WO2023137866A1 - 结合rpa和ai的热线业务处理方法、装置及电子设备 - Google Patents

结合rpa和ai的热线业务处理方法、装置及电子设备 Download PDF

Info

Publication number
WO2023137866A1
WO2023137866A1 PCT/CN2022/083447 CN2022083447W WO2023137866A1 WO 2023137866 A1 WO2023137866 A1 WO 2023137866A1 CN 2022083447 W CN2022083447 W CN 2022083447W WO 2023137866 A1 WO2023137866 A1 WO 2023137866A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
business
key information
service
hotline
Prior art date
Application number
PCT/CN2022/083447
Other languages
English (en)
French (fr)
Inventor
焦栋
Original Assignee
来也科技(北京)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 来也科技(北京)有限公司 filed Critical 来也科技(北京)有限公司
Publication of WO2023137866A1 publication Critical patent/WO2023137866A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • 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
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Definitions

  • the present disclosure relates to the technical field of robotic process automation (RPA) and artificial intelligence (AI), in particular to a hotline service processing method, device and electronic equipment combining RPA and AI.
  • RPA robotic process automation
  • AI artificial intelligence
  • Robotic Process Automation uses specific "robot software” to simulate human operations on computers and automatically execute process tasks according to rules.
  • AI Artificial Intelligence
  • the present disclosure provides a hotline service processing method, device and electronic equipment combining RPA and AI to solve the technical problems of low service efficiency, high labor cost and poor service quality of service hotline in related technologies.
  • the embodiment of the first aspect of the present disclosure provides a hotline service processing method combining RPA and AI, which is applied to an RPA hotline service robot.
  • the method includes: in response to the service hotline being answered, obtain the dialogue voice between the connection party and the caller; based on the speech recognition ASR technology, perform voice recognition on the dialogue voice to obtain the first text corresponding to the caller and the second text corresponding to the connection party; based on natural language processing (NLP) technology, analyze the first text and the second text to obtain the target key information in the dialogue voice; according to the target key information, obtain and display the corresponding target service Knowledge: in response to the service hotline being hung up, inputting the first text, the second text, target key information and target business knowledge into the hotline service system.
  • NLP natural language processing
  • the embodiment of the second aspect of the present disclosure provides a hotline business processing device combining RPA and AI, which is applied to an RPA hotline service robot.
  • the device includes: a first acquisition module, which is used to respond to the service hotline being answered, and obtain the dialogue voice between the connection party and the caller; a recognition module, which is used to perform voice recognition on the dialogue voice based on the speech recognition ASR technology, so as to obtain the first text corresponding to the caller and the second text corresponding to the connection party; the analysis module is used to analyze the first text and the second text based on natural language processing (NLP) technology, so as to obtain the target in the dialogue voice
  • NLP natural language processing
  • the embodiment of the third aspect of the present disclosure proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor.
  • the processor executes the computer program, the method described in the embodiment of the first aspect of the present disclosure is implemented.
  • the embodiment of the fourth aspect of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method described in the above-mentioned embodiment of the first aspect of the present disclosure is implemented.
  • the embodiment of the fifth aspect of the present disclosure provides a computer program product, including a computer program.
  • the computer program is executed by a processor, the method as described in the above-mentioned embodiment of the first aspect of the present disclosure is implemented.
  • the target key information in the dialogue voice between the connection party and the caller is obtained, and then the target business knowledge corresponding to the target key information is obtained and displayed, which provides a reference for the connection party to handle the service hotline business in real time, thereby improving the quality and efficiency of business processing, and reducing labor costs because there is no need to manually enter business data.
  • Fig. 1 is a schematic flowchart of a hotline service processing method combining RPA and AI according to an embodiment of the present disclosure.
  • Fig. 2 is a schematic flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present disclosure.
  • Fig. 3 is a schematic flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present disclosure.
  • Fig. 4 is a schematic 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 disclosure.
  • Fig. 6 is a block diagram of an electronic device for implementing the hotline service processing method combining RPA and AI according to an embodiment of the present disclosure.
  • This disclosure provides a combination of RPA and AI, using an RPA hotline service robot to replace manual labor to record the needs of callers, answer the questions of callers, and enter business data in the hotline service system. Since the RPA hotline service robot can work 7*24 hours without interruption as long as it has data, it can greatly reduce labor costs and improve the efficiency of business processing. By using the combination of RPA and AI to record the needs of callers, answer the questions of callers, and enter business data in the hotline service system. Can guarantee the quality of business processing.
  • service hotline refers to a hotline that provides users with services such as question consultation, business acceptance, complaints and suggestions, such as government service hotlines, shopping service hotlines, etc.
  • hotline service system refers to the business system corresponding to the service hotline, on which the business corresponding to the service hotline can be processed, such as business acceptance, backup user consultation issues or user complaints and suggestions, etc.
  • the hotline service system can also use the hotline portal website as the service entrance, so that users can not only dial the service hotline, but also log in to the hotline portal website to consult questions or make complaints and suggestions.
  • business refers to the work that needs to be handled according to the needs of the caller after the service hotline calls.
  • RPA hotline service robot refers to an RPA robot that can automatically process service hotline business by combining AI technology and RPA technology.
  • the "connecting party” refers to the party answering the service hotline, such as an operator.
  • “Caller” refers to the party who dials the service hotline, such as citizens and other users.
  • acceptance department refers to the business acceptance department corresponding to the service hotline.
  • the accepting departments may include: Housing Construction Bureau, which handles housing construction business, the Education Bureau, which handles education business, and the Environmental Protection Bureau, which handles environmental protection business. wait.
  • Housing Construction Bureau which handles housing construction business
  • the Education Bureau which handles education business
  • the Environmental Protection Bureau which handles environmental protection business. wait.
  • Business system of the acceptance department refers to the system used by the acceptance department to process business.
  • service category refers to the category to which the service corresponding to the service hotline belongs.
  • the service hotline is a government service hotline, that is, the business corresponding to the service hotline is all kinds of government affairs, then the business category can include discipline inspection and supervision, urban and rural construction, environmental protection, rural agriculture, education, etc.
  • business knowledge refers to information related to business processing of the service hotline.
  • the business knowledge can provide references for the connection party to handle business, thereby assisting the connection party to better handle business. For example, when the caller complains about a certain incident, the business knowledge includes which acceptance department needs to handle the business, or when the caller inquires about a certain question, the business knowledge includes how to answer the question, etc.
  • ASR Automatic Speech Recognition
  • a technology for converting human speech into text The goal of "ASR” is to convert the lexical content of human speech into computer-readable input, such as keystrokes, binary codes, or sequences of characters.
  • Fig. 1 is a flowchart of a hotline service processing method combining RPA and AI according to an embodiment of the present disclosure. As shown in Figure 1, the method may include the following steps:
  • Step 101 in response to the service hotline being answered, acquire the dialogue voice between the connecting party and the calling party.
  • the hotline service processing method combining RPA and AI in the embodiment of the present disclosure is performed by a hotline service processing device combining RPA and AI.
  • the hotline service processing device combining RPA and AI is referred to as a hotline service processing device for short.
  • the hotline service processing device can be implemented by an RPA hotline service robot.
  • the hotline service processing device can be an RPA hotline service robot, or the hotline service processing device can be configured in an RPA hotline service robot, which is not limited in this disclosure.
  • the RPA hotline service robot may be configured in an electronic device, and the electronic device may include but not limited to a terminal device, a server, etc., and this embodiment does not specifically limit the electronic device.
  • Embodiments of the present disclosure are illustrated by taking the hotline service processing device as an example of an RPA hotline service robot installed in a terminal device.
  • the RPA hotline service robot in this embodiment can execute the method in a specific time period or in real time throughout the day, which is not limited in the present disclosure.
  • the specific time period can be set as required.
  • the above-mentioned RPA hotline service robot may also be activated based on receiving an activation instruction.
  • the connection party can trigger the above-mentioned activation instruction for the RPA hotline service robot through dialogue.
  • triggering the starting command for the RPA hotline service robot can be realized in various ways, for example, the starting command of the RPA hotline service robot can be triggered by voice and/or text, and for example, the starting command of the RPA hotline service robot can also be triggered by triggering a specified control on the dialogue interaction interface, which is not specifically limited in the embodiments of the present disclosure.
  • the connecting party when the service hotline calls, the connecting party can answer the call, and in response to the service hotline being answered, the RPA hotline service robot can obtain the dialogue voice between the connecting party and the calling party in real time during the dialogue process between the calling party and the connecting party.
  • Step 102 Based on the ASR technology for speech recognition, speech recognition is performed on the dialogue speech to obtain the first text corresponding to the calling party and the second text corresponding to the connecting party.
  • the RPA hotline service robot can perform speech recognition on the dialogue voice in real time based on the ASR technology, and convert the dialogue voice into text, and, through the ASR technology, can distinguish the voices of the connecting party and the calling party in real time, thereby obtaining the first text corresponding to the calling party and the second text corresponding to the connecting party.
  • the RPA hotline service robot after the RPA hotline service robot obtains the first text corresponding to the caller and the second text corresponding to the connection party, it can also display the first text and the second text through the human-computer interaction interface of the hotline service system, so as to facilitate the connection party to view.
  • Step 103 based on natural language processing (NLP) technology, analyze the first text and the second text to obtain target key information in the dialog speech.
  • NLP natural language processing
  • the RPA hotline service robot can analyze the first text and the second text in real time based on natural language processing (Natural Language Processing, NLP) technology, understand the intention of the calling party, and obtain the target key information in the dialogue voice.
  • natural language processing Natural Language Processing, NLP
  • the target key information is key information that can indicate the needs of the caller, for example, it may include key information such as the caller's intention, problem description, event, event time, location, and person in the dialogue voice.
  • the RPA hotline service robot can obtain the key target information in the dialogue voice: time “23:23 at night”, location “A district B construction site”, event “construction”, “noise disturbance”, and intention “complaint”.
  • Step 104 according to the target key information, acquire and display the corresponding target business knowledge.
  • target service knowledge refers to service knowledge related to the needs of the caller of the current call. For example, when the demand of the caller of this call is to complain about a certain event, the target business knowledge may include which acceptance department needs to accept the business; or, when the demand of the caller of this call is to consult a certain question, the target business knowledge may include the answer to the question consulted by the caller.
  • the corresponding relationship between each key information and each business knowledge can be stored in the knowledge base, so that the RPA hotline service robot can search the knowledge base to find the key information matching the target key information in the knowledge base, and use the found business knowledge corresponding to the key information as the target business knowledge.
  • the target business knowledge after obtaining the target business knowledge corresponding to the target key information, the target business knowledge can be displayed.
  • the target business knowledge when displaying the target business knowledge, it can be displayed through the human-computer interaction interface of the hotline service system, so that the connection party can perform business processing according to the target business knowledge displayed on the human-computer interaction interface.
  • target business knowledge when displaying target business knowledge, it may be displayed in a preset manner, which is not limited in the present disclosure. For example, all the content of the target business knowledge can be displayed, or, when the content of the target business knowledge is large, the keywords of the target business knowledge can be displayed first, and then all the content of the target business knowledge can be displayed after the connection party clicks on the keyword.
  • the RPA hotline service robot is based on NLP technology, and the target key information obtained from the dialogue voice includes: time “weekend”, location "A hospital”, event "doctor consultation”. Then the RPA robot can obtain the key information matching the target key information from the knowledge base by searching the knowledge base. Assume that the business knowledge corresponding to the key information "weekend", "A hospital” and “doctor consultation” in the knowledge base includes "A hospital has a doctor on weekends”.
  • the RPA hotline service robot is based on NLP technology, and the key target information obtained from the dialogue voice includes: time “23:23 at night”, location "A district B construction site”, event “construction”, “noise disturbance”, and intention “complaint”. Then the RPA robot can obtain the key information matching the target key information from the knowledge base by searching the knowledge base.
  • the RPA hotline service robot can use this business knowledge as the target business knowledge, and display the target business knowledge through the human-computer interface of the hotline service system, so that the connection party can Reply to the caller based on the target business knowledge.
  • the connection party can inform the caller that the business has been recorded and will pass it on to the Housing and Urban-Rural Development Bureau to accept the business.
  • connection party By obtaining and displaying the corresponding target business knowledge according to the target key information, it provides a reference for the connection party to process the business in real time, so that the inexperienced connection party can quickly obtain the business knowledge related to the needs of the caller of this call without searching the knowledge base, thereby improving the efficiency of business processing and reducing labor costs.
