CN114443825A

CN114443825A - Hot line service processing method and device combining RPA and AI and electronic equipment

Info

Publication number: CN114443825A
Application number: CN202210080200.7A
Authority: CN
Inventors: 焦栋
Original assignee: Laiye Technology Beijing Co Ltd
Current assignee: Laiye Technology Beijing Co Ltd
Priority date: 2022-01-24
Filing date: 2022-01-24
Publication date: 2022-05-06
Also published as: WO2023137866A1

Abstract

The application relates to a hotline service processing method, a hotline service processing device and electronic equipment which combine RPA and AI, wherein the method comprises the following steps: responding to the answering of the service hotline, and acquiring the conversation voice of the caller and the caller; performing voice recognition on the spoken voice based on a voice recognition ASR technology to obtain a first text corresponding to the caller and a second text corresponding to the caller; analyzing the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice; acquiring and displaying corresponding target business knowledge according to the target key information; and responding to the hanging up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into the hotline service system. By adopting the mode of combining the RPA and the AI, the target service knowledge is acquired and displayed, reference is provided for a wiring party to process the service in real time, the quality and the efficiency of service handling are improved, service data do not need to be input manually, and the labor cost is reduced.

Description

Hot line service processing method and device combining RPA and AI and electronic equipment

Technical Field

The present application relates to the technical field of Robot Process Automation (RPA) and Artificial Intelligence (AI), and in particular, to a hotline service processing method and apparatus combining RPA and AI, and an electronic device.

Background

Robot Process Automation (RPA) is a Process task automatically executed according to rules by simulating human operations on a computer through specific robot software.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.

Currently, many cumbersome and repetitive business processes require manual work to process. For example, in the service processing process of some service hotlines, an operator needs to manually record the requirement of an caller in the process of answering a call, if the requirement of the caller is a consultation problem, the operator needs to reply the problem of the caller in real time according to experience or search a knowledge base, and after the call is hung up, the operator needs to manually enter service data such as caller information and requirement information in a hotline service system. With the rapid increase of the number of calls of the service hotline, the workload of operators is increased greatly, if the operators only need to manually handle the hotline service, a large amount of labor cost is needed, and the efficiency and quality of service handling cannot be guaranteed. How to improve the business handling efficiency and quality of the service hotline and reduce the labor cost becomes a problem to be solved urgently.

Disclosure of Invention

The application provides a hotline business processing method and device combining RPA and AI and electronic equipment, and aims to solve the technical problems that in the related technology, a service hotline is low in business handling efficiency, high in labor cost and poor in business handling quality.

The embodiment of the first aspect of the present disclosure provides a hotline service processing method combining an RPA and an AI, which is applied to an RPA hotline service robot, and the method includes: responding to the answering of the service hotline, and acquiring the conversation voice of the caller and the caller; performing voice recognition on the spoken voice based on a voice recognition ASR technology to obtain a first text corresponding to the caller and a second text corresponding to the caller; analyzing the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice; acquiring and displaying corresponding target business knowledge according to the target key information; and responding to the hanging up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into the hotline service system.

The embodiment of the second aspect of the present disclosure provides a hotline service processing device combining RPA and AI, which is applied to an RPA hotline service robot, and the device includes: the first acquisition module is used for responding to the answering of the service hotline and acquiring the conversation voice of the caller and the caller; the recognition module is used for carrying out voice recognition on the spoken voice based on the voice recognition ASR technology so as to obtain a first text corresponding to the caller and a second text corresponding to the caller; the analysis module is used for analyzing the first text and the second text based on a Natural Language Processing (NLP) technology so as to acquire target key information in the dialogue voice; the processing module is used for acquiring and displaying corresponding target business knowledge according to the target key information; and the first entry module is used for responding to the hanging up of the service hotline and entering the first text, the second text, the target key information and the target business knowledge into the hotline service system.

An embodiment of a third aspect of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method according to the embodiment of the first aspect of the present disclosure.

A fourth aspect of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method according to the first aspect of the present disclosure.

A fifth aspect of the present disclosure provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the method according to the first aspect of the present disclosure.

The technical scheme provided by the embodiment of the application can have the following beneficial effects:

by adopting the mode of combining the RPA and the AI, the target key information in the dialogue voice of the wiring party and the calling party is acquired, and then the target business knowledge corresponding to the target key information is acquired and displayed, so that reference is provided for the wiring party to process the business of the service hotline in real time, the business handling quality and efficiency are improved, and the manual entry of business data is not needed, so that the labor cost is reduced.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.

Fig. 1 is a schematic flow diagram of a hotline service processing method in conjunction with RPA and AI according to one embodiment of the present disclosure;

FIG. 2 is a flow diagram of a hotline service processing method incorporating RPA and AI according to another embodiment of the disclosure;

FIG. 3 is a flow diagram of a hotline service processing method incorporating RPA and AI according to another embodiment of the disclosure;

fig. 4 is an architecture diagram of a hotline service processing method combining RPA and AI according to another embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a hotline service processing device combining RPA and AI according to an embodiment of the present application;

fig. 6 is a block diagram of an electronic device for implementing a hotline service processing method in conjunction with RPA and AI according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the embodiments of the present application/disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application/disclosure, and should not be construed as limiting the present application/disclosure.

In the description of this application/disclosure, the term "plurality" refers to two or more.

