Method and apparatus for predicting online customer service consultation queue time

Abstract

The present invention relates to the field of computer technologies, and provides a method and apparatus for predicting an online customer service consultation queue time. A specific embodiment of the method comprises: in response to receiving an online customer service consultation request from a user, determining a skill group corresponding to the user, and acquiring the customer service status of the skill group; when the customer service status is that all customer service representatives are busy, adding the user into a waiting queue; acquiring queuing features of the user and customer service status features of the skill group, wherein the customer service status features comprise the number of currently available customer service representatives and the number of conversations being processed by each customer service representative; and predicting a queue time of the user by means of a queue time estimation model on the basis of the queuing features of the user, the number of currently available customer service representatives, and the number of conversations being processed by each customer service representative. The embodiment greatly reduces errors in prediction results, and improves the queue time prediction accuracy and prediction performance.

Description

Method and device for predicting online customer service consultation queue time

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese invention patent application No. 202310699670.6 filed on June 13, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of computer technology, and in particular to a method and device for predicting the queuing time of online customer service consultation. Background Art

[0004] With the booming development of internet e-commerce, online customer service systems have become a crucial component of e-commerce websites. For consumers, consulting online customer service systems is the most convenient way to learn about products they want to purchase. However, online customer service staff are limited, and during peak hours, user traffic surges, placing significant pressure on customer service. This results in some users being unable to access human customer service promptly, forcing them to wait in a waiting queue. Once a user enters the waiting queue, the key is to inform them of their estimated wait time, which directly determines whether they choose to queue. The accuracy of this estimated wait time also directly impacts the user's waiting experience.

[0005] Currently, when estimating a user's waiting time, we can generally count the number of people currently in the queue and calculate the estimated waiting time by multiplying the average waiting time by the number of people. We can also use NLP (Natural Language Processing) technology to predict the end of a single conversation. The estimated end time of all ongoing conversations of all customer service representatives who can receive the user is accumulated to obtain the waiting time required for the user.

[0006] In the process of implementing the present disclosure, the inventors found that whether the existing technology estimates the queue length based on statistical methods or based on NLP technology, the estimation error of the queue length is large and the prediction performance is low.

[0007] Summary of the Invention

[0008] In view of this, the embodiments of the present disclosure provide a method and device for predicting the queue length for online customer service consultation, which greatly reduces the error of the prediction results and improves the prediction accuracy and prediction performance of the queue length.

[0009] To achieve the above objectives, according to one aspect of an embodiment of the present disclosure, a method for predicting the length of online customer service consultation queues is provided, comprising:

[0010] In response to receiving an online customer service consultation request from a user, determining a skill group corresponding to the user and obtaining a customer service status of the skill group;

[0011] If the customer service status indicates that all customer service staff are busy, the user is added to a waiting queue;

[0012] Obtaining the user's queue characteristics and the skill group's customer service status characteristics, wherein the customer service status characteristics include the number of currently available customer service representatives and the number of sessions being handled by each customer service representative;

[0013] The queue duration prediction model is used to predict the queue duration of the user based on the queue characteristics of the user, the number of currently available customer service representatives, and the number of sessions being handled by each customer service representative.

[0014] Optionally, the queuing characteristics of the user include the queue number of the user in the waiting queue and the queue number of the user in the skill group; based on the queuing characteristics of the user, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, the queuing time prediction model is used to predict the queuing time of the user, including: based on the queue number of the user in the waiting queue and the queue number of the user in the skill group, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, the queuing time prediction model is used to predict the queuing time of the user.

[0015] Optionally, before using a queue time prediction model to predict the queue time of the user based on the queue characteristics of the user, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, the method further includes: determining the queue time period corresponding to the user based on the sending time of the user's online customer service consultation request; using a queue time prediction model to predict the queue time of the user based on the queue characteristics of the user, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, including: using a queue time prediction model to predict the queue time of the user based on the queue time period corresponding to the user, the queue number of the user in the waiting queue, the queue number of the user in the skill group, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative.

[0016] Optionally, the queuing time prediction model is constructed in the following manner: obtaining user online customer service consultation session data in a recent period; extracting session features corresponding to each session from the user online customer service consultation session data, the session features including the time of requesting online consultation, queuing period, skill group, the user's queue number in the waiting queue and the user's queue number in the skill group, the currently available number of customer service representatives in the skill group and the number of sessions being processed by each customer service representative, as well as the actual online consultation time; obtaining the queuing time corresponding to each session based on the time of requesting online consultation and the actual online consultation time corresponding to each session; for each session, using the queuing time corresponding to the session to mark the session features corresponding to the session to generate training data corresponding to the session; and performing model training based on the training data corresponding to each session to construct the queuing time prediction model.