  • Step 105 in response to the service hotline being hung up, input the first text, the second text, target key information and target business knowledge into the hotline service system.
  • the RPA hotline service robot in response to the service hotline being hung up, can enter business data such as the first text, the second text, target key information, and target business knowledge in the hotline service system, so as to back up the business content of this call, so as to facilitate subsequent traceability of the business content of this call.
  • RPA hotline service robot uses the RPA hotline service robot to enter business data such as the first text, the second text, target key information, and target business knowledge in the hotline service system, so that the connection party does not have to manually enter business data, reducing labor costs.
  • the RPA hotline service robot responds to the service hotline being answered, obtains the dialogue voice between the connection party and the caller, and performs voice recognition on the dialogue voice based on the speech recognition ASR technology to obtain the first text corresponding to the caller and the second text corresponding to the connection party, and based on the natural language processing (NLP) technology, parses the first text and the second text to obtain the key information of the dialogue.
  • NLP natural language processing
  • the target business knowledge corresponding to the target key information is displayed, which provides a reference for the connection party to process the business of the service hotline in real time, thereby improving the quality and efficiency of business processing, and reducing labor costs because there is no need to manually enter business data.
  • Fig. 2 is a flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present disclosure. As shown in Fig. 2, the method includes:
  • Step 201 in response to the service hotline being answered, acquire the dialogue voice between the connecting party and the calling party.
  • Step 202 Based on the speech recognition ASR technology, speech recognition is performed on the dialogue speech to obtain the first text corresponding to the calling party and the second text corresponding to the connecting party.
  • Step 203 based on natural language processing (NLP) technology, analyze the first text and the second text to obtain target key information in the dialog speech.
  • NLP natural language processing
  • Step 204 according to the target key information, query the first corresponding relationship between each key information and each business knowledge, so as to obtain the target business knowledge corresponding to the target key information.
  • Step 205 display the target business knowledge through the hotline service system.
  • the first correspondence between each key information and each business knowledge can be learned in advance based on historical business data through machine learning, and the first correspondence can be stored in the knowledge base, so that after the RPA hotline service robot acquires the target key information, it can search the knowledge base for key information that matches the target key information in the knowledge base, and use the found business knowledge corresponding to the key information as the target business knowledge, and then display the target business knowledge through the hotline service system.
  • the historical business data can be the business data entered after the experienced operator answers the call of the service hotline and handles the business based on experience, or it can be the business data entered after the operator answers the call of the service hotline and handles the business according to the target business knowledge recommended by the RPA hotline service robot, which is not limited in this disclosure.
  • the target key information query the first corresponding relationship between each key information and each business knowledge to obtain the target business knowledge corresponding to the target key information, and then display the target business knowledge through the hotline service system, which provides a reference for the connection party to process the business in real time, so that the inexperienced connection party does not need to search the knowledge base, but can quickly obtain the business knowledge related to the caller's needs for this call, thereby improving the efficiency of business processing.
  • the business knowledge corresponding to the key information can be directly used as the target business knowledge and displayed through the hotline service system.
  • the key information that completely matches the target key information may not exist in the knowledge base.
  • a plurality of first key information in the knowledge base that has a high degree of matching with the target key information may be determined, and the business knowledge corresponding to the multiple first key information is used as the target business knowledge, and displayed through the hotline service system, so that the connection party can choose which business knowledge to answer the caller based on the business knowledge corresponding to the multiple first key information.
  • step 204 may be implemented in the following manner: according to the target key information, query the first correspondence to obtain multiple candidate business knowledge corresponding to the target key information; and use the multiple candidate business knowledge as the target business knowledge.
  • the multiple candidate business knowledges are the business knowledge corresponding to the multiple first key information respectively.
  • the plurality of first key information is key information in the knowledge base whose matching degree with the target key information is greater than a preset first threshold.
  • the preset first threshold can be set as required, and the present disclosure does not limit this.
  • step 204 can be implemented in the following manner: according to the target key information, query the first corresponding relationship to obtain multiple candidate business knowledge corresponding to the target key information; among the multiple candidate business knowledge, at least one candidate business knowledge that satisfies a preset condition is used as the target business knowledge.
  • the preset condition can be set according to needs, for example, the number of views of the candidate business knowledge is greater than the preset second threshold, or the number of views of the candidate business knowledge ranks in the top N, where N is a positive integer greater than 0 and can be set according to needs.
  • Step 206 in response to the service hotline being hung up, input the first text, the second text, target key information and target business knowledge into the hotline service system.
  • the RPA hotline service robot in response to the service hotline being hung up, can enter business data such as the first text, the second text, target key information, and target business knowledge in the hotline service system, so as to back up the business content of this call, so as to facilitate subsequent traceability of the business content of this call.
  • the business data entered into the hotline service system can also be used as historical business data for further machine learning to provide data support for subsequent business consultation, complaints and suggestions.
  • the RPA hotline service robot responds to the service hotline being answered, obtains the dialogue voice between the connection party and the caller, and performs speech recognition on the dialogue voice based on the speech recognition ASR technology to obtain the first text corresponding to the caller and the second text corresponding to the connection party, and based on the natural language processing (NLP) technology, parses the first text and the second text to obtain the target key information in the dialogue voice.
  • the hotline service system displays the target business knowledge, and in response to the service hotline being hung up, enters the first text, the second text, target key information, and target business knowledge into the hotline service system.
  • the hotline service system displays the target business knowledge corresponding to the target key information, which provides a reference for the caller to handle the service hotline business in real time, thereby improving the quality and efficiency of business processing, and reducing labor costs because there is no need to manually enter business data.
  • the connection party can process and reply the caller in real time according to the displayed target business knowledge.
  • the demand of the caller may be complaints and suggestions, etc., which cannot be processed in real time and need to be dispatched to a certain acceptance department for processing.
  • the method for processing the hotline business of RPA and AI provided by the embodiment of the present disclosure will be further described below in combination with FIG. 3 .
  • Fig. 3 is a flowchart of a hotline service processing method combining RPA and AI according to another embodiment of the present disclosure. As shown in Fig. 3 , the method includes:
  • Step 301 in response to the service hotline being answered, acquire the dialogue voice between the connecting party and the calling party.
  • Step 302 Based on the speech recognition ASR technology, speech recognition is performed on the dialogue speech to obtain the first text corresponding to the calling party and the second text corresponding to the connecting party.
  • Step 303 based on natural language processing (NLP) technology, analyze the first text and the second text to obtain target key information in the dialogue speech.
  • NLP natural language processing
  • Step 304 according to the target key information, acquire and display the corresponding target business knowledge.
  • Step 305 in response to the service hotline being hung up, input the first text, the second text, target key information and target business knowledge into the hotline service system.
  • Step 306 according to the target key information in the dialogue voice, query the second corresponding relationship between each key information and each service category, so as to obtain the target service category to which the target key information belongs.
  • the RPA hotline service robot can issue a dispatch order, so that the RPA hotline service robot can execute step 306 and subsequent steps in response to receiving the dispatch order.
  • the order dispatching instruction can be realized in various ways, for example, the order dispatching instruction can be triggered by voice and/or text, and for example, the order dispatching instruction can also be triggered by triggering a specified control on the dialogue interaction interface, which is not specifically limited in the embodiments of the present disclosure.
  • the second corresponding relationship between each key information and each business category can be learned in advance based on historical business data by means of machine learning, so that the RPA hotline service robot can query the second corresponding relationship between each key information and each business category according to the target key information in the dialogue voice, and use the found business category corresponding to the key information that matches the target key information as the target business category.
  • the service category corresponding to the key information may be directly used as the target service category.
  • multiple second key information with a high degree of matching with the target key information may be determined, and the business categories corresponding to the multiple second key information are used as the target business category, and displayed through the hotline service system, so that the connection party can select the target business category to which the target key information belongs according to the business categories corresponding to the multiple second key information.
  • step 306 can be implemented in the following manner: according to the target key information, query the second corresponding relationship between each key information and each business category to obtain multiple candidate business categories to which the target key information belongs; display multiple candidate business categories; and determine the first business category as the target service category in response to the selection of the first business category among the multiple candidate business categories.
  • the plurality of candidate service categories are the service categories respectively corresponding to the plurality of second key information.
  • the plurality of second key information is key information whose matching degree with the target key information is greater than a preset third threshold.
  • the preset third threshold may be set as required, and the present disclosure does not limit this.
  • Step 307 according to the target business category, query the third corresponding relationship between each business category and each acceptance department, so as to obtain the target acceptance department corresponding to the target business category.
  • the third corresponding relationship between each business category and each acceptance department can be set in advance, or the third correspondence between each business category and each acceptance department can be learned through machine learning based on historical business data, so that the RPA hotline service robot can query the third correspondence between each business category and each acceptance department according to the target business category, and accurately obtain the target acceptance department corresponding to the target business category.
  • Step 308 accessing the business system of the target acceptance department, and inputting the first text, the second text, target key information and target business category into the business system of the target acceptance department.
  • the RPA hotline service robot after the RPA hotline service robot obtains the target acceptance department corresponding to the target business category, it can log in to the business system of the target acceptance department, and enter the first text, the second text, the key information of the target and the target business category into the business system of the target acceptance department.
  • the RPA hotline service robot combined with AI technology can accurately and quickly determine the target acceptance department of the business corresponding to this call according to the dialogue voice between the caller and the connection party of this call, and then automatically transfer the business corresponding to this call to the target acceptance department, thereby improving the accuracy and efficiency of business processing and reducing labor costs.
  • the RPA hotline service robot can also enter the target business category and target acceptance department into the hotline service system for business data backup, which facilitates the follow-up of the follow-up process of the business of this call.
  • the process of entering the target business category and target acceptance department into the hotline service system may be performed between steps 307 and 308, or may be performed after step 308, which is not limited in the present disclosure.
  • the target acceptance department can conduct business processing based on the business data, and enter the business processing data including the processing process and processing results into the business system of the target acceptance department.
  • the RPA hotline service robot can follow up the subsequent processing process of the business data, and after the target acceptance department enters the business processing data in its business system, obtain the business processing data from the business system of the target acceptance department, and then enter the business processing data into the hotline service system. In this way, the backup of the business data for this call can be completed, and the business processing data entered into the hotline service system can also be used as historical business data for further machine learning, providing data support for subsequent business consultation, complaints and suggestions.
  • the RPA hotline service robot to enter data in the hotline service system and the business system of the target acceptance department, the labor cost required for data entry is reduced.
  • the RPA hotline service robot queries the second corresponding relationship between each key information and each business category according to the target key information in the dialogue voice to obtain the target business category to which the target key information belongs, and according to the target business category, queries the third corresponding relationship between each business category and each acceptance department to obtain the target acceptance department corresponding to the target business category, accesses the business system of the target acceptance department, and enters the first text, the second text, the target key information and the target business category into the business system of the target acceptance department, realizing the combination of RPA and AI technology.
  • the dialogue voice between the caller and the operator of this call accurately and quickly determine the target acceptance department of the business, and then automatically transfer the business corresponding to this call to the target acceptance department, thereby improving the accuracy and efficiency of business processing and reducing labor costs.
