WO2019200763A1 - 坐席答疑请求处理方法、电子装置、计算机可读存储介质 - Google Patents

坐席答疑请求处理方法、电子装置、计算机可读存储介质 Download PDF

Info

Publication number
WO2019200763A1
WO2019200763A1 PCT/CN2018/095869 CN2018095869W WO2019200763A1 WO 2019200763 A1 WO2019200763 A1 WO 2019200763A1 CN 2018095869 W CN2018095869 W CN 2018095869W WO 2019200763 A1 WO2019200763 A1 WO 2019200763A1
Authority
WO
WIPO (PCT)
Prior art keywords
question
request
expert
agent
answering
Prior art date
Application number
PCT/CN2018/095869
Other languages
English (en)
French (fr)
Inventor
胡祥
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019200763A1 publication Critical patent/WO2019200763A1/zh

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
    • 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
    • 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
    • G06Q30/01—Customer relationship services

Definitions

  • the present application relates to the field of customer service technologies, and in particular, to a method for processing a question answering request, an electronic device, and a computer readable storage medium.
  • agent usually refers to the customer service personnel who receive the consultation call from the customer service by using the headset, the agent software, etc., and provide services to the customer by answering the questions. Therefore, the agent can be said to be an important bridge between the customer and the insurance company.
  • the agent usually queries the expert related to the problem in the operation interface and sends a question and answer request to the expert.
  • the button for issuing the question and answer request is usually coupled with the button of the query expert, and there may be an operation such as a check prompt during the operation, which will bring the seat with less experience. Inconvenience in operation and trouble, so that the operation efficiency is low;
  • the agent needs to wait for a certain delay to see the reply of the expert, and after seeing the reply, if the agent needs to ask questions again, he needs to give another expert to the expert. A new Q&A request is initiated, and the steps of this operation are repeated, and the operation efficiency is low.
  • the purpose of the present application is to provide a method for processing a question answering request, an electronic device, and a computer readable storage medium, thereby overcoming the problem that the processing efficiency of the answering request for the agent in the financial service platform in the prior art is low to some extent. Improve the efficiency of processing requests for seat Q&A.
  • a method for processing a question answering request including the following steps:
  • S05 Acquire a reply content fed back by the expert end through the built-in question answering channel of the system, and forward the content to the agent end, where the reply content is in the form of text, voice or picture;
  • the instant messaging interface is invoked to establish a communication connection between the agent end and the expert end, and an instant communication window is provided to the agent end and the expert end, so that the agent end and the expert end perform an instant Interact until the end of the Q&A process.
  • the present application further provides an electronic device including a memory and a processor, where the memory is configured to store an agent question request processing system executable by the processor, where the agent question request processing system includes :
  • a Q&A request receiving module configured to receive a Q&A request sent by the agent side
  • a question type obtaining module configured to obtain a question type of the question and answer request according to the question and answer request
  • An expert screening module for screening corresponding experts according to the type of question
  • a question answering request sending module configured to send the question content corresponding to the question and answer request to the corresponding expert end for reply
  • the reply content forwarding module is configured to obtain the reply content fed back by the expert end through the built-in question answering channel of the system, and forward the content to the agent end, where the reply content is in the form of text, voice or picture;
  • a judging module configured to determine, in a preset time period, whether a Q&A request sent by the agent end is the same as the question content or a Q&A request that satisfies a preset similarity threshold with the question content;
  • a window providing module configured to: when the judgment result of the determining module is YES, invoke an instant communication interface to establish a communication connection between the agent end and the expert end, and provide instant communication to the agent end and the expert end a window, so that the agent end interacts with the expert end immediately until the answering process is ended.
  • the present application further provides a computer device including a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor implements a seat answer when the computer program is executed Request the following steps for the processing method:
  • S05 Acquire a reply content fed back by the expert end through the built-in question answering channel of the system, and forward the content to the agent end, where the reply content is in the form of text, voice or picture;
  • the instant messaging interface is invoked to establish a communication connection between the agent end and the expert end, and an instant communication window is provided to the agent end and the expert end, so that the agent end and the expert end perform an instant Interact until the end of the Q&A process.
  • the present application further provides a computer readable storage medium, where a server answering request processing system is stored, and the agent answering request processing system can be executed by at least one processor to enable at least one processing.
  • the following steps are performed to execute the above-mentioned agent answer request processing method:
  • S05 Acquire a reply content fed back by the expert end through the built-in question answering channel of the system, and forward the content to the agent end, where the reply content is in the form of text, voice or picture;
  • the instant messaging interface is invoked to establish a communication connection between the agent end and the expert end, and an instant communication window is provided to the agent end and the expert end, so that the agent end and the expert end perform an instant Interact until the end of the Q&A process.
  • the positive progress of the application is that in the process of responding to the request for the answering of the agent, the received question answering request is first analyzed to determine the type of the question, and then the expert who can answer the question is selected according to the question type and the question is answered.
  • the content of the question is sent to the corresponding expert, and then the reply content fed back by the expert end through the system built-in question answer channel is forwarded to the agent side.
  • the instant messaging interface is invoked to establish a communication connection between the agent end and the expert end, and an instant communication window is respectively provided to the agent end and the expert end, so that the agent end and the expert end can perform instant interaction until the answering process is ended.
  • the process can not only improve the operation efficiency of the agent, but also the result of the expert screening. More accurate, it can guarantee more accurate reply content, which can improve the quality of service; on the other hand, in the case of a request for re-answering the same question content on the agent side, an instant communication window can be provided to the agent side and the expert side. In order to enable instant interaction between the agent and the expert, the efficiency of the agent can be improved, and the expert can be more efficiently answered and feedback to the customer, thereby improving the quality of service.
  • FIG. 1 is an optional schematic flowchart of a method for processing a question answering request according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of an optional program module of a seat answering request processing system according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of another optional program module of the agent answering request processing system according to an embodiment of the present application.
  • FIG. 4 is a schematic diagram of still another optional program module of the agent answer request processing system according to an embodiment of the present application.
  • FIG. 5 is a schematic diagram of an optional hardware architecture of an electronic device according to an embodiment of the present application.
  • FIG. 1 is an optional schematic flowchart of a method for processing a question answer request in the present application. As shown in FIG. 1 , the method may include the following steps:
  • the answering request can be sent through the agent side.
  • the agent end can be a terminal corresponding to the agent.
  • the question and answer request is usually issued to the expert.
  • the so-called expert can be understood as a person who is more familiar with the relevant knowledge in a certain field in the industry. In the case of insurance behavior, such as those who are more familiar with the knowledge of traffic accident claims, those who are more familiar with health insurance knowledge, etc.
  • the expert side can be the terminal corresponding to the expert.
  • an operation button for initiating a question and answer request may be set in the relevant operation interface of the agent end (for example, a “answer” button), and the agent may send a question and answer request by triggering a “answer” button. That is to say, after the agent triggers the “answer” button, the answer request sent by the agent can be received.
  • a first operation option for inputting a question content may be provided in an interface for initiating a question request, such as an input field for inputting voice or text, and the agent may input the question content by voice or text, and The above "answer" button is triggered after the question content is input to initiate a question and answer request. That is to say, the question and answer request under this kind of implementation mainly includes the content of the question.
  • a second operation option for selecting a question type may be provided in an interface for initiating a question request, such as a check box or a pull-down menu including multiple question type information, wherein, for example, in the insurance industry, the question type may be Including auto insurance, accident insurance, health insurance, travel insurance, sickness insurance, etc.
  • the agent can select the question type by operating the check box or the drop-down menu, and trigger the above “answer” button after the selection is completed to initiate the answer request. That is to say, the question type request may also be included in the answer request in the implementation manner.
  • the Q&A request may be analyzed to determine the type of the Q&A request, and then the subsequent operation is performed according to the determined question type.
  • the type of question for how to determine the question and answer request can be carried out in various ways in the specific implementation.
  • the keyword content can be identified by the question content received through the first operation option, and the text recognition and voice recognition in the prior art can be specifically
  • the content information or the voice information in the question content is identified and the keywords contained therein are determined.
  • the keyword can be a word or word related to the insurance item, such as illness, health, rear-end, traffic, accident, tourism, hospital, and the like.
  • the type of the question corresponding to the keyword can be determined according to the correspondence between the preset keyword and the question type.
  • the correspondence between the keyword and the question type can be saved in the form of a file or a data table, and the content can be as shown in Table 1.
  • the question type information received through the second operation option may be extracted to determine the question type of the question answer request according to the extraction result.
  • the first expert list corresponding to the question type may be determined according to the corresponding relationship between the preset question type and the expert.
  • each question type may correspond to one or more experts, because one or more experts may be included in the first expert list.
  • the correspondence between the question type and the expert may be saved in the form of a file or a data table, and the content may be as shown in Table 2.
  • each expert in the first expert list is currently in an idle state
  • the second expert list is determined according to the expert who is currently in an idle state, that is, the second expert list is in an idle state and can reply to the agent in time. Initiated questions.
  • a target expert is determined from the second expert list, and in this embodiment, the target expert can be determined from the second expert list in a variety of ways. For example, an expert may be randomly selected as a target expert in the second expert list to send a question and answer request, or may be arranged in a preset order (for example, by last name sequence), and the expert ranked first is selected as the target expert. Send a Q&A request.
  • the question and answer request can be sent to the expert end used by the target expert determined in S03 to answer the question after the target expert receives the answer request through the expert end.
  • S05 Acquire the reply content fed back by the expert end through the built-in answering channel of the system and forward it to the agent end.
  • the expert can reply to the Q&A request received by the expert, and feedback the reply content through the system's built-in Q&A channel.
  • the feedback through the system's built-in Q&A channel is the reply in the form of existing feedback, that is, only Feedback the response in the form of text, voice or pictures.
  • the reply content can be forwarded to the agent side, so that the agent can get the reply of the expert in time to feedback to the customer.
  • the preset time period can be set according to actual needs, for example, can be set to 30 seconds. That is to say, it can be determined whether the Q&A request is received again within 30 seconds and the Q&A request is the same as the question content of the Q&A request in S01, or the similarity with the question content of the Q&A request in S01 can satisfy the preset similarity threshold. (For example, the similarity of more than 85%), to indicate that the agent wants to have a deeper understanding of the same question content.
  • the determination of whether the content of the question is the same or not can be determined by the semantic similarity calculation method in the prior art, and will not be described here.
  • the subsequent steps are continued; if the result of the judgment is that the agent is not received, the message is sent in S01. If the question content of the Q&A request is the same or the Q&A request satisfying the preset similarity threshold, the Q&A process for the Q&A request is ended.
  • the instant messaging interface is invoked to establish a communication connection between the agent end and the expert end, and an instant communication window is provided to the agent end and the expert end, so that the agent end interacts with the expert end instantaneously until the answering process is ended.
  • the judgment result in S06 is that the answer request sent by the agent end is the same as the question content of the question answer request in S01 or the answer request satisfying the preset similarity threshold, it may indicate that the agent may still have an unclear request for the current question request. Or if you want to know more about it, you can call the instant messaging interface to establish a communication connection between the agent and the expert, and provide an instant communication window to the agent and the expert, so that the agent can directly access the instant communication window. Entering the content of the question, the expert can directly input the reply content through the instant communication window, that is, the agent end and the expert side communicate by means of chat until the entire answering process is ended.
  • the agent needs to re-initiate the answer request for the same question content and wants to re-initiate the answer request, and the system needs to re-select the expert to reply, but provides the communication window to the agent and the expert respectively. Therefore, both the agent and the expert can communicate with the problem in a chat manner through the instant messaging window, thereby improving the operation efficiency of the agent and the expert, thereby more effectively feeding the expert reply content to the customer to improve the service. quality.
  • the prompt information related to the Q&A request can be displayed in the interface of the expert replying question.
  • the prompt information may include: the number of the answering requests waiting for the reply, the number of the answering questions that have been answered, the duration of the answering request currently being answered, the length of time that the next question answering request has been waited for, and the like.
  • the received question answer request is first analyzed to determine the corresponding question type, and then the expert who can answer the question is selected according to the question type and the question request is answered.
  • the content of the question is sent to the corresponding expert, and then the reply content of the expert end feedback through the system built-in question answer channel is forwarded to the agent end.
  • the instant communication interface can be called to establish a communication connection between the agent end and the expert end, and provide an instant communication window to the agent end and the expert end, so that the agent end can interact with the expert end instantaneously until the answering process is ended.
  • the process can not only improve the operation efficiency of the agent, but also the result of the expert screening. More accurate, it can guarantee more accurate reply content, which can improve the quality of service; on the other hand, in the case of a request for re-answering the same question content on the agent side, an instant communication window can be provided to the agent side and the expert side. In order to enable instant interaction between the agent and the expert, the efficiency of the agent can be improved, and the expert can be more efficiently answered and feedback to the customer, thereby improving the quality of service.
  • FIG. 2-4 shows an optional structural block diagram of the agent answering request processing system.
  • the agent challenge request processing system is partitioned into one or more program modules, one or more program modules are stored in a storage medium and executed by one or more processors to complete the application.
  • the program module referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable for describing the execution process of the agent answer request processing system in the storage medium than the program itself. The following description will specifically describe the programs of the embodiment. Module features:
  • the agent answering request processing system 20 can include:
  • the Q&A request receiving module 21 is configured to receive a Q&A request sent by the agent side;
  • the question type obtaining module 22 is configured to obtain a question type of the question answer request according to the question answer request;
  • the expert screening module 23 can be configured to screen corresponding experts according to the type of the question
  • the Q&A request sending module 24 can be configured to send the content of the question corresponding to the question and answer request to the corresponding expert to reply;
  • the reply content forwarding module 25 is configured to obtain the reply content fed back by the expert end through the built-in question answering channel of the system, and forward the content to the agent end, where the reply content is in the form of text, voice or picture;
  • the judging module 26 is configured to determine whether, in the preset time period, the answer request sent by the agent end is the same as the question content or the question request content meets the preset similarity threshold;
  • the window providing module 27 is configured to: when the judgment result of the determining module 26 is YES, invoke an instant communication interface to establish a communication connection between the agent end and the expert end, and provide an instant communication window to the agent end and the expert end, so that the agent end and the agent end The expert interacts instantly until the end of the Q&A process.
  • the electronic device may further include: a first operation option providing module, configured to provide a first operation option for inputting the question content in the interface for initiating the question request.
  • a first operation option providing module configured to provide a first operation option for inputting the question content in the interface for initiating the question request.
  • the question and answer request acquisition module 21 can also be used to receive the input question content through the first operation option.
  • the question type obtaining module 22 may include:
  • the identification unit 221 can be used to identify keywords in the content of the question
  • the determining unit 222 is configured to determine a type of the question corresponding to the keyword according to the correspondence between the preset keyword and the question type.
  • the electronic device may further include: a second operation option providing module, configured to provide a second operation option for selecting a question type in the interface for initiating the question request.
  • a second operation option providing module configured to provide a second operation option for selecting a question type in the interface for initiating the question request.
  • the question and answer request obtaining module 21 is further configured to: receive the selection operation of the question type by using the second operation option.
  • the question type obtaining module 22 may be specifically configured to: extract question type information in the question and answer request to determine a corresponding question type.
  • the expert screening module 23 may include:
  • the first expert list determining unit 231 is configured to determine a first expert list corresponding to the question type according to the corresponding relationship between the preset question type and the expert;
  • the second expert list determining unit 232 is configured to determine whether the expert in the first expert list is currently in an idle state, and determine the second expert list according to the expert currently in the idle state;
  • the target expert determining unit 233 is operable to determine a target expert from the second expert list.
  • the electronic device may further include a prompt information providing module, and may be configured to display the prompt information related to the answering request in the page of the expert replying the question.
  • the prompt information related to the answering request may include: the number of answering requests waiting for the reply, the number of answering requests that have been answered, the duration of the answering request currently being answered, and the length of time that the next question answering request has been waited.
  • FIG. 5 is a schematic diagram of a hardware architecture of an embodiment of an electronic device according to the present application.
  • the electronic device 100 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance.
  • it can be a smartphone, a tablet, a laptop, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster composed of multiple servers).
  • the electronic device 100 includes at least, but not limited to, a memory 10, a processor 30, a network interface 40, and an agent question request processing system 20 that are communicably coupled to one another via a system bus. among them:
  • the memory 10 includes at least one type of computer readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory. (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 10 can be an internal storage module of the electronic device 100, such as a hard disk or memory of the electronic device 100.
  • the memory 10 may also be an external storage device of the electronic device 100, such as a plug-in hard disk equipped on the electronic device 100, a smart memory card (SMC), and a secure digital (Secure Digital, SD) card, flash card, etc.
  • the memory 10 can also include both an internal storage module of the electronic device 100 and an external storage device thereof.
  • the memory 10 is generally used to store an operating system installed in the electronic device 100 and various types of application software, such as program codes of the agent answer request processing system 20. Further, the memory 10 can also be used to temporarily store various types of data that have been output or are to be output.
  • Processor 30 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 30 is typically used to control the overall operation of the electronic device 100, such as performing control and processing related to data interaction or communication with the electronic device 100, and the like.
  • the processor 30 is configured to run program code or processing data stored in the memory 10, such as the running agent question request processing system 20 and the like.
  • Network interface 40 may include a wireless network interface or a wired network interface that is typically used to establish a communication connection between electronic device 100 and other electronic devices.
  • the network interface 40 is used to connect the electronic device 100 to an external terminal through a network, establish a data transmission channel, a communication connection, and the like between the electronic device 100 and an external terminal.
  • the network can be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Wireless or wired networks such as Bluetooth or Wi-Fi.
  • FIG. 5 only shows an electronic device having components 10-40, but it should be understood that not all illustrated components may be implemented and that more or fewer components may be implemented instead.
  • the agent question request processing system 20 stored in the memory 10 may also be divided into one or more program modules, one or more program modules being stored in the memory 10 and processed by one or more The processor (this embodiment is processor 30) is executed to complete the application.
  • a computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the computer program as in the first embodiment The steps of the agent's answering request processing method.
  • the embodiment further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program executable by the at least one processor, so that the at least one processor performs the agent answering request as in the first embodiment.
  • the steps of the processing method are not limited to:
  • the computer readable storage medium includes a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • a computer readable storage medium may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device.
  • the computer readable storage medium may also be an external storage device of a computer device, such as a plug-in hard disk equipped with the smart disk (SMC), Secure Digital (Secure Digital) , SD) card, flash card (Flash Card), etc.
  • the computer readable storage medium can also include both an internal storage unit of the computer device and an external storage device thereof.
  • the computer readable storage medium is generally used to store an operating system installed on a computer device and various types of application software, such as a program code of the agent answer request processing system of the second embodiment.
  • the computer readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

本申请公开一种坐席答疑请求处理方法，包括：接收坐席端发送的答疑请求；根据答疑请求获取疑问类型；根据疑问类型筛选出相对应的专家；将答疑请求对应的疑问内容发送给对应的专家端进行答复；获取专家端通过系统内置答疑通道反馈的答复内容并转发给坐席端；判断在预设时间段内，是否接收到坐席端发送的与疑问内容相同的答疑请求或与疑问内容满足预置相似度阈值的答疑请求，若是，则调用即时通信接口建立座席端与专家端之间的通信连接，并向坐席端及专家端提供即时通信窗口，以便坐席端与专家端进行即时交互，若否，则结束答疑过程。本申请解决现有技术中金融服务平台中针对坐席答疑请求处理效率较低的问题，可提高针对坐席答疑请求的处理效率。

Description

坐席答疑请求处理方法、电子装置、计算机可读存储介质
本申请申明享有2018年4月18日递交的申请号为CN 2018103507707、名称为“坐席答疑请求处理方法、电子装置、计算机可读存储介质”的中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及客服技术领域，具体涉及一种坐席答疑请求处理方法、电子装置、计算机可读存储介质。
背景技术
现如今，保险、银行等金融服务行业的发展越来越快，如何能够更好的向客户提供服务是金融服务行业的重要目标。以保险行业为例，通常会设置一定数量的坐席为客户提供相关服务。所谓坐席，通常是指通过使用耳麦、坐席软件等接听客服打来的咨询电话的客服人员，通过回答问题为客户提供服务，因此，坐席可以说是客户与保险公司之间的重要桥梁。
在实际情况中，很多时候坐席会遇到回答不了的问题，此时就需要使用专家答疑功能，在现有坐席软件的操作界面中，存在如下问题：
一方面，坐席通常会在操作界面中查询出与问题相关的专家，并向该专家发出答疑请求。但是，在现有相关操作界面中，发出答疑请求的按钮与查询专家的按钮通常耦合在一起，且操作过程中还可能存在校验提示等操作，此种操作会给经验较少的坐席带来操作上的不便以及困扰，从而操作效率较低；
另一方面，在专家答复完成后，坐席需要在一定的延时后才能看到专家的答复内容，而且在看到答复内容后，若坐席需再次针对答复内容发出提问，还需要另外向该专家发起一个新的答疑请求，此种操作过程步骤反复，操作效率较低。
针对相关技术中金融服务平台中针对坐席答疑请求的处理效率较低的问题，目前尚未提出有效的解决方案。
发明内容
本申请的目的在于提供一种坐席答疑请求处理方法、电子装置、计算机可读存储介质，进而在一定程度上克服现有技术中金融服务平台中针对坐席答疑请求的处理效率较低的问题，可提高针对坐席答疑请求的处理效率。
本申请是通过下述技术方案来解决上述技术问题：
根据本申请的一个方面，提供了坐席答疑请求处理方法，包括如下步骤：
S01，接收坐席端发送的答疑请求；
S02，根据所述答疑请求获取答疑请求的疑问类型；
S03，根据所述疑问类型筛选出相对应的专家；
S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
为了实现上述目的，根据本申请的另一方面，本申请还提供一种电子装置，包括存储器和处理器，存储器用于存储可被处理器执行的坐席答疑请求处理系统，坐席答疑请求处理系统包括：
答疑请求接收模块，用于接收坐席端发送的答疑请求；
疑问类型获取模块，用于根据所述答疑请求获取答疑请求的疑问类型；
专家筛选模块，用于根据所述疑问类型筛选出相对应的专家；
答疑请求发送模块，用于将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
答复内容转发模块，用于获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
判断模块，用于判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求；
窗口提供模块，用于在判断模块的判断结果为是时，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
为了实现上述目的，本申请还提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现坐席答疑请求处理方法的以下步骤：
S01，接收坐席端发送的答疑请求；
S02，根据所述答疑请求获取答疑请求的疑问类型；
S03，根据所述疑问类型筛选出相对应的专家；
S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
为了实现上述目的，本申请还提供一种计算机可读存储介质，计算机可读存储介质内存储有坐席答疑请求处理系统，坐席答疑请求处理系统可被至少一个处理器所执行，以使至少一个处理器执行上述的坐席答疑请求处理方法的以下步骤：
S01，接收坐席端发送的答疑请求；
S02，根据所述答疑请求获取答疑请求的疑问类型；
S03，根据所述疑问类型筛选出相对应的专家；
S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
本申请的积极进步效果在于：在针对坐席答疑请求的处理过程中，先对接收到的答疑请求进行分析以确定对应的疑问类型，再根据疑问类型筛选出能够回答问题的专家并将答疑请求中的疑问内容发送给对应的专家端，然后将该专家端通过系统内置答疑通道反馈的答复内容转发给坐席端，若该坐席端在收到答复内容后想要针对同一疑问内容继续提问，则可调用即时通信接口建立该座席端与该专家端之间的通信连接，并向该坐席端及该专家端分别提供即时通信窗口，以便该座席端与该专家端可进行即时交互直至结束答疑过程。通过上述方案，一方面，无需人工查询与疑问相关的专家，而是根据答疑请求智能化确定疑问类型并筛选出能够对应解答的专家，该处理过程不但可提高坐席端的操作效率，而且专家筛选结果更为准确，可保证提供更准确的答复内容，进而可提高服务质量；另一方面，在坐席端针对同一疑问内容再次发出答疑请求的情况下，可向座席端及专家端提供即时通信窗口，以便坐席端与专家端进行即时交互，以此，可提高坐席的操作效率，可更高效的得到专家答复并反馈客户，从而提高服务质量。
附图说明
图1是根据本申请实施例的坐席答疑请求处理方法的一种可选的流程示意图；
图2是根据本申请实施例的坐席答疑请求处理系统的一种可选的程序模块示意图；
图3是根据本申请实施例的坐席答疑请求处理系统的另一种可选的程序模块示意图；
图4是根据本申请实施例的坐席答疑请求处理系统的又一种可选的程序模块示意图；以及
图5是根据本申请实施例的电子装置的一种可选的硬件架构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本 申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
实施例一
下面结合附图对本申请提供的坐席答疑请求处理方法进行说明。
图1为本申请坐席答疑请求处理方法的一种可选的流程示意图，如图1所示，该方法可以包括以下步骤：
S01，接收坐席端发送的答疑请求。
在实际应用中，在坐席接听客户咨询电话的过程中，遇到自己无法准确回答的问题时，则可通过座席端发送答疑请求。其中，座席端可为坐席对应使用的终端。
该答疑请求通常为向专家端发出，所谓专家可理解为较为熟知本行业内某领域相关知识的人员，在保险行为例，比如较为熟知交通事故理赔知识的人员、较为熟知健康保险知识的人员等，专家端可为专家对应使用的终端。
在本实施例中，可在坐席端的相关操作界面中，设置用于发起答疑请求的操作按钮(比如，可为“答疑”按钮)，坐席可通过触发“答疑”按钮以发送答疑请求。也就是说，在坐席触发“答疑”按钮后，则可接收到座席端发送的答疑请求。
在具体实现时，还可以在发起答疑请求的界面中提供用于输入疑问内容的第一操作选项，如用于输入语音或文字的输入栏，坐席可通过语音或者文字的方式输入疑问内容，并在输入疑问内容后触发上述“答疑”按钮，以发起答疑请求。也就是说，该种实现方式下的答疑请求中主要包括疑问内容。
此外，还可以在发起答疑请求的界面中提供用于选择疑问类型的第二操作选项，如包括多种疑问类型信息的复选框或者下拉菜单，其中，以保险行业为例，疑问类型比如可包括车险、意外险、健康险、旅游险、疾病险等。坐席可通过操作复选框或下拉菜单对疑问类型进行选择，并在选择完成后触发上述“答疑”按钮，以发起答疑请求。也就是说，该种实现方式下的答疑请求中还可包括疑问类型信息。
S02，根据答疑请求获取答疑请求的疑问类型。
在接收到坐席端发送的答疑请求后，可先对该答疑请求进行分析，以确定答疑请求的疑问类型，然后再根据确定的疑问类型进行后续操作。其中，针对如何确定答疑请求的疑问类型，在具体实现时可通过多种方式来进行。
比如，上述在发起答疑请求的界面中提供第一操作选项的实现方式下，可对通过第一操作选项接收到的疑问内容进行关键词识别，具体可通过现有技术中的文字识别、语音识别等方式，对疑问内容中的文字信息或语音信息进行内容识别并确定其中包含的关键词。其中，关键词可为与保险项目相关的字或词，比如可为病、健康、追尾、交通、事故、旅游、医院等。
然后，可根据预先设置的关键词与疑问类型的对应关系，确定与关键词对应的疑问类型。在本实施例中，可将关键词与疑问类型的对应关系以文件或者数据表的形式进行保存，内容可如表1所示。
表1关键词与疑问类型的对应关系
关键词 疑问类型
健康、病、医院 健康险
追尾、交通、事故 交通险、车险
旅游、飞机、火车 旅游险
... ...
再比如，上述在发起答疑请求的页面中提供第二操作选项的实现方式下，可对通过第二操作选项接收到的疑问类型信息进行提取操作，以根据提取结果确定答疑请求的疑问类型。
S03，根据疑问类型筛选出相对应的专家。
在本实施例中，可先根据预置的疑问类型与专家的对应关系，确定与疑问类型对应的第一专家列表。其中，由于每个疑问类型可对应一个或多个专家，因为该第一专家列表中可包括一个或多个专家。
在本实施例中，可将疑问类型与专家的对应关系以文件或者数据表的形式进行保存，内容可如表2所示。
疑问类型 专家
健康险 专家001
交通险、车险 专家002，专家003，专家004
旅游险 专家005，专家006
... ...
然后，可判断第一专家列表中的各专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表，也就是说，第二专家列表都是处于空闲状态且可及时答复坐席发起的疑问。
接下来，从第二专家列表中确定一个目标专家，在本实施例中，可通过多种方式从第二专家列表中确定目标专家。比如，可在第二专家列表中随机选择一位专家作为目标专家以发送答疑请求，也可以按照预置的排列顺序(比如以姓氏音序进行排列)，选择排列在首位的专家作为目标专家以发送答疑请求。
以此，可针对当前答疑请求确定出最为专业且处于空闲状态的专家以发送答疑请求，以确保得到准确且快速的专家答复。
S04，将答疑请求对应的疑问内容发送给相应的专家端进行答复。
也就是说，可将答疑请求发送给S03中确定的目标专家所使用的专家端，以在该目标专家通过专家端接收到答疑请求后进行问题答复。
S05，获取专家端通过系统内置答疑通道反馈的答复内容并转发给坐席端。
其中，专家可对通过专家端接收到的答疑请求进行答复，并将答复内容通过系统内置答疑通道进行反馈，其中，通过系统内置答疑通道进行反馈即为以现有反馈形式进行答复，也就是仅将答复内容以文字、语音或图片等形式进行反馈。
在获取到专家端的答复内容后，可将答复内容转发给坐席端，以便坐席及时获知专家答复内容，从而向客户进行反馈。
S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程。
在本实施例中，该预设时间段可根据实际需求进行设置，比如可设置为30秒等。也就是说，可判断在30秒内，是否再次接收到答疑请求且该答疑请求与S01中答疑请求的疑问内容相同，或者与S01中答疑请求的疑问内容的相似度能够满足预置相似度阈值(比如达到85％以上的相似度)，以表明座席端希望对同一疑问内容进行更为深入的了解。
其中，关于判断疑问内容是否相同，可以现有技术中的语义相似度计算方法等进行判断，在此不赘述。
若判断结果为接收到坐席端发送的与S01中答疑请求的疑问内容相同或满足预置相似度阈值的答疑请求，则继续执行后续步骤；若判断结果为没有接收到坐席端发送的与S01 中答疑请求的疑问内容相同或满足预置相似度阈值的答疑请求，则结束针对该答疑请求的答疑过程。
S07，调用即时通信接口建立座席端与专家端之间的通信连接，并向坐席端及专家端提供即时通信窗口，以便坐席端与专家端进行即时交互直至结束答疑过程。
具体的，在S06中的判断结果为接收到坐席端发送的与S01中答疑请求的疑问内容相同或满足预置相似度阈值的答疑请求时，则可表明坐席可能就当前答疑请求还存在不清楚或想要深入了解，此时，则可调用即时通信接口建立座席端与专家端之间的通信连接，并向坐席端及专家端分别提供即时通信窗口，以便坐席端可通过该即时通信窗口直接输入疑问内容，专家端可通过该即时通信窗口直接输入答复内容，也即实现座席端与专家端以聊天的方式进行沟通，直至结束整个答疑过程。
以此，不同于现有方案中，坐席针对同一疑问内容想要继续提问时需重新发起答疑请求且系统需重新选择专家进行答复的处理方式，而是向座席端和专家端分别提供即使通信窗口，以便座席端和专家端都可以通过该即时通信窗口以聊天方式进行与问题相关的沟通，以此可提高坐席端及专家端的操作效率，从而更高效的将专家答复内容反馈客户，以提高服务质量。
此外，还可以在专家答复问题的界面中显示与答疑请求相关的提示信息。其中，该提示信息可包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长等。以此，可便于专家及时且清楚的获知自己的工作进度，以对答复的时间、内容等进行合理调整，以提高操作效率。
根据本实施例的各个实施方式，在针对坐席答疑请求的处理过程中，先对接收到的答疑请求进行分析以确定对应的疑问类型，再根据疑问类型筛选出能够回答问题的专家并将答疑请求中的疑问内容发送给对应的专家端，然后将该专家端通过系统内置答疑通道反馈的答复内容转发给坐席端，若该坐席端在收到答复内容后想要针对同一疑问内容继续提问，则可调用即时通信接口建立该座席端与该专家端之间的通信连接，并向该坐席端及该专家端分别提供即时通信窗口，以便该座席端与该专家端可进行即时交互直至结束答疑过程。通过上述方案，一方面，无需人工查询与疑问相关的专家，而是根据答疑请求智能化确定疑问类型并筛选出能够对应解答的专家，该处理过程不但可提高坐席端的操作效率，而且专家筛选结果更为准确，可保证提供更准确的答复内容，进而可提高服务质量；另一方面，在坐席端针对同一疑问内容再次发出答疑请求的情况下，可向座席端及专家端提供即时通信窗口，以便坐席端与专家端进行即时交互，以此，可提高坐席的操作效率，可更高效的 得到专家答复并反馈客户，从而提高服务质量。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。
实施例二
基于上述实施例一中提供的坐席答疑请求处理方法，本实施例中提供一种坐席答疑请求处理系统，具体地，图2-4示出了该坐席答疑请求处理系统的可选的结构框图，该坐席答疑请求处理系统被分割成一个或多个程序模块，一个或者多个程序模块被存储于存储介质中，并由一个或多个处理器所执行，以完成本申请。本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段，比程序本身更适合描述坐席答疑请求处理系统在存储介质中的执行过程，以下描述将具体介绍本实施例各程序模块的功能：
如图2所示，坐席答疑请求处理系统20可包括：
答疑请求接收模块21，可用于接收坐席端发送的答疑请求；
疑问类型获取模块22，可用于根据答疑请求获取答疑请求的疑问类型；
专家筛选模块23，可用于根据疑问类型筛选出相对应的专家；
答疑请求发送模块24，可用于将答疑请求对应的疑问内容发送给相应的专家端进行答复；
答复内容转发模块25，可用于获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
判断模块26，可用于判断在预设时间段内，是否接收到坐席端发送的与疑问内容相同的答疑请求或与疑问内容满足预置相似度阈值的答疑请求；
窗口提供模块27，可用于在判断模块26的判断结果为是时，调用即时通信接口建立座席端与专家端之间的通信连接，并向坐席端及专家端提供即时通信窗口，以便坐席端与专家端进行即时交互直至结束答疑过程。
进一步地，该电子装置还可包括：第一操作选项提供模块，可用于在发起答疑请求的界面中提供用于输入疑问内容的第一操作选项。
基于此，答疑请求获取模块21，还可用于通过第一操作选项接收输入的疑问内容。
如图3所示，疑问类型获取模块22可包括：
识别单元221，可用于识别疑问内容中的关键词；
确定单元222，可用于根据预置的关键词与疑问类型的对应关系，确定与关键词对应的疑问类型。
进一步的，该电子装置还可包括：第二操作选项提供模块，可用于在发起答疑请求的界面中提供用于选择疑问类型的第二操作选项。
基于此，答疑请求获取模块21，还可用于：通过第二操作选项接收对疑问类型的选择操作。
疑问类型获取模块22，可具体用于：提取答疑请求中的疑问类型信息，以确定相应的疑问类型。
进一步地，如图4所示，专家筛选模块23可包括：
第一专家列表确定单元231，可用于根据预置的疑问类型与专家的对应关系，确定与疑问类型对应的第一专家列表；
第二专家列表确定单元232，可用于判断第一专家列表中的专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表；
目标专家确定单元233，可用于从第二专家列表中确定一个目标专家。
在具体实现时，该电子装置，还可包括提示信息提供模块，可用于在专家答复问题的页面中显示与答疑请求相关的提示信息。
其中，与答疑请求相关的提示信息可包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长。
关于上述实施例中的装置，其中各个单元、模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
实施例三
在本申请优选的实施例三中提供一种电子装置。图5是根据本申请电子装置一实施例的硬件架构示意图。本实施例中，电子装置100是一种能够按照事先设定或者存储的指令，自动进行数值计算和/或信息处理的设备。例如，可以是智能手机、平板电脑、笔记本电脑、台式计算机、机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器，或者多个服务器所组成的服务器集群)等。如图所示，电子装置100至少包括但不限于：可通过系统总线相互通信连接存储器10、处理器30、网络接口40、以及坐席答疑请求处理系统20。其中：
存储器10至少包括一种类型的计算机可读存储介质，可读存储介质包括闪存、硬盘、 多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，存储器10可以是电子装置100的内部存储模块，例如该电子装置100的硬盘或内存。在另一些实施例中，存储器10也可以是电子装置100的外部存储设备，例如该电子装置100上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，存储器10还可以既包括电子装置100的内部存储模块也包括其外部存储设备。本实施例中，存储器10通常用于存储安装于电子装置100的操作系统和各类应用软件，例如坐席答疑请求处理系统20的程序代码等。此外，存储器10还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器30在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器30通常用于控制电子装置100的总体操作，例如执行与电子装置100进行数据交互或者通信相关的控制和处理等。本实施例中，处理器30用于运行存储器10中存储的程序代码或者处理数据，例如运行的坐席答疑请求处理系统20等。
网络接口40可包括无线网络接口或有线网络接口，该网络接口40通常用于在电子装置100与其他电子装置之间建立通信连接。例如，网络接口40用于通过网络将电子装置100与外部终端相连，在电子装置100与外部终端之间的建立数据传输通道和通信连接等。网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是，图5仅示出了具有部件10-40的电子装置，但是应理解的是，并不要求实施所有示出的部件，可以替代的实施更多或者更少的部件。
在本实施例中，存储于存储器10中的坐席答疑请求处理系统20还可以被分割为一个或者多个程序模块，一个或者多个程序模块被存储于存储器10中，并由一个或多个处理器(本实施例为处理器30)所执行，以完成本申请。
实施例四
在实施例还提供一种计算机设备，该计算机设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，该处理器执行所述计算机程序时实现如实施 例一的坐席答疑请求处理方法的步骤。
实施例五
本实施例还提供一种计算机可读存储介质，计算机可读存储介质内存储有计算机程序，计算机程序可被至少一个处理器所执行，以使至少一个处理器执行如实施例一的坐席答疑请求处理方法的步骤。
本实施例中，计算机可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，计算机可读存储介质可以是计算机设备的内部存储单元，例如该计算机设备的硬盘或内存。在另一些实施例中，计算机可读存储介质也可以是计算机设备的外部存储设备，例如该计算机设备上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，计算机可读存储介质还可以既包括计算机设备的内部存储单元也包括其外部存储设备。本实施例中，计算机可读存储介质通常用于存储安装于计算机设备的操作系统和各类应用软件，例如实施例二的坐席答疑请求处理系统的程序代码等。此外，计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的各类数据。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种坐席答疑请求处理方法，其特征在于，包括如下步骤：
    S01，接收坐席端发送的答疑请求；
    S02，根据所述答疑请求获取答疑请求的疑问类型；
    S03，根据所述疑问类型筛选出相对应的专家；
    S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
    S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
    S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
    S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
  2. 根据权利要求1所述的坐席答疑请求处理方法，其特征在于，还包括，在发送答疑请求的界面中提供用于输入疑问内容的第一操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第一操作选项接收输入的疑问内容；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    识别所述疑问内容中的关键词；
    根据预置的关键词与疑问类型的对应关系，确定与所述关键词对应的疑问类型。
  3. 根据权利要求1所述的坐席答疑请求处理方法，其特征在于，还包括：在发送答疑请求的界面中提供用于选择疑问类型的第二操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第二操作选项接收对疑问类型的选择操作；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    提取所述答疑请求中的疑问类型信息，以确定相应的疑问类型。
  4. 根据权利要求1所述的坐席答疑请求处理方法，其特征在于，在S03中根据所述疑问类型筛选出相对应的专家包括：
    根据预置的疑问类型与专家的对应关系，确定与所述疑问类型对应的第一专家列表；
    判断第一专家列表中的专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表；
    从第二专家列表中确定一个目标专家。
  5. 根据权利要求1所述的坐席答疑请求处理方法，其特征在于，还包括在专家答复问题的页面中显示与答疑请求相关的提示信息，
    所述与答疑请求相关的提示信息包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长。
  6. 一种电子装置，包括存储器和处理器，其特征在于，所述存储器用于存储可被所述处理器执行的坐席答疑请求处理系统，所述坐席答疑请求处理系统包括：
    答疑请求接收模块，用于接收坐席端发送的答疑请求；
    疑问类型获取模块，用于根据所述答疑请求获取答疑请求的疑问类型；
    专家筛选模块，用于根据所述疑问类型筛选出相对应的专家；
    答疑请求发送模块，用于将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
    答复内容转发模块，用于获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
    判断模块，用于判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求；
    窗口提供模块，用于在判断模块的判断结果为是时，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
  7. 根据权利要求6所述的电子装置，其特征在于，还包括第一操作选项提供模块，用于在发送答疑请求的页面中提供用于输入疑问内容的第一操作选项；
    所述答疑请求接收模块，还用于通过所述第一操作选项接收输入的疑问内容；
    所述疑问类型获取模块，包括：
    识别单元，用于识别所述疑问内容中的关键词；
    确定单元，用于根据预置的关键词与疑问类型的对应关系，确定与所述关键词对应的疑问类型。
  8. 根据权利要求6所述的电子装置，其特征在于，还包括：第二操作选项提供模块，用于在发送答疑请求的页面中提供用于选择疑问类型的第二操作选项；
    所述答疑请求接收模块，还用于：通过所述第二操作选项接收对疑问类型的选择操作；
    所述疑问类型获取模块，具体用于：提取所述答疑请求中的疑问类型信息，以确定相应的疑问类型。
  9. 根据权利要求6所述的电子装置，其特征在于，所述专家筛选模块包括：
    第一专家列表确定单元，用于根据预置的疑问类型与专家的对应关系，确定与疑问类型对应的第一专家列表；
    第二专家列表确定单元，用于判断第一专家列表中的专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表；
    目标专家确定单元，用于从第二专家列表中确定一个目标专家。
  10. 根据权利要求6所述的电子装置，其特征在于，还包括提示信息提供模块，用于在专家答复问题的页面中显示与答疑请求相关的提示信息，
    其中，与答疑请求相关的提示信息可包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长。
  11. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现坐席答疑请求处理方法的以下步骤：
    S01，接收坐席端发送的答疑请求；
    S02，根据所述答疑请求获取答疑请求的疑问类型；
    S03，根据所述疑问类型筛选出相对应的专家；
    S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
    S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
    S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
    S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
  12. 根据权利要求11所述的计算机设备，其特征在于，在所述坐席答疑请求处理方法中，还包括，在发送答疑请求的界面中提供用于输入疑问内容的第一操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第一操作选项接收输入的疑问内容；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    识别所述疑问内容中的关键词；
    根据预置的关键词与疑问类型的对应关系，确定与所述关键词对应的疑问类型。
  13. 根据权利要求11所述的计算机设备，其特征在于，在所述坐席答疑请求处理方法中，还包括：在发送答疑请求的界面中提供用于选择疑问类型的第二操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第二操作选项接收对疑问类型的选择操作；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    提取所述答疑请求中的疑问类型信息，以确定相应的疑问类型。
  14. 根据权利要求11所述的计算机设备，其特征在于，在所述坐席答疑请求处理方法中，在S03中根据所述疑问类型筛选出相对应的专家包括：
    根据预置的疑问类型与专家的对应关系，确定与所述疑问类型对应的第一专家列表；
    判断第一专家列表中的专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表；
    从第二专家列表中确定一个目标专家。
  15. 根据权利要求11所述的计算机设备，其特征在于，在所述坐席答疑请求处理方法中，还包括在专家答复问题的页面中显示与答疑请求相关的提示信息，
    所述与答疑请求相关的提示信息包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长。
  16. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质内存储有计算机程序，所述计算机程序可被至少一个处理器所执行，以使所述至少一个处理器执行坐席答疑请求处理方法的以下步骤：
    S01，接收坐席端发送的答疑请求；
    S02，根据所述答疑请求获取答疑请求的疑问类型；
    S03，根据所述疑问类型筛选出相对应的专家；
    S04，将所述答疑请求对应的疑问内容发送给相应的专家端进行答复；
    S05，获取所述专家端通过系统内置答疑通道反馈的答复内容并转发给所述坐席端，所述答复内容为文字、语音或图片形式；
    S06，判断在预设时间段内，是否接收到所述坐席端发送的与所述疑问内容相同的答疑请求或与所述疑问内容满足预置相似度阈值的答疑请求，若是，则执行S07，若否，则结束答疑过程；
    S07，调用即时通信接口建立所述座席端与所述专家端之间的通信连接，并向所述坐席端及所述专家端提供即时通信窗口，以便所述坐席端与所述专家端进行即时交互直至结束答疑过程。
  17. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述坐席答疑请求处理方法中，还包括，在发送答疑请求的界面中提供用于输入疑问内容的第一操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第一操作选项接收输入的疑问内容；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    识别所述疑问内容中的关键词；
    根据预置的关键词与疑问类型的对应关系，确定与所述关键词对应的疑问类型。
  18. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述坐席答疑请求处理方法中，还包括：在发送答疑请求的界面中提供用于选择疑问类型的第二操作选项；
    在S01接收坐席端发送的答疑请求之前包括：
    通过所述第二操作选项接收对疑问类型的选择操作；
    在S02中根据所述答疑请求获取答疑请求的疑问类型包括：
    提取所述答疑请求中的疑问类型信息，以确定相应的疑问类型。
  19. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述坐席答疑请求处理方法中，在S03中根据所述疑问类型筛选出相对应的专家包括：
    根据预置的疑问类型与专家的对应关系，确定与所述疑问类型对应的第一专家列表；
    判断第一专家列表中的专家当前是否处于空闲状态，并根据当前处于空闲状态的专家确定第二专家列表；
    从第二专家列表中确定一个目标专家。
  20. 根据权利要求16所述的计算机可读存储介质，其特征在于，在所述坐席答疑请求处理方法中，还包括在专家答复问题的页面中显示与答疑请求相关的提示信息，
    所述与答疑请求相关的提示信息包括：等待答复的答疑请求数量、已答复的答疑请求数量、当前正在答复的答疑请求的所用时长、下一答疑请求已等待的时长。
PCT/CN2018/095869 2018-04-18 2018-07-17 坐席答疑请求处理方法、电子装置、计算机可读存储介质 WO2019200763A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810350770.7 2018-04-18
CN201810350770.7A CN108550057B (zh) 2018-04-18 2018-04-18 坐席答疑请求处理方法、电子装置、计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019200763A1 true WO2019200763A1 (zh) 2019-10-24

Family

ID=63515521

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/095869 WO2019200763A1 (zh) 2018-04-18 2018-07-17 坐席答疑请求处理方法、电子装置、计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108550057B (zh)
WO (1) WO2019200763A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113285970A (zh) * 2021-02-19 2021-08-20 江苏省广电有线信息网络股份有限公司无锡分公司 一种基于数字电视和手机终端的信息答疑平台

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109361765A (zh) * 2018-11-29 2019-02-19 苏州思必驰信息科技有限公司 语音对话方法及装置
CN110351332B (zh) * 2019-05-30 2022-04-15 深圳壹账通智能科技有限公司 动态调整时间阈值的方法、装置、计算机设备和存储介质
CN111740849A (zh) * 2020-06-22 2020-10-02 中国银行股份有限公司 坐席操作系统及方法
CN112085577A (zh) * 2020-09-03 2020-12-15 上海容基工程项目管理有限公司 一种招投标在线答疑方法、设备、系统及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100014653A1 (en) * 2008-07-16 2010-01-21 Cisco Technology, Inc. Method and apparatus for scheduling callbacks via offline offer tasks to knowledge workers
CN101867487A (zh) * 2009-03-30 2010-10-20 阿瓦雅公司 用图形呼叫连接象征管理联系中心的系统和方法
CN102821215A (zh) * 2011-06-07 2012-12-12 华为技术有限公司 呼叫处理方法和座席终端
CN107294839A (zh) * 2017-06-09 2017-10-24 南京跃豚智能科技有限公司 在移动终端快速建立会话的方法以及移动终端
CN107873131A (zh) * 2015-05-29 2018-04-03 甲骨文国际公司 基于客户关系管理数据的推荐名单

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103379229B (zh) * 2012-04-28 2017-02-15 恒生电子股份有限公司 一种用于专家座席的数据传送方法及系统
CN105227792B (zh) * 2014-06-10 2018-06-26 华为技术有限公司 呼叫路由方法、装置及系统
CN104780281A (zh) * 2015-04-09 2015-07-15 中国工商银行股份有限公司 远程求助系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100014653A1 (en) * 2008-07-16 2010-01-21 Cisco Technology, Inc. Method and apparatus for scheduling callbacks via offline offer tasks to knowledge workers
CN101867487A (zh) * 2009-03-30 2010-10-20 阿瓦雅公司 用图形呼叫连接象征管理联系中心的系统和方法
CN102821215A (zh) * 2011-06-07 2012-12-12 华为技术有限公司 呼叫处理方法和座席终端
CN107873131A (zh) * 2015-05-29 2018-04-03 甲骨文国际公司 基于客户关系管理数据的推荐名单
CN107294839A (zh) * 2017-06-09 2017-10-24 南京跃豚智能科技有限公司 在移动终端快速建立会话的方法以及移动终端

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"The . Next Step . . . of the Bank Customer Service Center", CHINA CREDIT CARD, 30 April 2008 (2008-04-30), pages 21 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113285970A (zh) * 2021-02-19 2021-08-20 江苏省广电有线信息网络股份有限公司无锡分公司 一种基于数字电视和手机终端的信息答疑平台
CN113285970B (zh) * 2021-02-19 2023-12-01 江苏省广电有线信息网络股份有限公司无锡分公司 一种基于数字电视和手机终端的信息答疑平台

Also Published As

Publication number Publication date
CN108550057A (zh) 2018-09-18
CN108550057B (zh) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2019200763A1 (zh) 坐席答疑请求处理方法、电子装置、计算机可读存储介质
CN108763499B (zh) 基于智能语音的呼叫质检方法、装置、设备及存储介质
CN107784051B (zh) 在线客服应答系统及方法
EP3343411A1 (en) Sql auditing method and apparatus, server and storage device
US20110125826A1 (en) Stalking social media users to maximize the likelihood of immediate engagement
WO2019061998A1 (zh) 断点智能分流方法、电子装置及计算机可读存储介质
CN110336791B (zh) 一种断点数据传输方法、装置、设备及计算机存储介质
WO2019200762A1 (zh) 保险平台数据处理方法、电子装置及计算机可读存储介质
US11025567B2 (en) Systems and methods for mediation using NLP and machine learning techniques
US20150106899A1 (en) System and method for cross-cloud identity matching
CN109688185A (zh) 坐席业务处理方法、装置、设备及计算机可读存储介质
CN109615443B (zh) 基于区块链的用户处理方法、装置、服务器及存储介质
US11907878B2 (en) System and method of running an agent guide script-flow in an employee desktop web client
CN109389306B (zh) 一种用户订单的同步方法和装置
CN111191066A (zh) 一种基于图像识别的宠物身份识别方法和装置
KR20120137624A (ko) 집단지성 서비스 시스템 및 그 방법
CN114003818A (zh) 页面推荐方法、装置、服务器及存储介质
US11088974B2 (en) Cross-platform messaging system
WO2019062020A1 (zh) 异步任务统一处理方法、装置及存储介质
US20140172874A1 (en) Intelligent analysis queue construction
WO2019196243A1 (zh) 坐席协办任务管理方法、装置、计算机设备及存储介质
US20190179902A1 (en) Systems and methods for task automation using natural language processing
CN112637206B (zh) 一种业务数据主动获取方法和系统
CN111767544B (zh) 多频重放攻击漏洞确定方法、装置、设备及可读存储介质
US20170155711A1 (en) Processing Requests

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18915060

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18915060

Country of ref document: EP

Kind code of ref document: A1