[0017] Optionally, after using the queue time prediction model to predict the queue time of the user, it also includes: in response to the user's specified operation trigger event, re-acquiring the user's queue characteristics and the customer service status characteristics of the skill group, the customer service status characteristics including the current number of available customer service staff and the number of sessions being handled by each customer service; based on the user's queue characteristics, the current number of available customer service staff and the number of sessions being handled by each customer service, using the queue time prediction model to predict the user's queue time to update the user's queue time.

[0018] Optionally, after using the queue time prediction model to predict the queue time of the user, it also includes: in response to detecting that a customer service has ended the session being processed and released resources, taking out the queued user from the waiting queue and assigning it to the customer service, refreshing the waiting queue and updating the customer service status; when the customer service status is still that all customer services are busy, re-acquiring the user's queue characteristics and the customer service status characteristics of the skill group, the customer service status characteristics include the current number of available customer services and the number of sessions being processed by each customer service; based on the user's queue characteristics, the current number of available customer services and the number of sessions being processed by each customer service, using the queue time prediction model to predict the user's queue time to update the user's queue time.

[0019] Optionally, the method further includes: when the customer service status is that there is a customer service that is not busy, allocating the user to the customer service that is not busy.

[0020] According to another aspect of an embodiment of the present disclosure, a device for predicting the length of an online customer service consultation queue is provided, comprising:

[0021] A status acquisition module is used to determine the skill group corresponding to the user and obtain the customer service status of the skill group in response to receiving an online customer service consultation request from the user;

[0022] A queue adding module, configured to add the user to a waiting queue when the customer service status indicates that all customer service staff are busy;

[0023] A feature acquisition module is used to obtain the queuing characteristics of the user and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available customer service representatives and the number of sessions being processed by each customer service representative;

[0024] The duration prediction module is used to predict the user's queue duration using a queue duration estimation model based on the user's queue characteristics, the number of currently available customer service representatives, and the number of sessions being handled by each customer service representative.

[0025] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, including: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for predicting the waiting time for online customer service consultation provided by an embodiment of the present disclosure.

[0026] According to another aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for predicting the online customer service consultation queue length provided by an embodiment of the present disclosure is implemented.

[0027] One embodiment disclosed above has the following advantages or beneficial effects: by responding to a user's online customer service consultation request, determining the skill group corresponding to the user and obtaining the customer service status of the skill group; when the customer service status is that all customer service staff are busy, adding the user to the waiting queue; obtaining the user's queuing characteristics and the customer service status characteristics of the skill group, the customer service status characteristics include the current number of available customer service staff and the number of sessions being handled by each customer service staff; based on the user's queuing characteristics, the current number of available customer service staff and the number of sessions being handled by each customer service staff, a technical solution is used to predict the user's queuing time using a queuing time estimation model, which can predict the current user's queuing time based on the status of the online customer service staff that can receive the user in the customer service system at the time the current user comes online, the status of the sessions being received by these customer service staff, and the queuing characteristics of the user, thereby greatly reducing the error of the prediction result and improving the prediction accuracy and prediction performance of the queuing time.

[0028] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to better understand the present disclosure and do not constitute an improper limitation of the present disclosure.

[0030] FIG1 is a schematic diagram of the main steps of a method for predicting the queuing time of online customer service consultation according to an embodiment of the present disclosure;

[0031] FIG2 is a schematic diagram of a process for predicting the length of time to wait for online customer service consultation according to an embodiment of the present disclosure;

[0032] FIG3 is a schematic diagram of the error in the prediction result of the queuing time according to an embodiment of the present disclosure;

[0033] FIG4 is a schematic diagram of the main modules of a device for predicting the queuing time of online customer service consultation according to an embodiment of the present disclosure;

[0034] FIG5 is a diagram of an exemplary system architecture in which embodiments of the present disclosure may be applied;

[0035] FIG6 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0037] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions disclosed herein all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken with respect to user personal information to prevent unauthorized access to user personal information data and to safeguard the security of user personal information, network security, and national security.

[0038] With the booming development of internet e-commerce, online customer service systems have become a crucial component of e-commerce websites. For consumers, consulting online customer service systems is the most convenient way to learn about products they want to purchase. However, online customer service personnel are limited, and their daily schedules must balance busy and off-peak hours. During busy periods, user traffic surges, placing heavy pressure on customer service, preventing some users from accessing live customer service in a timely manner and forcing them to wait in a queue. The consultation queue system reduces peak-to-valley traffic and fully utilizes customer service resources, allowing users to access live customer service after a short wait, rather than leaving messages without a response. This maximizes user pickup rates and improves the user experience.