  • the hotline service system can provide a service portal, such as a service hotline or a hotline portal, so that users can dial the service hotline or log in to the service hotline portal to consult questions or make complaints and suggestions.
  • a service portal such as a service hotline or a hotline portal
  • the RPA hotline service robot can obtain the dialogue voice between the connection party and the caller, and based on ASR technology, perform speech recognition on the dialogue voice to obtain the first text corresponding to the caller and the second text corresponding to the connection party.
  • the second text corresponding to the connection party is "Hello, may I help you”
  • the first text corresponding to the caller is "Construction site B in area A is still under construction at 23:23 at night, and the noise disturbs the residents. I hereby complain and hope that the department will intervene.”
  • the RPA hotline service robot can analyze the first text and the second text based on NLP technology, understand the intention of the caller, and obtain the key target information in the dialogue voice: time “23:23 at night", location "A district B construction site”, event “construction”, “noise disturbance”, and intention “complaint”. Furthermore, the RPA hotline service robot can query the first corresponding relationship between each key information and each business knowledge based on the key information of the target, obtain the target business knowledge corresponding to the key information of the target, "This problem belongs to the problem of urban and rural construction, and needs to be accepted and solved by the Bureau of Housing and Urban-Rural Development", and display the target business knowledge through the hotline service system. Among them, the first corresponding relationship can be obtained through machine learning through historical business data.
  • connection party can determine that the caller’s demand for this call is a complaint suggestion.
  • This type of business cannot be processed in real time and needs to be dispatched to a certain acceptance department for processing, so that the connection party can inform the caller that the business has been recorded and will pass it on to the Housing and Construction Bureau to accept the business.
  • the target business knowledge corresponding to the target key information is displayed, which provides a reference for the caller to handle the business of the service hotline in real time, so that the inexperienced caller can quickly obtain the business knowledge related to the needs of the caller of this call without searching the knowledge base, thereby improving the efficiency of business processing and reducing labor costs.
  • the RPA hotline service robot can automatically enter the first text, the second text, target key information and target business knowledge into the hotline service system to back up the business content of this call, which is convenient for subsequent traceability of the business content of this call, and makes it unnecessary for the connection party to manually enter business data, thereby reducing the labor cost required for entering business data.
  • connection party can issue an instruction to the RPA hotline service robot, so that the RPA hotline service robot can query the second corresponding relationship between each key information and each business category according to the target key information in the dialogue voice, and determine that the target business category to which the target key information belongs is the urban and rural construction category. Category, entered into the business system of the Housing and Urban-rural Development Bureau.
  • the RPA hotline service robot can enter the target business category and target acceptance department into the hotline service system for backup, and follow up the follow-up processing process of the business of this call based on the backup data.
  • the Bureau of Housing and Urban-Rural Development handles the complaint and suggestion, it can enter the business processing data including the processing process and processing results into the business system of the Bureau of Housing and Urban-Rural Development, so that the RPA hotline service robot can obtain business processing data from the business system of the Bureau of Housing and Urban-Rural Development and enter the business processing data into the hotline service system.
  • the business processing data entered into the hotline service system can also be used as historical business data for further machine learning, providing data support for subsequent business consultation, complaints and suggestions.
  • the combination of RPA and AI technology is realized, and according to the dialogue voice between the caller and the operator of this call, the target acceptance department of the business is accurately and quickly determined, and then the business corresponding to this call is automatically approved to the target acceptance department, thereby improving the accuracy and efficiency of business processing and reducing labor costs. And by using the RPA hotline service robot to enter data in the hotline service system and the business system of the target acceptance department, the labor cost required for data entry is reduced.
  • Fig. 5 is a schematic structural diagram of a hotline service processing device combining RPA and AI according to an embodiment of the present disclosure.
  • the hotline business processing device 500 combining RPA and AI is applied to an RPA hotline service robot, and includes: a first acquisition module 501 , an identification module 502 , an analysis module 503 , a processing module 504 and a first entry module 505 .
  • the first acquiring module 501 is configured to acquire the dialogue voice between the connecting party and the calling party in response to the service hotline being answered.
  • the recognition module 502 is configured to perform speech recognition on the dialogue speech based on the speech recognition ASR technology, so as to obtain the first text corresponding to the calling party and the second text corresponding to the connecting party.
  • the parsing module 503 is configured to parse the first text and the second text based on natural language processing (NLP) technology, so as to obtain target key information in the dialogue speech.
  • NLP natural language processing
  • the processing module 504 is configured to acquire and display corresponding target business knowledge according to target key information.
  • the first input module 505 is configured to input the first text, the second text, target key information and target business knowledge into the hotline service system in response to the service hotline being hung up.
  • the hotline business processing device combined with RPA and AI in the embodiment of the present disclosure can execute the hotline business processing method combined with RPA and AI.
  • the hotline business processing device combined with RPA and AI can be realized by an RPA hotline service robot.
  • the hotline service processing apparatus combined with RPA and AI can be configured in electronic equipment, and the electronic equipment can include but not limited to terminal equipment, servers, etc., and this embodiment does not specifically limit the electronic equipment.
  • the processing module 504 includes:
  • the first acquisition unit is configured to query the first corresponding relationship between each key information and each business knowledge according to the target key information, so as to obtain the target business knowledge corresponding to the target key information;
  • the first display unit is used to display target business knowledge through the hotline service system.
  • the first obtaining unit is specifically configured to: query the first correspondence according to the target key information, so as to obtain multiple candidate business knowledge corresponding to the target key information; and use at least one candidate business knowledge that satisfies a preset condition among the multiple candidate business knowledge as the target business knowledge.
  • the hotline service processing device 500 combining RPA and AI further includes:
  • the second acquisition module is used to query the second corresponding relationship between each key information and each business category according to the target key information in the dialogue voice, so as to obtain the target business category to which the target key information belongs;
  • the third acquisition module is used to query the third corresponding relationship between each business category and each acceptance department according to the target business category, so as to obtain the target acceptance department corresponding to the target business category;
  • the second input module is used to access the business system of the target acceptance department, and input the first text, the second text, target key information and target business category into the business system of the target acceptance department.
  • the second acquisition module includes:
  • the second acquisition unit is configured to query the second corresponding relationship between each key information and each business category according to the target key information, so as to acquire multiple candidate business categories to which the target key information belongs;
  • the second display unit is used to display multiple candidate business categories
  • a processing unit configured to determine the first service category as the target service category in response to the selection of the first service category among the plurality of candidate service categories.
  • the hotline service processing device 500 combining RPA and AI further includes:
  • the third input module is used for inputting the target business category and the target acceptance department into the hotline service system.
  • the hotline service processing device 500 combining RPA and AI further includes:
  • the fourth obtaining module is used to obtain the business processing data corresponding to the dialogue voice from the business system of the target acceptance department;
  • the fourth input module is used to input business processing data into the hotline service system.
  • the hotline service processing device 500 combining RPA and AI further includes:
  • the display module is used to display the first text and the second text.
  • the hotline service processing device in response to the service hotline being answered, obtains the dialogue voice between the connection party and the caller, and performs speech recognition on the dialogue voice based on the speech recognition ASR technology to obtain the first text corresponding to the caller and the second text corresponding to the connection party.
  • the first text, the second text, target key information and target business knowledge are entered into the hotline service system, so that by using the combination of RPA and AI, the target business knowledge corresponding to the target key information is displayed, which provides a reference for the connection party to handle the business of the service hotline in real time, thereby improving the quality and efficiency of business processing, and reducing labor costs because there is no need to manually enter business data.
  • the embodiments of the present disclosure also propose an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the processor executes the computer program, it implements the hotline service processing method combining RPA and AI as described in any of the foregoing method embodiments.
  • the embodiments of the present disclosure also propose a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the hotline service processing method combining RPA and AI as described in any of the foregoing method embodiments is implemented.
  • the embodiments of the present disclosure further propose a computer program product, when the instruction processor in the computer program product executes, implement the hotline business processing method combining RPA and AI as described in any of the foregoing method embodiments.
  • FIG. 6 shows 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 limit the functions and scope of use of the embodiments of the present disclosure.
  • electronic device 12 takes the form of a general-purpose computing device.
  • Components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16 , system memory 28 , bus 18 connecting various system components including memory 28 and processing unit 16 .
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to Industry Standard Architecture (hereinafter referred to as: ISA) bus, Micro Channel Architecture (Micro Channel Architecture; hereinafter referred to as: MAC) bus, enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards Association; hereinafter referred to as: VESA) local bus and peripheral component interconnection (Peripheral Component Interconnection) ; Hereinafter referred to as: PCI) bus.
  • ISA Industry Standard Architecture
  • MAC Micro Channel Architecture
  • VESA Video Electronics Standards Association
  • PCI peripheral component interconnection
  • Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.
  • the memory 28 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (Random Access Memory; hereinafter referred to as: RAM) 30 and/or a cache memory 32 .
  • RAM Random Access Memory
  • the electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 34 may be used to read from and write to non-removable, non-volatile magnetic media (not shown in Figure 6, commonly referred to as "hard drives").
  • a disk drive for reading and writing a removable nonvolatile disk such as a "floppy disk”
  • an optical disk drive for reading and writing a removable nonvolatile disk such as a Compact Disc Read Only Memory (hereinafter referred to as CD-ROM), a Digital Video Disc Read Only Memory (hereinafter referred to as DVD-ROM) or other optical media
  • each drive may be connected to bus 18 via one or more data media interfaces.
  • Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present 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 or some combination of which may include the implementation of a network environment.
  • the program modules 42 generally perform the functions and/or methods of the embodiments described in this disclosure.
  • the electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the electronic device 12, and/or with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, modem, etc.). Such communication may occur through input/output (I/O) interface 22 .
  • the electronic device 12 can also communicate with one or more networks (such as a local area network (Local Area Network; hereinafter referred to as: LAN), a wide area network (Wide Area Network; hereinafter referred to as: WAN) and/or a public network such as the Internet) through the network adapter 20.
  • networks such as a local area network (Local Area Network; hereinafter referred to as: LAN), a wide area network (Wide Area Network; hereinafter referred to as: WAN) and/or a public network such as the Internet
  • network adapter 20 communicates with other modules of electronic device 12 via bus 18 .
  • 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 running the programs stored in the memory 28 , such as implementing the methods mentioned in the foregoing embodiments.
  • first and second are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features.
  • the features defined as “first” and “second” may explicitly or implicitly include at least one of these features.
  • “plurality” means at least two, such as two, three, etc., unless otherwise specifically defined.
  • a "computer-readable medium” may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device.
  • computer-readable media include the following: electrical connections with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), read-only memory (ROM), erasable-editable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disc read-only memory (CDROM).
  • the computer readable medium may even be paper or other suitable medium on which the program can be printed, since the program can be obtained electronically, for example, by optical scanning of the paper or other medium, followed by editing, interpretation, or other suitable processing as necessary, and then stored in the computer memory.
  • various parts of the present disclosure may be implemented in hardware, software, firmware or a combination thereof.
  • various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if it is implemented by hardware as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with logic gates for implementing logic functions on data signals, an application specific integrated circuit with suitable combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
  • PGA programmable gate array
  • FPGA field programmable gate array
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.
  • the storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Finance (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本公开涉及一种结合RPA和AI的热线业务处理方法、装置及电子设备，方法包括：响应于服务热线被接听，获取接线方与来电方的对话语音；基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本；基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息；根据目标关键信息，获取并展示对应的目标业务知识；响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。通过采用RPA和AI结合的方式，获取并展示目标业务知识，为接线方实时处理业务提供了参考，提高了业务办理的质量及效率，且无需通过人工录入业务数据，减少了人工成本。