It can be understood that in the process of processing the business of some service hotlines, the operator needs to manually record the requirement of the caller in the process of answering the incoming call, if the requirement of the caller is a consultation problem, the operator needs to reply the problem of the caller in real time according to experience or search a knowledge base, and after the incoming call is hung up, the operator needs to manually enter business data such as caller information and requirement information in the hotline service system. With the rapid increase of the number of calls of the service hotline, the workload of operators is increased greatly, if the operators only need to manually handle the hotline service, a large amount of labor cost is needed, and the efficiency and quality of service handling cannot be guaranteed. How to improve the business handling efficiency and quality of the service hotline and reduce the labor cost becomes a problem to be solved urgently.

The application provides a through the combination of RPA and AI, use RPA hotline service robot to replace the manual work to record caller's demand, answer caller's problem and type in hotline service system business data's thinking, because RPA hotline service robot as long as there is data just can be 7 x 24 hours uninterrupted duty, just so can great reduction human cost, improve the efficiency of business handling, and through adopting RPA and AI combined mode to record caller's demand, answer caller's problem and type in hotline service system business data, can guarantee the quality of business handling.

For the purpose of clearly explaining the embodiments of the present invention, terms related to the embodiments of the present invention will be explained first.

In the description of the present application, the "service hotline" refers to a hotline for providing services such as a problem consultation, a business acceptance, a complaint suggestion, etc. to a user, such as a government affairs service hotline, a shopping service hotline, etc.

In the description of the present application, the "hotline service system" refers to a service system corresponding to a service hotline, and services corresponding to the service hotline can be processed on the hotline service system, such as performing service acceptance, backing up a problem of a user consultation, or a complaint suggestion of the user. In addition, the hotline service system can also use a hotline portal as a service entrance, so that the user can perform question consultation or complaint suggestion and the like by dialing the service hotline and logging in the hotline portal. After the service is called by the service hotline, the work to be processed is required according to the requirement of the calling party.

In the description of the present application, the "RPA hotline service robot" refers to an RPA robot that can automatically process traffic of a service hotline in conjunction with AI technology and RPA technology.

In the description of the present application, "party to wire," refers to a party to listen to a service hotline, such as an operator. The "caller" refers to a party who dials a service hotline, such as a user of a citizen.

In the description of the present application, "acceptance department" refers to a business acceptance department corresponding to a service hotline. For example, taking the service line as a government affair service line as an example, that is, the service line provides a business service in terms of government affairs, the acceptance department may include: a residential building bureau for accepting a service in the building aspect of a house, an education bureau for accepting a service in the education aspect, an environmental protection bureau for accepting a service in the environmental protection aspect, and the like; taking the service line as the shopping service line as an example, that is, the service line provides business service in shopping, the accepting department may include: a logistics department accepting the business in the aspect of logistics, a quality inspection department accepting the business in the aspect of cargo quality, and the like. The "business system of the acceptance department", namely the system used by the acceptance department for processing the business.

In the description of the present application, "traffic class" refers to a class to which a traffic corresponding to a service hotline belongs. For example, taking a service hotline as a government affair service hotline as an example, that is, the service corresponding to the service hotline is a service in various government affairs, the service category may include a discipline inspection supervision category, an urban and rural construction category, an environmental protection category, a rural agricultural category, an education problem category, and the like; taking the service hotline as a shopping service hotline as an example, that is, the service corresponding to the service hotline is various shopping-related services, the service category may include a quality category, a logistics category, and the like.

In the description of the present application, "business knowledge" refers to information related to business processing of a service hotline, and the business knowledge can provide a reference for a connector to handle business, thereby assisting the connector to handle business better. For example, when the caller complains about an event, the business knowledge includes which accepting department the business needs to accept, or when the caller consults a certain question, the business knowledge includes how the question needs to be solved.

In the description of the present application, "ASR" refers to Automatic Speech Recognition (Automatic Speech Recognition), and particularly to a technology for converting human Speech into text. The goal of "ASR" is to convert the lexical content in human speech into computer readable input, such as keystrokes, binary codes, or character sequences.

These and other aspects of the embodiments of the present application/disclosure will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the present application/disclosed embodiments are disclosed in detail as being indicative of some of the ways in which the principles of the present application/disclosed embodiments may be employed, but it is understood that the scope of the embodiments is not limited thereby. Rather, the embodiments of the application/disclosure include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

The hotline service processing method, apparatus and electronic device combining RPA and AI according to the embodiments of the present application/disclosure are described below with reference to the accompanying drawings.

Fig. 1 is a flowchart of a hotline service processing method combining RPA and AI according to an embodiment of the present application/disclosure. As shown in fig. 1, the method may include the steps of:

and step 101, responding to the answer of the service hotline, and acquiring the conversation voice of the caller and the caller.

The hotline service processing method combining the RPA and the AI according to the embodiment of the present application is executed by a hotline service processing device combining the RPA and the AI, and hereinafter, the hotline service processing device combining the RPA and the AI is simply referred to as a hotline service processing device, and the hotline service processing device may be implemented by an RPA hotline service robot, for example, the hotline service processing device may be an RPA hotline service robot, or the hotline service processing device may be configured in the RPA hotline service robot, which is not limited in the present application.

The RPA hotline service robot may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal device, a server, and the like, and the embodiment does not specifically limit the electronic device. The embodiment of the present disclosure takes a hotline service processing apparatus as an example of an RPA hotline service robot installed in a terminal device.

The RPA hotline service robot in this embodiment may execute the method in real time in a specific time period or all day, which is not limited by this disclosure. Wherein the specific time period can be set as desired.