[0039] After a user enters the waiting queue, the key is to inform them of their estimated wait time. This directly determines whether they choose to queue, and the accuracy of the estimated wait time directly impacts their queue experience. Therefore, queue time estimation is achieved through an algorithm that comprehensively calculates the user's queue time based on the historical frequency of customer service conversations ending, the estimated remaining time for each ongoing conversation, and the different skill groups of different users. In e-commerce customer service systems, self-operated merchants often have dozens to tens of thousands of customer service representatives to handle simultaneously. Larger customer service systems often have tens of thousands of customer service representatives to manage and handle, and individual customer service representatives often have to handle traffic from dozens of skill groups. Therefore, it's impossible to use simple rules to determine the waiting time for a user to enter the queue. Furthermore, online customer service representatives must handle multiple conversations simultaneously, each one releasing its own session before the next one can be served. Since each user is unique, it's difficult to determine how long a conversation with a customer service representative will end. Therefore, accurately estimating a user's queue time is a difficult task.

[0040] Currently, the following two methods are often used to estimate the waiting time of users: (1) Statistical method, which counts the number of people in the queue and multiplies the average time it takes to queue by the number of people to estimate the waiting time; (2) NLP technology-based method for predicting the end time of a single-call session, which predicts the end time of a single-call session and accumulates the estimated end time of all ongoing sessions of all customer service representatives who can receive the user to obtain the waiting time for a single user.

[0041] However, both methods have certain defects. The main problems with statistical methods are as follows: (1) The queuing time for each person varies greatly, with a high standard deviation, which results in a large error in the overall estimated time after averaging; (2) There is no time difference and no statistics on the number of current customer service representatives. For example, there are fewer customer service representatives in the early morning hours, which results in a long queuing time for each user and a large prediction error. Problems with methods based on NLP technology to predict the end time of a single conversation: (1) Based on the content of the conversation between the current user and the customer service representative, the NLP technology predicts the end time of the current conversation. The error in the predicted time for each conversation is large. After testing, it was found that the error cannot be more than tens of seconds. The final estimated queuing time requires the accumulation of the predicted time of multiple conversations, which will infinitely amplify the error; (2) It is necessary to predict the estimated end time of all conversations currently being received by the online customer service representative. The queuing time estimation for one user requires thousands of predictions, which has low performance and low feasibility.

[0042] In order to solve the above-mentioned technical problems existing in the prior art, the present disclosure provides a method for predicting the waiting time for online customer service consultation, the implementation principle of which is: according to the current user's online time, the status of online customer service staff who can receive the user, the session status of these customer service staff, and the position of the user in the waiting queue are obtained in the current customer service system, and relevant features are extracted. At the same time, the actual waiting time of historical users queuing under the current features is used as a label, and model learning is performed based on the machine learning regression method to predict the estimated waiting time when the current user enters the waiting queue, divide the waiting time into multiple slices, and return them to the front end to present to the user.

[0043] Figure 1 is a schematic diagram of the main steps of the method for predicting the online customer service consultation queue length according to an embodiment of the present disclosure. As shown in Figure 1, the method for predicting the online customer service consultation queue length according to the embodiment of the present disclosure mainly includes the following steps S101 to S104.

[0044] Step S101: In response to receiving a user's online customer service consultation request, determine the user's corresponding skill group and obtain the customer service status of the skill group. When a user requests online customer service consultation, the system first determines the corresponding skill group based on the business scope. Each skill group corresponds to an online customer service consultation task for a specific business.

[0045] After determining the skill group corresponding to the user, the agent status of that skill group is retrieved. Each skill group may include multiple agents, and each agent may also correspond to multiple skill groups. Each agent can handle multiple online customer service consultation sessions simultaneously. When all agents in the skill group are handling sessions, and the number of sessions currently handled by each agent reaches the limit for that agent, the agent status of the skill group is "All agents are busy." Otherwise, if any agent is not handling a session, or the number of sessions currently handled by an agent does not reach the limit for that agent, the agent status of the skill group is considered "Some agents are available."

[0046] Step S102: If the customer service status indicates that all agents are busy, the user is added to a waiting queue. If all agents in the skill group are processing sessions, and the number of sessions currently being processed by each agent exceeds the limit for the number of sessions that the agent can handle, all agents are busy, and the user is added to a waiting queue.

[0047] Step S103: Obtain the queuing characteristics of the user and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available customer service staff and the number of sessions being handled by each customer service staff. After the user is added to the waiting queue, the queuing time of the user will be estimated based on the user's queuing situation and the status characteristics of the customer service of the skill group. Among them, the queuing characteristics of the user mainly include the queue number of the user in the waiting queue and the queue number of the user in the skill group. Among them, the waiting queue stores all the queuing users who need online customer service consultation and their corresponding online customer service consultation requests, and also stores the skill group information corresponding to each user. Therefore, the first queue number of the user in the waiting queue and the second queue number of the user in the corresponding skill group can be obtained based on the information of the waiting queue.

[0048] Step S104: Predicting the queuing time of the user using a queuing time estimation model based on the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being handled by each customer service representative.

