CN116109099A - Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium - Google Patents
Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN116109099A CN116109099A CN202310140779.6A CN202310140779A CN116109099A CN 116109099 A CN116109099 A CN 116109099A CN 202310140779 A CN202310140779 A CN 202310140779A CN 116109099 A CN116109099 A CN 116109099A
- Authority
- CN
- China
- Prior art keywords
- customer service
- user
- manual
- list
- dialogue information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063118—Staff planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
Abstract
The application discloses a customer service scheduling method, a customer service scheduling device, terminal equipment and a storage medium, wherein the customer service scheduling method comprises the following steps: acquiring first dialogue information of a user and a robot customer service; analyzing the first dialogue information to generate a corresponding manual customer service instruction; according to the manual customer service instruction, acquiring a free customer service list of the robot customer service; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
Description
Technical Field
The present disclosure relates to the field of intelligent scheduling technologies, and in particular, to a customer service scheduling method, a device, a terminal device, and a storage medium.
Background
In the process of enterprise digitization, the instant communication system becomes standard, so that the circulation speed of the information in the enterprise is greatly increased.
For the inside of enterprises, part of business, such as manpower, finance and the like, needs to accept a lot of consultations every day, but training manpower needs to consume a lot of resources, and the busy and idle states of business personnel are uneven and cannot be coordinated in time; for the consultant, multiple queries are needed, which is time-consuming and labor-consuming, so that the consultation of the user is not solved in time.
Therefore, a solution for solving the problem of high labor cost and low efficiency of business consultation is needed.
Disclosure of Invention
The main purpose of the application is to provide a customer service scheduling method, a customer service scheduling device, terminal equipment and a storage medium, and aims to solve the technical problems of high labor cost and low efficiency of business consultation.
In order to achieve the above object, the present application provides a customer service scheduling method, which includes:
acquiring first dialogue information of a user and a robot customer service;
analyzing the first dialogue information to generate a corresponding manual customer service instruction;
acquiring a free customer service list of the robot customer service according to the manual customer service instruction;
Scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service.
Optionally, the step of analyzing the first dialogue information and generating the corresponding manual customer service instruction includes:
analyzing the first dialogue information to obtain corresponding chat records and evaluation feedback;
distributing corresponding service channels according to the chat records;
and generating a corresponding manual customer service instruction according to the evaluation feedback and the service channel.
Optionally, the manual service includes one or more than one, and the step of scheduling the corresponding manual service based on the idle service list and a preset scheduling algorithm includes:
storing the user into a pre-created list to be supported;
detecting whether the artificial customer service exists in the idle customer service list;
if the artificial customer service exists, acquiring a user service relationship between the user and the artificial customer service based on the robot customer service;
and migrating the manual guest obeying the idle customer service list to a preset supported list.
Optionally, when receiving the manual customer service ending instruction, the customer service scheduling method further comprises the following steps:
judging whether the artificial customer service exists in the supported list or not;
and if the manual customer service exists in the supported list, deleting the relationship between the user and the customer.
Optionally, after the step of deleting the relationship between the user and the client, the method further includes:
detecting a requester of the manual customer service ending instruction;
and if the request person is the manual customer service, acquiring the next user of the user from the list to be supported.
Optionally, after the step of detecting whether the artificial customer service exists in the free customer service list, the method further includes:
if the manual customer service does not exist, acquiring questioning data of the user aiming at the first dialogue information;
and depositing the questioning data to a preset platform and grouping the questioning data to each supporting person, wherein the platform comprises one or more supporting persons.
Optionally, after the step of forwarding the first dialogue information to the artificial customer service and obtaining the second dialogue information of the user and the artificial customer service, the method further includes:
Extracting key semantics in the second dialogue information to obtain corresponding question-answer corpus;
and feeding back the question-answer corpus to the robot customer service to optimize the robot customer service.
The embodiment of the application also provides a customer service dispatching device, which comprises:
the first dialogue acquisition module is used for acquiring first dialogue information of customer service of a user and the robot;
the instruction generation module is used for analyzing the first dialogue information and generating a corresponding manual customer service instruction;
the list acquisition module is used for acquiring an idle customer service list of the robot customer service according to the manual customer service instruction;
the customer service scheduling module is used for scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and the second dialogue acquisition module is used for forwarding the first dialogue information to the artificial customer service and acquiring second dialogue information of the user and the artificial customer service.
