CN111988478A - Incoming call management method, device, server and storage medium - Google Patents

Incoming call management method, device, server and storage medium Download PDF

Info

Publication number
CN111988478A
CN111988478A CN202010914301.0A CN202010914301A CN111988478A CN 111988478 A CN111988478 A CN 111988478A CN 202010914301 A CN202010914301 A CN 202010914301A CN 111988478 A CN111988478 A CN 111988478A
Authority
CN
China
Prior art keywords
target user
queuing
queuing time
incoming call
queue
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
Application number
CN202010914301.0A
Other languages
Chinese (zh)
Inventor
余自雷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Financial Technology Co Ltd Shanghai
Original Assignee
OneConnect Financial Technology Co Ltd Shanghai
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OneConnect Financial Technology Co Ltd Shanghai filed Critical OneConnect Financial Technology Co Ltd Shanghai
Priority to CN202010914301.0A priority Critical patent/CN111988478A/en
Publication of CN111988478A publication Critical patent/CN111988478A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M3/00Automatic or semi-automatic exchanges
    • H04M3/42Systems providing special services or facilities to subscribers
    • H04M3/50Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/523Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
    • H04M3/5238Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing with waiting time or load prediction arrangements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M3/00Automatic or semi-automatic exchanges
    • H04M3/42Systems providing special services or facilities to subscribers
    • H04M3/50Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5141Details of processing calls and other types of contacts in an unified manner
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12Messaging; Mailboxes; Announcements

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the application provides an incoming call management method, an incoming call management device, a server and a storage medium, and can be applied to the fields of smart cities, artificial intelligence and the like. The method comprises the steps of obtaining queuing time length prediction information of a target user when detecting that the target user of an incoming call meets a queuing time length prediction condition, wherein the queuing time length prediction information comprises at least one of the following items: the information of the user arranged before the target user in the queue allocated to the target user and the information of the processing personnel corresponding to the queue; calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user; generating a notification message to the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user; and sending the notification message to a terminal corresponding to the target user. By the method and the device, incoming call experience of the user can be improved, and queuing duration prediction accuracy is improved.

