, including:

[0013] S201, obtaining the service node data of each served person and extracting the corresponding service window Ws1 from the served person information;

[0014] S202, performing correlation analysis on all service windows according to the service window information, and extracting correlation degrees between different service windows;

[0015] S203, according to the correlation degree between the different service windows extracted in S202, screening a number of related service windows Ws_re whose correlation strength with the service window Ws1 extracted in S201 meets a preset threshold;

[0016] S204, extracting the service personnel data of multiple time spans of the service window Ws1 from the historical data, and extracting the service personnel data of several related service windows Ws_re according to the time span;

[0017] S205 , training a prediction model for the number of newly added service recipients using the service node data, the service recipient data of multiple time spans of the service window Ws1 in the historical data, and the service recipient data of several related service windows Ws_re as input data.

[0018] Further preferably, in S3, it is determined that any future time period Whether the number of service personnel exceeds the current service personnel carrying capacity threshold within the period includes the following steps:

[0019] S301, initialize the time window t=0; generate a time series list of the predicted number of newly added service personnel according to the number of newly added service personnel in a future scheduling cycle of any service window ;

[0020] S302: List the current status of each service personnel , calculate the remaining service time of each service personnel, according to Update the remaining service time of each service personnel in the on-the-job status list of each service personnel;

[0021] S303, obtain t+ according to the time series list N of the number of newly added service personnel The number of newly served personnel during the time period, and the newly served personnel will be added to the waiting list;

[0022] S304, check the remaining service time of all service personnel, and determine whether there is a service personnel whose remaining service time is 0; if there is a service personnel whose remaining service time is 0, assign it to the service personnel in the waiting queue in the order of the service personnel. The service personnel will be removed from the waiting list and their waiting time will be added to the waiting time list. If there is no service personnel with a remaining service time of 0, the waiting time of all other individuals in the service personnel waiting list will be added directly. ;

[0023] S305, update the time window, set t=t+ ; Compare t and The size of; if t> , then calculate the waiting time list The average ;

[0024] S306: Compare the average values ​​of the waiting time list Compared with the result of the preset service personnel carrying capacity threshold TT, when , it is determined that the number of served personnel exceeds the current service personnel carrying capacity threshold.

[0025] Further preferably, in S4, calculating the number of service personnel that need to be added includes the following process:

[0026] S401. Enter a future time period Inside, every Time series list of the predicted number of new service personnel within the time interval ;

[0027] S402: Calculate the average value of each element in the efficiency list of the service personnel who are not currently on duty ;

[0028] S403, initialize the number of service personnel to be added, ; Initialize the time window, let ;

[0029] S404, update the on-the-job status list of each service personnel, add Service staff, , and new personnel ; Update the efficiency list of each service staff, add Service staff, , and new personnel ;

[0030] S402. Calculate the remaining service time of each service personnel: Update each element of the service personnel on-the-job status list C: ;

[0031] S403: When the number of service personnel exceeds the current service personnel carrying capacity threshold, the service personnel assigned with new service personnel reset their remaining service time to , the waiting time of all other individuals in the service staff waiting list is added ;

[0032] S404, update the number of service personnel to be added, , and repeat the above steps to determine whether the number of service personnel still exceeds the current service personnel carrying capacity threshold; otherwise, the number of new service personnel to be added is returned .

[0033] The present application discloses a method for monitoring, warning and allocating resources for the dynamic number of service personnel, which can dynamically predict the number of service personnel that will be served at each service window (such as different departments of a hospital, security checkpoints at a station, administrative service counters, etc.). Based on the dynamic prediction results, the predicted number of service personnel in a certain period of time in the future and the carrying capacity of the current service personnel are evaluated. Finally, based on the principle of minimizing the average waiting time of service personnel, the stability of service personnel arrangement is ensured, and the required service personnel are dynamically allocated. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The present invention is a workflow diagram of the method for monitoring, warning and allocating resources of the dynamic number of service personnel.

[0035] Figure 2 The flowchart of the method for predicting the number of service personnel is shown in FIG.

[0036] Figure 3 A calculation method to determine whether the number of service personnel exceeds the current service personnel carrying capacity threshold.