Alternatively, the RPA hotline service robot may be started based on receiving a start instruction. For example, the operator may trigger the above-mentioned start instruction for the RPA hotline service robot by means of a dialog. The triggering of the starting instruction for the RPA hotline service robot may be implemented in various ways, for example, the starting instruction for the RPA hotline service robot may be triggered in a manner of voice and/or text, and for example, the starting instruction for the RPA hotline service robot may also be triggered in a manner of triggering a designated control on a dialog interaction interface, which is not specifically limited in this embodiment of the application.

In the embodiment of the application, when the service hotline calls, the caller can answer the call, and in response to the answer of the service hotline, the RPA hotline service robot can acquire the conversation voice of the caller and the caller in real time in the conversation process of the caller and the caller.

Step 102, based on the speech recognition ASR technology, performing speech recognition on the spoken speech to obtain a first text corresponding to the caller and a second text corresponding to the caller.

In the embodiment of the application, the RPA hotline service robot can perform speech recognition on the conversation speech in real time based on the ASR technology, convert the conversation speech into the text, and can distinguish the speech of the caller from the speech of the caller in real time through the ASR technology, thereby obtaining the first text corresponding to the caller and the second text corresponding to the caller.

In the embodiment of the application, after the RPA hotline service robot acquires the first text corresponding to the caller and the second text corresponding to the caller, the first text and the second text can be displayed through a human-computer interaction interface of the hotline service system, so that the caller can conveniently check the texts.

And 103, analyzing the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice.

In an embodiment of the application, after acquiring the first text corresponding to the caller and the second text corresponding to the caller, the RPA hotline service robot may analyze the first text and the second text in real time based on a Natural Language Processing (NLP) technology, and understand an intention of the caller to acquire target key information in the conversational speech.

The target key information is key information that can indicate a requirement of the caller, and may include, for example, key information of an intention of the caller in the conversational speech, a problem description, an event, a time, a location, a person of the event, and the like.

For example, suppose the second text is "you are good and ask what can help you", and the first text is "the night 23:23 of the A area B construction site is still under construction, noise disturbs people, and thus complaints and hope department intervention treatment". Then the RPA hotline service robot can acquire target key information in the conversational speech based on NLP technology: time "23: 23 at night", place "a district B site", event "construction", "noise disturbing residents", intention "complaint".

And 104, acquiring and displaying corresponding target business knowledge according to the target key information.

The "target business knowledge" refers to business knowledge related to the requirement of the caller of the current call. For example, when the requirement of the caller of the current call is to complain about a certain event, the target service knowledge may include which accepting department is required for the service to accept; or, when the caller of the current call needs to consult a certain question, the target service knowledge may include an answer to the question consulted by the caller.

In the embodiment of the application, the corresponding relation between each piece of key information and each piece of business knowledge can be stored in the knowledge base, so that the RPA hot line service robot can search the knowledge base for the key information matched with the target key information and use the business knowledge corresponding to the searched key information as the target business knowledge.

In the embodiment of the application, after the target business knowledge corresponding to the target key information is acquired, the target business knowledge can be displayed. When the target business knowledge is displayed, the target business knowledge can be displayed through a human-computer interaction interface of the hotline service system, so that a connector can process business according to the target business knowledge displayed on the human-computer interaction interface.

In addition, when the target business knowledge is displayed, the target business knowledge can be displayed in a preset mode, and the method is not limited in the application. For example, all the contents of the target business knowledge may be displayed, or when the contents of the target business knowledge are more, the keywords of the target business knowledge may be displayed first, and after the keywords are clicked by the connecting party, all the contents of the target business knowledge may be displayed.

For example, assume that the second text is "you are good, ask for what can help you," and the first text is "ask for a hospital a has a doctor to visit on weekends". The RPA hotline service robot is based on NLP technology, and the target key information obtained from the dialogue voice comprises: time "weekend", location "hospital a", event "doctor visit". The RPA robot can retrieve the knowledge base to obtain the key information matched with the target key information from the knowledge base, and if the business knowledge corresponding to the key information of 'weekend', 'Hospital A' and 'doctor reception' in the knowledge base comprises 'Hospital A has doctor reception on weekend', the RPA hot-line service robot can take the business knowledge as the target business knowledge and display the target business knowledge through a human-computer interaction interface of a hot-line service system, so that a wiring party can answer the problem of consultation of the calling party according to the target business knowledge.

Or, the second text is 'good you ask what can help you' and the first text is 'A area B construction site night 23:23 is still under construction, noise disturbs people, and complaints and hope department intervention processing'. The RPA hotline service robot is based on NLP technology, and the target key information obtained from the dialogue voice comprises: time "23: 23 at night", location "construction site B in area a", event "construction", "noise disturbing residents", intention "complaints". The RPA robot can retrieve the knowledge base to obtain the key information matched with the target key information from the knowledge base, and if the business knowledge corresponding to the key information in the knowledge base, namely '23: 23 at night', 'construction site in area A and B', 'construction', 'noise disturbing citizen' and 'complaint', comprises 'the problem belongs to the urban and rural construction problem and needs to be accepted and solved by a building bureau', the RPA hot-line service robot can take the business knowledge as the target business knowledge and display the target business knowledge through a human-computer interaction interface of a hot-line service system, so that a wiring party can reply to an incoming call party according to the target business knowledge. For example, the caller can be informed that the service is recorded and the caller can go to the building office to accept the service.