The embodiment of the application also provides a terminal device, which comprises a memory, a processor and a customer service dispatcher stored on the memory and capable of running on the processor, wherein the customer service dispatcher realizes the steps of the customer service dispatching method when being executed by the processor.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a customer service scheduling program, and the customer service scheduling program realizes the steps of the customer service scheduling method when being executed by a processor.
The customer service scheduling method, the customer service scheduling device, the terminal equipment and the storage medium provided by the embodiment of the application are used for acquiring the first dialogue information of the customer service of the user and the robot; analyzing the first dialogue information to generate a corresponding manual customer service instruction; acquiring a free customer service list of the robot customer service according to the manual customer service instruction; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
Drawings
Fig. 1 is a schematic diagram of a functional module of a terminal device to which a customer service scheduling device of the present application belongs;
FIG. 2 is a schematic flow chart of a first exemplary embodiment of a customer service scheduling method according to the present application;
FIG. 3 is a block diagram of a customer service dispatch system according to the customer service dispatch method of the present application;
FIG. 4 is a flow chart of a customer service dispatch system construction of the customer service dispatch method of the present application;
FIG. 5 is a flow chart of a second exemplary embodiment of a customer service scheduling method of the present application;
FIG. 6 is a flow chart of a third exemplary embodiment of a customer service scheduling method of the present application;
FIG. 7 is a flow chart of manual customer service dispatch for the customer service dispatch method of the present application;
fig. 8 is a flowchart of a fourth exemplary embodiment of a customer service scheduling method of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The main solutions of the embodiments of the present application are: acquiring first dialogue information of a user and a robot customer service; analyzing the first dialogue information to generate a corresponding manual customer service instruction; acquiring a free customer service list of the robot customer service according to the manual customer service instruction; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
Technical terms related to embodiments of the present application:
load balancing, the english name Load Balance, means that loads (work tasks) are balanced and distributed to a plurality of operation units to run, such as an FTP server, a Web server, an enterprise core application server, and other main task servers, so as to cooperatively complete the work tasks. The load balancing is built on the original network structure, and the method is transparent, low in cost and effective, and can expand the bandwidth of the server and the network equipment, strengthen the data processing capacity of the network, increase the throughput and improve the usability and flexibility of the network.
NLP (natural language processing) technology, the key to processing natural language is to let a computer "understand" natural language, so natural language processing is also called natural language Understanding (NLU, naturalLanguage Understand), also called computational linguistics (Computational Linguistics). On the one hand, it is a branch of language information processing, and on the other hand, it is one of the core topics of artificial intelligence (AI, artificial Intelligence).
In the embodiment of the application, for the interior of an enterprise, part of services such as manpower, finance and the like still need to be accepted every day, but training manpower needs to consume a large amount of resources, and the busy and idle states of service personnel are uneven and cannot be coordinated in time; for the consultant, multiple queries are needed, which is time-consuming and labor-consuming, so that the consultation of the user is not solved in time.
Therefore, the scheme of the embodiment of the application designs a set of gradual customer service system construction strategy based on the instant messaging, the robot question-answering system and the online customer service system from the practical problems of reducing the labor cost of business consultation and improving the business consultation efficiency, and solves the technical problems of high labor cost and low efficiency of business consultation.
Specifically, referring to fig. 1, fig. 1 is a schematic functional block diagram of a terminal device to which a customer service scheduling apparatus of the present application belongs. The customer service dispatching device can be a device which is independent of the terminal equipment and can carry out customer service dispatching, and the device can be carried on the terminal equipment in a form of hardware or software. The terminal equipment can be an intelligent mobile terminal with a data processing function such as a mobile phone and a tablet personal computer, and can also be a fixed terminal equipment or a server with a data processing function.
In this embodiment, the terminal device to which the customer service scheduling apparatus belongs at least includes an output module 110, a processor 120, a memory 130, and a communication module 140.
The memory 130 stores an operating system and a customer service dispatcher, and the customer service dispatcher may send the acquired first dialogue information of the user and the robot customer service; analyzing the first dialogue information to generate a corresponding manual customer service instruction; according to the manual customer service instruction, an idle customer service list of the robot customer service is obtained; based on the idle customer service list and a preset scheduling algorithm, scheduling corresponding manual customer service; forwarding the first dialogue information to the artificial customer service, acquiring second dialogue information of the user and the artificial customer service, and storing the second dialogue information and the like in the memory 130; the output module 110 may be a display screen or the like. The communication module 140 may include a WIFI module, a mobile communication module, a bluetooth module, and the like, and communicates with an external device or a server through the communication module 140.