[0037] Figure 4 A method for calculating the number of additional service personnel required. DETAILED DESCRIPTION

[0038] The present invention is further described in detail below through the accompanying drawings and specific embodiments.

[0039] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring the dynamic number of service personnel and allocating resources, including the following steps:

[0040] S1. Acquire the information of the service personnel, the service window information and the service personnel information; further include constructing a service personnel information database and collecting service personnel related variables; constructing a service personnel information database and collecting service personnel related variables;

[0041] The variables related to the service recipients are collected through the existing information systems of various departments. The variables include personal information of the service recipients, service records, service process nodes, etc. The patient personal information includes the name, age, gender, home address, etc. of the service recipients. The service records include the service window number, service personnel number, etc. The service process nodes include appointment time, arrival time, service acceptance time, charging time, etc. The above time variables include but are not limited to date, time period, time, etc.

[0042] The variables related to service personnel are collected through the existing human resources system of the service unit (hospital, station, government service department). The variables include key characteristic data such as service personnel personal information, service efficiency, and on-the-job status. The personal information of service personnel includes the service personnel's name, title, window, contact information, etc. The service efficiency is the number of service personnel that the service personnel can receive per minute. The on-the-job status is in service, idle, not scheduled, etc.

[0043] S2. Input the obtained service personnel information and service personnel information into the trained prediction model for the number of newly added service personnel, and predict the number of newly added service personnel in a future scheduling cycle of any service window to obtain the number of newly added service personnel;

[0044] The model for predicting the number of newly added service personnel is constructed using a machine learning algorithm, with the service personnel data and service window data in the historical data as input, and the number of newly added service personnel in a future scheduling cycle of the service window as output for training;

[0045] like Figure 2 As shown, in S2, the number of newly added service personnel in a future scheduling cycle of any service window is predicted to obtain the number of newly added service personnel, including:

[0046] S201, obtaining the service node data of each served person and extracting the corresponding service window Ws1 from the served person information;

[0047] S202, performing correlation analysis on all service windows according to the service window information, and extracting correlation degrees between different service windows;

[0048] S203, according to the correlation degree between the different service windows extracted in S202, screening a number of related service windows Ws_re whose correlation strength with the service window Ws1 extracted in S201 meets a preset threshold;

[0049] S204, extracting the service personnel data of multiple time spans of the service window Ws1 from the historical data, and extracting the service personnel data of several related service windows Ws_re according to the time span;

[0050] S205 , training a prediction model for the number of newly added service recipients using the service node data, the service recipient data of multiple time spans of the service window Ws1 in the historical data, and the service recipient data of several related service windows Ws_re as input data.

[0051] The service personnel quantity prediction model uses a deep learning method to establish a data-driven model. The specific methods used include but are not limited to time series data prediction models such as long short-term memory neural networks, recurrent neural networks, and attention mechanisms. The data-driven input variables of the service window number prediction model are the multi-time span historical data of the window in the service personnel information database described in step 1, and the multi-time span service personnel data of the strongly correlated window. The strongly correlated window is obtained based on the correlation analysis of the historical medical data of a certain service window and the data of other service windows in the department (such as between different departments of the hospital and between different windows of administrative services, there will be a certain correlation in the flow of personnel). The specific methods used include but are not limited to Pearson correlation coefficient method, Spearman correlation coefficient method, variance analysis method, etc. The multiple time spans include but are not limited to 1 day before the prediction time, 1 week before the prediction time, 1 month before the prediction time, 1 quarter before the prediction time, and 1 year before the prediction time.

[0052] S3. Determine any future time period based on the number of newly added service personnel obtained Check whether the number of service personnel exceeds the current service personnel capacity threshold; initialize the on-the-job status list of each service personnel , where each element value is 0; initialize the waiting list of service personnel ; Initialize the waiting time list of the service personnel who have received the service Initialize the service personnel carrying capacity threshold TT, in minutes. The physical meaning of this value is: the maximum limit of the average waiting time of the service personnel.