The method and the device have the advantages that the corresponding target business knowledge is obtained and displayed according to the target key information, and reference is provided for the caller to process the business in real time, so that an inexperienced caller can quickly obtain the business knowledge related to the demand of the caller of the incoming call without searching a knowledge base, the business handling efficiency is improved, the labor cost is reduced, the caller can answer the caller with reference to the target business knowledge, the business handling accuracy is improved, and the business handling quality is improved.

And 105, responding to the hanging up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into the hotline service system.

In the embodiment of the application, in response to the hanging-up of the service hotline, the RPA hotline service robot can input the first text, the second text, the target key information, the target service knowledge and other service data in the hotline service system so as to backup the service content of the incoming call, thereby facilitating the follow-up tracing of the service content of the incoming call.

The RPA hot-line service robot is used for inputting the first text, the second text, the target key information, the target business knowledge and other business data in the hot-line service system, so that a wiring party does not need to manually input the business data, and the labor cost is reduced.

In the embodiment of the application, the RPA hotline service robot responds to the service hotline being answered, acquires dialogue voice of a connecting party and an incoming party, performs voice recognition on the dialogue voice based on a voice recognition ASR technology to acquire a first text corresponding to the incoming party and a second text corresponding to the connecting party, analyzes the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice, acquires and displays corresponding target business knowledge according to the target key information, responds to the hanging-up of the service hotline, records the first text, the second text, the target key information and the target business knowledge into a hotline service system, thereby displaying the target business knowledge corresponding to the target key information by adopting a mode of combining RPA and AI to provide reference for the real-time processing of the service hotline by the connecting party, therefore, the quality and the efficiency of service handling are improved, and the labor cost is reduced because the service data does not need to be input manually.

With reference to fig. 2, a process of acquiring and displaying target service knowledge corresponding to target key information in the hotline service processing method for RPA and AI provided in the embodiment of the present application is further described below.

Fig. 2 is a flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present application, as shown in fig. 2, the method includes:

step 201, in response to the service hotline being answered, obtaining the conversation voice of the caller and the caller.

Step 202, based on the ASR technology, speech recognition is performed on the spoken speech to obtain a first text corresponding to the caller and a second text corresponding to the caller.

Step 203, analyzing the first text and the second text based on the NLP technology to obtain the target key information in the dialogue voice.

The specific implementation process and principle of steps 201-203 can refer to the above embodiments, which are not limited in this application.

And 204, inquiring a first corresponding relation between each key information and each business knowledge according to the target key information to acquire the target business knowledge corresponding to the target key information.

And step 205, displaying the target business knowledge through the hot line service system.

In the embodiment of the application, a first corresponding relation between each piece of key information and each piece of business knowledge can be obtained through learning in a machine learning mode in advance according to historical business data, and the first corresponding relation is stored in a knowledge base, so that after the RPA hot-line service robot obtains the target key information, the RPA hot-line service robot can search the knowledge base for the key information matched with the target key information, use the found business knowledge corresponding to the key information as the target business knowledge, and further display the target business knowledge through a hot-line service system.

The historical service data may be service data entered after an experienced operator answers a service hotline call and processes a service according to experience, or may be service data entered after the operator answers the service hotline call and processes the service according to target service knowledge recommended by the RPA hotline service robot, which is not limited in the present application.

The first corresponding relation between each key information and each service knowledge is inquired according to the target key information to obtain the target service knowledge corresponding to the target key information, and then the target service knowledge is displayed through the hot line service system, and a reference is provided for a connector to process services in real time, so that an inexperienced connector can quickly obtain the service knowledge relevant to the requirement of the caller of the incoming call without searching a knowledge base, the service handling efficiency is improved, the connector can answer the caller with reference to the target service knowledge, the service handling accuracy is improved, and the service handling quality is improved.

It should be noted that, in a possible implementation form, there may be key information completely matching target key information in the knowledge base, and at this time, business knowledge corresponding to the key information may be directly used as target business knowledge and displayed through the hotline service system.

In another possible implementation form, the knowledge base may not have key information completely matching the target key information, and at this time, a plurality of pieces of first key information with a high matching degree with the target key information in the knowledge base may be determined, and business knowledge corresponding to the plurality of pieces of first key information is used as the target business knowledge and is displayed through the hotline service system, so that the connecting party can automatically select which business knowledge to answer the incoming call party according to the business knowledge corresponding to the plurality of pieces of first key information.

That is, in the embodiment of the present application, step 204 may be implemented by: inquiring the first corresponding relation according to the target key information to obtain a plurality of candidate business knowledge corresponding to the target key information; and taking the plurality of candidate business knowledge as target business knowledge. The candidate business knowledge is business knowledge corresponding to the first key information. The plurality of first key information are key information, the matching degree of the key information with the target key information in the knowledge base is greater than a preset first threshold value. The first threshold is preset, and may be set as needed, which is not limited in this application.

In another possible implementation form, at least one candidate business knowledge meeting the preset condition in the plurality of candidate business knowledge may be used as the target business knowledge and displayed through the hotline service system, so that the caller can answer the caller according to the at least one candidate business knowledge. That is, step 204 may be implemented by: inquiring the first corresponding relation according to the target key information to obtain a plurality of candidate business knowledge corresponding to the target key information; and taking at least one candidate business knowledge meeting preset conditions from the candidate business knowledge as target business knowledge.

The preset condition may be set as required, for example, the browsing volume of the candidate service knowledge is greater than a preset second threshold, or the browsing volume of the candidate service knowledge is ranked in top N, where N is a positive integer greater than 0, and may be set as required.

And step 206, responding to the hanging up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into the hotline service system.

