CN111932144A

CN111932144A - Customer service seat allocation method, customer service seat allocation device, server and storage medium

Info

Publication number: CN111932144A
Application number: CN202010864488.8A
Authority: CN
Inventors: 殷腾飞
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shanghai Co Ltd
Priority date: 2020-08-25
Filing date: 2020-08-25
Publication date: 2020-11-13
Anticipated expiration: 2040-08-25
Also published as: CN111932144B

Abstract

The application provides a customer service seat allocation method, a customer service seat allocation device, a server and a storage medium, and the customer service seat allocation method, the customer service seat allocation device, the server and the storage medium receive a consultation problem sent by a client and determine text information representing the consultation problem; the text information is classified based on the pre-trained customer service seat allocation model to determine a candidate customer service mode for providing the consulting service for the client, so that the problem of inaccurate customer service seat allocation caused by the dependence on the corresponding relation between keywords and the customer service seats in the prior art is solved; and when the candidate customer service seat transfers the customer to the target customer service seat, the optimization of the customer service seat distribution model is automatically realized based on the target customer service seat and the consultation problem, so that the accuracy of the subsequent customer service seat distribution based on the customer service seat distribution model is improved, the accurate recommendation of the customer service seat is realized, and the convenience of the later maintenance of the customer service seat distribution method is improved.

Description

Customer service seat allocation method, customer service seat allocation device, server and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for distributing customer service seats, a server and a storage medium.

Background

In an Instant Messaging (IM) product, customer service agent allocation is a crucial part in a pre-sale marketing/after-sale service scene, and the accuracy of customer service agent allocation directly affects the efficiency of the customer service agent in solving the customer consultation problem.

The traditional customer service seat distribution mode is that the customer service seats are distributed according to the busy state of the customer service seats so as to achieve the balance of the number of customers to be served by each customer service seat, only the number of the customers to be served by the customer service seats is concerned, and the consultation problem which is handled by the customer service seats with great strength is not considered, so that the condition that the customer service seats cannot answer the consultation problem often exists, and the distribution accuracy of the customer service seats is low.

The existing customer service seat allocation mode is to preset the corresponding relation between keywords and customer service seats, acquire the keywords contained in the consultation problem sent by the client and allocate the customer service seats corresponding to the keywords in the consultation problem to the client. Although the mode can play the advantages and different business familiarity of each customer service seat to a certain extent, the distribution of the customer service seats is relatively rigid and inconvenient for later maintenance depending on the setting of the corresponding relation between the keywords and the customer service seats; moreover, if the problem which is handled by the customer service seat is changed and the corresponding relation between the keywords and the customer service seat is not updated in time, the condition that the customer service seat is not accurately allocated can be caused; moreover, the same meaning has a plurality of different description modes, and the keywords are usually difficult to be completely configured, which also affects the precision degree of customer service seat distribution.

Disclosure of Invention

In view of this, the present application provides a method, an apparatus, a server and a storage medium for customer service agent allocation, so as to improve the accuracy of customer service agent allocation and the convenience of post-maintenance. The technical scheme is as follows:

a customer service agent allocation method comprises the following steps:

receiving a consultation problem sent by a client, and determining text information representing the consultation problem;

classifying the text information according to a pre-trained customer service seat distribution model to determine candidate customer service seats for providing consultation services for the client in at least one customer service seat;

pushing the consultation problem to the candidate customer service seat;

responding to the feedback information of the candidate customer service seat to the consultation problem to determine a target customer service seat for providing consultation service for the client;

and if the target customer service seat and the candidate customer service seat are not the same customer service seat, optimizing the customer service seat distribution model based on the consultation problem and the training sample constructed by the target customer service seat.

A customer service agent distribution device comprising:

the system comprises a consultation problem receiving unit, a consultation problem analyzing unit and a consultation question analyzing unit, wherein the consultation problem receiving unit is used for receiving a consultation problem sent by a client and determining text information representing the consultation problem;

the candidate customer service seat determining unit is used for classifying the text information according to a pre-trained customer service seat distribution model to determine candidate customer service seats used for providing consultation services for the client in at least one customer service seat;

the consultation problem pushing unit is used for pushing the consultation problem to the candidate customer service seat;

the target customer service seat determining unit is used for responding to the feedback information of the candidate customer service seats to the consultation problem to determine a target customer service seat for providing consultation service for the client;

and the optimization unit is used for optimizing the customer service seat distribution model based on the consultation problem and the training sample constructed by the target customer service seat if the target customer service seat and the candidate customer service seat are not the same customer service seat.

A server, comprising: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used for realizing the customer service seat allocation method.

A computer-readable storage medium having stored thereon computer-executable instructions for performing the customer service agent allocation method.

The embodiment of the application provides a customer service agent allocation method, a customer service agent allocation device, a server and a storage medium, wherein a consultation problem sent by a client is received, text information representing the consultation problem is determined, and the text information is classified and processed based on a pre-trained customer service agent allocation model to determine a candidate customer service mode for providing consultation service for the client, so that the problem of inaccurate customer service agent allocation caused by the dependence on the corresponding relation between keywords and customer service agents in the prior art is solved; and when the candidate customer service seat transfers the customer to the target customer service seat, the optimization of the customer service seat distribution model is automatically realized based on the target customer service seat and the consultation problem, so that the accuracy of subsequent customer service seat distribution based on the customer service seat distribution model is improved, and the convenience of later maintenance of the customer service seat distribution method provided by the embodiment of the application is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic diagram of a customer service agent distribution system according to an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of another customer service agent distribution system according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of another customer service agent distribution system according to an embodiment of the present disclosure;

fig. 4 is a flowchart of a method for generating a customer service agent allocation model according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a method for generating a customer service agent allocation model according to an embodiment of the present application;

FIG. 6 is a schematic diagram illustrating an intelligent customer service distribution process according to an embodiment of the present disclosure;

fig. 7 is a schematic diagram of a method for automatically correcting a customer service seat assignment model according to an embodiment of the present application;

fig. 8 is a flowchart of a method for allocating customer service agents according to an embodiment of the present disclosure;

fig. 9 is a schematic diagram illustrating a method for allocating customer service agents according to an embodiment of the present disclosure;

fig. 10 is a schematic diagram illustrating another method for allocating customer service agents according to an embodiment of the present disclosure;

fig. 11 is a schematic structural diagram of a customer service seat distribution device according to an embodiment of the present disclosure;

fig. 12 is a block diagram of a hardware structure of a server to which a customer service agent allocation method according to an embodiment of the present application is applied.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example (b):

in an Instant Messaging (IM) customer service product, customer service distribution logic is a crucial part in a pre-sale marketing/after-sale service scene, and the accuracy of customer service distribution directly influences the solution efficiency of the final problem and the sales order rate.

Currently, the following customer service distribution systems are commonly used in the industry:

the earliest customer service distribution systems are implemented based on fixed distribution, which may be: an entrance on the instant messaging application corresponds to a fixed customer service seat, and the customer service is directly distributed no matter what customers come. For example, referring to fig. 1, no matter which client clicks the online service button of the service agent a on the instant messaging application, the service agent a is assigned to serve the client; no matter which client clicks the online service button of the service seat B on the instant messaging application, the service seat B is assigned to serve the client.

When a customer service seat is not on-line or is serving multiple customers, the conventional customer service seat allocation system allocates a new customer to the customer service seat which may not be normally served according to the on-line/reception state allocation of the customer service seat in conjunction with fig. 2, and thus the new customer service seat is preferentially allocated to the customer service seat which is on-line and not currently in a busy state.

The existing customer service agent distribution system is assigned according to assigned keywords, see fig. 3, by assigning special keywords to assign to specific customer service agents, which can be set according to the service that each customer service agent excels in, in order to assign the customer to the most excellence one.

The customer service seat distribution system shown in fig. 1-2 only focuses on the problem that the number of receptions does not consider the service scope or excellence of each customer service seat, the distribution accuracy is not ideal enough, and the distributed customer service seats cannot be guaranteed to solve the consultation problem of clients.

In the embodiment of the application, the accuracy of customer service seat distribution can be regarded as the precision degree of the customer service seat distribution, the more adept the customer service seat distributed for a client is to process the consultation problem provided by the client, the higher the precision degree of the customer service seat distribution is; on the contrary, the more inelegant the customer service agent allocated for the customer service is in handling the consultation problem proposed by the customer, the lower the accuracy of the customer service agent allocation is.

The customer service seat distribution system shown in fig. 3 solves the problem of unsatisfactory distribution accuracy to a certain extent through a keyword distribution mode, but keywords are difficult to set completely, especially Chinese is boldly and profound, the expression mode is very rich, and the simple keyword matching is difficult to distribute accurately. In addition, the customer service seat allocation system shown in fig. 3 depends on the setting of the corresponding relationship between the keywords and the customer service seats, the allocation strategy is rigid and inflexible, and even if the allocation is wrong, one customer is allocated to a certain customer service seat, and the customer service seat is still allocated in the next time, so that automatic optimization cannot be realized through self-learning.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The embodiment of the application provides a method for carrying out Natural Language Processing (NLP) on consultation problems sent by clients, and finding the customer service seat which is most adept to process the consultation problems through an NLP classification model to distribute. And when the customer service seat distribution is inaccurate, the NLP classification model can be corrected according to the actual processing person of the consultation problem (the customer service seat actually distributed for the client), the learning is retrained, and the distribution accuracy is self-improved.

Natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.

Further, the customer service seat allocation method provided by the embodiment of the application can also adopt a voice processing technology, and when the consultation problem input by the client is voice, the voice can be identified through the voice processing technology to obtain text information of the consultation problem.

Key technologies of speech technology (speech technology) are automatic speech recognition technology (ASR) and speech synthesis technology (TTS), as well as voiceprint recognition technology. The computer can listen, see, speak and feel, and the development direction of the future human-computer interaction is provided, wherein the voice becomes one of the best viewed human-computer interaction modes in the future.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like.

The scheme provided by the embodiment of the application is applied to the field of intelligent customer service, and is particularly used for realizing automatic distribution of customer service agents. Moreover, the solution provided in the embodiment of the present application relates to a speech processing technology of artificial intelligence, a natural language processing technology, and the like, and is specifically described by the following embodiments:

the method for distributing the customer service seats is applied to an instant messaging system, the instant messaging system is composed of a terminal and a server, wherein the terminal provides instant messaging application, and the server provides technical support for the instant messaging application on the terminal. The instant messaging application provided by the terminal is provided with a problem consultation inlet (such as an online customer service button), after a client clicks the problem consultation inlet, a consultation window is displayed on the terminal, the client can edit the consultation problem which the client wants to input and input the consultation problem into the consultation window, the terminal transmits the consultation problem input into the consultation window to the server, and the server distributes a customer service seat for the client according to the consultative question.

In the embodiment of the application, a server is provided with a pre-trained NLP classification model (also called a customer service agent allocation model), and after receiving a consultation problem sent by a client, the server converts the consultation problem into text information and inputs the text information into the customer service agent allocation model to obtain a customer service agent for being allocated to the client.

In order to provide good consultation service for the client, a plurality of customer service account numbers can be set, and after the customer service logs in the instant messaging application through the customer service account numbers, the consultation service can be provided for the client based on the customer service account numbers. Correspondingly, a client can log in the instant messaging application through a client account, a consultation problem is sent through the client account, the server performs classified calculation on the consultation problem sent by the client based on a customer service distribution model to determine a customer service account for providing consultation service for the client, communication connection between the client account and the determined customer service account is established, information interaction between the client currently logging in the client account and customer service of the customer service account determined by the current login is achieved, and the purpose that the customer service provides consultation service for the client is achieved.

The embodiment of the application provides a customer service seat distribution method, which relates to a customer service seat distribution model training process, a customer service seat intelligent distribution process and a customer service seat distribution automatic correction process.

The customer service seat distribution model training process is mainly used for initializing training sample data required by an NLP classification model obtained by first training, the training sample data can be the problem consulted by a client and the customer service seat for solving the problem correspondingly, the training sample data comprises at least one training sample, and the NLP classification model to be trained is trained on the basis of the training sample to obtain the NLP classification model used in the subsequent actual distribution process.

The intelligent customer service seat distribution process is used for the actual customer service seat distribution process, and after a client accesses the intelligent customer service seat distribution process, text information of consultation questions sent by the client is input into the NLP classification model to obtain the customer service seats to be distributed to the client.

The automatic correction process of the customer service seat distribution model is self-learning logic in the customer service seat distribution method provided by the embodiment of the application, when the customer service seat feels that the distributed customers are not right, customer switching can be carried out, the customers are distributed to other customer service seats, correspondingly, the automatic correction process can automatically use the switched new customer service seats and consultation problems sent when the customers access, the NLP classification model is corrected and relearned, the updated NLP classification model is obtained, and the follow-up intelligent customer service seat distribution process can use the updated NLP classification model, so that accurate customer service seats are distributed to the customers sending the same consultation problems in the follow-up process.

The customer service seat assignment model training process is mainly used for generating an NLP classification model, that is, generating a customer service seat assignment model, and please refer to fig. 4 for a specific generation manner of the customer service seat assignment model.

As shown in fig. 4, the method includes:

s401, obtaining a training sample set formed by a plurality of training samples, wherein the training samples indicate historical consultation problems sent by a client and customer service seats actually distributed to the client according to the historical consultation problems;

the customer service seat distribution model training process can be considered as a process for initializing a training customer service seat distribution model, the training process is executed only once in the whole life cycle of the customer service seat distribution model, the customer service seat distribution model is generated through the customer service seat distribution model training process, the customer service seat distribution model can be used for distributing customer service seats for customers subsequently, and further, the customer service seat distribution model generated in the customer service seat distribution model training process can be optimized through the customer service seat distribution model automatic correction process subsequently.

The training samples of the customer service agent assignment model training process may be the problem from past customer consultation (which may also be referred to as a historical consultation problem) and the customer service agent that actually solves the historical consultation problem, such as the following format:

consultation problem	Customer service seat
		What did not get to ask me about the purchased game item?	Customer service seat A
I complain that I filled money not arrived on account!	Customer service seat A
		I report someone to use the store-on!	Customer service seat B
Your game activity today seems to be problematic.	Customer service seat C
		……	……

In the embodiment of the application, the customer service account number comprises an account number name and a password, one customer service account number can be regarded as one customer service seat, and different customer service account numbers can be regarded as different customer service seats.

The account names of different customer service accounts are different, the account name of the customer service account can represent a customer service seat, and the account name can be a customer service employee number. In this case, the training sample may be composed of a consultation question and a customer service number.

S402, updating the historical consultation problems in the training samples into text information representing the historical consultation problems to obtain target training samples;

referring to fig. 5, all training samples in the collected training sample set may be input to NLP classification algorithm (e.g., textCNN, FastText, etc.) for training to generate a customer service assignment model. The NLP classification algorithm may be considered as a to-be-trained NLP classification model, that is, a to-be-trained customer service agent allocation model.

It should be noted that the consultation question entered by the client may be text, speech, or both. Therefore, by taking a training sample as an example, in the embodiment of the application, before the training sample is input into the customer service seat allocation model to be trained, text information representing the historical consultation problem in the training sample can be determined, the historical consultation problem in the training sample is updated to the text information representing the historical consultation problem to obtain a target training sample, and the target training sample is input into the customer service seat allocation model to be trained.

And S403, training the to-be-trained customer service seat distribution model based on all target training samples to obtain a customer service seat distribution model.

According to the method and the device for distributing the customer service seats, the target training samples are input into the to-be-trained customer service seat distribution model, the customer service seats indicated by the target training samples are trained by the to-be-trained customer service seat distribution model, and the to-be-trained customer service seat distribution model is trained to obtain the customer service seat distribution model.

And obtaining a corresponding target training sample for each training sample in the training sample set, inputting all the obtained target training samples into the customer service agent distribution model to be trained, and training the customer service agent distribution model to be trained on the basis of all the target training samples to obtain the customer service agent distribution model.

In the embodiment of the application, the customer service seat distribution model is composed of a feature extraction model and a classification model, wherein the feature extraction model is used for extracting feature information of text information in a target training sample, and the feature information can be a feature vector; the feature extraction model inputs feature information of the text information in the extracted target training sample into the classification model, and the classification model classifies the consultation problem in the target training sample represented by the feature information so as to determine a customer service seat (candidate customer service seat) for providing consultation service for a customer sending the consultation problem.

Fig. 6 is a schematic diagram of an intelligent customer service agent allocation process provided in the embodiment of the present application. The intelligent customer service seat allocation process is used for an actual customer service seat allocation process, after a customer accesses (i.e., after the customer sends a consultation problem), text information representing the consultation problem is automatically determined and then input into the generated customer service seat allocation model (i.e., an NLP classification model), the trained customer service seat allocation model is combined to calculate to obtain which customer service seat the consultation problem should be allocated to (for convenience of distinguishing, the customer service seat determined by the customer service seat allocation model is called a candidate customer service seat) for processing, and finally the accessed customer is allocated to the corresponding customer service seat.

Referring to fig. 7, a schematic diagram of a method for automatically correcting a customer service seat assignment model is shown, after a customer assigns a candidate customer service seat, if the candidate customer service seat finds that the assignment is incorrect, the customer cannot handle a consultation problem sent by the customer, and the customer can be manually transferred to other customer service seats capable of handling the consultation problem. At the moment, a self-learning function of the customer service seat allocation method is triggered, the customer service seat allocation method can input the transferred new customer service seat and the consultation problem when the customer accesses into the NLP classification model again for correction, the new NLP classification model is trained again, and the new NLP classification model (namely, the optimized NLP classification model) is used for subsequent customer allocation, so that the self-learning purpose can be achieved, and the secondary error is avoided.

A method for allocating customer service seats provided in the embodiments of the present application is described in detail below with reference to an actual process for allocating customer service seats and a process for automatically correcting a customer service seat allocation model, and please refer to fig. 8 specifically.

As shown in fig. 8, the method includes:

s801, receiving a consultation problem sent by a client, and determining text information representing the consultation problem;

in the embodiment of the application, a client can open an instant messaging application on a terminal, and register a user for the instant messaging application to obtain a registered account, wherein the registered account comprises an account name and a password (for convenience of distinguishing, the registered account is called as a client account), the client logs in the instant messaging application on the terminal through the client account, a consultation entrance (such as an online customer service button) is arranged on the instant messaging application, the client clicks the consultation entrance, the instant messaging application displays a consultation interface, after the client inputs a consultation problem in the consultation interface, the terminal can send the consultation problem to a server, and after the server receives the consultation problem, the server can determine text information representing the consultation problem.

The consultation question inputted by the client may be text or voice or may include both text and voice, so that the server needs to determine text information representing the consultation question after receiving the consultation question transmitted by the client through the terminal.

For example, taking an consult question as an example, the manner of determining the text information characterizing the consult question may be: detecting whether text content exists in the consultation problem, and if the text content exists in the consultation problem, extracting the text content in the consultation problem (for the convenience of distinguishing, the text content in the consultation problem is called as first text content); detecting whether voice information exists in the consultation problem, if the voice information exists in the consultation problem, identifying the voice information in the consultation problem to obtain text content for representing the voice information (for the convenience of distinguishing, the text content for representing the voice information is called as second text content); and splicing the first text content and the second text content into text information representing the consultation problem.

Further, if the text content does not exist in the consultation problem but the voice information exists, the second text content can be determined as the text information representing the consultation problem; if there is text content but no voice information in the consultation problem, the first text content may be determined as text information characterizing the consultation problem.

For example, the consultation question input by the client is composed of a text content and a piece of voice information, and in the consultation question, the text content is located before the voice information, the text content in the consultation question can be extracted and determined as a first text content, the voice information in the consultation question is subjected to voice recognition to obtain a second text content representing the voice information, the first text content and the second text content are spliced into the text information representing the consultation question, and the first text content in the text information is located before the second text content.

The above preferred manner for determining the text information representing the consulting questions provided by the embodiment of the present application is also applicable to the process for determining the text information representing the historical consulting questions. That is, in the embodiment of the present application, the manner of determining the text information representing the historical consultation problem is the same as the manner of determining the text information representing the consultation problem, so that the accuracy of the agent allocation model can be ensured.

S802, classifying the text information according to a pre-trained customer service seat distribution model to determine candidate customer service seats for providing consultation services for clients in at least one customer service seat;

in the embodiment of the application, after receiving a consultation problem sent by a client through a terminal and determining text information representing the consultation problem, a server inputs the text information into a pre-trained customer service seat allocation model, and the customer service seat allocation model classifies the consultation problem according to the text information to obtain a customer service seat for providing consultation service for the client (for convenience of distinguishing, the customer service seat becomes a candidate customer service seat).

S803, pushing the consultation problem to the candidate customer service seat;

in the embodiment of the application, after the server receives the consultation problem sent by the client through the terminal and determines a candidate customer service seat for providing consultation service for the client according to a customer service seat allocation model, the consultation information can be pushed to the candidate customer service seat, and after the consultation information is pushed to the customer service account number of the candidate customer service seat, the current customer service using the customer service account number can return feedback information of the consultation problem to the server according to whether the customer service seat is adept to process the consultation problem.

As a preferred implementation manner of the embodiment of the present application, if the candidate customer service agent directly solves the consultation problem to the client after receiving the consultation information, it may be determined that the feedback information characterization of the candidate customer service agent on the consultation problem is adept to process.

As another preferred implementation manner of the embodiment of the present application, if the candidate customer service agent clicks the adequacy processing button from the adequacy processing button and the non-adequacy processing button after receiving the consultation information, it may be determined that the feedback information of the candidate customer service agent on the consultation problem indicates adequacy processing.

As a preferred implementation manner of the embodiment of the present application, if the candidate customer service agent transfers the consultation problem to another customer service agent after receiving the consultation information, it may be determined that the candidate customer service agent is not good at processing the consultation problem, and the transferred customer service agent may be considered as a target customer service agent good at processing the consultation problem.

As another preferred implementation manner of the embodiment of the present application, if the candidate customer service agent clicks the unauthorized processing button from the unauthorized processing button and the unauthorized processing button after receiving the consultation information, it may be determined that the feedback information of the candidate customer service agent on the consultation question represents unauthorized processing, and further, the candidate customer service agent may be required to transfer the consultation question to a target customer service agent that is authorized to process the consultation question.

S804, responding to feedback information of the candidate customer service seat to the consultation problem, and determining a target customer service seat for providing consultation service for the client;

in the embodiment of the application, the feedback information of the candidate customer service seat on the consultation problem represents adept processing/not adept processing, and when the feedback information of the candidate customer service seat on the consultation problem represents not adept processing, the candidate customer service seat is indicated not to be adept processing the consultation problem; when the feedback information of the candidate customer service agent to the consultation question is characterized in being good at processing, the candidate customer service agent is indicated to be good at processing the consultation question.

The method for transferring the consultation problem to the target customer service seat by the candidate customer service seat can be as follows: the server pushes a current online customer service seat list in at least one customer service seat to the candidate customer service seats, the candidate customer service seats manually select target customer service seats which are good at processing the consultation problem from the customer service seat list, and the consultation problem is transferred to the target customer service seats.

S805, detecting whether the target customer service seat and the candidate customer service seat are the same customer service seat; if the target customer service seat and the candidate customer service seat are not the same customer service seat, executing step S806;

in the embodiment of the application, if the feedback information representation of the candidate customer service seat on the consultation problem is adept to process, the candidate customer service seat is used as a finally determined target customer service seat for providing the consultation service for the client; and if the feedback information representation of the candidate customer service seat on the consultation problem is not good at processing, taking another customer service seat to which the candidate customer service seat transfers the consultation problem as a finally determined target customer service seat for providing the consultation service for the client.

S806, optimizing a customer service seat distribution model based on the consultation problem and the training sample constructed by the target customer service seat.

According to the embodiment of the application, if the target customer service seat and the candidate customer service seat are not the same, it is indicated that the result of distributing the customer service seat of the consultation problem sent by the client by the current customer service seat distribution model is not accurate, at this time, a training sample needs to be constructed according to the consultation problem and the target customer service seat, and the current customer service seat distribution model is optimally trained based on the training sample to obtain the optimized customer service seat distribution model, so that the accuracy of distributing the customer service seat of the customer service seat distribution model is further improved.

Further, according to the method for allocating customer service seats provided in the embodiments of the present application, if the target customer service seat and the candidate customer service seat are the same customer service seat, the customer service seat allocation model does not need to be optimized according to the consultation problem sent by the customer service and the target customer service seat.

In the embodiment of the application, the customer service seat allocation model is composed of a feature extraction model and a classification model, the feature extraction model is used for extracting feature information of text information representing the consultation problem, and the classification model is used for classifying the consultation problem according to the feature information to obtain candidate customer service seats for processing the consultation problem. Specifically, after receiving a consultation problem sent by a client and determining text information representing the consultation problem, the text information is input into a feature extraction model, feature information of the text information is extracted by the feature extraction model and input into a classification model, and the classification model classifies the consultation problem according to the feature information to obtain a customer service seat (candidate customer service seat) for providing consultation service for the client sending the consultation problem.

The text information is classified according to the pre-trained customer service seat allocation model to determine candidate customer service seats for providing the consulting service for the client in at least one customer service seat, and the candidate customer service seats may be: the method comprises the steps of inputting text information representing a consultation problem input by a client into a customer service seat distribution model, carrying out classification processing on the consultation problem by the customer service seat distribution model according to the text information, and outputting matching information of each customer service seat in at least one customer service seat relative to the consultation problem, namely outputting one piece of matching information for each customer service seat in at least one customer service seat. The matching information characterizes the adequacy in processing; and selecting one customer service seat from the at least one customer service seat as a candidate customer service seat by utilizing the matching information of each customer service seat in the at least one customer service seat relative to the consultation problem.

Specifically, text information representing a consultation problem input by customer service is input into a feature extraction model, feature information of the text information is extracted by the feature extraction model and input into a classification model, the consultation problem is classified and processed by the classification model according to the feature information to obtain matching information of each customer service seat in at least one customer service seat relative to the consultation problem, and then one customer service seat is selected from the at least one customer service seat as a candidate customer service seat by utilizing the matching information of each customer service seat in the at least one customer service seat relative to the consultation problem.

In the embodiment of the application, at least one customer service seat is all customer service seats indicated by training samples for training candidate customer service seats.

As a preferred implementation manner of the embodiment of the present application, by using matching information of each of the at least one customer service agent with respect to the consultation problem, a customer service agent with the highest adequacy in handling the consultation problem is selected from the at least one customer service agent and used as a candidate customer service agent for providing consultation service to a client who sends the consultation problem.

As another implementation manner of the embodiment of the application, the idle state information of each of the at least one current customer service agent may be obtained, and in combination with the idle state information of each of the at least one customer service agent and the matching information of each customer service agent with respect to the consultation problem, one customer service agent is selected from the at least one customer service agent to serve as a candidate customer service agent for providing consultation service to a client sending the consultation problem.

The idle state information of the customer service seat represents the customer reception number of the customer service seat. Determining each customer service seat with the relative processing degree of the consultation problem meeting the preset condition from at least one customer service seat, selecting one customer service seat with the highest processing degree of the relative consultation problem from the unselected customer service seats in all the determined customer service seats, judging whether the customer service number of the currently selected customer service seat reaches a preset upper limit value, and if the customer service number of the currently selected customer service seat does not reach the preset upper limit value, determining the currently selected customer service seat as a candidate customer service seat; and if the customer reception number of the currently selected customer service seat reaches a preset upper limit value, returning to execute a process of selecting a customer service seat with the highest processing degree relative to the consultation problem from the unselected customer service seats in all the determined customer service seats until the candidate customer service seat is selected.

According to the embodiment of the application, if the adequacy processing degree of the customer service seat relative to the consultation problem reaches the preset standard degree, the customer service seat is determined to meet the preset condition; and if the adequacy processing degree of the customer service seat relative to the consultation problem does not reach the preset standard degree, determining that the customer service seat does not meet the preset condition.

If the customer service number of each customer service seat meeting the preset condition determined from the at least one customer service seat reaches the preset upper limit value, each customer service seat meeting the preset condition determined from the at least one customer service seat can be monitored, and once the customer service seat with the customer service number not meeting the preset upper limit value is monitored, the monitored customer service seat is determined to be a candidate customer service seat.

And allocating the client sending the consultation problem to a candidate customer service seat, if the candidate customer service seat is not good at processing the consultation problem, pushing a customer service seat list to the candidate customer service seat, wherein the customer service seat list indicates the currently online customer service seats except the candidate seat in at least one customer service seat, and the candidate customer service seat can select one customer service seat good at processing the consultation problem from the customer service seat list as a target customer service seat and transfer the client to the target customer service seat.

Further, the customer service seat list provided in the embodiment of the present application not only indicates each current online customer service seat in at least one customer service seat, except for candidate customer service seats, but also each customer service seat indicated by the customer service seat list carries a recommendation index, and for one customer service seat, the recommendation index of the customer service seat is related to matching information of a relative consultation problem of the customer service seat and current idle state information of the customer service seat.

The recommendation index of the customer service agent is positively correlated with the adequacy processing degree of the matching information representation of the customer service agent relative consultation problems; the better the customer service agent is at handling the advisory problem, the higher the recommendation index of the customer service agent.

The recommendation index of the customer service seat is inversely related to the customer reception number represented by the idle state information of the current customer service seat; the larger the number of customer receptions of the current customer service agent, the lower the recommendation index of the customer service agent.

The customer service seat allocation method provided by the embodiment of the application can not only allocate customer service seats based on the adequacy degree of the customer service seats to consultation problems, but also can be combined with other allocation logics, for example, the customer service seats already take care of a plurality of customers, and when reaching the upper limit of the care, the current customers can be allocated to other customer service seats which are not busy by combining other allocation logics.

The above is only a preferred manner of another allocation logic provided in the embodiment of the present application, and the other allocation logic is not limited to be related to only the customer reception number, and a specific manner related to the other allocation logic may be set by the inventor according to his own needs, and is not limited herein.

A detailed description will now be given of a method for allocating customer service agents according to an embodiment of the present application, with reference to fig. 9.

As shown in fig. 9, after a client accesses and sends a query question of the client, the method for allocating customer service agents provided in the embodiment of the present application automatically determines text information representing the query question sent by the client, performs NLP processing on the text information, converts the text information into a numerical vector (feature vector) that can be calculated by a machine learning classification algorithm (i.e., a classification model), and then performs classification by using a classification model trained in advance to obtain a customer service agent allocation result (candidate customer service agents).

Fig. 10 is a schematic diagram of a method for allocating customer service agents according to an embodiment of the present application. As shown in fig. 10, after the user accesses, if the result of assigning the service agent (candidate service agent) of the current classification model is not accurate, the candidate service agent will manually transfer the client to another service agent (target service agent) which is skilled in processing. According to the customer service seat allocation method provided by the embodiment of the application, when the switching operation is detected, the NLP classification model is automatically corrected by the correct target customer service seat after switching, and retraining is carried out. With the new NLP classification model, then a user consultation with similar questions would be assigned to the correct customer service agent.

According to the customer service seat allocation method provided by the embodiment of the application, an NLP classification algorithm can select an algorithm integrating text vector conversion and classification, such as textCNN and FastText, and can also select a text feature vector extraction algorithm (for example doc2vec) by self and match with a machine learning multi-class classification algorithm (for example, decision tree) to realize the process in two steps, and in this case, the text feature extraction algorithm and the classification algorithm both need to be trained to use a model. In addition, the scheme can be further matched with other distribution schemes to achieve a more ideal effect.

According to the customer service seat allocation method, intelligent recognition and classification are carried out on consultation problems sent by a client through an NLP technology, the problems that keyword matching is rigid and complete setting is difficult are avoided, the method is more intelligent and more accurate compared with the existing keyword matching, the client can be accurately allocated to a customer service seat capable of solving the problems of the client, the efficiency of working of the customer service seat is higher, the solution efficiency of the consultation problems of the client is higher, and the recognition hit rate and the accuracy rate of the consultation problems sent by the client are greatly improved.

And when the customer service seat finds that the accessed customer is not the customer service seat which can be handled by the customer service seat, the customer service seat can be transferred to the customer service seat which can be handled really. By utilizing the self-learning capability of AI, when the customer service seat is transferred to a customer, the automatic correction logic is triggered, the NLP classification model is retrained, and the distribution accuracy is continuously improved by self, so that the customer service seat distribution method provided by the embodiment of the application is more intelligent.

Fig. 11 is a schematic diagram of a customer service agent distribution device according to an embodiment of the present application.

As shown in fig. 11, the apparatus includes:

a consultation question receiving unit 111, configured to receive a consultation question sent by a client, and determine text information representing the consultation question;

a candidate customer service seat determining unit 112, configured to perform classification processing on the text information according to a pre-trained customer service seat allocation model to determine a candidate customer service seat used for providing a consultation service for the client in at least one customer service seat;

a consultation question pushing unit 113 for pushing a consultation question to the candidate customer service seat;

a target customer service seat determining unit 114, configured to determine a target customer service seat for providing a customer with a consultation service in response to feedback information of the candidate customer service seat to the consultation problem;

and the optimizing unit 115 is configured to optimize the customer service seat allocation model based on the training sample constructed by the consultation problem and the target customer service seat if the target customer service seat and the candidate customer service seat are not the same customer service seat.

In the embodiment of the present application, preferably, the consultation problem receiving unit includes:

the consultation question receiving subunit is used for receiving the consultation question sent by the client;

the text extraction unit is used for extracting first text content in the consultation question;

the voice recognition unit is used for recognizing the voice information in the consultation problem to obtain second text content used for representing the voice information;

and the text information generating unit is used for splicing the first text content and the second text content into text information representing the consultation problem.

In the embodiment of the present application, preferably, the customer service seat allocation model is composed of a feature extraction model and a classification model, and the candidate customer service seat determining unit includes:

the characteristic extraction unit is used for inputting the text information into the characteristic extraction model to extract the characteristic information of the text information;

and the classification unit is used for performing classification processing on the characteristic information by utilizing the classification model to determine candidate customer service seats for providing the consultation service for the client in at least one customer service seat.

In this embodiment of the application, preferably, the target customer service seat determining unit includes:

the feedback information receiving unit is used for receiving feedback information of the candidate customer service agents on the consultation problems;

the judging unit is used for judging whether the feedback information represents the adept treatment of the consultation problem;

the first determining unit is used for determining a target customer service seat except the candidate customer service seat for providing the consultation service for the client from at least one customer service seat if the feedback information represents that the consultation problem is not handled well;

and the second determining unit is used for determining the candidate customer service seat as the target customer service seat if the feedback information indicates that the consultation problem is processed intensely.

In the embodiment of the present application, preferably, the classification unit includes:

the matching information generating unit is used for inputting the characteristic information into the classification model and outputting the matching information of each customer service seat relative to the consultation problem in at least one customer service seat, and the matching information represents the adequacy degree of handling the consultation problem;

the state information acquisition unit is used for acquiring the idle state information of each customer service seat in at least one current customer service seat;

and the third determining unit is used for determining candidate customer service seats for providing the consultation service for the client from the at least one customer service seat based on the idle state information of each customer service seat in the at least one customer service seat and the matching information of each customer service seat relative to the consultation problem.

In this embodiment, preferably, the first determining unit includes:

the system comprises a customer service seat list determining unit, a service information acquiring unit and a service information acquiring unit, wherein the customer service seat list determining unit is used for determining a customer service seat list which indicates each currently online customer service seat except candidate customer service seats in at least one customer service seat;

the customer service seat list pushing unit is used for pushing a customer service seat list to the candidate customer service seats;

and the selecting unit is used for responding to the selection operation of the candidate customer service seat on each customer service seat indicated by the customer service seat list, and determining the customer service seat selected by the candidate customer service seat as the target customer service seat.

In the embodiment of the application, preferably, each customer service seat indicated by the customer service seat list carries a recommendation index, and the recommendation index of the customer service seat is related to the idle state information of the current customer service seat and the matching information of the customer service seat with respect to the consultation problem.

Cloud technology (cloud technology) refers to a technology for unifying series resources such as hardware, software, network and the like in a wide area network or a local area network to realize data calculation,Storage ofTreating and mixingSharingASupport tubeProvided is a technique.

The cloud technology (cloud technology) is based on a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied in a cloud computing business model, can form a resource pool, is used as required, and is flexible and convenient. Cloud computing technology will become an important support. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-like websites and more web portals. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing.

Cloud computing (cloud computing) is a computing model that distributes computing tasks over a pool of resources formed by a large number of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the "cloud" appear to the user as being infinitely expandable and available at any time, available on demand, expandable at any time, and paid for on-demand.

As a basic capability provider of cloud computing, a cloud computing resource pool (called as an ifas (Infrastructure as a Service) platform for short is established, and multiple types of virtual resources are deployed in the resource pool and are selectively used by external clients.

According to the logic function division, a PaaS (Platform as a Service) layer can be deployed on an IaaS (Infrastructure as a Service) layer, a SaaS (Software as a Service) layer is deployed on the PaaS layer, and the SaaS can be directly deployed on the IaaS. PaaS is a platform on which software runs, such as a database, a web container, etc. SaaS is a variety of business software, such as web portal, sms, and mass texting. Generally speaking, SaaS and PaaS are upper layers relative to IaaS.

Cloud computing (cloud computing) refers to a delivery and use mode of an IT infrastructure, and refers to obtaining required resources in an on-demand and easily-extensible manner through a network; the generalized cloud computing refers to a delivery and use mode of a service, and refers to obtaining a required service in an on-demand and easily-extensible manner through a network. Such services may be IT and software, internet related, or other services. Cloud Computing is a product of development and fusion of traditional computers and Network Technologies, such as Grid Computing (Grid Computing), distributed Computing (distributed Computing), Parallel Computing (Parallel Computing), Utility Computing (Utility Computing), Network Storage (Network Storage Technologies), Virtualization (Virtualization), load balancing (LoadBalance), and the like.

With the development of diversification of internet, real-time data stream and connecting equipment and the promotion of demands of search service, social network, mobile commerce, open collaboration and the like, cloud computing is rapidly developed. Different from the prior parallel distributed computing, the generation of cloud computing can promote the revolutionary change of the whole internet mode and the enterprise management mode in concept.

The Cloud Call Center (Cloud Call Center) is a Call Center system built based on the Cloud computing technology, enterprises do not need to purchase any software and hardware systems, can rapidly own the Call Center by only having basic conditions such as personnel, places and the like, and software and hardware platforms, communication resources, daily maintenance and services are provided by server providers. The method has the characteristics of short construction period, low investment, low risk, flexible deployment, strong system capacity flexibility, low operation and maintenance cost and the like; no matter the call center and the customer service center are adopted, enterprises can establish a set of call center system which has comprehensive, stable and reliable functions and can distribute calls all over the country and access all over the country only by renting services according to needs.

The instant communication system is composed of a terminal and a server. The terminal may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like. The server can be a service device which provides service for a user on a network side, can be an independent physical server, can also be a server cluster or distributed system formed by a plurality of physical servers, and can also be a cloud server which provides basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (content delivery network), a big data and artificial intelligence platform and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

In the embodiment of the application, the server provides the customer service agent allocation method based on the cloud call center, and for convenience of understanding, the customer service agent allocation method provided by the embodiment of the application is described in detail from the perspective of the server. Fig. 12 is a block diagram of a hardware structure of a server according to an embodiment of the present disclosure. Referring to fig. 12, the hardware structure of the server may include: a processor 121, a communication interface 122, a memory 123 and a communication bus 124;

in the embodiment of the present invention, the number of the processor 121, the communication interface 122, the memory 123 and the communication bus 124 may be at least one, and the processor 121, the communication interface 122 and the memory 123 complete communication with each other through the communication bus 124;

processor 121 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present invention, or the like;

the memory 123 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;

wherein the memory stores a program, the processor may invoke the program stored in the memory, and the program is operable to:

classifying the text information according to a pre-trained customer service seat distribution model to determine candidate customer service seats for providing consultation services for clients in at least one customer service seat;

pushing a consultation question to the candidate customer service seat;

responding to feedback information of the candidate customer service seat to the consultation problem to determine a target customer service seat for providing consultation service for the client;

and if the target customer service seat and the candidate customer service seat are not the same customer service seat, optimizing a customer service seat distribution model based on the training samples constructed by the consultation problem and the target customer service seat.

Alternatively, the detailed function and the extended function of the program may be as described above.

Furthermore, an embodiment of the present application further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions are used to execute the customer service agent allocation method.

Alternatively, the detailed functionality and extended functionality of the computer-executable instructions may be as described above.

The method, the device, the server and the storage medium for distributing the customer service agents provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include or include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A customer service agent allocation method is characterized by comprising the following steps:

pushing the consultation problem to the candidate customer service seat;

2. The method of claim 1, wherein receiving a consultation question sent by a client, determining text information characterizing the consultation question comprises:

receiving a consultation problem sent by a client;

extracting first text content in the consultation question;

recognizing voice information in the consultation problem to obtain second text content used for representing the voice information;

and splicing the first text content and the second text content into text information representing the consultation problem.

3. The method of claim 1, wherein the customer service seat assignment model is composed of a feature extraction model and a classification model, and the determining candidate customer service seats for providing the consulting service for the customer in at least one customer service seat by classifying the text information according to a pre-trained customer service seat assignment model comprises:

inputting the text information into the feature extraction model to extract feature information of the text information;

and classifying the characteristic information by using the classification model to determine candidate customer service seats for providing consultation services for the client in at least one customer service seat.

4. The method of claim 1, wherein determining a target customer service agent for providing consulting services to the customer in response to the feedback information of the candidate customer service agent to the consulting question comprises:

receiving feedback information of the candidate customer service seat on the consultation problem;

determining whether the feedback information characterizes an excellence in handling the advisory issue;

determining a target customer service agent for providing consulting services for said customer from said at least one customer service agent other than said candidate customer service agent if said feedback information indicates not good at handling said consulting question;

and if the feedback information indicates excellence in processing the consultation problem, determining the candidate customer service seat as a target customer service seat.

5. The method of claim 3, wherein the classifying the feature information using the classification model to determine candidate customer service agents of at least one customer service agent for providing consulting services to the customer comprises:

inputting the characteristic information into the classification model and outputting matching information of each customer service seat in at least one customer service seat relative to the consultation problem, wherein the matching information represents the adequacy degree of handling the consultation problem;

acquiring the idle state information of each customer service seat in the at least one current customer service seat;

and determining candidate customer service seats for providing the consultation service for the client from the at least one customer service seat based on the idle state information of each customer service seat in the at least one customer service seat and the matching information of each customer service seat relative to the consultation problem.

6. The method of claim 5, wherein determining a target customer service agent for providing consulting services for the customer other than the candidate customer service agent from the at least one customer service agent comprises:

determining a customer service seat list indicating each of the at least one customer service seats which are currently on-line except the candidate customer service seat;

pushing the customer service seat list to the candidate customer service seats;

and responding to the selection operation of the candidate customer service seat on each customer service seat indicated by the customer service seat list, and determining the customer service seat selected by the candidate customer service seat as a target customer service seat.

7. The method of claim 1, wherein each of the customer service agents indicated by the list of customer service agents carries a recommendation index, the recommendation index for a customer service agent being related to current idle state information for the customer service agent and matching information for the customer service agent to the advisory problem.

8. A customer service agent distribution device, comprising:

9. A server, comprising: at least one memory and at least one processor; the memory stores a program, and the processor calls the program stored in the memory, and the program is used for realizing the customer service seat allocation method according to any one of claims 1-7.

10. A computer-readable storage medium having computer-executable instructions stored thereon for performing the method of assigning customer service agents of any one of claims 1-7.