[0053] like Figure 3 As shown, in S3, determine any future time period Whether the number of service personnel exceeds the current service personnel carrying capacity threshold within the period includes the following steps:

[0054] The input variables are: (1) a certain period of time in the future Time series list of the predicted number of new service personnel within each ∆T time interval , the values ​​in the list represent the number of new service personnel in a certain time interval; (2) the efficiency list of each service personnel at present , the value in the list represents the service efficiency of a service staff, the unit is: minutes / person; (3) The current status list of each service staff , the value in the table represents the remaining service time of a service staff for the current service recipient. If the value is 0, it means that the service staff is currently idle and is not providing service to the service recipient; (4) Waiting list of the current service recipient , indicating the service recipients who have arrived at the service window but are still waiting for service. If the list is empty, it means that there are no service recipients waiting. (5) List of waiting time for service recipients who have received service ; (6) Service personnel carrying capacity threshold TT. The output result is a Boolean value O, which indicates whether the number of service personnel exceeds the current service personnel carrying capacity threshold.

[0055] S301, initialize the time window t=0; generate a time series list of the predicted number of newly added service personnel according to the number of newly added service personnel in a future scheduling cycle of any service window ;

[0056] S302: List the current status of each service personnel , calculate the remaining service time of each service personnel, according to Update the remaining service time of each service personnel in the on-the-job status list of each service personnel;

[0057] S303, obtain t+ according to the time series list N of the number of newly added service personnel The number of newly served personnel during the time period, and the newly served personnel will be added to the waiting list;

[0058] S304, check the remaining service time of all service personnel, and determine whether there is a service personnel whose remaining service time is 0; if there is a service personnel whose remaining service time is 0, assign it to the service personnel in the waiting queue in the order of the service personnel. The service personnel will be removed from the waiting list and their waiting time will be added to the waiting time list. If there is no service personnel with a remaining service time of 0, the waiting time of all other individuals in the service personnel waiting list will be added directly. ;

[0059] S305, update the time window, set t=t+ ; Compare t and The size of; if t> , then calculate the waiting time list The average ;

[0060] S306: Compare the average values ​​of the waiting time list Compared with the result of the preset service personnel carrying capacity threshold TT, when , it is determined that the number of served personnel exceeds the current service personnel carrying capacity threshold.

[0061] It should be noted that the average waiting time WT of the service personnel is avg The calculation is done using the following method:

[0062] S3031, set the initial time of each service personnel's remaining service time LT = 0, the service personnel waiting list P q = , let time window t be the starting time T S , set the time interval to ;

[0063] S3032. Calculate the remaining service time of each service personnel, LT = max(0, LT - );

[0064] S3033, input t+ The number of newly added service personnel in the time period, and the newly added service personnel sequence are added to the waiting list;

[0065] S3034, detecting the remaining service time of all service personnel, and determining whether there is a service personnel whose remaining service time is 0;

[0066] S3035. If the remaining service time of service personnel i is 0, the service personnel with LT=0 will be assigned to the service personnel in the order of the service personnel in the waiting list, and the service personnel who have been served will be removed. The remaining service time of service personnel i will be reset to LT=1 / E, and the waiting time of all other service personnel in the waiting list will be increased. ;

[0067] If there is no service personnel with a remaining service time of 0, then the waiting time of all the service personnel in the waiting list will be added directly. ;

[0068] S3036, update the time window, let t=t+∆ ;

[0069] S3037, determine the service personnel list P q Is it empty, and t>T E If so, then output the average waiting time WT of the service personnel under this scheduling plan avg ; If the service personnel list P q Not empty, or t<=T E , then repeat S3032-S3036.

[0070] S4. If the number of service personnel exceeds the current service personnel carrying capacity threshold, the number of service personnel that needs to be added is calculated.