Wherein the customer service dispatcher in the memory 130 when executed by the processor performs the steps of:
acquiring first dialogue information of a user and a robot customer service;
analyzing the first dialogue information to generate a corresponding manual customer service instruction;
acquiring a free customer service list of the robot customer service according to the manual customer service instruction;
scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
analyzing the first dialogue information to obtain corresponding chat records and evaluation feedback;
distributing corresponding service channels according to the chat records;
and generating a corresponding manual customer service instruction according to the evaluation feedback and the service channel.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
storing the user into a pre-created list to be supported;
detecting whether the artificial customer service exists in the idle customer service list;
If the artificial customer service exists, acquiring a user service relationship between the user and the artificial customer service based on the robot customer service;
and migrating the manual guest obeying the idle customer service list to a preset supported list.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
judging whether the artificial customer service exists in the supported list or not;
and if the manual customer service exists in the supported list, deleting the relationship between the user and the customer.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
detecting a requester of the manual customer service ending instruction;
and if the request person is the manual customer service, acquiring the next user of the user from the list to be supported.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
if the manual customer service does not exist, acquiring questioning data of the user aiming at the first dialogue information;
and depositing the questioning data to a preset platform and grouping the questioning data to each supporting person, wherein the platform comprises one or more supporting persons.
Further, the customer service dispatcher in the memory 130 when executed by the processor also performs the steps of:
extracting key semantics in the second dialogue information to obtain corresponding question-answer corpus;
and feeding back the question-answer corpus to the robot customer service to optimize the robot customer service.
According to the scheme, the first dialogue information of the customer service of the user and the robot is obtained; analyzing the first dialogue information to generate a corresponding manual customer service instruction; acquiring a free customer service list of the robot customer service according to the manual customer service instruction; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
Based on the above terminal device architecture, but not limited to the above architecture, the method embodiments of the present application are presented.
Referring to fig. 2, fig. 2 is a flowchart of a first exemplary embodiment of a customer service scheduling method according to the present application. The customer service scheduling method comprises the following steps:
step S210, acquiring first dialogue information of customer service of a user and a robot;
the execution main body of the method of the embodiment may be a customer service scheduling device, or may be a customer service scheduling terminal device or a server, and the customer service scheduling device is used for example in the embodiment, and the customer service scheduling device may be integrated on a terminal device such as a smart phone, a tablet computer, etc. with a data processing function.
The scheme of the embodiment mainly realizes the customer service scheduling, especially the progressive customer service scheduling, and designs a set of progressive customer service system construction strategy based on the instant messaging, the robot question answering system and the online customer service system from the practical problems of reducing the labor cost of business consultation and improving the business consultation efficiency, thereby solving the technical problems of high labor cost and low efficiency of business consultation.
In this embodiment, a customer service scheduling system is used to schedule customer service, referring to fig. 3, fig. 3 is a structural diagram of the customer service scheduling system related to the customer service scheduling method in this application, where the structural diagram of the customer service scheduling system includes: a configuration center module, a data module and a load balancing module; the configuration center module comprises a question and answer management capability layer, a question and answer data engine layer and a question and answer operation capability layer; the data module is used for acquiring data by, but not limited to, the following software: mysql Mgr, redis, elasticSearch, mongoDB, etc.
Specifically, the customer service includes a manual customer service and a robot customer service. When the user needs business consultation, the user requests customer service or dials customer service voice through a chat dialog box at the front end of the system, so that the customer service dispatching system is accessed into the robot customer service in advance, the user firstly asks the robot customer service, and the robot customer service calls a knowledge base and searches for corresponding answers, so that the questions of most users can be solved.
Step S220, analyzing the first dialogue information to generate a corresponding manual customer service instruction;
specifically, the first dialogue information is user and robot customer service dialogue information including but not limited to chat logs, rating feedback, and the like. And judging whether the user needs manual customer service intervention business consultation or not according to the dialogue information analysis and the target experience evaluation result of the user. If the first dialogue information is detected to need manual customer service to intervene, a manual customer service instruction is generated at the front end of the system. The manual customer service instruction carries first dialogue information.
Step S230, acquiring a free customer service list of the robot customer service according to the manual customer service instruction;
it should be noted that, in the embodiment of the present application, one or more than one robot customer service is included, one robot customer service corresponds to one manual customer service, one user may correspond to a plurality of robot customer services, and a plurality of robot customer services may exist in the same dialog box or the same customer service voice call, that is, a plurality of manual customer services may exist in the same dialog box or the same customer service voice call, so that for a user aspect, only one robot customer service and one manual customer service, or only one robot customer service and a plurality of manual customer services, so that experience feeling of user consultation may be improved.