In the embodiment of the application, in response to the hanging-up of the service hotline, the RPA hotline service robot can input the first text, the second text, the target key information, the target service knowledge and other service data in the hotline service system so as to backup the service content of the incoming call, thereby facilitating the follow-up tracing of the service content of the incoming call. Moreover, the business data recorded into the hotline service system can also be used as historical business data for further machine learning, and data support is provided for subsequent business consultation, complaint advice and other businesses.

In the embodiment of the application, the RPA hotline service robot responds to the answering of the service hotline, acquires the dialogue voice of a connector and a caller, performs voice recognition on the dialogue voice based on a voice recognition ASR technology to acquire a first text corresponding to the caller and a second text corresponding to the connector, analyzes the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice, inquires a first corresponding relation between each key information and each business knowledge according to the target key information to acquire target business knowledge corresponding to the target key information, displays the target business knowledge through the hotline service system, responds to the hanging-off of the service hotline, records the first text, the second text, the target key information and the target business knowledge into the hotline service system, and therefore, by adopting a mode of combining RPA and AI, target business knowledge corresponding to the target key information is displayed through the hot line service system, reference is provided for a connector to process the business of the service hot line in real time, and therefore quality and efficiency of business handling are improved, and due to the fact that business data do not need to be input manually, labor cost is reduced.

Through the analysis, when the demand of the caller is question consultation and the like, the caller can process and reply to the caller in real time according to the displayed target business knowledge. In a possible implementation form, the requirement of the caller may be a complaint suggestion, and such services cannot be processed in real time and need to be sent to a certain acceptance department for processing, and the hotline service processing method for RPA and AI provided in the embodiment of the present application is further described below with reference to fig. 3 for the above-mentioned situation.

Fig. 3 is a flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present application, as shown in fig. 3, the method includes:

step 301, in response to the service hotline being answered, obtaining the conversation voice of the caller and the caller.

Step 302, based on the ASR technology, speech recognition is performed on the spoken speech to obtain a first text corresponding to the caller and a second text corresponding to the caller.

Step 303, analyzing the first text and the second text based on the NLP technology to obtain target key information in the dialogue speech.

And 304, acquiring and displaying corresponding target business knowledge according to the target key information.

And 305, responding to the hanging up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into the hotline service system.

The specific implementation process and principle of the steps 301-305 can refer to the description of the above embodiments, and are not described herein again.

Step 306, according to the target key information in the dialogue voice, querying a second corresponding relation between each key information and each service category to obtain a target service category to which the target key information belongs.

In the embodiment of the application, after the service hotline is hung up, if the wiring party determines that the requirement of the caller of the incoming call cannot be processed in real time and the service needs to be dispatched to a certain acceptance department for processing, a dispatching order instruction can be issued to the RPA hotline service robot, so that the RPA hotline service robot can respond to the received dispatching order instruction and execute the step 306 and subsequent steps. The order dispatching instruction may be implemented in various ways, for example, the order dispatching instruction may be triggered in a manner of voice and/or text, and for example, the order dispatching instruction may also be triggered in a manner of triggering a designated control on a dialog interaction interface, which is not specifically limited in this embodiment of the present application.

In the embodiment of the application, a second corresponding relationship between each piece of key information and each service category can be obtained by learning in a machine learning manner in advance according to historical service data, so that the RPA hot line service robot can query the second corresponding relationship between each piece of key information and each service category according to target key information in conversation voice, and use the service category corresponding to the searched key information matched with the target key information as the target service category. By utilizing the RPA hot line service robot to intelligently determine the target class, the problem of non-uniform judgment standards existing in the manual determination of the target business class is avoided, and the accuracy of the determined target business class and the business processing efficiency are improved.

It should be noted that, in a possible implementation form, there may be key information that is completely matched with the target key information, and at this time, the service category corresponding to the key information may be directly used as the target service category. In another possible implementation form, there may not be key information that completely matches the target key information, and at this time, a plurality of pieces of second key information having a higher matching degree with the target key information may be determined, and the service categories corresponding to the plurality of pieces of second key information are displayed as target service categories through the hotline service system, so that the operator may select, by himself or herself, the target service category to which the target key information belongs according to the service categories corresponding to the plurality of pieces of second key information.

That is, in the embodiment of the present application, step 306 may be implemented by: according to the target key information, inquiring a second corresponding relation between each key information and each service category to obtain a plurality of candidate service categories to which the target key information belongs; displaying a plurality of candidate business categories; in response to a first traffic class of the plurality of candidate traffic classes being selected, the first traffic class is determined to be the target traffic class.

The plurality of candidate service categories are service categories corresponding to the plurality of second key information respectively. The plurality of second key information is key information of which the matching degree with the target key information is greater than a preset third threshold value. The third threshold is preset, and may be set as needed, which is not limited in this application.

Step 307, according to the target service category, querying a third corresponding relationship between each service category and each receiving department to obtain a target receiving department corresponding to the target service category.

In the embodiment of the application, a third corresponding relationship between each service category and each accepting department may be preset, or the third corresponding relationship between each service category and each accepting department may be obtained through machine learning according to historical service data, so that the RPA hot-line service robot may query the third corresponding relationship between each service category and each accepting department according to a target service category, and accurately obtain a target accepting department corresponding to the target service category.

And 308, accessing the service system of the target acceptance department, and inputting the first text, the second text, the target key information and the target service type into the service system of the target acceptance department.

In the embodiment of the application, after the RPA hotline service robot acquires the target acceptance department door corresponding to the target business category, the RPA hotline service robot can log in the business system of the target acceptance department, and record the first text, the second text, the target key information and the target business category into the business system of the target acceptance department.