[0071] like Figure 4 As shown, in S4, the number of service personnel that needs to be added is calculated, including the following process:

[0072] S401. Enter a future time period Inside, every Time series list of the predicted number of new service personnel within the time interval ;

[0073] S402: Calculate the average value of each element in the efficiency list of the service personnel who are not currently on duty ;

[0074] S403, initialize the number of service personnel to be added, ; Initialize the time window, let ;

[0075] S404, update the on-the-job status list of each service personnel, add Service staff, , and new personnel ; Update the efficiency list of each service staff, add Service staff, , and new personnel ;

[0076] S402. Calculate the remaining service time of each service personnel: Update each element of the service personnel on-the-job status list C: ;

[0077] S403: When the number of service personnel exceeds the current service personnel carrying capacity threshold, the service personnel assigned with new service personnel reset their remaining service time to , the waiting time of all other individuals in the service staff waiting list is added ;

[0078] S404, update the number of service personnel to be added, , and repeat the above steps to determine whether the number of service personnel still exceeds the current service personnel carrying capacity threshold; otherwise, the number of new service personnel to be added is returned .

[0079] The specific implementation steps include:

[0080] The input variables of this method are: (1) a certain period of time in the future Inside, every Time series list of the predicted number of new service personnel within the time interval ; (2) Current efficiency list of each service staff ; (3) A list of the efficiency of service personnel affiliated with the service window who are currently not on duty (not scheduled or on vacation) , the value in the list represents the service efficiency of a service staff, the unit is: minutes / person; (4) The current status list of each service staff ,(5)Currently served personnel waiting list ; (6) List of waiting times for service recipients who have received service ; (7) Service personnel carrying capacity threshold TT. The output variable is an int integer value variable: the number of new service personnel to be added .

[0081] Furthermore, the specific execution steps of the above calculation are:

[0082] S01: Load (1) Add a time series list of the predicted number of service personnel ; (2) Current efficiency list of each service staff ; (3) Efficiency list of service personnel who are not currently on duty (not scheduled or on vacation) ; (4) List of current service personnel on-the-job status ;(5)The waiting list of the current service personnel ; (6) List of waiting times for service recipients who have received service ; (7) Service personnel carrying capacity threshold TT.

[0083] S02: Calculate the average value of each element in the efficiency list of service personnel who are not currently on duty (not scheduled or on vacation) .

[0084] S03: Initialize the number of service personnel to be added, .

[0085] S04: Initialize the time window, ;

[0086] S05: Update the on-duty status list of each service personnel, add Service staff, , and new personnel ; Update the efficiency list of each service staff, add Service staff, , and new personnel ;

[0087] S06: Calculate the remaining service time of each service personnel: Update each element of the service personnel on-duty status list C: .

[0088] S07: Obtain t+ according to the time series list N of the number of newly added service personnel The number of newly served personnel during the time period, and the newly served personnel will be added to the waiting list;

[0089] S08: Check the remaining service time of all service personnel, and determine whether there is a service personnel whose remaining service time is 0;

[0090] S09_1: If the remaining service time of a service staff is 0, that is, a service staff , then they will be assigned to the waiting queue in the order of the service personnel. The service personnel will be removed from the waiting list and their waiting time will be added to the waiting time list. The agent assigned the new agent resets his remaining service time to , the waiting time of all other individuals in the service staff waiting list is added ;

[0091] S09_2: If there is no service personnel with a remaining service time of 0, the waiting time of all other individuals in the service personnel waiting list will be added directly. ;

[0092] S010: Update the time window, let t=t+ ;

[0093] S011: Determine t> If the result is true, the waiting time list is calculated. Otherwise, repeat steps S6-S11.

[0094] S012: Judgment If the result is true, update the number of service personnel to be added. , and repeat steps S04-S012; otherwise, the number of new service personnel to be added is returned