Specifically, the free customer service list is used for storing the manual customer service with the current state free. The first dialogue information carried in the manual customer service instruction is analyzed, so that the service information consulted by the user can be obtained, manual customer service corresponding to the service can be inquired according to the service information, further manual customer service in an idle state can be screened out, namely the supported manual customer service can be selected, and the identifier of the supportable manual customer service is placed in an idle customer service list, so that the corresponding manual customer service can be scheduled according to the identifier in the idle customer service list.
Step S240, scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
specifically, when the system rear end receives the manual customer service instruction, a dispatching algorithm of the customer service dispatching system is executed, the busy and idle conditions of the current manual customer service are comprehensively balanced, whether the manual customer service available for distribution exists or not is judged, if the supportable manual customer service exists, a channel option is provided, and the manual customer service is led to intervene in the current consultation flow.
Step S250, forwarding the first dialogue information to the artificial customer service, and obtaining second dialogue information of the user and the artificial customer service.
Specifically, the second dialogue information is dialogue information between the user and the human customer service, including but not limited to chat records, evaluation feedback, and the like. When the manual customer service flow is initiated, the system automatically sorts the first dialogue information between the user and the robot, and combines and forwards the first dialogue information to a dialogue window or a dialogue group window of the manual customer service, so that the information acquisition complexity of the manual customer service is reduced. Therefore, repeated questioning and manual customer service checking difficulties of the user can be reduced, and the working efficiency is further improved.
Further, referring to fig. 4, fig. 4 is a flowchart of a customer service dispatching system construction of the customer service dispatching method of the present application. The method comprises the following specific steps of:
(1) the system is accessed into the robot customer service in advance, and the user firstly dialogues with the robot customer service, and solves the questioning of most users by using rich knowledge base. (2) And judging whether manual customer service intervention is needed or not according to dialogue information analysis and target experience evaluation results of the user. (3) If manual customer service intervention is needed, a dispatching algorithm of a customer service system is executed, the busy and idle conditions of the current manual customer service are comprehensively balanced, and if the available allocation personnel exist, channel options are provided, so that the manual customer service is involved in the current consultation flow. (4) Before providing customer service channel options, a single chat customer service mode or a group customer service mode can be selected to be initiated according to user preference, the group mode ensures the problem solving speed of questioners under the condition of wide problem involvement, and the user experience is optimized. (5) When the customer service flow is initiated, chat replies of the user and the robot are automatically tidied, and are combined and forwarded to the manual customer service or the group, so that the information acquisition complexity of the manual customer service is reduced. (6) If no customer service exists at present, a user question request is precipitated to a system platform, various support staff are widely distributed, and solutions of informed support staff are sought. (7) After the customer service process is finished, customer service dialogue data are collected, key semantic components are extracted to form question-answer corpus, the question-answer corpus is fed back to the robot customer service system, the richness of a language source is improved, and the question-answer capability of the robot customer service is enhanced.
According to the scheme, the first dialogue information of the customer service of the user and the robot is obtained; analyzing the first dialogue information to generate a corresponding manual customer service instruction; acquiring a free customer service list of the robot customer service according to the manual customer service instruction; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
Referring to fig. 5, fig. 5 is a schematic flow chart of a second exemplary embodiment of a customer service scheduling method of the present application. Based on the embodiment shown in fig. 2, step S220 is to analyze the first session information to generate a corresponding manual service instruction, including:
Step S510, analyzing the first dialogue information to obtain corresponding chat records and evaluation feedback;
for most users, business consultation needs to be subjected to multiple interrogation, which is time-consuming and labor-consuming; for the inside of enterprises, training manpower needs to consume a lot of resources, and there are differences in part of human cognition. Therefore, the embodiment of the application starts from the complexity of service consultation, and provides a collaborative work mechanism of user evaluation feedback and customer service flow, so that the complexity of service consultation is reduced.
Specifically, the current service requirement of the user can be determined by analyzing the dialogue information of the user and the robot customer service to obtain chat records and evaluation feedback in the dialogue information.
Step S520, distributing corresponding service channels according to the chat records;
specifically, the chat log contains keywords of the business to be consulted by the user. The service channels are used to divide different services. Corresponding service channels are determined according to the chat records, and then manual customer service of corresponding services is distributed, so that users can be quickly and accurately matched with the corresponding manual customer service of the services without multiple interrogation, different service channels are divided in enterprises, and the cost of training manpower is reduced.
And step S530, generating a corresponding manual customer service instruction according to the evaluation feedback and the service channel.