Description

结合RPA和AI的热线业务处理方法、装置及电子设备
相关申请的交叉引用
本公开基于申请号为202210080200.7、申请日为2022年01月24日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本公开作为参考。
技术领域
本公开涉及机器人流程自动化RPA和人工智能AI技术领域，特别涉及一种结合RPA和AI的热线业务处理方法、装置及电子设备。
背景技术
机器人流程自动化(Robotic Process Automation，简称RPA)，是通过特定的“机器人软件”，模拟人在计算机上的操作，按规则自动执行流程任务。
人工智能(Artificial Intelligence，简称AI)是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门技术科学。
目前，很多繁琐、重复的业务流程需要人工来进行处理。比如，在某些服务热线的业务处理过程中，接线员在接听来电的过程中，需要人工记录来电人员的需求，若来电人员的需求为咨询问题，则需要接线员根据经验或者检索知识库，实时回复来电人员的问题，在来电挂断后，还需要接线员在热线服务系统中人工录入来电人员信息、需求信息等业务数据。随着服务热线的来电数量的快速增长，接线员的工作量也日益剧增，若仅依靠人工来办理热线业务，则需要大量的人力成本，且无法保证业务办理的效率和质量。如何提高服务热线的业务办理效率和质量、降低人工成本，已经成为亟待解决的问题。
发明内容
本公开提供一种结合RPA和AI的热线业务处理方法、装置及电子设备，以解决相关技术中的服务热线的业务办理效率低、人工成本高和业务办理质量差的技术问题。
本公开第一方面实施例提供一种结合RPA和AI的热线业务处理方法，应用于RPA热线服务机器人，该方法包括：响应于服务热线被接听，获取接线方与来电方的对话语音；基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本；基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息；根据目标关键信息，获取并展示对应的目标业务知识；响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
本公开第二方面实施例提供一种结合RPA和AI的热线业务处理装置，应用于RPA 热线服务机器人，该装置，包括：第一获取模块，用于响应于服务热线被接听，获取接线方与来电方的对话语音；识别模块，用于基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本；解析模块，用于基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息；处理模块，用于根据目标关键信息，获取并展示对应的目标业务知识；第一录入模块，用于响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
本公开第三方面实施例提出了一种电子设备，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，该处理器执行计算机程序时，实现如本公开上述第一方面实施例所述的方法。
本公开第四方面实施例提出了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如本公开上述第一方面实施例所述的方法。
本公开第五方面实施例提出了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现如本公开上述第一方面实施例所述的方法。
本公开实施例提供的技术方案可以包括以下有益效果：
通过采用RPA和AI结合的方式，获取接线方与来电方的对话语音中的目标关键信息，进而获取并展示目标关键信息对应的目标业务知识，为接线方实时处理服务热线的业务提供了参考，从而提高了业务办理的质量及效率，并且由于无需通过人工录入业务数据，从而减少了人工成本。
本公开的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本公开的实践了解到。
附图说明
在附图中，除非另外规定，否则贯穿多个附图相同的附图标记表示相同或相似的部件或元素。这些附图不一定是按照比例绘制的。应该理解，这些附图仅描绘了根据本公开的一些实施方式，而不应将其视为是对本公开范围的限制。
图1是根据本公开一个实施例的结合RPA和AI的热线业务处理方法的流程示意图。
图2是根据本公开另一个实施例的结合RPA和AI的热线业务处理方法的流程示意图。
图3是根据本公开另一个实施例的结合RPA和AI的热线业务处理方法的流程示意图。
图4是根据本公开另一个实施例的结合RPA和AI的热线业务处理方法的架构示意图。
图5是根据本公开一个实施例的结合RPA和AI的热线业务处理装置的结构示意图。
图6是用来实现本公开实施例的结合RPA和AI的热线业务处理方法的电子设备的框图。
具体实施方式
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本公开，而不能理解为对本公开的限制。
在本公开的描述中，术语“多个”指两个或两个以上。
可以理解的是，在某些服务热线的业务处理过程中，接线员在接听来电的过程中，需要人工记录来电人员的需求，若来电人员的需求为咨询问题，则需要接线员根据经验或者检索知识库，实时回复来电人员的问题，在来电挂断后，还需要接线员在热线服务系统中人工录入来电人员信息、需求信息等业务数据。随着服务热线的来电数量的快速增长，接线员的工作量也日益剧增，若仅依靠人工来办理热线业务，则需要大量的人力成本，且无法保证业务办理的效率和质量。如何提高服务热线的业务办理效率和质量、降低人工成本，已经成为亟待解决的问题。
本公开提供一种通过RPA和AI的结合，使用RPA热线服务机器人替代人工来记录来电人员的需求、解答来电人员的问题及在热线服务系统中录入业务数据的思路，由于RPA热线服务机器人只要有数据就可以7*24小时不间断工作，这样就可以大大的降低人力成本，提高业务办理的效率，且通过采用RPA和AI结合的方式来记录来电人员的需求、解答来电人员的问题及在热线服务系统中录入业务数据，可以保证业务办理的质量。
为了清楚说明本发明的各实施例，首先对本发明实施例中涉及到的技术名词进行解释说明。
在本公开的描述中，“服务热线”，是指为用户提供问题咨询、业务受理、投诉建议等服务的热线，比如政务服务热线、购物服务热线等。
在本公开的描述中，“热线服务系统”，指服务热线对应的业务系统，在热线服务系统上可以处理服务热线对应的业务，比如进行业务受理、备份用户咨询的问题或者用户的投诉建议等。另外，热线服务系统还可以热线门户网站作为服务入口，从而使得用户除了可以通过拨打服务热线，还可以通过登录热线门户网站，进行问题咨询或者投诉建议等。其中，“业务”即服务热线来电后，针对来电方的需求，需要处理的工作。
在本公开的描述中，“RPA热线服务机器人”是指可结合AI技术和RPA技术，自动对服务热线的业务进行处理的RPA机器人。
在本公开的描述中，“接线方”，指接听服务热线的一方，比如接线员。“来电方”，指拨打服务热线的一方，比如市民等用户。
在本公开的描述中，“受理部门”，指服务热线对应的业务受理部门。比如，以服务热线为政务服务热线为例，即服务热线提供的为政务方面的业务服务，则受理部门可以包括：受理住房建设方面的业务的住建局、受理教育方面的业务的教育局、受理环保方面的业务的环保局等；以服务热线为购物服务热线为例，即服务热线提供的为购物方 面的业务服务，则受理部门可以包括：受理物流方面的业务的物流部门、受理货物质量方面的业务的质检部门等。“受理部门的业务系统”，即受理部门处理业务所使用的系统。
在本公开的描述中，“业务类别”，指服务热线对应的业务所属的类别。比如，以服务热线为政务服务热线为例，即服务热线对应的业务为各类政务方面的业务，则业务类别可以包括纪检监察类别、城乡建设类别、环境保护类别、农村农业类别、教育问题类别等；以服务热线为购物服务热线为例，即服务热线对应的业务为各类购物方面的业务，则业务类别可以包括质量类别、物流类别等。
在本公开的描述中，“业务知识”，指与服务热线的业务处理有关的信息，业务知识能够为接线方办理业务提供参考，从而辅助接线方更好的办理业务。比如，来电方投诉了某个事件时，业务知识包括该业务需要哪个受理部门来受理，或者，来电方咨询了某个问题时，业务知识包括该问题需要如何解答等。
在本公开的描述中，“ASR”指自动语音识别(Automatic Speech Recognition)，具体是指一种将人的语音转换为文本的技术。“ASR”的目标是将人类的语音中的词汇内容转换为计算机可读的输入，例如按键、二进制编码或者字符序列。
参照下面的描述和附图，将清楚本公开的实施例的这些和其他方面。在这些描述和附图中，具体公开了本公开的实施例中的一些特定实施方式，来表示实施本公开的实施例的原理的一些方式，但是应当理解，本公开的实施例的范围不受此限制。相反，本公开的实施例包括落入所附加权利要求书的精神和内涵范围内的所有变化、修改和等同物。
以下结合附图描述根据本公开实施例的结合RPA和AI的热线业务处理方法、装置及电子设备。
图1是本公开一个实施例的结合RPA和AI的热线业务处理方法的流程图。如图1所示，该方法可包括以下步骤：
步骤101，响应于服务热线被接听，获取接线方与来电方的对话语音。
需要说明的是，本公开实施例的结合RPA和AI的热线业务处理方法，由结合RPA和AI的热线业务处理装置执行，以下将结合RPA和AI的热线业务处理装置简称为热线业务处理装置，该热线业务处理装置，可以由RPA热线服务机器人实现，例如，热线业务处理装置可以为RPA热线服务机器人，或者热线业务处理装置可以配置在RPA热线服务机器人中，本公开对此不作限制。
其中，RPA热线服务机器人可以配置在电子设备中，该电子设备可以包括但不限于终端设备、服务器等，该实施例对电子设备不作具体限定。本公开实施例以热线业务处理装置为终端设备中安装的RPA热线服务机器人为例进行示例性说明。
其中，本实施例中的RPA热线服务机器人可以在特定的时间段，或者全天实时执行该方法，本公开对此不作限制。其中，特定的时间段可以根据需要设置。
或者，上述RPA热线服务机器人还可以是基于接收到启动指令而启动的。例如，接线方可通过对话的方式，触发针对RPA热线服务机器人的上述启动指令。其中，触 发针对RPA热线服务机器人的启动指令可通过多种方式实现，例如，可通过语音和/或文字的方式触发RPA热线服务机器人的启动指令，又例如，还可以通过触发对话交互界面上的指定控件的方式，来触发RPA热线服务机器人的启动指令，本公开的实施例对此不作具体限定。
在本公开的实施例中，在服务热线来电时，接线方可以接听来电，响应于服务热线被接听，RPA热线服务机器人可以在来电方与接线方的对话过程中，实时获取接线方与来电方的对话语音。
步骤102，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本。
在本公开的实施例中，RPA热线服务机器人可以基于ASR技术，实时对对话语音进行语音识别，将对话语音转换为文本，并且，通过ASR技术，可以实时区分接线方和来电方的语音，从而获取来电方对应的第一文本及接线方对应的第二文本。
在本公开的实施例中，RPA热线服务机器人获取来电方对应的第一文本及接线方对应的第二文本后，还可以通过热线服务系统的人机交互界面展示第一文本及第二文本，以方便接线方查看。
步骤103，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息。
在本公开的实施例中，获取来电方对应的第一文本及接线方对应的第二文本后，RPA热线服务机器人可以基于自然语言处理(Natural Language Processing，NLP)技术，对第一文本和第二文本进行实时解析，理解来电方的意图，以获取对话语音中的目标关键信息。
其中，目标关键信息，为能表明来电方的需求的关键信息，比如可以包括对话语音中来电方的意图、问题描述、事件、事件的时间、地点、人物等关键信息。
比如，假设第二文本为“您好，请问有什么可以帮助您”、第一文本为“A区B工地夜间23:23还在施工，噪音扰民，特此投诉，望部门介入处理”。则RPA热线服务机器人基于NLP技术，可以获取对话语音中的目标关键信息：时间“夜间23:23”、地点“A区B工地”、事件“施工”“噪音扰民”、意图“投诉”。
步骤104，根据目标关键信息，获取并展示对应的目标业务知识。
其中，“目标业务知识”，指与本次来电的来电方的需求相关的业务知识。比如本次来电的来电方的需求为投诉某个事件时，目标业务知识可以包括该业务需要哪个受理部门来受理；或者，本次来电的来电方的需求为咨询某个问题时，目标业务知识可以包括来电方咨询的问题的答案。
在本公开的实施例中，可以在知识库中存储各关键信息与各业务知识的对应关系，从而RPA热线服务机器人可以通过检索知识库，在知识库中查找与目标关键信息匹配的关键信息，并将查找到的该关键信息对应的业务知识作为目标业务知识。
在本公开的实施例中，获取目标关键信息对应的目标业务知识后，可以展示目标业 务知识。其中，展示目标业务知识时，可以通过热线服务系统的人机交互界面进行展示，从而接线方可以根据人机交互界面上展示的目标业务知识，进行业务处理。
另外，在展示目标业务知识时，可以通过预设方式来展示，本公开对此不作限制。比如，可以展示目标业务知识的所有内容，或者，在目标业务知识的内容较多时，可以先展示目标业务知识的关键词，在接线方点击关键词后，再展示目标业务知识的所有内容。
举例来说，假设第二文本为“您好，请问有什么可以帮助您”、第一文本为“请问A医院在周末有医生接诊吗”。RPA热线服务机器人基于NLP技术，从对话语音中获取的目标关键信息包括：时间“周末”、地点“A医院”、事件“医生接诊”。则RPA机器人可以通过检索知识库，从知识库中获取与目标关键信息匹配的关键信息，假设知识库中关键信息“周末”、“A医院”、“医生接诊”对应的业务知识包括“A医院在周末有医生接诊”，则RPA热线服务机器人可以将该业务知识作为目标业务知识，并通过热线服务系统的人机交互界面展示该目标业务知识，从而使得接线方可以根据该目标业务知识，答复来电方咨询的问题。
或者，假设第二文本为“您好，请问有什么可以帮助您”、第一文本为“A区B工地夜间23:23还在施工，噪音扰民，特此投诉，望部门介入处理”。RPA热线服务机器人基于NLP技术，从对话语音中获取的目标关键信息包括：时间“夜间23:23”、地点“A区B工地”、事件“施工”“噪音扰民”、意图“投诉”。则RPA机器人可以通过检索知识库，从知识库中获取与目标关键信息匹配的关键信息，假设知识库中关键信息“夜间23:23”、“A区B工地”、“施工”“噪音扰民”、“投诉”对应的业务知识包括“该问题属于城乡建设问题、需要由住建局受理解决”，则RPA热线服务机器人可以将该业务知识作为目标业务知识，并通过热线服务系统的人机交互界面展示该目标业务知识，从而使得接线方可以根据该目标业务知识，回复来电方。比如，接线方可以告知来电方业务已记录，会转达住建局受理该业务。
通过根据目标关键信息，获取并展示对应的目标业务知识，为接线方实时处理业务提供了参考，从而使得没有经验的接线方不必检索知识库，即可快速获取与本次来电的来电方的需求相关的业务知识，从而提高了业务办理效率，减少了人工成本，并且，使得接线方可以参考目标业务知识答复来电方，从而提高了业务办理的准确性，进而提高了业务办理的质量。
步骤105，响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
在本公开的实施例中，响应于服务热线被挂断，RPA热线服务机器人即可在热线服务系统中录入第一文本、第二文本、目标关键信息及目标业务知识等业务数据，以对本次来电的业务内容进行备份，方便后续对本次来电的业务内容进行追溯。
通过RPA热线服务机器人在热线服务系统中录入第一文本、第二文本、目标关键信息及目标业务知识等业务数据，使得接线方不必通过人工录入业务数据，减少了人工 成本。
在本公开的实施例中，RPA热线服务机器人响应于服务热线被接听，获取接线方与来电方的对话语音，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息，根据目标关键信息，获取并展示对应的目标业务知识，响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统，由此，通过采用RPA和AI结合的方式，展示目标关键信息对应的目标业务知识，为接线方实时处理服务热线的业务提供了参考，从而提高了业务办理的质量及效率，并且由于无需通过人工录入业务数据，从而减少了人工成本。
下面结合图2，对本公开实施例提供的RPA和AI的热线业务处理方法中，获取并展示目标关键信息对应的目标业务知识的过程进行进一步说明。
图2是根据本公开另一个实施例的结合RPA和AI的热线业务处理方法的流程图，如图2所示，该方法包括：
步骤201，响应于服务热线被接听，获取接线方与来电方的对话语音。
步骤202，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本。
步骤203，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息。
其中，步骤201-203的具体实现过程及原理，可以参考上述实施例，本公开对此不作限制。
步骤204，根据目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取目标关键信息对应的目标业务知识。
步骤205，通过热线服务系统，展示目标业务知识。
在本公开的实施例中，可以预先根据历史业务数据，通过机器学习的方式，学习得到各关键信息与各业务知识之间的第一对应关系，并将第一对应关系存储在知识库中，从而RPA热线服务机器人在获取目标关键信息后，可以通过检索知识库，在知识库中查找与目标关键信息匹配的关键信息，并将查找到的该关键信息对应的业务知识作为目标业务知识，进而通过热线服务系统，展示目标业务知识。
其中，历史业务数据，可以是有经验的接线方接听服务热线来电，并根据经验办理业务后录入的业务数据，也可以是接线方接听服务热线来电，根据RPA热线服务机器人推荐的目标业务知识办理业务后录入的业务数据，本公开对此不作限制。
通过根据目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取目标关键信息对应的目标业务知识，进而通过热线服务系统，展示目标业务知识，为接线方实时处理业务提供了参考，从而使得没有经验的接线方不必检索知识库，即可快速获取与本次来电的来电方的需求相关的业务知识，从而提高了业务办理效率，并且， 使得接线方可以参考目标业务知识答复来电方，从而提高了业务办理的准确性，进而提高了业务办理的质量。
需要说明的是，在一种可能的实现形式中，知识库中可能存在与目标关键信息完全匹配的关键信息，此时可以将该关键信息对应的业务知识直接作为目标业务知识，通过热线服务系统进行展示。
在另一种可能的实现形式中，知识库中可能并不存在与目标关键信息完全匹配的关键信息，此时，可以确定知识库中与目标关键信息的匹配度较高的多个第一关键信息，并将多个第一关键信息对应的业务知识作为目标业务知识，通过热线服务系统进行展示，从而使得接线方可以根据多个第一关键信息对应的业务知识，自行选择根据哪个业务知识答复来电方。
即，本公开的实施例中，步骤204可以通过以下方式实现：根据目标关键信息，查询第一对应关系，以获取目标关键信息对应的多个候选业务知识；将多个候选业务知识作为目标业务知识。其中，多个候选业务知识，即为多个第一关键信息分别对应的业务知识。其中，多个第一关键信息，为知识库中与目标关键信息的匹配度大于预设第一阈值的关键信息。其中，预设第一阈值，可以根据需要设置，本公开对此不作限制。
在另一种可能的实现形式中，还可以将多个候选业务知识中，满足预设条件的至少一个候选业务知识，作为目标业务知识，通过热线服务系统进行展示，从而使得接线方根据至少一个候选业务知识答复来电方。即，步骤204可以通过以下方式实现：根据目标关键信息，查询第一对应关系，以获取目标关键信息对应的多个候选业务知识；将多个候选业务知识中，满足预设条件的至少一个候选业务知识，作为目标业务知识。
其中，预设条件，可以根据需要设置，比如可以为候选业务知识的浏览量大于预设第二阈值，或者为候选业务知识的浏览量排在前N名，其中，N为大于0的正整数，可以根据需求设置。
步骤206，响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
在本公开的实施例中，响应于服务热线被挂断，RPA热线服务机器人即可在热线服务系统中录入第一文本、第二文本、目标关键信息及目标业务知识等业务数据，以对本次来电的业务内容进行备份，方便后续对本次来电的业务内容进行追溯。并且，录入热线服务系统的业务数据还可以作为历史业务数据，用于进一步的机器学习，为后续的业务咨询、投诉建议等业务提供数据支撑。
本公开实施例中，RPA热线服务机器人响应于服务热线被接听，获取接线方与来电方的对话语音，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息，根据目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取目标关键信息对应的目标业务知识，通过热线服务系统，展示目标业务知识，响应于服务热线被挂断，将第一文本、第二文 本、目标关键信息及目标业务知识，录入热线服务系统，由此，通过采用RPA和AI结合的方式，通过热线服务系统展示目标关键信息对应的目标业务知识，为接线方实时处理服务热线的业务提供了参考，从而提高了业务办理的质量及效率，并且由于无需通过人工录入业务数据，从而减少了人工成本。
通过上述分析可知，在来电方的需求是问题咨询等时，接线方可以根据展示的目标业务知识，实时处理并回复来电方。在一种可能的实现形式中，来电方的需求可能是投诉建议等，这类业务无法实时处理，需要派发到某个受理部门处理，下面针对上述情况，结合图3，对本公开实施例提供的RPA和AI的热线业务处理方法进行进一步说明。
图3是根据本公开另一个实施例的结合RPA和AI的热线业务处理方法的流程图，如图3所示，该方法包括：
步骤301，响应于服务热线被接听，获取接线方与来电方的对话语音。
步骤302，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本。
步骤303，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息。
步骤304，根据目标关键信息，获取并展示对应的目标业务知识。
步骤305，响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
其中，上述步骤301-305的具体实现过程及原理，可以参考上述实施例的描述，此处不再赘述。
步骤306，根据对话语音中的目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取目标关键信息所属的目标业务类别。
在本公开的实施例中，服务热线被挂断后，若接线方确定本次来电的来电方的需求无法实时处理，需要将该业务派发到某个受理部门处理，则可以向RPA热线服务机器人下发派单指令，从而RPA热线服务机器人可以响应于接收到派单指令，执行步骤306及后续步骤。其中，派单指令，可以通过多种方式实现，例如，可通过语音和/或文字的方式触发派单指令，又例如，还可以通过触发对话交互界面上的指定控件的方式，来触发派单指令，本公开的实施例对此不作具体限定。
在本公开的实施例中，可以预先可以根据历史业务数据，通过机器学习的方式，学习得到各关键信息与各业务类别之间的第二对应关系，从而RPA热线服务机器人可以根据对话语音中的目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，并将查找到的与目标关键信息匹配的关键信息对应的业务类别，作为目标业务类别。通过利用RPA热线服务机器人智能确定目标类别，避免了人工确定目标业务类别存在的判断标准不统一的问题，提高了确定的目标业务类别的准确性及业务处理效率。
需要说明的是，在一种可能的实现形式中，可能存在与目标关键信息完全匹配的关键信息，此时可以将该关键信息对应的业务类别直接作为目标业务类别。在另一种可能 的实现形式中，可能并不存在与目标关键信息完全匹配的关键信息，此时，可以确定与目标关键信息的匹配度较高的多个第二关键信息，并将多个第二关键信息对应的业务类别作为目标业务类别，通过热线服务系统进行展示，从而使得接线方可以根据多个第二关键信息对应的业务类别，自行选择目标关键信息所属的目标业务类别。
即，本公开的实施例中，步骤306可以通过以下方式实现：根据目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取目标关键信息所属的多个候选业务类别；展示多个候选业务类别；响应于多个候选业务类别中的第一业务类别被选择，将第一业务类别确定为目标业务类别。
其中，多个候选业务类别，即为多个第二关键信息分别对应的业务类别。其中，多个第二关键信息，为与目标关键信息的匹配度大于预设第三阈值的关键信息。其中，预设第三阈值，可以根据需要设置，本公开对此不作限制。
步骤307，根据目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取目标业务类别对应的目标受理部门。
在本公开的实施例中，可以预先设置各业务类别与各受理部门之间的第三对应关系，或者根据历史业务数据，通过机器学习的方式，学习得到各业务类别与各受理部门之间的第三对应关系，从而RPA热线服务机器人可以根据目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，准确获取目标业务类别对应的目标受理部门。
步骤308，访问目标受理部门的业务系统，并将第一文本、第二文本、目标关键信息及目标业务类别，录入目标受理部门的业务系统。
在本公开的实施例中，RPA热线服务机器人获取目标业务类别对应的目标受理部门后，即可登录目标受理部门的业务系统，并将第一文本、第二文本、目标关键信息及目标业务类别，录入目标受理部门的业务系统。
由此，可以实现RPA热线服务机器人结合AI技术，根据本次来电的来电方与接线方之间的对话语音，准确、快速的确定本次来电对应的业务的目标受理部门，进而自动将本次来电对应的业务批转至目标受理部门，从而提高了业务办理的准确性和效率，减少了人工成本。
另外，在本公开的实施例中，RPA热线服务机器人还可以将目标业务类别及目标受理部门，录入热线服务系统，以进行业务数据备份，便于对本次来电的业务的后续处理流程的跟进。其中，将目标业务类别及目标受理部门，录入热线服务系统的过程，可以在步骤307和308之间执行，也可以在步骤308之后执行，本公开对此不作限制。
可以理解的是，在RPA热线服务机器人在目标受理部门的业务系统中录入业务数据后，目标受理部门即可根据该业务数据进行业务处理，并将包含处理过程及处理结果的业务处理数据录入目标受理部门的业务系统中。RPA热线服务机器人可以对该业务数据的后续处理流程进行跟进，并在目标受理部门在其业务系统中录入业务处理数据后，从目标受理部门的业务系统中，获取该业务处理数据，进而将业务处理数据录入热线服务系统。由此，即可完成针对本次来电的业务数据的备份，并且，录入热线服务系统的 业务处理数据还可以作为历史业务数据，用于进一步的机器学习，为后续的业务咨询、投诉建议等业务提供数据支撑。且通过利用RPA热线服务机器人在热线服务系统及目标受理部门的业务系统中进行数据录入，减少了数据录入所需的人工成本。
本公开实施例中，RPA热线服务机器人通过根据对话语音中的目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取目标关键信息所属的目标业务类别，根据目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取目标业务类别对应的目标受理部门，访问目标受理部门的业务系统，并将第一文本、第二文本、目标关键信息及目标业务类别，录入目标受理部门的业务系统，实现了结合RPA和AI技术，根据本次来电的来电方与接线方之间的对话语音，准确、快速的确定业务的目标受理部门，进而自动将本次来电对应的业务批转至目标受理部门，从而提高了业务办理的准确性和效率，减少了人工成本。
下面参考图4，对本公开提供的结合RPA和AI的热线业务处理方法进行说明。
参考图4，热线服务系统可以提供服务入口，比如服务热线或热线门户网站，从而使得用户可以通过拨打服务热线，或者登录服务热线门户网站，进行问题咨询或者投诉建议等。
在服务热线被接听后，响应于服务热线被接听，RPA热线服务机器人可以获取接线方与来电方的对话语音，并基于ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本。其中，假设接线方对应的第二文本为“您好，请问有什么可以帮助您”，来电方对应的第一文本为“A区B工地夜间23:23还在施工，噪音扰民，特此投诉，望部门介入处理”。
进一步的，RPA热线服务机器人可以基于NLP技术对第一文本和第二文本进行解析，理解来电方的意图，获取对话语音中的目标关键信息：时间“夜间23:23”、地点“A区B工地”、事件“施工”“噪音扰民”、意图“投诉”。进一步的，RPA热线服务机器人可以根据目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，获取目标关键信息对应的目标业务知识“该问题属于城乡建设问题、需要由住建局受理解决”，并通过热线服务系统展示该目标业务知识。其中，第一对应关系，可以通过历史业务数据，通过机器学习得到。接线方根据经验及热线服务系统上展示的目标业务知识，即可确定本次来电的来电方的需求是投诉建议，这类业务无法实时处理，需要派发到某个受理部门处理，从而接线方可以告知来电方业务已记录，会转达住建局受理该业务。
由此，通过采用RPA和AI结合的方式，展示目标关键信息对应的目标业务知识，为接线方实时处理服务热线的业务提供了参考，从而使得没有经验的接线方不必检索知识库，即可快速获取与本次来电的来电方的需求相关的业务知识，从而提高了业务办理效率，减少了人工成本，并且，使得接线方可以参考目标业务知识答复来电方，从而提高了业务办理的准确性，进而提高了业务办理的质量。
在服务热线被挂断后，RPA热线服务机器人可以自动将第一文本、第二文本、目标 关键信息及目标业务知识录入热线服务系统，以对本次来电的业务内容进行备份，方便后续对本次来电的业务内容进行追溯，且使得接线方不必通过人工录入业务数据，从而减少了录入业务数据所需的人工成本。
进一步的，接线方可以向RPA热线服务机器人下发派单指令，从而RPA热线服务机器人可以根据对话语音中的目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，并确定目标关键信息所属的目标业务类别为城乡建设类，由于城乡建设类对应的受理部门为住建局，则RPA热线服务机器人可以确定目标受理部门为住建局，进而访问住建局的业务系统，并将第一文本、第二文本、目标关键信息及目标业务类别，录入住建局的业务系统。
另外，RPA热线服务机器人可以将目标业务类别及目标受理部门录入热线服务系统，以进行备份，并根据备份的数据，对本次来电的业务的后续处理流程进行跟进。在住建局对此次投诉建议进行业务处理后，可以将包括处理过程及处理结果的业务处理数据录入住建局的业务系统，从而RPA热线服务机器人可以从住建局的业务系统中获取业务处理数据，并将业务处理数据录入热线服务系统。并且，录入热线服务系统的业务处理数据还可以作为历史业务数据，用于进一步的机器学习，为后续的业务咨询、投诉建议等业务提供数据支撑。
由此，实现了结合RPA和AI技术，根据本次来电的来电方与接线方之间的对话语音，准确、快速的确定业务的目标受理部门，进而自动将本次来电对应的业务批转至目标受理部门，从而提高了业务办理的准确性和效率，减少了人工成本。且通过利用RPA热线服务机器人在热线服务系统及目标受理部门的业务系统中进行数据录入，减少了数据录入所需的人工成本。
为了实现上述实施例，本公开还提出了一种结合RPA和AI的热线业务处理装置。图5是根据本公开一个实施例的结合RPA和AI的热线业务处理装置的结构示意图。
如图5所示，该结合RPA和AI的热线业务处理装置500，应用于RPA热线服务机器人，包括：第一获取模块501、识别模块502、解析模块503、处理模块504及第一录入模块505。
第一获取模块501，用于响应于服务热线被接听，获取接线方与来电方的对话语音。
识别模块502，用于基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本。
解析模块503，用于基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息。
处理模块504，用于根据目标关键信息，获取并展示对应的目标业务知识。
第一录入模块505，用于响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统。
需要说明的是，本公开实施例的结合RPA和AI的热线业务处理装置，可以执行结合RPA和AI的热线业务处理方法，该结合RPA和AI的热线业务处理装置，可以由 RPA热线服务机器人实现，例如，结合RPA和AI的热线业务处理装置可以为RPA热线服务机器人，或者结合RPA和AI的热线业务处理装置可以配置在RPA热线服务机器人中，本公开对此不作限制。
其中，结合RPA和AI的热线业务处理装置可以配置在电子设备中，该电子设备可以包括但不限于终端设备、服务器等，该实施例对电子设备不作具体限定。
在本公开的一个实施例中，处理模块504，包括：
第一获取单元，用于根据目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取目标关键信息对应的目标业务知识；
第一展示单元，用于通过热线服务系统，展示目标业务知识。
在本公开的一个实施例中，第一获取单元，具体用于：根据目标关键信息，查询第一对应关系，以获取目标关键信息对应的多个候选业务知识；将多个候选业务知识中，满足预设条件的至少一个候选业务知识，作为目标业务知识。
在本公开的一个实施例中，结合RPA和AI的热线业务处理装置500还包括：
第二获取模块，用于根据对话语音中的目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取目标关键信息所属的目标业务类别；
第三获取模块，用于根据目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取目标业务类别对应的目标受理部门；
第二录入模块，用于访问目标受理部门的业务系统，并将第一文本、第二文本、目标关键信息及目标业务类别，录入目标受理部门的业务系统。
在本公开的一个实施例中，第二获取模块，包括：
第二获取单元，用于根据目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取目标关键信息所属的多个候选业务类别；
第二展示单元，用于展示多个候选业务类别；
处理单元，用于响应于多个候选业务类别中的第一业务类别被选择，将第一业务类别确定为目标业务类别。
在本公开的一个实施例中，结合RPA和AI的热线业务处理装置500还包括：
第三录入模块，用于将目标业务类别及目标受理部门，录入热线服务系统。
在本公开的一个实施例中，结合RPA和AI的热线业务处理装置500还包括：
第四获取模块，用于从目标受理部门的业务系统中，获取对话语音对应的业务处理数据；
第四录入模块，用于将业务处理数据录入热线服务系统。
在本公开的一个实施例中，结合RPA和AI的热线业务处理装置500还包括：
展示模块，用于展示第一文本及第二文本。
需要说明的是，前述对结合RPA和AI的热线业务处理方法实施例的解释说明也适用于该实施例的结合RPA和AI的热线业务处理装置，本公开结合RPA和AI的热线业务处理装置实施例中未公布的细节，此处不再赘述。
综上，本公开实施例的结合RPA和AI的热线业务处理装置，响应于服务热线被接听，获取接线方与来电方的对话语音，基于语音识别ASR技术，对对话语音进行语音识别，以获取来电方对应的第一文本及接线方对应的第二文本，基于自然语言处理NLP技术，对第一文本及第二文本进行解析，以获取对话语音中的目标关键信息，根据目标关键信息，获取并展示对应的目标业务知识，响应于服务热线被挂断，将第一文本、第二文本、目标关键信息及目标业务知识，录入热线服务系统，由此，通过采用RPA和AI结合的方式，展示目标关键信息对应的目标业务知识，为接线方实时处理服务热线的业务提供了参考，从而提高了业务办理的质量及效率，并且由于无需通过人工录入业务数据，从而减少了人工成本。
为了实现上述实施例，本公开实施例还提出一种电子设备，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，所述处理器执行所述计算机程序时，实现如前述任一方法实施例所述的结合RPA和AI的热线业务处理方法。
为了实现上述实施例，本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如前述任一方法实施例所述的结合RPA和AI的热线业务处理方法。
为了实现上述实施例，本公开实施例还提出一种计算机程序产品，当所述计算机程序产品中的指令处理器执行时，实现如前述任一方法实施例所述的结合RPA和AI的热线业务处理方法。
图6示出了适于用来实现本公开实施方式的示例性电子设备的框图。图6显示的电子设备12仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示，电子设备12以通用计算设备的形式表现。电子设备12的组件可以包括但不限于：一个或者多个处理器或者处理单元16，系统存储器28，连接不同系统组件(包括存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture；以下简称：ISA)总线，微通道体系结构(Micro Channel Architecture；以下简称：MAC)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association；以下简称：VESA)局域总线以及外围组件互连(Peripheral Component Interconnection；以下简称：PCI)总线。
电子设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
存储器28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory；以下简称：RAM)30和/或高速缓存存储器32。电子设备12可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以用于读写不可移动的、非易失性磁介质(图6未显示，通 常称为“硬盘驱动器”)。尽管图6中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如：光盘只读存储器(Compact Disc Read Only Memory；以下简称：CD-ROM)、数字多功能只读光盘(Digital Video Disc Read Only Memory；以下简称：DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线18相连。存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本公开各实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如存储器28中，这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本公开所描述的实施例中的功能和/或方法。
电子设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与一个或者多个使得用户能与该电子设备12交互的设备通信，和/或与使得该电子设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且，电子设备12还可以通过网络适配器20与一个或者多个网络(例如局域网(Local Area Network；以下简称：LAN)，广域网(Wide Area Network；以下简称：WAN)和/或公共网络，例如因特网)通信。如图6所示，网络适配器20通过总线18与电子设备12的其它模块通信。应当明白，尽管图6中未示出，可以结合电子设备12使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在存储器28中的程序，从而执行各种功能应用以及数据处理，例如实现前述实施例中提及的方法。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本公开的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本公开的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部 分，并且本公开的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本公开的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本公开各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。尽管上面已经示出和描述了本公开的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本公开的限制，本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (15)

  1. 一种结合机器人流程自动化RPA和人工智能AI的热线业务处理方法，应用于RPA热线服务机器人，所述方法包括：
    响应于服务热线被接听，获取接线方与来电方的对话语音；
    基于语音识别ASR技术，对所述对话语音进行语音识别，以获取所述来电方对应的第一文本及所述接线方对应的第二文本；
    基于自然语言处理NLP技术，对所述第一文本及所述第二文本进行解析，以获取所述对话语音中的目标关键信息；
    根据所述目标关键信息，获取并展示对应的目标业务知识；
    响应于所述服务热线被挂断，将所述第一文本、所述第二文本、所述目标关键信息及所述目标业务知识，录入热线服务系统。
  2. 根据权利要求1所述的方法，其中，所述根据所述目标关键信息，获取并展示对应的目标业务知识，包括：
    根据所述目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取所述目标关键信息对应的所述目标业务知识；
    通过所述热线服务系统，展示所述目标业务知识。
  3. 根据权利要求2所述的方法，其中，所述根据所述目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取所述目标关键信息对应的所述目标业务知识，包括：
    根据所述目标关键信息，查询所述第一对应关系，以获取所述目标关键信息对应的多个候选业务知识；
    将所述多个候选业务知识中，满足预设条件的至少一个候选业务知识，作为所述目标业务知识。
  4. 根据权利要求1-3任一项所述的方法，其中，所述方法还包括：
    根据所述对话语音中的所述目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取所述目标关键信息所属的目标业务类别；
    根据所述目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取所述目标业务类别对应的目标受理部门；
    访问所述目标受理部门的业务系统，并将所述第一文本、所述第二文本、所述目标关键信息及所述目标业务类别，录入所述目标受理部门的业务系统。
  5. 根据权利要求4所述的方法，其中，所述根据所述对话语音中的所述目标关键 信息，查询各关键信息与各业务类别之间的第二对应关系，以获取所述目标关键信息所属的目标业务类别，包括：
    根据所述目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取所述目标关键信息所属的多个候选业务类别；
    展示多个所述候选业务类别；
    响应于多个所述候选业务类别中的第一业务类别被选择，将所述第一业务类别确定为所述目标业务类别。
  6. 根据权利要求4或5所述的方法，其中，所述根据所述目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取所述目标业务类别对应的目标受理部门之后，还包括：
    将所述目标业务类别及所述目标受理部门，录入所述热线服务系统。
  7. 根据权利要求4-6中任一项所述的方法，其中，所述将所述第一文本、所述第二文本、所述目标关键信息、所述目标业务类别，录入所述目标受理部门的业务系统之后，还包括：
    从所述目标受理部门的业务系统中，获取所述对话语音对应的业务处理数据；
    将所述业务处理数据录入所述热线服务系统。
  8. 一种结合RPA和AI的热线业务处理装置，应用于RPA热线服务机器人，所述装置包括：
    第一获取模块，用于响应于服务热线被接听，获取接线方与来电方的对话语音；
    识别模块，用于基于语音识别ASR技术，对所述对话语音进行语音识别，以获取所述来电方对应的第一文本及所述接线方对应的第二文本；
    解析模块，用于基于自然语言处理NLP技术，对所述第一文本及所述第二文本进行解析，以获取所述对话语音中的目标关键信息；
    处理模块，用于根据所述目标关键信息，获取并展示对应的目标业务知识；
    第一录入模块，用于响应于所述服务热线被挂断，将所述第一文本、所述第二文本、所述目标关键信息及所述目标业务知识，录入热线服务系统。
  9. 根据权利要求8所述的装置，其中，所述处理模块，包括：
    第一获取单元，用于根据所述目标关键信息，查询各关键信息与各业务知识之间的第一对应关系，以获取所述目标关键信息对应的所述目标业务知识；
    第一展示单元，用于通过所述热线服务系统，展示所述目标业务知识。
  10. 根据权利要求9所述的装置，其中，所述第一获取单元，具体用于：
    根据所述目标关键信息，查询所述第一对应关系，以获取所述目标关键信息对应的多个候选业务知识；
    将所述多个候选业务知识中，满足预设条件的至少一个候选业务知识，作为所述目标业务知识。
  11. 根据权利要求8-10任一项所述的装置，其中，所述装置还包括：
    第二获取模块，用于根据所述对话语音中的所述目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取所述目标关键信息所属的目标业务类别；
    第三获取模块，用于根据所述目标业务类别，查询各业务类别与各受理部门之间的第三对应关系，以获取所述目标业务类别对应的目标受理部门；
    第二录入模块，用于访问所述目标受理部门的业务系统，并将所述第一文本、所述第二文本、所述目标关键信息及所述目标业务类别，录入所述目标受理部门的业务系统。
  12. 根据权利要求11所述的装置，其中，所述第二获取模块，包括：
    第二获取单元，用于根据所述目标关键信息，查询各关键信息与各业务类别之间的第二对应关系，以获取所述目标关键信息所属的多个候选业务类别；
    第二展示单元，用于展示多个所述候选业务类别；
    处理单元，用于响应于多个所述候选业务类别中的第一业务类别被选择，将所述第一业务类别确定为所述目标业务类别。
  13. 根据权利要求11或12所述的装置，其中，所述装置还包括：
    第三录入模块，用于将所述目标业务类别及所述目标受理部门，录入所述热线服务系统。
  14. 一种电子设备，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，所述处理器执行所述计算机程序时，实现如权利要求1-7中任一项所述的方法。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其中，该计算机程序被处理器执行时实现如权利要求1-7中任一项所述的方法。
PCT/CN2022/083447 2022-01-24 2022-03-28 结合rpa和ai的热线业务处理方法、装置及电子设备 WO2023137866A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210080200.7 2022-01-24
CN202210080200.7A CN114443825A (zh) 2022-01-24 2022-01-24 结合rpa和ai的热线业务处理方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2023137866A1 true WO2023137866A1 (zh) 2023-07-27

Family

ID=81370293

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/083447 WO2023137866A1 (zh) 2022-01-24 2022-03-28 结合rpa和ai的热线业务处理方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN114443825A (zh)
WO (1) WO2023137866A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111147676A (zh) * 2019-12-23 2020-05-12 广州供电局有限公司 基于电力it服务呼叫中心智能辅助坐席应答服务实现方法
US20200382634A1 (en) * 2018-04-16 2020-12-03 Huawei Technologies Co., Ltd. Call processing method and apparatus, server, storage medium, and system
CN112259090A (zh) * 2020-09-10 2021-01-22 北京百度网讯科技有限公司 基于语音交互的业务办理方法、装置和电子设备
CN112702472A (zh) * 2020-12-10 2021-04-23 广州云徙科技有限公司 一种全渠道热线客服系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200382634A1 (en) * 2018-04-16 2020-12-03 Huawei Technologies Co., Ltd. Call processing method and apparatus, server, storage medium, and system
CN111147676A (zh) * 2019-12-23 2020-05-12 广州供电局有限公司 基于电力it服务呼叫中心智能辅助坐席应答服务实现方法
CN112259090A (zh) * 2020-09-10 2021-01-22 北京百度网讯科技有限公司 基于语音交互的业务办理方法、装置和电子设备
CN112702472A (zh) * 2020-12-10 2021-04-23 广州云徙科技有限公司 一种全渠道热线客服系统

Also Published As

Publication number Publication date
CN114443825A (zh) 2022-05-06

Similar Documents

Publication Publication Date Title
CN108897867B (zh) 用于知识问答的数据处理方法、装置、服务器和介质
US7236932B1 (en) Method of and apparatus for improving productivity of human reviewers of automatically transcribed documents generated by media conversion systems
US11157699B2 (en) Interactive method and apparatus based on test-type application
US7184539B2 (en) Automated call center transcription services
US8370155B2 (en) System and method for real time support for agents in contact center environments
US7542902B2 (en) Information provision for call centres
KR101004501B1 (ko) 쿼리에 기초하여 사용자에게 문서의 정보를 렌더링하는 방법, 음성 쿼리에 기초하여 사용자에게 정보를 렌더링하는 방법, 사용자에게 정보를 제공하는 방법, 및 컴퓨터 판독 가능 기록 매체
US11258902B2 (en) Partial automation of text chat conversations
US20130103391A1 (en) Natural language processing for software commands
US20070143100A1 (en) Method & system for creation of a disambiguation system
CN110415679B (zh) 语音纠错方法、装置、设备和存储介质
CN111212190A (zh) 一种基于话术策略管理的对话管理方法、装置和系统
KR20200032893A (ko) 챗봇 서비스를 위한 커뮤니케이션 정보 처리 시스템 및 그 제어 방법
WO2006085661A1 (ja) 質問応答データ編集装置、質問応答データ編集方法、質問応答データ編集プログラム
WO2021169485A1 (zh) 一种对话生成方法、装置及计算机设备
EP3295457B1 (en) Automatic visual display of audibly presented options to increase user efficiency and interaction performance
WO2023236252A1 (zh) 答案生成方法、装置、电子设备及存储介质
CN116521841B (zh) 用于生成回复信息的方法、装置、设备及介质
WO2023236253A1 (zh) 文档检索方法、装置及电子设备
CN113011159A (zh) 人工座席监听方法、装置、电子设备及存储介质
KR20110048675A (ko) 음성인식과 태깅을 이용한 콜센터 상담 방법 및 상담 시스템
CN113158690A (zh) 对话机器人的测试方法和装置
WO2023137866A1 (zh) 结合rpa和ai的热线业务处理方法、装置及电子设备
KR100803900B1 (ko) 음성 인식 ａｒｓ 서비스 방법 및 시스템
CN108920715B (zh) 客服的智能化辅助方法、装置、服务器和存储介质

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: 22921300

Country of ref document: EP

Kind code of ref document: A1