[0095] Obviously, the above embodiments are only examples for clear explanation, and are not intended to limit the implementation methods. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A method for monitoring the dynamic number of service personnel and early warning and resource allocation, characterized in that: The following steps are involved: S1. Obtaining the service personnel information, service window information and service personnel information; S2. Input the obtained service personnel information and service personnel information into the trained prediction model for the number of newly added service personnel, and predict the number of newly added service personnel in a future scheduling cycle of any service window to obtain the number of newly added service personnel; S3. Determine any future time period based on the number of newly added service personnel Whether the number of served personnel exceeds the current service personnel carrying capacity threshold; when the average value of the average waiting time exceeds the preset service personnel carrying capacity threshold TT, it is determined that the number of served personnel exceeds the current service personnel carrying capacity threshold; Among them, the average waiting time WT of the service personnel is determined avg The calculation is done using the following method: S3031, set the initial time of each service personnel's remaining service time LT = 0, the service personnel waiting list P q = , let time window t be the starting time T S , set the time interval to ; S3032. Calculate the remaining service time of each service personnel, LT = max(0, LT - ); S3033, input t+ During the time period, the number of service personnel is increased, and the sequence of the newly added service personnel is added to the waiting list; S3034, detecting the remaining service time of all service personnel, and determining whether there is a service personnel whose remaining service time is 0; S3035. If the remaining service time of service personnel i is 0, the service personnel with LT=0 will be assigned to the service personnel in the order of the service personnel in the waiting list, and the service personnel who have been served will be removed. The remaining service time of service personnel i will be reset to LT=1 / E, and the waiting time of all other service personnel in the waiting list will be increased. ; E is work efficiency; If there is no service personnel with a remaining service time of 0, the waiting time of all the service personnel in the waiting list will be added directly. ; S3036, update the time window, let t = t + ; S3037, determine the service personnel list P q Is it empty, and t>T E If yes, then output the average waiting time WT of the service personnel avg ; If the service personnel list P q Not empty, or t<=T E , then repeat S3032-S3036; S4. If the number of service personnel exceeds the current service personnel carrying capacity threshold, the number of service personnel that needs to be added is calculated; the calculation of the number of service personnel that needs to be added includes the following process: S401. Enter a future time period Inside, every Time series list of the predicted number of new service personnel within the time interval ; S402: Calculate the average value of each element in the efficiency list of the service personnel who are not currently on duty ; S403, initialize the number of service personnel to be added, ; Initialize the time window, let ; S404, update the on-the-job status list of each service personnel, add Service staff, ,in, is the remaining service time of the current service personnel, The remaining service time of the newly added service personnel is set to 0; update the efficiency list E of each service personnel, and add Service staff, ,in, For the efficiency of current service personnel, is the efficiency of the new service personnel, and the efficiency of the new service personnel is set to ; S405, calculate the remaining service time of each service personnel, according to Update the elements of the service personnel's on-the-job status list C; S406: When the number of service personnel exceeds the current service personnel carrying capacity threshold, newly assigned service personnel are assigned, and their remaining service time is reset to , the waiting time of all other individuals in the service staff waiting list is added ; S407, update the number of service personnel to be added, , and repeat the above steps to determine whether the number of service personnel still exceeds the current service personnel carrying capacity threshold; otherwise, the number of new service personnel to be added is returned .

2. The method for monitoring, warning and allocating resources of the dynamic number of service personnel according to claim 1 is characterized in that: In S2, the prediction model for the number of newly added service personnel is constructed using a machine learning algorithm, with the service personnel data and service window data in historical data as input, and the number of newly added service personnel in a future scheduling cycle of the service window as output for training.

3. The method for monitoring, warning and allocating resources of the dynamic number of service personnel according to claim 1 is characterized in that: In S2, the number of newly added service personnel in a future scheduling cycle of any service window is predicted to obtain the number of newly added service personnel, including: S201, obtaining the service node data of each served person and extracting the corresponding service window Ws1 from the served person information; S202, performing correlation analysis on all service windows according to the service window information, and extracting correlation degrees between different service windows; S203, according to the correlation degree between the different service windows extracted in S202, screening a number of related service windows Ws_re whose correlation strength with the service window Ws1 extracted in S201 meets a preset threshold; S204, extracting the service personnel data of multiple time spans of the service window Ws1 from the historical data, and extracting the service personnel data of several related service windows Ws_re according to the time span; S205 , training a prediction model for the number of newly added service recipients using the service node data, the service recipient data of multiple time spans of the service window Ws1 in the historical data, and the service recipient data of several related service windows Ws_re as input data.

Citation Information

Patent Citations

  • Queue early warning system

    CA2612777A1

  • Customer service center telephone traffic load prediction method

    CN104113644A

  • Hospital intelligent doctor-seeing system based on machine vision

    CN108288498A

  • Scheduling scheme processing method and device based on business volume, equipment and medium

    CN114118691A

  • Business handling duration estimation method and device, equipment, storage medium and product

    CN115394003A