Specifically, the evaluation feedback may be a score of the user on the robot customer service, may be feedback information of requesting the manual customer service, or may be preference bias of the user. In addition, before providing customer service channel options, the user can choose to initiate a single chat customer service or group customer service mode according to user preference bias, and the group mode ensures the problem solving speed of questioners under the condition of wide problem involvement, and optimizes user experience.
Further, the specific step of converting the robot customer service into the manual customer service can comprise the following steps: when the system receives an instruction, judging the type of the instruction; if the instruction is a non-customer service instruction, calling a question and answer engine to search, and if a corresponding answer exists, generating corresponding information to push to a user; if the instruction is a manual customer service instruction, judging whether a free manual customer service exists in the free customer service list so as to acquire free customer service information; if the idle manual customer service exists, a corresponding user request is generated to push the manual customer service; if no free manual customer service exists, putting the user into a waiting queue; if the instruction is a manual customer service ending instruction, the temporary data of the customer service flow is clear, and the user is thrown out of the waiting queue to be provided for the manual customer service for supporting.
According to the scheme, the corresponding chat records and evaluation feedback are obtained by analyzing the first dialogue information; distributing corresponding service channels according to the chat records; and generating a corresponding manual customer service instruction according to the evaluation feedback and the service channel. By analyzing the dialogue information of the user and the robot customer service, the business required by the user is determined, the technical problem that the user needs to be subjected to multiple interrogation and the internal training of the enterprise needs to consume a large amount of resources in business consultation is solved, the matching degree of the business consultation and the manual customer service is improved, and the business consultation efficiency is further improved.
Referring to fig. 6, fig. 6 is a flowchart of a third exemplary embodiment of a customer service scheduling method according to the present application. Based on the embodiment shown in fig. 2, the manual service includes one or more than one positions, and step S240, based on the idle service list and a preset scheduling algorithm, schedules a corresponding manual service, including:
step S610, storing the user into a pre-created list to be supported;
in the business consultation process, because the information is limited, the business support personnel are busy and idle unevenly, and the way of people to find people cannot be coordinated in time, so that the problem of users cannot be solved in the first time. Therefore, the embodiment of the application starts from the problem of timely responding to business consultation, proposes a busy and idle analysis and scheduling allocation strategy of the customer service system, solves the technical problem that manual customer service is difficult to coordinate timely, and further improves the efficiency of business consultation.
Referring to fig. 7, fig. 7 is a flow chart of manual customer service dispatching in the customer service dispatching method of the present application. Specifically, the list to be supported is used to determine the users who need to request manual customer service. When the manual customer service instruction is received, the user corresponding to the manual customer service instruction can be analyzed, and then the identification of the user is stored in the to-be-supported list, so that the user who needs to request the manual customer service is determined.
Step S620, detecting whether the artificial customer service exists in the free customer service list;
specifically, because the working state of the artificial customer service can generate the situation of uneven busy line, whether the assignable artificial customer service corresponding to the service exists or not is determined by detecting whether the assignable artificial customer service exists in the idle customer service list.
Step S630, if the artificial customer service exists, acquiring a user customer service relationship between the user and the artificial customer service based on the robot customer service;
specifically, the user customer service relationship is a unique identifier between a user and a human customer service of a corresponding service. The user obtains the manual customer service of the corresponding service through the robot customer service, and a corresponding user customer service relationship is generated, namely, a unique index between the user and the manual customer service can be generated by binding the identification of the robot customer service with the identification of the manual customer service, so that the corresponding manual customer service can be found through the identification of the robot customer service according to the user customer service relationship.
Further, in step S620, after detecting whether the manual service exists in the free service list, the method further includes:
if the manual customer service does not exist, acquiring questioning data of the user aiming at the first dialogue information; and depositing the questioning data to a preset platform and grouping the questioning data to each supporting person, wherein the platform comprises one or more supporting persons.
Specifically, the support personnel are the personnel related to the business consultation, and can also be the artificial customer service. When the system cannot be matched with the manual customer service of the service corresponding to the user or the manual customer service is difficult to answer the service consultation, related support personnel can be requested to the superior or other departments. All support personnel are included in the platform. The platform is used for precipitating the question request of the user to the platform and widely distributing various support staff to seek the solutions of the informed support staff when the fact that no assignable artificial customer service exists in the current idle artificial customer service list is detected. In addition, the system packages the information of the working state of the manual customer service and sends the information to the front end of the system so as to inform the user that the working state of the manual customer service is busy at present.