[0049] According to one embodiment of the present disclosure, the user's queue characteristics include the user's queue number in the waiting queue and the user's queue number in the skill group. Furthermore, based on the user's queue characteristics, the currently available number of agents, and the number of sessions currently being handled by each agent, a queue duration prediction model is used to predict the user's queue duration. This may specifically include: using the queue duration prediction model to predict the user's queue duration based on the user's queue number in the waiting queue, the user's queue number in the skill group, the currently available number of agents, and the number of sessions currently being handled by each agent.

[0050] According to another embodiment of the present disclosure, before using a queue duration prediction model to predict the queue duration of the user based on the queue characteristics of the user, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, the method may further include: determining the queue period corresponding to the user based on the sending time of the user's online customer service consultation request. Furthermore, using a queue duration prediction model to predict the queue duration of the user based on the queue characteristics of the user, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative may specifically include: using a queue duration prediction model to predict the queue duration of the user based on the queue period corresponding to the user, the queue number of the user in the waiting queue, the queue number of the user in the skill group, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative.

[0051] According to an embodiment of the present disclosure, the queuing time prediction model is constructed in the following manner: obtaining user online customer service consultation session data in a recent period; extracting session features corresponding to each session from the user online customer service consultation session data, the session features including the time of requesting online consultation, queuing period, belonging skill group, the queue number of the user in the waiting queue and the queue number of the user in the skill group, the currently available number of customer service representatives of the skill group and the number of sessions being processed by each customer service representative, as well as the actual online consultation time; obtaining the queuing time corresponding to each session based on the time of requesting online consultation and the actual online consultation time corresponding to each session; for each session, using the queuing time corresponding to the session to mark the session features corresponding to the session to generate training data corresponding to the session; performing model training based on the training data corresponding to each session to construct the queuing time prediction model.

[0052] Specifically, when building a queue time estimation model, the present disclosure first obtains user online customer service consultation session data from a recent period. For example, it can filter out user queue session data, customer service reception data, and actual queue time data from the past month. The user queue session data is used to extract model training features and labels; the customer service reception data is used to calculate the user's call time, the number of customer service representatives currently available to receive the user, and the number of ongoing conversations with these representatives; the actual queue time is obtained by tracking the user's queue time and obtaining the time between the user's queue start and the time they enter the line and speak with a human customer service representative.

[0053] In order to construct a mapping relationship between the user's queue status and customer service reception status at a certain moment and the user's actual queue time, the embodiment of the present disclosure needs to construct user profile features and customer service profile features respectively. At the same time, these features must be available at any time during the user's queue process. The feature definitions are as follows:

[0054] Queuing time: This is divided into hourly segments, and the time period during which users access the line is numbered. Because the time it takes for users to queue up varies during different time periods, for example, queuing in the early morning often takes more than 10 minutes due to the small number of available customer service representatives. Therefore, the queuing time period can affect the actual length of time users wait in line.

[0055] The user's queue number in the waiting queue: This is the sequence number of the current user in the waiting queue in the customer service system. The higher the queue number, the shorter the waiting time.

[0056] The user's queue number in the skill group to which they belong: Since users first navigate to the corresponding skill group through the system and queue under the skill group, the queue number under the skill group must be recorded. If the overall queue is large but the number of people queuing in the skill group is small, it indicates that the current incoming service is unevenly distributed. Users can still access the line in a shorter queue time in skill groups with fewer people in the queue.

[0057] The number of currently available agents in the skill group is a summary of the number of agents in the customer service system who are assigned to the skill group for this user's incoming calls. A higher number of agents means faster release of ongoing sessions and shorter user queue times.

[0058] Number of sessions being handled by customer service: This indicates the number of sessions currently being handled by customer service representatives who can handle currently queued users. A higher number of sessions indicates a higher probability of upcoming session releases, which shortens user queue times.

[0059] Skill group ID: When a user calls in, they are first navigated to the corresponding skill group through the system. Due to business differences and the number of customer service personnel, the queue time for different skill groups also varies. Therefore, this feature is also important for predicting user queue time.

[0060] In order to establish a mapping relationship between the user queue status and customer service reception status at a certain moment and the user's actual queue time, the embodiment of the present disclosure needs to construct a label of the user's actual queue time for model learning. Generally, you can bury points at the time when the user starts queuing and ends queuing, record the user's actual queue time, and use it as a label for model training data. However, when burying points is not performed, it is impossible to obtain the user's actual queue time. Therefore, it is necessary to construct a method to simulate the user's actual queue time as a label for model learning. The specific method is as follows: with minutes as the granularity, take the conversations that generate messages within each minute, assume that these message users enter the line at the beginning of one minute and queue up at the same time, then take the conversations that are happening at this moment, obtain the time from the actual end time of each conversation to the current moment, sort them according to the time length from small to large, and traverse the queued users and ongoing conversations in turn. If the customer service received by the ongoing conversation can receive the queued user's skill group, then the end time of this conversation is the waiting time of the current queued user, and so on. Theoretically, if the customer service representative has not grabbed the order, is not online or is on hold, and the upper limit of the connection mode has not been adjusted, then the queued user may only be connected after the current ongoing session ends.