Therefore, the RPA hot-line service robot can accurately and quickly determine the target acceptance department of the business corresponding to the incoming call according to the dialogue voice between the caller and the caller of the incoming call by combining the AI technology, and then automatically transfer the business corresponding to the incoming call to the target acceptance department, thereby improving the accuracy and efficiency of business handling and reducing the labor cost.

In addition, in the embodiment of the application, the RPA hotline service robot can also record the target service category and the target acceptance department into the hotline service system to perform service data backup, so as to facilitate follow-up of the subsequent processing flow of the service of the current call. The process of entering the target business category and the target acceptance department into the hotline service system may be executed between

steps

307 and 308, or may be executed after step 308, which is not limited in the present application.

It can be understood that, after the RPA hotline service robot enters the service data in the service system of the target acceptance department, the target acceptance department can perform service processing according to the service data, and enter the service processing data including the processing procedure and the processing result into the service system of the target acceptance department. The RPA hotline service robot can follow up the subsequent processing flow of the business data, and after the target acceptance department inputs the business processing data into the business system of the target acceptance department, the RPA hotline service robot acquires the business processing data from the business system of the target acceptance department and then inputs the business processing data into the hotline service system. Therefore, the backup of the business data aiming at the current incoming call can be completed, and the business processing data recorded into the hotline service system can also be used as historical business data for further machine learning and providing data support for subsequent business consultation, complaint suggestions and other businesses. And the RPA hot-line service robot is used for data entry in the hot-line service system and the business system of the target acceptance department, so that the labor cost required by the data entry is reduced.

In the embodiment of the application, the RPA hot-line service robot queries the second corresponding relationship between each key information and each service category according to the target key information in the conversation voice to obtain the target service category to which the target key information belongs, queries the third corresponding relationship between each service category and each acceptance department according to the target service category to obtain the target acceptance department corresponding to the target service category, accesses the service system of the target acceptance department, and records the first text, the second text, the target key information and the target service category into the service system of the target acceptance department, so as to realize the accurate and rapid determination of the target acceptance department of the service according to the conversation voice between the caller and the operator of the current call by combining the RPA and AI technologies, and further automatically transfer the service corresponding to the current call to the target acceptance department, thereby improving the accuracy and efficiency of the service handling, the labor cost is reduced.

The hotline service processing method combining RPA and AI provided by the present application is explained with reference to fig. 4.

Referring to fig. 4, the hotline service system may provide a service portal, such as a service hotline or a hotline portal, so that a user may make a question consultation or complaint recommendation, etc. by dialing the service hotline or logging into the service hotline portal.

After the service hotline is answered, in response to the service hotline being answered, the RPA hotline service robot can acquire conversation voice of the caller and the caller, and performs voice recognition on the conversation voice based on an ASR (access router) technology to acquire a first text corresponding to the caller and a second text corresponding to the caller. Wherein, the second text corresponding to the wiring party is supposed to be 'good you, ask what can help you' for asking for, and the first text corresponding to the calling party is 'construction at night 23:23 of the construction site B in the area A, noise disturbing residents, complaints, and hope department intervention processing'.

Further, the RPA hotline service robot may analyze the first text and the second text based on NLP technology, understand the intention of the caller, and obtain the target key information in the conversation voice: time "23: 23 at night", place "a district B site", event "construction", "noise disturbing residents", intention "complaint". Further, the RPA hotline service robot may query a first corresponding relationship between each key information and each business knowledge according to the target key information, obtain a target business knowledge corresponding to the target key information, where the problem belongs to a city and countryside construction problem and needs to be handled and solved by a residential building bureau, and display the target business knowledge through the hotline service system. The first corresponding relation can be obtained through historical business data and machine learning. The caller can determine that the demand of the caller is a complaint suggestion according to experience and target service knowledge displayed on the hotline service system, the service cannot be processed in real time and needs to be dispatched to a certain acceptance department for processing, so that the caller can inform the caller that the service is recorded and can be transferred to a building office to accept the service.

Therefore, by adopting a mode of combining the RPA and the AI, the target business knowledge corresponding to the target key information is displayed, and reference is provided for a connector to process the business of the service hotline in real time, so that an inexperienced connector can quickly acquire the business knowledge related to the requirement of the caller of the call without searching a knowledge base, the business handling efficiency is improved, the labor cost is reduced, and the connector can reply the caller with reference to the target business knowledge, thereby the business handling accuracy is improved, and the business handling quality is improved.

After the service hotline is hung up, the RPA hotline service robot can automatically input the first text, the second text, the target key information and the target business knowledge into the hotline service system so as to backup the business content of the incoming call, the follow-up tracing of the business content of the incoming call is facilitated, a wiring party does not need to manually input business data, and therefore labor cost required for inputting the business data is reduced.

Further, the wiring party can issue a dispatching order to the RPA hotline service robot, so that the RPA hotline service robot can query a second corresponding relationship between each piece of key information and each service category according to target key information in the conversation voice, determine that the target service category to which the target key information belongs is an urban and rural construction category, and because an acceptance department corresponding to the urban and rural construction category is a residential building bureau, the RPA hotline service robot can determine that the target acceptance department is the residential building bureau, further access the service system of the residential building bureau, and input the first text, the second text, the target key information and the target service category into the service system of the residential building bureau.

In addition, the RPA hotline service robot can record the target business category and the target acceptance department into the hotline service system for backup, and follow up the subsequent processing flow of the business of the incoming call according to the backup data. After the building office performs service processing on the complaint suggestion, the service processing data including the processing process and the processing result can be recorded into a service system of the building office, so that the RPA hotline service robot can acquire the service processing data from the service system of the building office and record the service processing data into the hotline service system. Moreover, the business processing data recorded into the hotline service system can also be used as historical business data for further machine learning, and data support is provided for subsequent business consultation, complaint suggestion and other businesses.

Therefore, the method and the device realize the combination of the RPA and the AI technology, accurately and quickly determine the target acceptance department of the business according to the conversation voice between the caller and the caller of the call, and then automatically transfer the business corresponding to the call to the target acceptance department, thereby improving the accuracy and efficiency of business handling and reducing the labor cost. And the RPA hot-line service robot is used for data entry in the hot-line service system and the business system of the target acceptance department, so that the labor cost required by the data entry is reduced.

In order to implement the above embodiments, the present application further provides a hotline service processing apparatus combining RPA and AI. Fig. 5 is a schematic structural diagram of a hotline service processing device combining RPA and AI according to an embodiment of the present application.

As shown in fig. 5, the hotline service processing apparatus 500 combining RPA and AI is applied to an RPA hotline service robot, and includes: a first obtaining module 501, an identifying module 502, an analyzing module 503, a processing module 504 and a first entering module 505.

The first obtaining module 501 is configured to obtain a conversation voice between a caller and a receiver in response to the service hotline being answered;

the recognition module 502 is configured to perform speech recognition on speech based on an ASR (speech recognition) technology to obtain a first text corresponding to a caller and a second text corresponding to a caller;

the parsing module 503 is configured to parse the first text and the second text based on a natural language processing NLP technology to obtain target key information in the dialog speech;

the processing module 504 is configured to obtain and display corresponding target business knowledge according to the target key information;

and the first entry module 505 is configured to, in response to the hanging-up of the service hotline, enter the first text, the second text, the target key information, and the target business knowledge into the hotline service system.

It should be noted that, the hotline service processing device combining the RPA and the AI according to the embodiment of the present application may execute the hotline service processing method combining the RPA and the AI, and the hotline service processing device combining the RPA and the AI may be implemented by an RPA hotline service robot, for example, the hotline service processing device combining the RPA and the AI may be an RPA hotline service robot, or the hotline service processing device combining the RPA and the AI may be configured in the RPA hotline service robot, which is not limited in this application.

The hotline service processing apparatus combining the RPA and the AI may be configured in an electronic device, where the electronic device may include, but is not limited to, a terminal device, a server, and the like, and the embodiment does not specifically limit the electronic device.

In one embodiment of the present application, the processing module 504 includes:

the first acquisition unit is used for inquiring a first corresponding relation between each piece of key information and each piece of business knowledge according to the target key information so as to acquire the target business knowledge corresponding to the target key information;

and the first display unit is used for displaying the target business knowledge through the hotline service system.

In an embodiment of the present application, the first obtaining unit is specifically configured to:

inquiring the first corresponding relation according to the target key information to obtain a plurality of candidate business knowledge corresponding to the target key information;

and taking at least one candidate business knowledge meeting preset conditions from the candidate business knowledge as target business knowledge.

In an embodiment of the present application, the hotline service processing apparatus 500 combining RPA and AI further includes:

the second acquisition module is used for inquiring a second corresponding relation between each key information and each service category according to the target key information in the conversation voice so as to acquire the target service category to which the target key information belongs;

the third acquisition module is used for inquiring a third corresponding relation between each service category and each acceptance department according to the target service category so as to acquire the target acceptance department corresponding to the target service category;

and the second input module is used for accessing the service system of the target acceptance department and inputting the first text, the second text, the target key information and the target service type into the service system of the target acceptance department.

In one embodiment of the present application, the second obtaining module includes:

the second obtaining unit is used for inquiring a second corresponding relation between each key information and each service category according to the target key information so as to obtain a plurality of candidate service categories to which the target key information belongs;

the second display unit is used for displaying a plurality of candidate service categories;

a processing unit, configured to determine a first traffic class of the plurality of candidate traffic classes as a target traffic class in response to the first traffic class being selected.

and the third input module is used for inputting the target business category and the target acceptance department into the hotline service system.

the fourth acquisition module is used for acquiring service processing data corresponding to the conversation voice from a service system of the target acceptance department;

and the fourth recording module is used for recording the business processing data into the hotline service system.

and the display module is used for displaying the first text and the second text.

It should be noted that the foregoing explanation on the embodiment of the hotline service processing method in combination with the RPA and the AI is also applicable to the hotline service processing device in combination with the RPA and the AI of this embodiment, and details that are not published in the embodiment of the hotline service processing device in combination with the RPA and the AI of this application are not described here again.

To sum up, the hotline service processing apparatus combining RPA and AI according to the embodiment of the present application obtains the dialogue speech between the caller and the caller in response to the service hotline being answered, performs speech recognition on the dialogue speech based on the speech recognition ASR technology to obtain the first text corresponding to the caller and the second text corresponding to the caller, analyzes the first text and the second text based on the natural language processing NLP technology to obtain the target key information in the dialogue speech, obtains and displays the corresponding target service knowledge according to the target key information, inputs the first text, the second text, the target key information and the target service knowledge into the hotline service system in response to the service hotline being hung up, thereby displays the target service knowledge corresponding to the target key information by using the RPA and AI combination manner, and provides a reference for the caller to process the service of the service hotline in real time, therefore, the quality and the efficiency of service handling are improved, and the labor cost is reduced because the service data does not need to be input manually.

In order to implement the foregoing embodiment, an electronic device is further provided in an embodiment of the present disclosure, and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the hotline service processing method according to any one of the foregoing method embodiments is implemented by combining an RPA and an AI.

In order to implement the foregoing embodiments, the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the hotline service processing method in combination with RPA and AI according to any of the foregoing method embodiments.

In order to implement the foregoing embodiments, the present disclosure further provides a computer program product, wherein when being executed by an instruction processor of the computer program product, the hotline service processing method combining RPA and AI according to any one of the foregoing method embodiments is implemented.

FIG. 6 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in fig. 6 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, electronic device 12 is embodied in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described in this disclosure.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public Network such as the Internet via the Network adapter 20. As shown in FIG. 6, the network adapter 20 communicates with the other modules of the electronic device 12 via the bus 18. It should be appreciated that although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, implementing the methods mentioned in the foregoing embodiments.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure, and that changes, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present disclosure.

Claims

1. A hotline business processing method combining Robot Process Automation (RPA) and Artificial Intelligence (AI), which is applied to an RPA hotline service robot, and comprises the following steps:

responding to the answering of the service hotline, and acquiring the conversation voice of the caller and the caller;

based on a speech recognition ASR technology, performing speech recognition on the conversation speech to obtain a first text corresponding to the caller and a second text corresponding to the caller;

analyzing the first text and the second text based on a Natural Language Processing (NLP) technology to acquire target key information in the dialogue voice;

acquiring and displaying corresponding target business knowledge according to the target key information;

and responding to the hanging-up of the service hotline, and inputting the first text, the second text, the target key information and the target business knowledge into a hotline service system.

2. The method according to claim 1, wherein the acquiring and presenting the corresponding target business knowledge according to the target key information comprises:

inquiring a first corresponding relation between each key information and each business knowledge according to the target key information to acquire the target business knowledge corresponding to the target key information;

and displaying the target business knowledge through the hot line service system.

3. The method according to claim 2, wherein the querying, according to the target key information, a first corresponding relationship between each key information and each business knowledge to obtain the target business knowledge corresponding to the target key information comprises:

and taking at least one candidate business knowledge meeting preset conditions in the candidate business knowledge as the target business knowledge.

4. The method according to any one of claims 1-3, further comprising:

inquiring a second corresponding relation between each key information and each service category according to the target key information in the conversation voice so as to obtain a target service category to which the target key information belongs;

inquiring a third corresponding relation between each service category and each acceptance department according to the target service category to obtain a target acceptance department corresponding to the target service category;

and accessing the business system of the target acceptance department, and inputting the first text, the second text, the target key information and the target business category into the business system of the target acceptance department.

5. The method according to claim 4, wherein the querying, according to the target key information in the conversational speech, a second correspondence between each key information and each service category to obtain a target service category to which the target key information belongs comprises:

inquiring a second corresponding relation between each piece of key information and each service category according to the target key information to obtain a plurality of candidate service categories to which the target key information belongs;

displaying a plurality of the candidate business categories;

in response to a first traffic class of the plurality of candidate traffic classes being selected, determining the first traffic class as the target traffic class.

6. The method according to claim 4, wherein after the querying a third corresponding relationship between each service category and each receiving department according to the target service category to obtain a target receiving department corresponding to the target service category, the method further comprises:

and inputting the target business category and the target acceptance department into the hot line service system.

7. The method of claim 4, wherein after entering the first text, the second text, the target key information, and the target business category into a business system of the target acceptance department, the method further comprises:

acquiring service processing data corresponding to the conversation voice from a service system of the target acceptance department;

and recording the business processing data into the hot line service system.

8. A hotline service processing device combining RPA and AI, which is applied to an RPA hotline service robot, and comprises:

the first acquisition module is used for responding to the answering of the service hotline and acquiring the conversation voice of the caller and the caller;

the recognition module is used for carrying out voice recognition on the conversation voice based on a voice recognition ASR technology so as to obtain a first text corresponding to the caller and a second text corresponding to the caller;

the analysis module is used for analyzing the first text and the second text based on a Natural Language Processing (NLP) technology so as to acquire target key information in the dialogue voice;

the processing module is used for acquiring and displaying corresponding target business knowledge according to the target key information;

and the first entry module is used for responding to the hanging-up of the service hotline and entering the first text, the second text, the target key information and the target business knowledge into a hotline service system.

9. The apparatus of claim 8, wherein the processing module comprises:

10. The apparatus according to claim 9, wherein the first obtaining unit is specifically configured to:

11. The apparatus according to any one of claims 8-10, further comprising:

the second acquisition module is used for inquiring a second corresponding relation between each piece of key information and each service category according to the target key information in the conversation voice so as to acquire a target service category to which the target key information belongs;

a third obtaining module, configured to query, according to the target service category, a third correspondence between each service category and each acceptance department, so as to obtain a target acceptance department corresponding to the target service category;

12. The apparatus of claim 11, wherein the second obtaining module comprises:

a second obtaining unit, configured to query, according to the target key information, a second correspondence between each key information and each service category to obtain multiple candidate service categories to which the target key information belongs;

a processing unit, configured to determine a first traffic class of the plurality of candidate traffic classes as the target traffic class in response to the first traffic class being selected.

13. The apparatus of claim 11, further comprising:

and the third input module is used for inputting the target business category and the target acceptance department into the hot line service system.

14. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-7 when executing the computer program.

15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.