Step S640, migrating the artificial guest obeying the idle customer service list to a preset supported list.
Specifically, the supported list is used for storing manual service that has responded to the user request, that is, service in a busy state. When the working state of the artificial customer service is determined to be idle, migrating the information or the identifier of the artificial customer service from the idle customer service list to a supported list, that is, executing step S640 to indicate that the corresponding artificial customer service is successfully scheduled, so that the user enters the process of the artificial customer service. Therefore, one manual customer service corresponds to one user, and when the manual customer service supports business consultation of the user, other users request for scheduling at the same time, so that the error rate of customer service scheduling is reduced.
Further, when receiving a manual customer service ending instruction, the customer service scheduling method further comprises the following steps:
step S650, determining whether the artificial customer service exists in the supported list;
step S660, if the manual service exists in the supported list, deleting the relationship between the user and the client.
Specifically, the manual service ending instruction is used for ending the current manual service consultation. Because the user can have the situation of false touch, when receiving the manual customer service ending instruction, detecting whether the manual customer service exists in the supported list, and deleting the corresponding data of the relation between the user and the customer service and the dialogue list relation data if the manual customer service exists in the supported list, namely, if the user is in the manual customer service flow.
If the user does not exist in the manual customer service flow, setting that the answer user does not enter the manual customer service flow.
It should be noted that, the steps S650 to S660 may be any step between the steps S210 to S240 or the steps S610 to S640.
Wherein the user customer service relationship includes a unique index between the robot customer service identifier and the human customer service identifier and a current status value including, but not limited to, support, supportable, idle, unavailable, conversational, etc. The conversation listing relationship includes a unique index between a user identification, a robot service identification, and a human service identification.
Further, in step S660, if the manual service exists in the supported list, deleting the relationship between the user and the client further includes:
detecting a requester of the manual customer service ending instruction; and if the request person is the manual customer service, acquiring the next user of the user from the list to be supported.
Specifically, the requesting person is the person who initiated the manual customer service end instruction. The method comprises the steps of detecting whether a request person is artificial customer service, if so, modifying the state of a user into a supportable state through the artificial customer service, informing the user that the artificial customer service process is finished, throwing one person from a to-be-supported list, and requesting the user to support; if the requester is not the manual customer service, directly informing the user that the manual customer service process is finished;
Then, aiming at the customer service relationship associated with the applicant, judging whether the person bound with the applicant is a supporting person or not; if the user is a support person, the support person is used for modifying the state of the user into a supportable state, and informing the user that the manual customer service flow is finished, and one person is thrown out of the list to be supported to request the user to support.
And finally setting the answer type, so that when the subsequent message requesting support is sent to the manual customer service, the manual customer service does not process the message any more.
The embodiment stores the user into a pre-created list to be supported through the scheme; detecting whether the artificial customer service exists in the idle customer service list; if the artificial customer service exists, acquiring a user service relationship between the user and the artificial customer service based on the robot customer service; and migrating the manual guest obeying the idle customer service list to a preset supported list. Judging whether the artificial customer service exists in the supported list or not; and if the manual customer service exists in the supported list, deleting the relationship between the user and the customer. The user customer service relationship is generated to schedule corresponding manual customer service, so that a single chat mode or a group chat mode is realized, and the matching degree of business consultation can be improved; by deleting the customer service relation data and the dialogue list relation data, the running memory of the system can be reduced, and the customer service dispatching efficiency is improved.
Referring to fig. 8, fig. 8 is a flowchart of a fourth exemplary embodiment of a customer service scheduling method according to the present application. Based on the embodiment shown in fig. 2, step S250, after forwarding the first session information to the artificial customer service and obtaining the second session information of the user and the artificial customer service, further includes:
step 810, extracting key semantics in the second dialogue information to obtain a corresponding question-answer corpus;
because of the limitation of the natural language processing technology (NLP) effect in the industry, the accuracy of the current robot question and answer has a bottleneck, and only the problem of partial business consultation can be solved. Therefore, the embodiment of the application starts from low accuracy of the robot customer service questions and answers, proposes a data feedback and back feeding mechanism, realizes the closed loop of the robot questions and answers system, and enhances the automatic response capability of the system.
Specifically, the question-answer corpus is a corpus with keywords or features in the first dialogue information and the second dialogue information. After the business consultation is finished, the system records the first dialogue information and the second dialogue information, and automatically extracts the key dialogue information to form a question-answer corpus, and further feeds back a knowledge base, so that the automatic question-answer capability is improved. The key semantics of the first dialogue information and the second dialogue information are extracted through a data analysis system, the specific step of extracting the key semantics can be achieved through data acquisition, association analysis, similarity calculation, result arrangement and finally the key semantics are obtained.