[0061] The following example illustrates how to calculate the actual queuing time of a user, as shown in Table 1 below, which shows queue information of queuing users according to an embodiment of the present disclosure.

[0062] Table 1

[0063] Table 2 below shows the currently ongoing conversation queue, which mainly includes the customer service number (including the skill group information mounted by the customer service), the actual end time of the conversation (in seconds), and the matching queue user index.

[0064] Table 2

[0065] Combining Tables 1 and 2 above, we can see that the skill group that queued user 0 belongs to is not currently connected to any of the online agents. Therefore, this user cannot be connected until an agent who can handle this skill group comes online. This situation should indicate that the user's queue time is long or there is no agent available. This applies to users 1, 2, and 3. For queued user 4, agent A4-1006 is available to handle this skill group. Therefore, after the last call with this agent ends, this queued user can connect. Therefore, the actual session duration of 6 seconds represents this user's queue waiting time. For queued user 7, agent A3-1005 is available to handle this skill group. Therefore, after the last call with this agent ends, this queued user can connect. Therefore, the actual session duration of 5 seconds represents this user's queue waiting time.

[0066] Through the above introduction, the queue time corresponding to each session can be obtained. For each session, the queue time corresponding to the session is used to mark the session features corresponding to the session to generate training data corresponding to the session. Afterwards, model training is performed based on the training data corresponding to each session to construct a queue time estimation model. Specifically, in the embodiment of the present disclosure, when constructing the mapping relationship between the user queue status and customer service reception status and the real or simulated queue time, the GBDT (Gradient Boosting Decision Tree) regression algorithm can be used to train the queue time estimation model based on the aforementioned training data.

[0067] After building the queue time estimation model, the user's queue time can be predicted based on the user's corresponding queue period, the user's queue characteristics, the current number of available customer service representatives, and the number of sessions each customer service representative is handling.

[0068] According to another embodiment of the present disclosure, after predicting the user's queue time using a queue time estimation model, the method may further include: in response to a specified operation triggering an event by the user, re-obtaining the user's queue characteristics and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available agents and the number of sessions each agent is handling; and using the queue time estimation model to predict the user's queue time based on the user's queue characteristics, the currently available agents, and the number of sessions each agent is handling, thereby updating the user's queue time. The specified operation may be, for example, a click, swipe, return, or switch screen. When the user performs an event operation such as a click, swipe, return, or switch screen, the user's queue time prediction is triggered again. Because the estimated time may change at any time, for example, the initial estimated time is 3 minutes, but during the 3 minutes, the agent may leave for something, causing the queue time to increase, or the additional agent may shorten the estimated time. Recalculating based on the triggering of several events and obtaining more real-time features can make the estimated time more accurate.

[0069] According to another embodiment of the present disclosure, after using the queue time estimation model to predict the queue time of the user, it may also include: in response to detecting that a customer service has ended the session being processed and released resources, taking the queued user from the waiting queue and assigning it to the customer service, refreshing the waiting queue and updating the customer service status; when the customer service status is still that all customers are busy, re-acquiring the queue characteristics of the user and the customer service status characteristics of the skill group, the customer service status characteristics including the current number of available customers and the number of sessions being processed by each customer service; based on the queue characteristics of the user, the current number of available customers and the number of sessions being processed by each customer service, using the queue time estimation model to predict the queue time of the user to update the queue time of the user. When a customer service ends a session and releases resources, it triggers the system to update the waiting queue information and customer service status information, and assigns a new online customer service consultation task to the customer service. By updating the customer service status information and the waiting queue information, more accurate features can be provided to the algorithm, making the predicted queue time more accurate.

[0070] According to another embodiment of the present disclosure, the method may further include: if the customer service status indicates that a customer service representative is not busy, assigning the user to the customer service representative who is not busy. If a customer service representative is not busy, the user's online consultation request may be directly processed. Furthermore, while a user is in the queue, they may actively cancel the queue, at which point the process ends and the user's queue time no longer needs to be calculated.

[0071] Figure 2 is a schematic diagram of the process for predicting the online customer service consultation queue length according to one embodiment of the present disclosure. As shown in Figure 2, in the embodiment of the present disclosure, the process for predicting the online customer service consultation queue length is as follows: upon receiving a user's online customer service consultation request, it is determined that the customer has entered the line. Afterwards, the customer service status of the skill group is obtained, and based on the customer service status, it is determined whether there is an available customer service representative. If there is an available customer service representative, the online customer service consultation is directly initiated; otherwise, the user enters the waiting queue. Then, the user's queue characteristics and the customer service status characteristics of the skill group are obtained, and the queue length estimation model is used to predict the user's queue length, outputting the predicted queue length.

[0072] Afterwards, the system monitors whether the user has triggered a specified action event. If so, it re-executes the steps of obtaining the user's queue characteristics and the skill group's customer service status characteristics, using the queue duration estimation model to predict the user's queue duration, and outputting the predicted queue duration. Otherwise, it continuously monitors whether an agent has released resources. If an agent has released resources, the queued user is removed from the waiting queue and assigned to that agent. The waiting queue is then refreshed and the agent's status is updated. The system then re-executes the steps of obtaining the user's queue characteristics and the skill group's customer service status characteristics, using the queue duration estimation model to predict the user's queue duration, and outputting the predicted queue duration.

[0073] Figure 3 is a schematic diagram of the error in the prediction results of the queue duration according to the embodiment of the present disclosure. As shown in Figure 3, the horizontal axis shows the error result in seconds, and the vertical axis shows the percentile value. Using the queue duration prediction algorithm of the embodiment of the present disclosure for prediction, the average error of the prediction result is only 18.3 seconds. Among them, the error of the prediction result of the 25% percentile value is 2.8 seconds; the error of the prediction result of the 50% percentile value is 6.5 seconds; the error of the prediction result of the 75% percentile value is 15 seconds; the error of the prediction result of the 90% percentile value is 35.6 seconds; and the error of the prediction result of the 99% percentile value is 212 seconds.

[0074] It can be seen from this that using the queue duration prediction algorithm of the embodiment of the present disclosure to predict the queue duration greatly reduces the error of the prediction result, and the predicted queue duration is more accurate.

[0075] FIG4 is a schematic diagram of the main modules of the device for predicting the online customer service consultation queue length according to an embodiment of the present disclosure. As shown in FIG4 , the device for predicting the online customer service consultation queue length 400 according to the embodiment of the present disclosure mainly includes:

[0076] Status acquisition module 401 is used to determine the skill group corresponding to the user and obtain the customer service status of the skill group in response to receiving the user's online customer service consultation request;

[0077] The queue adding module 402 is configured to add the user to the waiting queue when the customer service status indicates that all customer service representatives are busy.

[0078] A feature acquisition module 403 is configured to acquire the user's queue characteristics and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available customer service representatives and the number of sessions being processed by each customer service representative.

[0079] The duration prediction module 404 is configured to use a queue duration estimation model to predict the queue duration of the user based on the queue characteristics of the user, the number of currently available customer service representatives, and the number of sessions being handled by each customer service representative.

[0080] According to one embodiment of the present disclosure, the user's queue characteristics include the user's queue number in the waiting queue and the user's queue number in the skill group. The duration prediction module 404 may also be configured to use a queue duration estimation model to predict the user's queue duration based on the user's queue number in the waiting queue, the user's queue number in the skill group, the number of currently available agents, and the number of sessions being handled by each agent.

[0081] According to another embodiment of the present disclosure, the online customer service consultation queuing time prediction device 400 also includes a queuing time period determination module (not shown in the figure), which is used to: determine the queuing time period corresponding to the user according to the sending time of the user's online customer service consultation request before using the queuing time prediction model to predict the user's queuing time based on the user's queuing characteristics, the currently available customer service staff and the number of sessions being processed by each customer service staff; the time prediction module 404 can also be used to: use the queuing time prediction model to predict the user's queuing time based on the queuing time period corresponding to the user, the user's queue number in the waiting queue and the user's queue number in the skill group, the currently available customer service staff and the number of sessions being processed by each customer service staff.

[0082] According to another embodiment of the present disclosure, the queuing time prediction model is constructed in the following manner: obtaining user online customer service consultation session data in a recent period; extracting session features corresponding to each session from the user online customer service consultation session data, the session features including the time of requesting online consultation, queuing period, skill group, the queue number of the user in the waiting queue and the queue number of the user in the skill group, the number of currently available customer service representatives of the skill group and the number of sessions being processed by each customer service representative, as well as the actual online consultation time; obtaining the queuing time corresponding to each session based on the time of requesting online consultation and the actual online consultation time corresponding to each session; for each session, using the queuing time corresponding to the session to mark the session features corresponding to the session to generate training data corresponding to the session; performing model training based on the training data corresponding to each session to construct the queuing time prediction model.

[0083] According to another embodiment of the present disclosure, the online customer service consultation queuing time prediction device 400 also includes a queuing time update module (not shown in the figure), which is used to: after using the queuing time prediction model to predict the queuing time of the user, in response to the user's specified operation trigger event, re-acquire the user's queuing characteristics and the customer service status characteristics of the skill group, the customer service status characteristics including the current number of available customer service staff and the number of sessions being handled by each customer service; based on the user's queuing characteristics, the current number of available customer service staff and the number of sessions being handled by each customer service, use the queuing time prediction model to predict the user's queuing time to update the user's queuing time.

[0084] According to another embodiment of the present disclosure, the online customer service consultation queuing time prediction device 400 also includes a queuing time update module (not shown in the figure), which is used to: after using the queuing time prediction model to predict the queuing time of the user, in response to detecting that a customer service has ended the session being processed and released resources, take the queued user out of the waiting queue and assign it to the customer service, refresh the waiting queue and update the customer service status; when the customer service status is still that all customer services are busy, re-acquire the user's queuing characteristics and the customer service status characteristics of the skill group, the customer service status characteristics include the current number of available customer services and the number of sessions being processed by each customer service; based on the user's queuing characteristics, the current number of available customer services and the number of sessions being processed by each customer service, use the queuing time prediction model to predict the user's queuing time to update the user's queuing time.

[0085] According to another embodiment of the present disclosure, the device 400 for predicting the waiting time of online customer service consultation also includes a customer service allocation module (not shown in the figure), which is used to: when the customer service status is that there is a customer service who is not busy, assign the user to the customer service who is not busy.

[0086] According to the technical solution of the embodiment of the present disclosure, by responding to the user's online customer service consultation request, the skill group corresponding to the user is determined, and the customer service status of the skill group is obtained; when the customer service status is that all customer service staff are busy, the user is added to the waiting queue; the user's queuing characteristics and the customer service status characteristics of the skill group are obtained, and the customer service status characteristics include the current number of available customer service staff and the number of sessions being handled by each customer service staff; according to the user's queuing characteristics, the current number of available customer service staff and the number of sessions being handled by each customer service staff, a queuing time estimation model is used to predict the user's queuing time. The technical solution can predict the current user's queuing time based on the status of the online customer service staff that can receive the user in the customer service system at the time the current user comes online, the status of the sessions being received by these customer service staff, and the queuing characteristics of the user, thereby greatly reducing the error of the prediction result and improving the prediction accuracy and prediction performance of the queuing time.

[0087] FIG5 shows an exemplary system architecture 500 to which the method for predicting the online customer service consultation queue length or the device for predicting the online customer service consultation queue length according to an embodiment of the present disclosure can be applied.

[0088] As shown in Figure 5, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0089] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, customer service consulting applications, instant messaging tools, social platform software, etc. (only as examples).

[0090] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0091] The server 505 may be a server that provides various services, such as a backend management server (for example only) that supports shopping websites browsed by users using terminal devices 501, 502, and 503. The backend management server may respond to data such as online customer service consultation requests received from users, determine the skill group corresponding to the user, and obtain the customer service status of the skill group; if the customer service status indicates that all customer service representatives are busy, add the user to a waiting queue; obtain the user's queuing characteristics and the customer service status characteristics of the skill group, the customer service status characteristics including the number of currently available customer service representatives and the number of sessions being handled by each customer service representative; use a queuing time estimation model to predict the user's queuing time based on the user's queuing characteristics, the currently available number of customer service representatives, and the number of sessions being handled by each customer service representative, and feed back the processing results (for example, the user's queuing time - for example only) to the terminal device.

[0092] It should be noted that the method for predicting the online customer service consultation queue length provided in the embodiment of the present disclosure is generally executed by the server 505. Accordingly, the device for predicting the online customer service consultation queue length is generally set in the server 505.

[0093] It should be understood that the number of terminal devices, networks and servers in Figure 5 is merely illustrative and any number of terminal devices, networks and servers may be provided as required.

[0094] 6, which shows a schematic diagram of a computer system 600 suitable for implementing a terminal device or server according to an embodiment of the present disclosure. The terminal device or server shown in FIG6 is merely an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0095] As shown in FIG6 , a computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the system 600 are also stored in the RAM 603. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0096] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.

[0097] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present disclosure are performed.

[0098] It should be noted that the computer-readable medium described in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0100] The units or modules involved in the embodiments described in the present disclosure may be implemented in software or in hardware. The units or modules described may also be provided in a processor. For example, they may be described as: a processor including a state acquisition module, a queue addition module, a feature acquisition module, and a duration prediction module. The names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves. For example, the duration prediction module may also be described as "a module for predicting the queuing duration of the user using a queuing duration prediction model based on the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative."

[0101] As another aspect, the present disclosure also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: in response to receiving an online customer service consultation request from a user, determining the skill group corresponding to the user and obtaining the customer service status of the skill group; when the customer service status is that all customer service staff are busy, adding the user to the waiting queue; obtaining the queuing characteristics of the user and the customer service status characteristics of the skill group, the customer service status characteristics including the current number of available customer service staff and the number of sessions being processed by each customer service staff; and using a queuing time estimation model to predict the queuing time of the user based on the queuing characteristics of the user, the current number of available customer service staff and the number of sessions being processed by each customer service staff.

[0102] According to the technical solution of the embodiment of the present disclosure, by responding to the user's online customer service consultation request, the skill group corresponding to the user is determined, and the customer service status of the skill group is obtained; when the customer service status is that all customer service staff are busy, the user is added to the waiting queue; the user's queuing characteristics and the customer service status characteristics of the skill group are obtained, and the customer service status characteristics include the current number of available customer service staff and the number of sessions being handled by each customer service staff; according to the user's queuing characteristics, the current number of available customer service staff and the number of sessions being handled by each customer service staff, a queuing time estimation model is used to predict the user's queuing time. The technical solution can predict the current user's queuing time based on the status of the online customer service staff that can receive the user in the customer service system at the time the current user comes online, the status of the sessions being received by these customer service staff, and the queuing characteristics of the user, thereby greatly reducing the error of the prediction result and improving the prediction accuracy and prediction performance of the queuing time.

[0103] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for predicting the length of online customer service consultation queue, comprising: In response to receiving an online customer service consultation request from a user, determining a skill group corresponding to the user, and obtaining a customer service status of the skill group; When the customer service status is that all customer service staff are busy, adding the user to a waiting queue; Obtaining the queuing characteristics of the user and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available customer service staff and the number of sessions being processed by each customer service staff; The queuing time estimation model is used to predict the queuing time of the user according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative.

2. The method according to claim 1, wherein: The queuing characteristics of the user include the queuing number of the user in the waiting queue and the queuing number of the user in the skill group; The queuing time of the user is predicted using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative, including: The queuing time estimation model is used to predict the queuing time of the user according to the queuing number of the user in the waiting queue and the queuing number of the user in the skill group, the number of currently available customer services and the number of sessions being handled by each customer service.

3. The method according to claim 2, wherein: Before predicting the queuing time of the user using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative, the method further includes: Determine the queuing time period corresponding to the user according to the sending time of the user's online customer service consultation request; The queuing time of the user is predicted using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative, including: The queuing time estimation model is used to predict the queuing time of the user according to the queuing time period corresponding to the user, the queuing number of the user in the waiting queue and the queuing number of the user in the skill group, the currently available number of customer service representatives and the number of sessions being handled by each customer service representative.

4. The method according to any one of claims 1 to 3, wherein: The queue duration estimation model is constructed in the following way: Get the user's online customer service consultation session data in the recent period; Extracting session features corresponding to each session from the user's online customer service consultation session data, the session features including the time of requesting online consultation, the queuing period, the skill group to which the user belongs, the queue number of the user in the waiting queue and the queue number of the user in the skill group to which the user belongs, the number of currently available customer services of the skill group to which the user belongs and the number of sessions being processed by each customer service, and the actual online consultation time; The queuing time corresponding to each session is obtained according to the requested online consultation time and the actual online consultation time corresponding to each session; For each session, use the queuing time corresponding to the session to mark the session features corresponding to the session to generate training data corresponding to the session; Model training is performed based on the training data corresponding to each session to build the queue duration estimation model.

5. The method according to claim 1, wherein: After predicting the queuing time of the user using the queuing time estimation model, the method further includes: In response to the user's designated operation triggering event, reacquire the user's queuing characteristics and the customer service status characteristics of the skill group, wherein the customer service status characteristics include the number of currently available customer service staff and the number of sessions being processed by each customer service staff; The queuing time of the user is predicted using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative, so as to update the queuing time of the user.

6. The method according to claim 1, wherein: After predicting the queuing time of the user using the queuing time estimation model, the method further includes: In response to detecting that a customer service has ended a session being processed and released resources, taking out a queued user from the waiting queue and assigning it to the customer service, refreshing the waiting queue and updating the customer service status; When the customer service status is still that all customer service staff are busy, re-acquire the queue characteristics of the user and the customer service status characteristics of the skill group, where the customer service status characteristics include the number of currently available customer service staff and the number of sessions being processed by each customer service staff; The queuing time of the user is predicted using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service representatives, and the number of sessions being processed by each customer service representative, so as to update the queuing time of the user.

7. The method according to claim 1, wherein: The method further comprises: When the customer service status is that there is a customer service that is not busy, the user is assigned to the customer service that is not busy.

8. A device for predicting the length of online customer service consultation queue, comprising: A status acquisition module, configured to determine the skill group corresponding to the user and acquire the customer service status of the skill group in response to receiving an online customer service consultation request from the user; A queue adding module, used for adding the user to the waiting queue when the customer service status is that all customer service staff are busy; A feature acquisition module, used to acquire the queuing features of the user and the customer service status features of the skill group, wherein the customer service status features include the number of currently available customer service staff and the number of sessions being processed by each customer service staff; The duration prediction module is used to predict the queuing time of the user using a queuing time estimation model according to the queuing characteristics of the user, the number of currently available customer service staff and the number of sessions being processed by each customer service staff.

9. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images