Description

Incoming call management method, device, server and storage medium
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a server, and a storage medium for incoming call management.
Background
The intelligent customer service system is a set of solution for enterprise telephone/online user service, and as the quantity of businesses of a company using the intelligent customer service system is larger and larger, all hotline telephone calls are more and more, so the intelligent customer service system performs call queue processing.
However, in the process of using the above method, once the queue is long, the user can always wait for incoming call, and the system can output a waiting prompt tone to prompt that the seat is busy and prompt the user whether to continue waiting, which makes the user's incoming call experience very unfriendly. If the time it takes for the user to wait in line is to be estimated, then the length of time each user's face check currently waiting in front of the user needs to be calculated. Furthermore, there are many uncertain factors affecting the queuing time, and if the queuing time is estimated by only a few factors, the estimated queuing time will be inaccurate.
Disclosure of Invention
The embodiment of the application provides an incoming call management method, an incoming call management device, a server and a storage medium, which can improve incoming call experience of a user and improve queuing time prediction accuracy.
In a first aspect, an embodiment of the present application provides an incoming call management method, including:
when detecting that an incoming call target user meets a queuing time prediction condition, acquiring queuing time prediction information of the target user, wherein the queuing time prediction information comprises at least one of the following items: the information of the users arranged in front of the target user in the queue distributed to the target user and the information of the processing personnel corresponding to the queue;
calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user;
generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user;
and sending the notification message to a terminal corresponding to the target user.
Optionally, the detecting that the target user of the incoming call meets the queuing time prediction condition includes:
when the target user is queued in a queue allocated for the target user, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or,
when the target user is in a queuing state and the predicted time of the target user is reached, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or,
when the target user is in a queuing state and a first user incoming call arranged in front of the target user is hung up or a second user service with an incoming call accepted is processed, determining that the target user with the incoming call detected meets a queuing time length prediction condition; or,
and when the target user is in a queuing state and the processing personnel corresponding to the queue are changed, determining that the target user detecting the incoming call meets the queuing time length prediction condition.
Optionally, the calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user includes:
taking the queuing time length prediction information as input data of a pre-trained regression model, and performing queuing time length prediction on the target user through the pre-trained regression model according to the queuing time length prediction information to obtain the queuing time length of the target user;
the pre-trained regression model is obtained by training queuing data of each sample user in a plurality of sample users.
Optionally, the predicting the queuing time of the target user according to the queuing time prediction information through the pre-trained regression model includes:
obtaining a feature vector corresponding to the queuing time length prediction information and a weight of a feature corresponding to the feature vector;
and calculating the queuing time of the target user according to the feature vector corresponding to the queuing time prediction information, the weight of the feature corresponding to the feature vector and the minimum value of the loss function obtained in the process of training the regression model by the pre-trained regression model.
Optionally, before obtaining the queuing time prediction information, the method further includes:
when detecting an incoming call request sent by a terminal corresponding to a target user, determining the area where the target user is located;
determining a first queue from the plurality of queues as a queue allocated to the target user according to the area where the target user is located and the area corresponding to each queue in the plurality of queues;
and queuing the target user in a queue allocated to the target user.
Optionally, before obtaining the queuing time prediction information, the method further includes:
when an incoming call request sent by a terminal corresponding to a target user is detected, determining processing items to be followed by the target user;
determining a second queue from the plurality of queues as a queue allocated to the target user according to the processing items to be followed by the target user and the processing items to be followed by each queue in the plurality of queues;
and queuing the target user in a queue allocated to the target user.
Optionally, the information of the user ranked before the target user includes at least one of: the number of users ranked before the target user, the number of users corresponding to each of a plurality of age groups among the users ranked before the target user, and the number of users corresponding to each of a plurality of resource types among the users ranked before the target user;
the information of the processing personnel comprises at least one of the following: the number of treating staff and the number of treating staff corresponding to each professional skill level.
In a second aspect, an embodiment of the present application provides an incoming call management apparatus, including:
an obtaining module, configured to obtain queuing duration prediction information of a target user when it is detected that the target user of an incoming call meets a queuing duration prediction condition, where the queuing duration prediction information includes at least one of the following: the information of the users arranged in front of the target user in the queue distributed to the target user and the information of the processing personnel corresponding to the queue;
the prediction module is used for calling a preset regression method and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user;
the message generating module is used for generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user;
and the communication module is used for sending the notification message to a terminal corresponding to the target user.
In a third aspect, an embodiment of the present application provides a server, including a processor, an output device, and a memory, where the processor, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement the method according to the first aspect.
In summary, the server predicts the queuing time for the target user according to the queuing time prediction information of the target user by introducing a regression method to obtain the queuing time of the target user, and then generates the notification message according to the queuing time to be sent to the terminal corresponding to the target user.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of an incoming call management method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another incoming call management method provided in an embodiment of the present application;
fig. 3 is a schematic network architecture diagram of an incoming call management system according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an incoming call management device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Please refer to fig. 1, which is a flowchart illustrating an incoming call management method according to an embodiment of the present application. The incoming call management method can be applied to a server, which can be a server or a server cluster. Specifically, the method may comprise the steps of:
s101, when detecting that an incoming call target user meets a queuing time length prediction condition, obtaining queuing time length prediction information of the target user, wherein the queuing time length prediction information comprises at least one of the following items: and the information of the users arranged in front of the target user in the queue allocated to the target user and the information of the processing personnel corresponding to the queue.
The target user of the incoming call can be any user of the incoming call. The incoming call may refer to an incoming telephone call or an incoming message call. The incoming telephone call may be, for example, an incoming telephone call sent through a carrier network. Or a voice call or a video call initiated through an application, which is not limited by the present application. The queue may be a linear table that allows delete operations to be performed at the front end of the table and insert operations to be performed at the back end of the table. The treating personnel referred to in the present application may be, for example, customer service personnel or seat personnel. The queue corresponds to at least one incoming call and the incoming call is not accepted by the user. Here, in addition to the queue mode, a linked list may also be used to queue the user, which allows the deletion operation and the insertion operation to be performed at any position of the table, and this application is not described herein again.
Wherein the information of the user ranked before the target user may include at least one of: the number of users ranked before the target user, the number of users in each of a plurality of age groups among the users ranked before the target user, and the number of users in each of a plurality of resource types (e.g., loan products or financial products) among the users ranked before the target user. In an embodiment, the queuing duration prediction information may further include a time when the target user starts queuing, where the time when the target user starts queuing may be a time period or a time point, which is not limited in this application. The information of the processing personnel may comprise at least one of the following: the number of processing personnel and the number of processing personnel corresponding to each of the plurality of levels of expertise. The professional skill level can be, for example, a primary level, a middle level, a high level, and the like, and the present application does not limit the present invention.
In one embodiment, if there is a hanging up user on an incoming call in the queue, then the hanging up user will not count into the number of users that are ranked before the target user. Accordingly, the user who has hung up the incoming call does not count the number of users corresponding to each of the plurality of age groups among the users before the target user. Accordingly, the user who hangs up the incoming call does not count the number of users corresponding to each resource type in the plurality of resource types among the users who are ranked before the target user.
According to the embodiment of the application, the server can allocate the queue to the target user when detecting the incoming call request sent by the terminal corresponding to the target user, and queue the target user in the queue allocated to the target user. The terminal includes but is not limited to a smart phone, a tablet computer and other smart terminals. The incoming call request includes, but is not limited to, being presented in the form of an incoming call, an incoming message, and the like.
In one embodiment, the incoming request may carry identification information of the target user, and the server may queue the target user in a queue according to the identification information of the target user carried by the incoming request. For example, the server may add the identification information of the target user carried by the incoming call request to a queue to queue the target user. The identification information of the target user herein includes, but is not limited to, the name of the target user, the contact phone number (e.g., mobile phone number) of the target user, and the like, which are used to uniquely identify the target user. Or, the server may generate a queuing identifier (e.g., a queuing number) of the target user according to the identification information of the target user carried in the incoming request when detecting the incoming request sent by the target user through the terminal, and add the queuing identifier to the queue to queue the target user.
In the embodiment of the application, in order to ensure that the target user can dynamically acquire the queuing time, when it is detected that the target user meets the queuing time prediction condition, the queuing time prediction information of the target user can be acquired to be used for queuing time prediction.
In one embodiment, the server detects that the target user of the incoming call satisfies the queuing time prediction condition, and may determine that the target user of the incoming call is detected to satisfy the queuing time prediction condition when the server queues the target user in a queue allocated to the target user. For example, the target user is user a, and the queue allocated for user a is queue 1. The server may determine that it is detected that the user a satisfies the queuing time duration prediction condition when queuing the user a in the queue 1.
In one embodiment, the server detects that the target user of the incoming call satisfies the queuing time prediction condition, and may determine that the target user of the incoming call is detected to satisfy the queuing time prediction condition when the target user is in a queuing state and the predicted time for the target user arrives. Here, the predicted time of the target user may be, for example, a time obtained according to the initial time of queuing (the time point when queuing is started) of the target user and a preset time interval (for example, every two minutes). For example, the target user is user a, the initial queuing time is 10:00 in the morning, the preset time interval is every two minutes, the server may determine that user a satisfies the queuing time prediction condition when detecting that 10:02 arrives, and may determine that user a satisfies the queuing time prediction condition when detecting that 10:04 arrives, and so on.
In an embodiment, the server detects that the target user of the incoming call satisfies the queuing time prediction condition, and may determine that the target user of the incoming call satisfies the queuing time prediction condition when the target user is in a queuing state and a first user of the incoming call before the target user hangs up or a second user of the incoming call is handled completely. The first user may refer to any user who is ranked before the target user, and the second user may refer to any user who has accepted an incoming call that is ranked before the target user.
In an embodiment, the server detects that the target user of the incoming call satisfies the queuing time prediction condition, and may determine that the target user of the incoming call satisfies the queuing time prediction condition when the target user is in a queuing state and a processing staff corresponding to the queue changes. The change of the processing personnel may refer to the increase of the processing personnel, the decrease of the processing personnel or the adjustment of the processing personnel, and the application does not limit the change.
S102, calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user.
Wherein, the preset regression method includes but is not limited to any one of the following: LASSO algorithm (LASSO, Least Absolute Shrinkage and Selection Operator) regression method, Ridge Ridge regression method, elastic network ElasticNet regression method. Each method may correspond to a regression model, for example, the LASSO regression method may correspond to the LASSO regression model, the Ridge regression method may correspond to the Ridge regression model, and the ElasticNet regression method may correspond to the ElasticNet regression model.
In the embodiment of the application, the server calls a preset regression method, the queuing time of the target user is predicted according to the queuing time prediction information, a pre-trained regression model can be scheduled for the server in the process of obtaining the queuing time of the target user, and the queuing time of the target user is predicted according to the queuing time prediction information, so that the queuing time of the target user is obtained. Specifically, the server may use the queuing time prediction information as input data of a pre-trained regression model, and perform queuing time prediction on the target user according to the queuing time prediction information through the pre-trained regression model to obtain the queuing time of the target user.