Step S820, feeding back the question-answer corpus to the robot customer service to optimize the robot customer service.
Specifically, after the key semantic components are extracted to form a question-answer corpus, the question-answer corpus is fed back to the robot customer service system, so that the robot customer service is optimized, the richness of a language source is improved, and the question-answer capability of the robot customer service is enhanced.
According to the scheme, the corresponding question-answer corpus is obtained by extracting key semantics in the second dialogue information; and feeding back the question-answer corpus to the robot customer service to optimize the robot customer service. After the service questioning is finished, relevant data of the process are analyzed, key corpus of the process is extracted, and the back feeding robot customer service knowledge base is used for enhancing the automatic response capability of the system. Thereby reducing the labor cost of business consultation and improving the efficiency of business consultation.
In addition, the embodiment of the application also provides a customer service dispatching device, which comprises:
the first dialogue acquisition module is used for acquiring first dialogue information of customer service of a user and the robot;
the instruction generation module is used for analyzing the first dialogue information and generating a corresponding manual customer service instruction;
The list acquisition module is used for acquiring an idle customer service list of the robot customer service according to the manual customer service instruction;
the customer service scheduling module is used for scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and the second dialogue acquisition module is used for forwarding the first dialogue information to the artificial customer service and acquiring second dialogue information of the user and the artificial customer service.
The principle and implementation process of customer service scheduling are realized in this embodiment, please refer to the above embodiments, and are not repeated here.
In addition, the embodiment of the application also provides a terminal device, which comprises a memory, a processor and a customer service dispatcher stored on the memory and capable of running on the processor, wherein the customer service dispatcher realizes the steps of the customer service dispatching method when being executed by the processor.
Because the customer service scheduler is executed by the processor and adopts all the technical schemes of all the embodiments, the customer service scheduler at least has all the beneficial effects brought by all the technical schemes of all the embodiments and is not described in detail herein.
In addition, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a customer service dispatcher, and the customer service dispatcher realizes the steps of the customer service dispatching method when being executed by a processor.
Because the customer service scheduler is executed by the processor and adopts all the technical schemes of all the embodiments, the customer service scheduler at least has all the beneficial effects brought by all the technical schemes of all the embodiments and is not described in detail herein.
Compared with the prior art, the customer service scheduling method, the customer service scheduling device, the terminal equipment and the storage medium provided by the embodiment of the application are used for acquiring the first dialogue information of customer service and robot customer service; analyzing the first dialogue information to generate a corresponding manual customer service instruction; acquiring a free customer service list of the robot customer service according to the manual customer service instruction; scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm; and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service. By establishing a strategy for reasonably scheduling and distributing the robot customer service and the manual customer service, namely, in the process of initiating a question with the robot customer service by a user, the current evaluation feedback information of the user is analyzed in real time, and the corresponding manual customer service is distributed for the user by combining the current working state of the manual customer service, the current user quantity and other dynamic data, so that the technical problems of high labor cost and low efficiency of business consultation are solved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a bit … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a one-bit storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to perform the method of each embodiment of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. The customer service dispatching method is characterized by comprising the following steps of:
acquiring first dialogue information of a user and a robot customer service;
analyzing the first dialogue information to generate a corresponding manual customer service instruction;
acquiring a free customer service list of the robot customer service according to the manual customer service instruction;
scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and forwarding the first dialogue information to the artificial customer service to acquire second dialogue information of the user and the artificial customer service.
2. The customer service dispatch method of claim 1, wherein the step of analyzing the first dialogue information to generate a corresponding manual customer service instruction comprises:
analyzing the first dialogue information to obtain corresponding chat records and evaluation feedback;
Distributing corresponding service channels according to the chat records;
and generating a corresponding manual customer service instruction according to the evaluation feedback and the service channel.
3. The customer service scheduling method as defined in claim 1, wherein the manual customer service includes one or more than one, and the step of scheduling the corresponding manual customer service based on the free customer service list and a preset scheduling algorithm includes:
storing the user into a pre-created list to be supported;
detecting whether the artificial customer service exists in the idle customer service list;
if the artificial customer service exists, acquiring a user service relationship between the user and the artificial customer service based on the robot customer service;
and migrating the manual guest obeying the idle customer service list to a preset supported list.