The pre-trained regression model may be trained from the queued data of each of the plurality of sample users. The queuing data of each sample user may include queuing information of the sample user and a corresponding queuing time, and the queuing information may include at least one of: the information of the user who is arranged in front of the sample user in the queue allocated to the sample user and the information of the processing person corresponding to the queue (referred to as the queue allocated to the sample user). The queuing information is in accordance with the type of information included in the queuing time length prediction information. That is, when the queuing information includes information of a user that is ranked before the sample user in the queue allocated to the sample user, the aforementioned queuing time period prediction information may include information of a user that is ranked before the target user in the queue allocated to the target user. When the queuing information includes information of a processing person corresponding to the queue allocated to the sample user, the aforementioned queuing time period prediction information may include information of a processing person corresponding to the queue allocated to the target user.
Wherein the information of the user ranked before the sample user may include at least one of: the number of users ranked before the sample user, the number of users corresponding to each of a plurality of age groups among the users ranked before the sample user, and the number of users corresponding to each of a plurality of resource types among the users ranked before the sample user. In one embodiment, the queuing information may also include the time at which the sample user started queuing. The time when the queuing is started may be a time period or a time point, which is not limited in this application. The information of the processing person may include at least one of: the number of processing personnel and the number of processing personnel corresponding to each of the plurality of levels of expertise.
In one embodiment, when the pre-trained regression model is a pre-trained LASSO regression model, the training process for the model may be as follows: and calculating the value of a loss function of the LASSO regression model according to the queuing data of each sample user in the plurality of sample users until the minimum value of the loss function is obtained, and determining that the training of the LASSO regression model is finished to obtain a pre-trained LASSO model. The process of calculating the value of the loss function can be referred to the following formula:
Figure BDA0002662801900000081
wherein,
Figure BDA0002662801900000082
the representation is a value of a loss function of the LASSO regression model, Y represents queuing time, X represents a feature vector obtained according to queuing data of a sample user, beta represents weight of features corresponding to the feature vector, and lambda represents a penalty term coefficient.
In an embodiment, the process of predicting the queuing time of the target user by the server according to the queuing time prediction information through the pre-trained regression model may specifically be that the server obtains a feature vector corresponding to the queuing time prediction information and a weight of a feature corresponding to the feature vector, and calculates the queuing time of the target user through the pre-trained regression model according to the feature vector corresponding to the queuing time prediction information, the weight of the feature corresponding to the feature vector and a minimum value of a loss function obtained in the process of training the regression model. When the pre-trained regression model is the pre-trained LASSO regression model, the minimum value of the loss function obtained in the process of training the regression model can be calculated by a formula 1.1.
S103, generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user.
And S104, sending the notification message to a terminal corresponding to the target user.
In the embodiment of the application, the server can generate the notification message to the target user according to the queuing time of the target user, and then send the notification message to the terminal corresponding to the target user, so as to inform the current queuing condition of the target user. The queuing time may also be understood as a queuing waiting time, or may also be understood as an incoming call waiting time, which is not limited in this application. The notification message may include a queuing time. In one embodiment, the notification message may include, in addition to the queuing duration, information such as the number of users that are queued ahead of the target user in the queue allocated for the target user.
In an embodiment, the server may perform speech synthesis processing according to the queuing time of the target user to obtain a notification message to the target user, where the notification message is a speech message, and send the notification message to a terminal corresponding to the target user. After receiving the notification message, the terminal corresponding to the target user may play the notification message for the user. For example, this notification message may be: you wait 3 people in front of you, and expect 3 minutes of waiting time, for example, you give up waiting and please hang up.
In one embodiment, the server may invoke a Speech synthesis service, such as a Text-To-Speech (TTS) Speech synthesis service, To perform Speech synthesis processing according To the queuing duration of the target user To obtain notification information for the target user.
In an embodiment, the step S101 to S104 may also be adopted to notify the queuing situation of the user arranged before the target user, and/or notify the queuing situation of the user arranged after the target user, which is not described herein again.
It can be seen that, in the embodiment shown in fig. 1, the server may predict the queuing time for the target user according to the queuing time prediction information of the target user by introducing a regression method to obtain the queuing time of the target user, so as to generate a notification message according to the queuing time to send to the terminal corresponding to the target user, improve the prediction accuracy of the queuing time, achieve an accurate queuing condition for dynamic broadcast, and improve the incoming call experience of the user.
The application relates to artificial intelligence technology, for example, a regression method is adopted to predict queuing time. In addition, the method and the system can be used for smart city construction, such as construction and daily operation of intelligent customer service systems of financial institutions and other institutions.
Please refer to fig. 2, which is a flowchart illustrating another incoming call management method according to an embodiment of the present application. The method may be applied in the aforementioned server. Compared with the embodiment of fig. 1, the embodiment of the present application introduces a queue allocation process in steps S201 to S203. Specifically, the method may comprise the steps of:
s201, when an incoming call request sent by a terminal corresponding to a target user is detected, determining the area where the target user is located.
In the embodiment of the application, the server can determine the area where the target user is located when detecting the incoming call request sent by the terminal corresponding to the target user. In the following, several ways of determining the region where the target user is located will be briefly listed, and the embodiments of the present application include, but are not limited to, the following listed ways of determining the region where the target user is located.
In one embodiment, the server may obtain a contact phone corresponding to the target user, and determine the area where the target user is located according to the contact phone of the target user.
In an embodiment, the server may send a location information obtaining request to a terminal corresponding to a target user, and the server may receive location information sent by the terminal corresponding to the target user, so as to determine an area where the target user is located according to the location information.
In one embodiment, the server may obtain an internet protocol address of a terminal corresponding to the target user, and determine a region where the target user is located according to the internet protocol address.
S202, according to the area where the target user is located and the area corresponding to each queue in the queues, determining a first queue from the queues as a queue distributed for the target user.
In this embodiment, the server may determine, according to the area where the target user is located and the area corresponding to each of the plurality of queues, a queue that is the same as the area where the target user is located from the plurality of queues as a first queue, and use the first queue as a queue allocated to the target user. The process can allocate a proper queue to the target user according to the processing items, so that the queuing is more targeted.
In one embodiment, when the number of queues in the same area as the target user is at least two, the server may determine, as the first queue, a queue with the least number of people queued from the at least two queues in the same area as the target user.
S203, queuing the target user in the queue distributed to the target user.
S204, when detecting that the incoming call target user meets the queuing time length prediction condition, acquiring queuing time length prediction information of the target user, wherein the queuing time length prediction information comprises at least one of the following items: and the information of the users arranged in front of the target user in the queue allocated to the target user and the information of the processing personnel corresponding to the queue.
S205, calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user.
S206, generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user.
And S207, sending the notification message to a terminal corresponding to the target user.
Steps S204 to S207 can refer to steps S101 to S104 in the embodiment of fig. 1, which is not described herein again in this embodiment of the present application.
In one embodiment, steps S201-S203 may be replaced with the following steps: when detecting an incoming call request sent by a terminal corresponding to a target user, a server determines processing items to be followed by the target user; and the server determines a second queue from the plurality of queues as a queue allocated to the target user according to the processing items to be followed by the target user and the processing items to be followed by each queue in the plurality of queues, and queues the target user in the queue allocated to the target user. The process can allocate a proper queue to the target user according to the processing items, so that the queuing is more targeted.
In an embodiment, the process that the server determines, according to the processing items to be followed by the target user and the processing items to be followed by each of the plurality of queues, a second queue as the queue allocated to the target user may be a process that the server determines, according to the processing items to be followed by the target user and the processing items to be followed by each of the plurality of queues, a queue matching the processing items to be followed by the target user from the plurality of queues as the second queue, and uses the second queue as the queue allocated to the target user. For example, the server may determine, from the plurality of queues, the dequeue 2 as the queue allocated to the target user, in the manner described above, in which the processed transaction to be followed by the target user is a deferred payment and the queue 2 in the plurality of queues is a deferred payment corresponding to the followed processed transaction.
In one embodiment, when there are at least two queues for the processing item to be followed by the target user, the server may determine, as the first queue, a queue with the least number of people queued from the at least two queues for the processing item to be followed by the target user.
In one embodiment, steps S201-S203 may be replaced with the following steps: when detecting an incoming call request sent by a target user through a terminal, the server determines the number of queuing people corresponding to each queue in the plurality of queues, and then determines a third queue (which is the queue with the minimum number of queuing people in the plurality of queues and is used for being distinguished from the first queue and the second queue) with the minimum number of queuing people from the plurality of queues according to the number of queuing people corresponding to each queue, wherein the third queue is used as a queue distributed for the target user. The user can be queued by determining the queue with less queuing number, the incoming call waiting time of the user can be reduced, and the incoming call experience of the user is improved.
As can be seen, in the embodiment shown in fig. 2, when receiving an incoming call request sent by a terminal corresponding to a target user, a server may select a queue allocated to the user from a plurality of queues according to a region where the target user is located to queue the user, and the process may match a suitable queue for the target user to queue, so that the queuing process is more targeted.
Referring to fig. 3, a schematic network architecture of an incoming call management system according to an embodiment of the present application is shown, where the incoming call management system may include a server 10 and a terminal 20 corresponding to a target user. Specifically, the method comprises the following steps:
the server can acquire queuing time prediction information of the target user by executing the step S101, can predict the queuing time of the target user by executing the step S102, then acquires a notification message for the target user by executing the step S103, and sends the notification message to the terminal 20 corresponding to the target user by executing the step S104, so that the aim of dynamically broadcasting the accurate queuing condition is fulfilled, the incoming call experience of the user is improved, and the accuracy of the queuing time prediction is improved by introducing a regression method.
Please refer to fig. 4, which is a schematic structural diagram of an incoming call management apparatus according to an embodiment of the present application. The apparatus may be applied to the aforementioned server. The incoming call management apparatus may include:
an obtaining module 401, configured to obtain, when it is detected that a target user of an incoming call meets a queuing time prediction condition, queuing time prediction information of the target user, where the queuing time prediction information includes at least one of the following: and the information of the users arranged in front of the target user in the queue allocated to the target user and the information of the processing personnel corresponding to the queue.
The prediction module 402 is configured to invoke a preset regression method, and predict the queuing time of the target user according to the queuing time prediction information, so as to obtain the queuing time of the target user.
A message generating module 403, configured to generate a notification message for the target user according to the queuing time of the target user, where the notification message is used to notify the queuing situation of the target user.
A communication module 404, configured to send the notification message to a terminal corresponding to the target user.
In an optional implementation manner, the obtaining module 401 determines that the target user who detected the incoming call meets the queuing time length prediction condition when detecting that the target user who detected the incoming call meets the queuing time length prediction condition, specifically, when queuing the target user in a queue allocated to the target user; or when the target user is in a queuing state and the predicted time of the target user is reached, determining that the target user detecting the incoming call meets the queuing time length prediction condition; or when the target user is in a queuing state and a first user incoming call arranged in front of the target user hangs up or a second user service processed by the incoming call is finished, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or when the target user is in a queuing state and the processing personnel corresponding to the queue changes, determining that the target user who detects the incoming call meets the queuing time length prediction condition.
In an optional implementation manner, the prediction module 402 calls a preset regression method, and performs queuing time prediction on the target user according to the queuing time prediction information to obtain the queuing time of the target user, specifically, the queuing time prediction information is used as input data of a pre-trained regression model, and the queuing time prediction is performed on the target user according to the queuing time prediction information through the pre-trained regression model to obtain the queuing time of the target user; the pre-trained regression model is obtained by training queuing data of each sample user in a plurality of sample users.
In an optional implementation manner, the prediction module 402 performs queuing time prediction on the target user according to the queuing time prediction information through the pre-trained regression model, specifically, obtains a feature vector corresponding to the queuing time prediction information and a weight of a feature corresponding to the feature vector; and calculating the queuing time of the target user according to the feature vector corresponding to the queuing time prediction information, the weight of the feature corresponding to the feature vector and the minimum value of the loss function obtained in the process of training the regression model by the pre-trained regression model.
In an alternative embodiment, the incoming call management device further comprises a queuing module 405.
In an optional implementation manner, the queuing module 405 is configured to determine, before obtaining the queuing duration prediction information, a region where the target user is located when detecting, through the communication module 404, an incoming call request sent by a terminal corresponding to the target user; determining a first queue from the plurality of queues as a queue allocated to the target user according to the area where the target user is located and the area corresponding to each queue in the plurality of queues; and queuing the target user in a queue allocated to the target user.
In an optional implementation manner, the queuing module 405 is further configured to, before obtaining the queuing time length prediction information, determine a processing item to be followed for the target user when an incoming call request sent by a terminal corresponding to the target user is detected through the communication module 404; determining a second queue from the plurality of queues as a queue allocated to the target user according to the processing items to be followed by the target user and the processing items to be followed by each queue in the plurality of queues; and queuing the target user in a queue allocated to the target user.
In an optional embodiment, the information of the user ranked before the target user includes at least one of: the number of users ranked before the target user, the number of users corresponding to each of a plurality of age groups among the users ranked before the target user, and the number of users corresponding to each of a plurality of resource types among the users ranked before the target user; the information of the processing personnel comprises at least one of the following: the number of treating staff and the number of treating staff corresponding to each professional skill level.
It can be seen that, in the implementation shown in fig. 4, the incoming call management device may predict the queuing time for the target user according to the queuing time prediction information of the target user by introducing a regression method, so as to obtain the queuing time of the target user, and thus generate a notification message according to the queuing time to send to the terminal corresponding to the target user, which improves the prediction accuracy of the queuing time, and achieves the purpose of dynamically broadcasting an accurate queuing condition.
Please refer to fig. 5, which is a schematic structural diagram of a server according to an embodiment of the present disclosure. The server described in this embodiment may include: a processor 1000, an input device 2000, an output device 3000, and a memory 4000. The processor 1000, the input device 2000, the output device 3000, and the memory 4000 may be connected by a bus or other means. In one embodiment, the input device 2000 is an optional device. The input device 2000 and the output device 3000 may be standard wired or wireless communication interfaces.
The Processor 1000 may be a Central Processing Unit (CPU), and may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 4000 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 4000 is used to store a set of program codes, and the processor 1000, the input device 2000 and the output device 3000 may call the program codes stored in the memory 4000. Specifically, the method comprises the following steps:
a processor 1000, configured to, when it is detected that a target user of an incoming call meets a queuing time prediction condition, obtain queuing time prediction information of the target user, where the queuing time prediction information includes at least one of: the information of the users arranged in front of the target user in the queue distributed to the target user and the information of the processing personnel corresponding to the queue; calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user; generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user; and sending the notification message to a terminal corresponding to the target user through an output device 3000.
In one embodiment, the processor 1000 determines that the target user who detected the incoming call satisfies the queuing time prediction condition when detecting that the target user satisfies the queuing time prediction condition, specifically, when queuing the target user in a queue allocated to the target user; or when the target user is in a queuing state and the predicted time of the target user is reached, determining that the target user detecting the incoming call meets the queuing time length prediction condition; or when the target user is in a queuing state and a first user incoming call arranged in front of the target user hangs up or a second user service processed by the incoming call is finished, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or when the target user is in a queuing state and the processing personnel corresponding to the queue changes, determining that the target user who detects the incoming call meets the queuing time length prediction condition.
In one embodiment, the processor 1000 calls a preset regression method, and performs queuing time prediction on the target user according to the queuing time prediction information to obtain the queuing time of the target user, specifically, the queuing time prediction information is used as input data of a pre-trained regression model, and the queuing time prediction is performed on the target user according to the queuing time prediction information through the pre-trained regression model to obtain the queuing time of the target user; the pre-trained regression model is obtained by training queuing data of each sample user in a plurality of sample users.
In one embodiment, the processor 1000 performs queuing duration prediction on the target user according to the queuing duration prediction information through the pre-trained regression model, specifically, obtains a feature vector corresponding to the queuing duration prediction information and a weight of a feature corresponding to the feature vector; and calculating the queuing time of the target user according to the feature vector corresponding to the queuing time prediction information, the weight of the feature corresponding to the feature vector and the minimum value of the loss function obtained in the process of training the regression model by the pre-trained regression model.
In an embodiment, the processor 1000 is further configured to, before obtaining the queuing time length prediction information, determine a region where the target user is located when detecting, through the input device 2000, an incoming call request sent by a terminal corresponding to the target user; determining a first queue from the plurality of queues as a queue allocated to the target user according to the area where the target user is located and the area corresponding to each queue in the plurality of queues; and queuing the target user in a queue allocated to the target user.
In one embodiment, the processor 1000 is further configured to determine, before obtaining the queuing time length prediction information, a processing item to be followed for the target user when an incoming call request sent by a terminal corresponding to the target user is detected through the input device 2000; determining a second queue from the plurality of queues as a queue allocated to the target user according to the processing items to be followed by the target user and the processing items to be followed by each queue in the plurality of queues; and queuing the target user in a queue allocated to the target user.
In one embodiment, the information of the user ranked before the target user includes at least one of: the number of users ranked before the target user, the number of users corresponding to each of a plurality of age groups among the users ranked before the target user, and the number of users corresponding to each of a plurality of resource types among the users ranked before the target user; the information of the processing personnel comprises at least one of the following: the number of treating staff and the number of treating staff corresponding to each professional skill level.
In a specific implementation, the processor 1000, the input device 2000, and the output device 3000 described in this embodiment of the present application may perform the implementation described in the embodiment of fig. 1 and fig. 2, and may also perform the implementation described in this embodiment of the present application, which is not described herein again.
The functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of sampling hardware, and can also be realized in a form of sampling software functional units.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the above embodiments of the methods. The computer readable storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. An incoming call management method, comprising:
when detecting that an incoming call target user meets a queuing time prediction condition, acquiring queuing time prediction information of the target user, wherein the queuing time prediction information comprises at least one of the following items: the information of the users arranged in front of the target user in the queue distributed to the target user and the information of the processing personnel corresponding to the queue;
calling a preset regression method, and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user;
generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user;
and sending the notification message to a terminal corresponding to the target user.
2. The method of claim 1, wherein the detecting that the target user of the incoming call satisfies the queuing time prediction condition comprises:
when the target user is queued in a queue allocated for the target user, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or,
when the target user is in a queuing state and the predicted time of the target user is reached, determining that the target user detecting the incoming call meets a queuing time length prediction condition; or,
when the target user is in a queuing state and a first user incoming call arranged in front of the target user is hung up or a second user service with an incoming call accepted is processed, determining that the target user with the incoming call detected meets a queuing time length prediction condition; or,
and when the target user is in a queuing state and the processing personnel corresponding to the queue are changed, determining that the target user detecting the incoming call meets the queuing time length prediction condition.
3. The method according to claim 1, wherein the calling a preset regression method and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user comprises:
taking the queuing time length prediction information as input data of a pre-trained regression model, and performing queuing time length prediction on the target user through the pre-trained regression model according to the queuing time length prediction information to obtain the queuing time length of the target user;
the pre-trained regression model is obtained by training queuing data of each sample user in a plurality of sample users.
4. The method of claim 3, wherein the predicting queuing length of the target user according to the queuing length prediction information through the pre-trained regression model comprises:
obtaining a feature vector corresponding to the queuing time length prediction information and a weight of a feature corresponding to the feature vector;
and calculating the queuing time of the target user according to the feature vector corresponding to the queuing time prediction information, the weight of the feature corresponding to the feature vector and the minimum value of the loss function obtained in the process of training the regression model by the pre-trained regression model.
5. The method according to claim 1, wherein before obtaining queuing duration prediction information, the method further comprises:
when detecting an incoming call request sent by a terminal corresponding to a target user, determining the area where the target user is located;
determining a first queue from the plurality of queues as a queue allocated to the target user according to the area where the target user is located and the area corresponding to each queue in the plurality of queues;
and queuing the target user in a queue allocated to the target user.
6. The method according to claim 1, wherein before obtaining queuing duration prediction information, the method further comprises:
when an incoming call request sent by a terminal corresponding to a target user is detected, determining processing items to be followed by the target user;
determining a second queue from the plurality of queues as a queue allocated to the target user according to the processing items to be followed by the target user and the processing items to be followed by each queue in the plurality of queues;
and queuing the target user in a queue allocated to the target user.
7. The method according to any one of claims 1 to 6,
the information of the user ranked before the target user includes at least one of: the number of users ranked before the target user, the number of users corresponding to each of a plurality of age groups among the users ranked before the target user, and the number of users corresponding to each of a plurality of resource types among the users ranked before the target user;
the information of the processing personnel comprises at least one of the following: the number of treating staff and the number of treating staff corresponding to each professional skill level.
8. An incoming call management apparatus, comprising:
an obtaining module, configured to obtain queuing duration prediction information of a target user when it is detected that the target user of an incoming call meets a queuing duration prediction condition, where the queuing duration prediction information includes at least one of the following: the information of the users arranged in front of the target user in the queue distributed to the target user and the information of the processing personnel corresponding to the queue;
the prediction module is used for calling a preset regression method and predicting the queuing time of the target user according to the queuing time prediction information to obtain the queuing time of the target user;
the message generating module is used for generating a notification message for the target user according to the queuing time of the target user, wherein the notification message is used for notifying the queuing condition of the target user;
and the communication module is used for sending the notification message to a terminal corresponding to the target user.
9. A server, comprising a processor, an output device, and a memory, the processor, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method according to any one of claims 1-7.
CN202010914301.0A 2020-09-02 2020-09-02 Incoming call management method, device, server and storage medium Pending CN111988478A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010914301.0A CN111988478A (en) 2020-09-02 2020-09-02 Incoming call management method, device, server and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010914301.0A CN111988478A (en) 2020-09-02 2020-09-02 Incoming call management method, device, server and storage medium

Publications (1)

Publication Number Publication Date
CN111988478A true CN111988478A (en) 2020-11-24

Family

ID=73447419

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010914301.0A Pending CN111988478A (en) 2020-09-02 2020-09-02 Incoming call management method, device, server and storage medium

Country Status (1)

Country Link
CN (1) CN111988478A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113489851A (en) * 2021-07-02 2021-10-08 拉卡拉支付股份有限公司 Information prompting method, device, electronic equipment, storage medium and program product
CN113553203A (en) * 2021-07-30 2021-10-26 北京达佳互联信息技术有限公司 Request processing method, device, server and storage medium
CN114240458A (en) * 2021-12-16 2022-03-25 山东沃伦通信技术有限公司 Call center customer intelligent queuing system and method based on big data
CN115695317A (en) * 2022-12-23 2023-02-03 海马云(天津)信息技术有限公司 Queuing and dequeuing method and device of access request, electronic equipment and storage medium
CN115879683A (en) * 2022-02-10 2023-03-31 北京中关村科金技术有限公司 Method and device for switching intelligent customer service into artificial customer service and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1465398A1 (en) * 2003-04-02 2004-10-06 Orange S.A. Call center with presentation of waiting times and selectable call-back times
CN101953143A (en) * 2008-05-05 2011-01-19 朗讯科技公司 A method and equipment for providing information to the user terminal in the call waiting queue
CN102263865A (en) * 2010-05-24 2011-11-30 中兴通讯股份有限公司 Real-time queuing feedback function realization method and system for next generation call center (NGCC)
CN107833341A (en) * 2017-11-22 2018-03-23 深圳怡化电脑股份有限公司 A kind of intelligent queuing method, equipment and computer-readable recording medium
CN109087435A (en) * 2018-08-13 2018-12-25 中国联合网络通信集团有限公司 The prediction technique and queuing system of queuing time
CN109558989A (en) * 2018-12-13 2019-04-02 平安科技(深圳)有限公司 Queuing time prediction technique, device, equipment and computer readable storage medium
CN110942190A (en) * 2019-11-22 2020-03-31 广东睿盟计算机科技有限公司 Queuing time prediction method and device, computer equipment and storage medium
CN110956294A (en) * 2018-09-26 2020-04-03 北京嘀嘀无限科技发展有限公司 Queuing time estimation method and device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1465398A1 (en) * 2003-04-02 2004-10-06 Orange S.A. Call center with presentation of waiting times and selectable call-back times
CN101953143A (en) * 2008-05-05 2011-01-19 朗讯科技公司 A method and equipment for providing information to the user terminal in the call waiting queue
CN102263865A (en) * 2010-05-24 2011-11-30 中兴通讯股份有限公司 Real-time queuing feedback function realization method and system for next generation call center (NGCC)
CN107833341A (en) * 2017-11-22 2018-03-23 深圳怡化电脑股份有限公司 A kind of intelligent queuing method, equipment and computer-readable recording medium
CN109087435A (en) * 2018-08-13 2018-12-25 中国联合网络通信集团有限公司 The prediction technique and queuing system of queuing time
CN110956294A (en) * 2018-09-26 2020-04-03 北京嘀嘀无限科技发展有限公司 Queuing time estimation method and device
CN109558989A (en) * 2018-12-13 2019-04-02 平安科技(深圳)有限公司 Queuing time prediction technique, device, equipment and computer readable storage medium
CN110942190A (en) * 2019-11-22 2020-03-31 广东睿盟计算机科技有限公司 Queuing time prediction method and device, computer equipment and storage medium

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113489851A (en) * 2021-07-02 2021-10-08 拉卡拉支付股份有限公司 Information prompting method, device, electronic equipment, storage medium and program product
CN113553203A (en) * 2021-07-30 2021-10-26 北京达佳互联信息技术有限公司 Request processing method, device, server and storage medium
CN114240458A (en) * 2021-12-16 2022-03-25 山东沃伦通信技术有限公司 Call center customer intelligent queuing system and method based on big data
CN115879683A (en) * 2022-02-10 2023-03-31 北京中关村科金技术有限公司 Method and device for switching intelligent customer service into artificial customer service and storage medium
CN115695317A (en) * 2022-12-23 2023-02-03 海马云(天津)信息技术有限公司 Queuing and dequeuing method and device of access request, electronic equipment and storage medium
CN115695317B (en) * 2022-12-23 2023-04-07 海马云(天津)信息技术有限公司 Queuing and dequeuing method and device of access request, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN111988478A (en) Incoming call management method, device, server and storage medium
US11882242B2 (en) System and method for a work distribution service
CN108989588B (en) Call distribution method, call center, electronic device, and storage medium
AU2017404110B2 (en) Agent allocation method and device, server, and storage medium
CN107231496B (en) Traffic processing method, service processing method, device and server
CN109783227B (en) Task allocation method, device and system and computer readable storage medium
US7761323B2 (en) Method and system for scheduling a customer service callback
US20080144803A1 (en) Dynamic agent skill balancing
CN107222646B (en) Call request distribution method and device
WO2017088593A1 (en) Service seat selection method, apparatus and system
CN109152061B (en) Channel allocation method, device, server and storage medium
KR20190012255A (en) Providing a personal assistance module with an optionally steerable state machine
CN110572524B (en) User call processing method, device, storage medium and server
CN110581928B (en) Telephone calling-out method, system, electronic equipment and storage medium
CN113032112A (en) Resource scheduling method and device, electronic equipment and storage medium
US9602310B2 (en) Associating system requests with SMS user responses
CN116414955B (en) Intelligent queuing method, device, equipment and medium based on client intention and intention
US20230388422A1 (en) Determination and display of estimated hold durations for calls
US20230060694A1 (en) Determination and display of estimated hold durations for calls
CN118071361A (en) Method, device, electronic equipment and computer readable medium for time delay distribution customer service
CN110572522A (en) method and device for reserving call back
CN107424281B (en) Batch queuing reservation method and device
CN113163061A (en) Method and device for distributing customer service terminals
CN113194109A (en) Method and device for pushing information
CN114827361A (en) Outbound processing method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.)

Applicant after: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI)

Address before: Room 201, Building A, No. 1 Qianwan Road, Qianhaisheng Cooperation Zone, Shenzhen City, Guangdong Province, 518000

Applicant before: ONECONNECT FINANCIAL TECHNOLOGY Co.,Ltd. (SHANGHAI)

SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
AD01 Patent right deemed abandoned
AD01 Patent right deemed abandoned

Effective date of abandoning: 20231229