4. A customer service scheduling method as defined in claim 3, wherein upon receiving a manual customer service end instruction, the customer service scheduling method further comprises the steps of:
judging whether the artificial customer service exists in the supported list or not;
and if the manual customer service exists in the supported list, deleting the relationship between the user and the customer.
5. The customer service scheduling method of claim 4, wherein after the step of deleting the user-to-customer relationship, further comprising:
Detecting a requester of the manual customer service ending instruction;
and if the request person is the manual customer service, acquiring the next user of the user from the list to be supported.
6. A customer service scheduling method according to claim 3, wherein after the step of detecting whether the artificial customer service exists in the free customer service list, the method further comprises:
if the manual customer service does not exist, acquiring questioning data of the user aiming at the first dialogue information;
and depositing the questioning data to a preset platform and grouping the questioning data to each supporting person, wherein the platform comprises one or more supporting persons.
7. The customer service scheduling method as defined in claim 1, wherein after the step of forwarding the first dialogue information to the artificial customer service to obtain the second dialogue information between the user and the artificial customer service, the method further comprises:
extracting key semantics in the second dialogue information to obtain corresponding question-answer corpus;
and feeding back the question-answer corpus to the robot customer service to optimize the robot customer service.
8. A customer service scheduling device, characterized in that the customer service scheduling device comprises:
The first dialogue acquisition module is used for acquiring first dialogue information of customer service of a user and the robot;
the instruction generation module is used for analyzing the first dialogue information and generating a corresponding manual customer service instruction;
the list acquisition module is used for acquiring an idle customer service list of the robot customer service according to the manual customer service instruction;
the customer service scheduling module is used for scheduling corresponding manual customer service based on the idle customer service list and a preset scheduling algorithm;
and the second dialogue acquisition module is used for forwarding the first dialogue information to the artificial customer service and acquiring second dialogue information of the user and the artificial customer service.
9. A terminal device, characterized in that it comprises a memory, a processor and a service scheduler stored on the memory and operable on the processor, which service scheduler, when executed by the processor, implements the steps of the service scheduling method according to any of claims 1-7.
10. A computer readable storage medium, wherein a customer service scheduler is stored on the computer readable storage medium, which when executed by a processor implements the steps of the customer service scheduling method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310140779.6A CN116109099A (en) | 2023-02-14 | 2023-02-14 | Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310140779.6A CN116109099A (en) | 2023-02-14 | 2023-02-14 | Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116109099A true CN116109099A (en) | 2023-05-12 |
Family
ID=86254105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310140779.6A Pending CN116109099A (en) | 2023-02-14 | 2023-02-14 | Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109099A (en) |
-
2023
- 2023-02-14 CN CN202310140779.6A patent/CN116109099A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109873909B (en) | Voice calling method, device and equipment and computer storage medium | |
| CN105592237B (en) | A kind of method, apparatus and intelligent customer service robot of session switching | |
| CN104754153B (en) | Customer service system and its customer service method | |
| CN111489095A (en) | Risk user management method and device, computer equipment and storage medium | |
| CN111831799A (en) | Information processing method, information processing apparatus, and information processing system | |
| CN114372130A (en) | Online customer service system based on intelligent voice question answering | |
| CN109977216A (en) | Dialogue recommended method and system based on scene | |
| CN111031185A (en) | Agent allocation method based on artificial intelligence navigation and related device | |
| CN111080234A (en) | Heuristic dialogue recruitment method and system | |
| WO2022104266A1 (en) | Machine learning system for routing optimization based on historical performance data | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN115982331A (en) | Information interaction method, device and equipment in session scene | |
| CN113806503A (en) | Dialog fusion method, device and equipment | |
| KR20110048675A (en) | Call center counsel method and counsel system using voice recognition and tagging | |
| CN111552793A (en) | Voice outbound method, device, terminal equipment and medium based on outbound robot | |
| CN113221005B (en) | Customer service pushing method, server and related products | |
| CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
| CN116595148B (en) | Method and system for realizing dialogue flow by using large language model | |
| CN116414955B (en) | Intelligent queuing method, device, equipment and medium based on client intention and intention | |
| CN116109099A (en) | Customer service scheduling method, customer service scheduling device, terminal equipment and storage medium | |
| CN114851210B (en) | Robot scheduling method based on cloud platform and scheduling cloud platform | |
| Kask et al. | Augmenting Digital Customer Touchpoints-Best Practices for Transforming Customer Experience Through Conversational AI | |
| US7356712B2 (en) | Method of dynamically assigning network access priorities | |
| CN113379229A (en) | Resource scheduling method and device | |
| CN111046151A (en) | Message processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |