CN112820316A - Intelligent customer service dialogue method and system - Google Patents
Intelligent customer service dialogue method and system Download PDFInfo
- Publication number
- CN112820316A CN112820316A CN202011622221.4A CN202011622221A CN112820316A CN 112820316 A CN112820316 A CN 112820316A CN 202011622221 A CN202011622221 A CN 202011622221A CN 112820316 A CN112820316 A CN 112820316A
- Authority
- CN
- China
- Prior art keywords
- target
- scene
- end equipment
- attribution
- sending
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000006854 communication Effects 0.000 claims abstract description 38
- 238000004891 communication Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims description 20
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 206010026749 Mania Diseases 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a dialogue method and a dialogue system for intelligent customer service, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving voice session information of front-end equipment in a call process; determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information; according to the scene attribution type, sending a first target answer corresponding to the scene attribution type to front-end equipment; feedback information is not obtained within the preset time length for sending the first target answer, and a second target answer corresponding to the scene attribution type is sent to the front-end equipment; or receiving feedback information aiming at the first target answer sent by the front-end equipment within the preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment. The invention solves the problems of low user demand rate and poor communication caused by the adoption of a one-to-one answering mode and a question-answer mode of the existing intelligent customer service.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a dialogue method and a dialogue system for intelligent customer service.
Background
Along with the popularization and application of the internet and electronic commerce, intelligent customer service is more and more. The intelligent customer service is developed on the basis of large-scale knowledge processing, is applied to the industry, relates to large-scale knowledge processing technology, natural language understanding technology, knowledge management technology, automatic question-answering system, reasoning technology and the like, has industrial universality, provides fine-grained knowledge management technology for enterprises, and establishes a quick and effective technical means based on natural language for communication between the enterprises and mass users; meanwhile, statistical analysis information required by fine management can be provided for enterprises, and a large amount of human resources and cost can be saved for the enterprises.
At present, most intelligent customer service is applied based on big data knowledge processing technology, namely, a large amount of visitor and customer service conversation records are collected firstly, and then are extracted, classified and managed, and are stored in a knowledge base for later use. When the intelligent customer service works, the knowledge stored in the knowledge base is read, the existing knowledge is read and then fed back to the customer, and a one-to-one answer conversation mode is adopted.
However, the traditional one-to-one answering mode, namely the one-to-one answering customer service mode, cannot meet the requirements of users for different appeal, and meanwhile, the communication experience of the users is reduced.
Disclosure of Invention
The embodiment of the invention provides a dialogue method and a dialogue system for intelligent customer service, which are used for solving the problems of low user demand rate and poor communication caused by the fact that the existing intelligent customer service adopts a one-to-one answering mode and a question-and-answer mode.
In order to solve the technical problems, the invention adopts the following technical scheme:
the embodiment of the invention provides a dialogue method and a dialogue system for intelligent customer service, which comprise the following steps:
receiving voice session information of front-end equipment in a call process;
determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information;
according to the scene attribution type, sending a first target answer corresponding to the scene attribution type to the front-end equipment;
receiving feedback information aiming at a first target answer sent by the front-end equipment within a preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment; or, feedback information is not acquired within a preset time length for sending the first target answer, and the second target answer corresponding to the scene attribution type is sent to the front-end equipment.
Optionally, the method further includes:
monitoring the voice volume sent by the front-end equipment in the communication process;
when the voice volume is larger than a first preset range, acquiring the tone words in the voice conversation information;
and determining a communication mode after a second preset time length according to the language word.
Optionally, the method for determining a communication mode after a second preset duration according to the language word includes:
if the tone words are of the peace and peace type, determining the communication mode after the second preset time length as the interactive communication is kept;
and if the language word is in a sharp category, determining the communication mode after the second preset time length as stopping continuing the communication.
Optionally, the method further includes:
and storing the feedback information sent by the front-end equipment in each conversation process, and applying the feedback information to the next voice interactive conversation.
Optionally, the determining, according to the voice session information, a scene attribution category to which a first target problem corresponding to the voice session information belongs includes:
determining keyword information of the first target problem through an analysis matching mechanism;
determining a first scene attribution category to which the first target problem belongs from a database according to the keyword information;
determining semantic information of the first target problem by analyzing a matching mechanism;
and determining a second scene category to which the first target problem belongs from the first scene attribution categories according to the semantic information.
Optionally, the analysis matching mechanism performs mechanism matching on the audio signal in the voice conversation information and the corresponding electric signal frequency band where the language word is located.
Optionally, the sharp class includes heavy and thick types; wherein the decibel range of the heavy and thick type is 60db to 70 db;
the peace class includes mild and manic; wherein the decibel range of the mild form is 20db to 40 db; the manic form has a decibel range of 40db to 60 db.
Optionally, the second target answer is a complement of the first target answer; alternatively, the second target answer is a further confirmation of the first target question.
The embodiment of the invention also provides a dialog system of intelligent customer service, which comprises:
the receiving module is used for receiving the voice conversation information of the front-end equipment in the conversation process;
the determining module is used for determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information;
the first sending module is used for sending a first target answer corresponding to the scene attribution type to the front-end equipment according to the scene attribution type;
the second sending module is used for receiving feedback information aiming at the first target answer and sent by the front-end equipment within a preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment; or, feedback information is not acquired within a preset time length for sending the first target answer, and the second target answer corresponding to the scene attribution type is sent to the front-end equipment.
Embodiments of the present invention further provide a computer-readable storage medium, in which a computer program is stored, where the computer program is executable by at least one processor, so as to cause the at least one processor to execute the steps of the intelligent customer service dialog method described above.
The invention has the beneficial effects that:
in the technical scheme, feedback information aiming at a first target answer sent by front-end equipment is received within a preset time length of the first target answer of a first target question of sending voice conversation information, and at least one extension question corresponding to a scene attribution type of the first target question is sent to the front-end equipment; or, feedback information is not acquired within a preset time length of a first target answer of a first target question of voice session information, and a second target answer corresponding to the scene attribution type is sent to the front-end equipment. The embodiment of the invention can enrich the communication capability and problem solving capability of intelligent customer service; the embodiment of the invention can send the extension problem to carry out deep interactive communication, so that the intelligent customer service can feel more natural and comfortable in communication and obtain better experience.
Drawings
FIG. 1 is a flow chart of a dialog method for intelligent customer service according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a dialog system of intelligent customer service according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help the full understanding of the embodiments of the present invention. Thus, it will be apparent to those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The invention provides a dialogue method and a dialogue system of intelligent customer service, aiming at the problems that the existing intelligent customer service adopts one-to-one answering and the customer service mode of one question and one answer causes low demand rate and poor communication sense of users, and the dialogue method and the dialogue system are used for communicating with the users to feel more natural and comfortable and obtain better experience.
It should be noted that the intelligent customer service system is a system that can realize communication and interaction between robots and people through natural language. The robot serves as a customer service staff role, identifies and understands problems brought forward by the user, understands the intention of the user through semantic analysis, communicates with the user in a humanized mode and provides information consultation and related services for the user.
It should be noted that the intelligent customer service system establishes a database to obtain a large number of conversation scenes, and conversation modes and question answering modes corresponding to the conversation scenes. Meanwhile, the database is used for mutually connecting the conversation modes in different conversation scenes in series to form the conversation richness of each conversation scene, wherein the conversation richness comprises large categories of scene scenes generated by conversation and answer modes of different small categories stored in each large category; and the system also comprises a data updating library which can update the database in real time.
As shown in fig. 1, an alternative embodiment of the present invention provides a dialog method for intelligent customer service, including:
the voice conversation information at least carries a first target problem of the voice input of the target object. The front-end equipment is a tool for sending voice conversation information to a target object, and can be a mobile terminal such as a mobile phone, a computer and an intelligent watch.
in the embodiment, according to the voice conversation information, determining a scene attribution category with the highest semantic similarity with a first target problem from a database; for example, the voice session information includes "how much money is in an X model of a car", and the scene attribution category is determined from the database as "X model of a car", so as to accurately locate the area corresponding to the first target problem.
here, the first target answer is an answer with the highest priority of a scene attribution category to which the first target question belongs.
Here, step 400 determines whether feedback information sent by the front-end device is received within a preset duration of sending the first target answer, gives a policy of sending an extended question to the front-end device after receiving the feedback information, and also gives a question of sending the second target answer to the front-end device after not receiving the feedback information, both of which can achieve the purpose of multiple answers to one question.
In this embodiment, if feedback information for a first target answer sent by a front-end device is received within a preset time period after the first target answer with the highest priority, it indicates that a target object recognizes the first target answer, and at this time, at least one extension question corresponding to a scene attribution category of the first target question is also sent to the front-end device, where the extension question is a supplement of the first target question, so as to achieve an objective of perfectly solving the first target question, where the feedback information is feedback information returned by the target object for the first target answer; according to the embodiment, the extension of the questions of the answer contents of the same category is realized, and the feedback is carried out in the conversation process, so that the experience of interactive communication is improved.
On the other hand, if the feedback information is not acquired within the preset time length for sending the first target answer, the second target answer corresponding to the scene attribution type is sent to the front-end equipment, the second target answer comprises a plurality of sub-answers with the priority lower than that of the first target answer, the purpose of replying a plurality of answers with different priorities for one question of the user is achieved, the technical effects of multiple questions and multiple answers and user experience improvement are achieved, and the technical problem that the user experience is poor due to the fact that the existing intelligent customer service adopts a question-answer mode is solved.
Optionally, the method further includes:
step 510, monitoring the voice volume sent by the front-end equipment in the communication process;
step 520, when the voice volume is larger than a first preset range, acquiring the tone words in the voice conversation information;
step 530, determining a communication mode after a second preset time length according to the language word.
In this embodiment, by monitoring the voice volume sent by the front-end device, particularly, by monitoring decibel information of the front-end device, when the voice volume is greater than a first preset range, the first preset range is preferably 20db to 60db, and if the voice volume is greater than 60db, the tone word in the voice session information to be acquired is acquired; and analyzing according to the acquired language word information, and determining whether the call mode after the second preset time length is any one of continuing the call or stopping the call.
Specifically, the linguistic words include a flat class and a sharp class, and step 530 includes:
if the tone words are of the peace and peace type, determining the communication mode after the second preset time length as the interactive communication is kept;
and if the language word is in a sharp category, determining the communication mode after the second preset time length as stopping continuing the communication.
In this embodiment, the voice call state of the current client is determined according to the analysis of the mood words. If the tone words are of the same type, the current conversation state can be normal, the interactive conversation can be continuously kept, if the tone words are of the sharp type, the condition that the user state is excited in the current conversation process can be indicated, a voice can be sent to remind the user, and then the current conversation is stopped.
Specifically, the sharp class includes heavy and thick types; wherein the decibel range of the heavy and thick type is 60db to 70 db;
the peace class includes mild and manic; wherein the decibel range of the mild form is 20db to 40 db; the manic form has a decibel range of 40db to 60 db.
It should be noted that, if the mood word is of a heavy type, that is, the decibel range is 60db to 70db, it is considered that the current call exceeds a normal call range, and at this time, the interaction with the front-end device is stopped; if the tone words are mild, the tone words and the front-end equipment are in a normal interaction state, and the current conversation state is kept; if the tone words are impatient, the emotion excitement of the user input by the front-end equipment is explained, and at the moment, the intelligent customer service can remind in real time to prevent the voice call from being hung up by mistake.
Optionally, the step 200 includes:
step 210, determining keyword information of the first target problem by analyzing a matching mechanism;
step 220, determining a first scene attribution category to which the first target problem belongs from a database according to the keyword information;
step 230, determining semantic information of the first target problem by analyzing a matching mechanism;
step 240, according to the semantic information, determining a second scene category to which the first target question belongs from the first scene attribution categories.
The embodiment analyzes a first scenario attribution category to which the first target question belongs through steps 210 and 220; for example, the first target question is "how much money the X model in the car" and the first scene attribution category is determined to be "car category" according to the keyword information "car"; then, continuing to determine, by analyzing a matching mechanism, that semantic information of the first target question is "how much money of the X model", and then further determining that a second scene category to which the first target question belongs is "how much money of the X model in the automobile". According to the embodiment, the attribution field of the problem is determined through the large category (the attribution category of the first scene), and then the specific problem in the attribution field is determined through the small category (the attribution category of the second scene), so that the problem is accurately positioned, and the problem can be more accurately called from the database.
Specifically, the analysis matching mechanism performs mechanism matching on the audio signal in the voice conversation information and the corresponding electric signal frequency band where the language word is located.
It should be noted that there are three general scenes where errors occur in the error rate of voice interaction, and the first is that feedback information of the front-end device is not received within a preset time; the second is that the intelligent customer service system can not match the understood voice information with the current database, the third is the voice problem sent by the front-end equipment, and the intelligent customer service system can not solve the problem, namely the problem is out of limit. The analysis and matching mechanism in this embodiment is to acquire the audio signal of the speech session information while understanding the speech session information, and to correspond to the electrical signal frequency band corresponding to the electrical signal frequency band in the database, so as to acquire the corresponding linguistic and linguistic words. The analysis matching mechanism improves the matching accuracy with the database and reduces the error rate of voice interaction.
Optionally, the second target answer is a complement of the first target answer; alternatively, the second target answer is a further confirmation of the first target question.
In this embodiment, the second target answer is a supplement to the first target answer, and the second target answer has a lower priority than the first target answer; for example, the first target question of the voice session information sent by the front-end device is "how to query the telephone charge", the first target answer with higher priority of the above-mentioned question is "the current telephone bill of the mobile phone is X yuan", the second target answer is "ask for whether you query other services yet", for example, when the first target question of the voice session information sent by the front-end device is "transact a bank card", the first target answer with higher priority of the above-mentioned question is "the bank card is generally classified into a debit card, a credit card, a magnetic stripe card, which type of bank card you need to transact", and the first target answer with lower priority is "the specific transaction mode of all types of bank cards mentioned below". The first target answer and the second target answer are obtained according to a database.
On the other hand, the second target answer is the further confirmation of the first target question, wherein it should be noted that the first target question is determined by the information carried by the answer with higher priority, for example, the information carried by the answer with higher priority is "transact credit card", and then the first target question is transact application card. It is easy to note that the above further confirmation means guiding, perfecting the solution of the first objective problem, for fundamentally solving the problem. For example, if the first target question is "inquire other mobile phone charge for checking bills", the first target answer may be "please input card numbers and passwords of other mobile phones", and in order to prevent the user from worrying about personal information being leaked, at this time, the second target answer is "you are relieved, card number collection is a necessary process for inquiring bills, and i strictly adhere to the privacy agreement", so as to achieve guidance and perfect solution of the first target question.
In summary, the intelligent customer service conversation method of the embodiment of the invention can determine the conversation scene and the answering mode to carry out multi-level classification, establish a matching mechanism, and enrich the communication capacity and the problem solving capacity of the intelligent customer service; the embodiment of the invention can also analyze the tone words according to the voice volume and record the problem when the user has strong tone, thereby fully perfecting the problem-solving data in the conversation and improving the customer service quality; the embodiment of the invention can also carry out deep interactive communication, thereby improving the experience of users.
Optionally, the method further includes:
step 600, storing feedback information sent by the front-end device in each call process, and applying the feedback information to the next voice interactive call.
In the embodiment, the feedback information sent by the front-end equipment in each call process is stored to the corresponding scene attribution category, so that the database for intelligent call is enriched, the same target problem can be avoided in the next call, and the defect that the target problem of the user cannot be solved due to no record in the database is overcome.
As shown in fig. 2, an embodiment of the present invention further provides a dialog system for intelligent customer service, including:
a receiving module 10, configured to receive voice session information of a front-end device in a call process;
a determining module 20, configured to determine, according to the voice session information, a scene attribution category to which a first target problem corresponding to the voice session information belongs;
a first sending module 30, configured to send a first target answer corresponding to the scene attribution category to the front-end device according to the scene attribution category;
a second sending module 40, configured to receive feedback information, which is sent by the front end device and is for the first target answer, within a preset duration of sending the first target answer, and send, to the front end device, at least one extension question corresponding to a scene attribution category of the first target question; or, feedback information is not acquired within a preset time length for sending the first target answer, and the second target answer corresponding to the scene attribution type is sent to the front-end equipment.
Optionally, the system further includes:
the monitoring module is used for monitoring the voice volume sent by the front-end equipment in the conversation process;
the acquisition module is used for acquiring the tone words in the voice conversation information when the voice volume is larger than a first preset range;
and the second determining module is used for determining the communication mode after a second preset time length according to the language word.
Optionally, the linguistic words include a flat class and a sharp class, and the second determining module includes:
the first determining unit is used for determining the communication mode after the second preset time length as the interactive communication is kept if the language word is of the Pinghe type;
and the second determining unit is used for determining the communication mode after the second preset time length as stopping continuing the communication if the language word is in the sharp category.
Optionally, the system further includes:
and the storage module is used for storing the feedback information sent by the front-end equipment in each conversation process and applying the feedback information to the next voice interactive conversation.
Optionally, the determining module 20 includes:
a third determining subunit, configured to determine, through an analysis matching mechanism, keyword information of the first target question;
the fourth determining subunit is configured to determine, according to the keyword information, a first scene attribution category to which the first target question belongs from a database;
a fifth determining subunit, configured to determine, through an analysis matching mechanism, semantic information of the first target problem;
a sixth determining subunit, configured to determine, according to the semantic information, a second scenario category to which the first target problem belongs from the first scenario attribution category.
Specifically, the analysis matching mechanism in the determination module 20 performs mechanism matching on the audio signal in the voice session information and the electrical signal frequency band where the corresponding speech word is located.
Note that the sharp class includes a heavy type; wherein the decibel range of the heavy and thick type is 60db to 70 db;
the peace class includes mild and manic; wherein the decibel range of the mild form is 20db to 40 db; the manic form has a decibel range of 40db to 60 db.
It should be noted that the second target answer is a supplement to the first target answer; alternatively, the second target answer is a further confirmation of the first target question.
Embodiments of the present invention further provide a computer-readable storage medium, in which a computer program is stored, where the computer program is executable by at least one processor, so as to cause the at least one processor to execute the steps of the intelligent customer service dialog method described above.
The computer-readable storage medium in this embodiment, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an application (App) mall, etc., has stored thereon a computer program that, when executed by a processor, implements a corresponding function. The computer-readable storage medium of this embodiment is used for storing a dialog system of intelligent customer service, and when being executed by a processor, the dialog system of intelligent customer service implements the dialog method of intelligent customer service of the above-mentioned embodiment.
Compared with the prior art, the intelligent customer service dialogue method, the intelligent customer service dialogue system and the computer-readable storage medium provided by the embodiment of the invention receive the voice conversation information of the front-end equipment in the conversation process; determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information; according to the scene attribution type, sending a first target answer corresponding to the scene attribution type to front-end equipment; feedback information is not obtained within the preset time length for sending the first target answer, and a second target answer corresponding to the scene attribution type is sent to the front-end equipment; or receiving feedback information aiming at the first target answer sent by the front-end equipment within the preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment. Therefore, the invention solves the problems that the existing intelligent customer service adopts a one-to-one answering mode and the customer service mode of asking for one answer causes low user demand rate and poor communication sense, and improves the communication efficiency of the intelligent customer service.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
While the preferred embodiments of the present invention have been described, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the following claims.
Claims (10)
1. A dialogue method of intelligent customer service is characterized by comprising the following steps:
receiving voice session information of front-end equipment in a call process;
determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information;
according to the scene attribution type, sending a first target answer corresponding to the scene attribution type to the front-end equipment;
receiving feedback information aiming at a first target answer sent by the front-end equipment within a preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment; or, feedback information is not acquired within a preset time length for sending the first target answer, and the second target answer corresponding to the scene attribution type is sent to the front-end equipment.
2. The intelligent customer service dialog method of claim 1, further comprising:
monitoring the voice volume sent by the front-end equipment in the communication process;
when the voice volume is larger than a first preset range, acquiring the tone words in the voice conversation information;
and determining a communication mode after a second preset time length according to the language word.
3. The dialog method of intelligent customer service according to claim 2, wherein the semantic words include a flat class and a sharp class, and the determining of the call mode after the second preset duration according to the semantic words comprises:
if the tone words are of the peace and peace type, determining the communication mode after the second preset time length as the interactive communication is kept;
and if the language word is in a sharp category, determining the communication mode after the second preset time length as stopping continuing the communication.
4. The intelligent customer service dialog method of claim 1, further comprising:
and storing the feedback information sent by the front-end equipment in each conversation process, and applying the feedback information to the next voice interactive conversation.
5. The dialog method of claim 2, wherein the determining, according to the voice session information, the category to which the first target question corresponding to the voice session information belongs includes:
determining keyword information of the first target problem through an analysis matching mechanism;
determining a first scene attribution category to which the first target problem belongs from a database according to the keyword information;
determining semantic information of the first target problem by analyzing a matching mechanism;
and determining a second scene category to which the first target problem belongs from the first scene attribution categories according to the semantic information.
6. The dialog method according to claim 5, wherein said analysis matching mechanism performs mechanism matching between the audio signal in said voice conversation information and the corresponding electrical signal frequency band in which said spoken word is located.
7. The intelligent customer service dialog method of claim 3 wherein the sharp class comprises a heavy type; wherein the decibel range of the heavy and thick type is 60db to 70 db;
the peace class includes mild and manic; wherein the decibel range of the mild form is 20db to 40 db; the manic form has a decibel range of 40db to 60 db.
8. The dialog method of an intelligent customer service according to claim 1, wherein the second target answer is a complement of the first target answer; alternatively, the second target answer is a further confirmation of the first target question.
9. A dialog system for intelligent customer service, comprising:
the receiving module is used for receiving the voice conversation information of the front-end equipment in the conversation process;
the determining module is used for determining a scene attribution category to which a first target problem corresponding to the voice session information belongs according to the voice session information;
the first sending module is used for sending a first target answer corresponding to the scene attribution type to the front-end equipment according to the scene attribution type;
the second sending module is used for receiving feedback information aiming at the first target answer and sent by the front-end equipment within a preset time length for sending the first target answer, and sending at least one extension question corresponding to the scene attribution type of the first target question to the front-end equipment; or, feedback information is not acquired within a preset time length for sending the first target answer, and the second target answer corresponding to the scene attribution type is sent to the front-end equipment.
10. A computer-readable storage medium, in which a computer program is stored which is executable by at least one processor to cause the at least one processor to perform the steps of the dialog method for intelligent customer service according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011622221.4A CN112820316A (en) | 2020-12-31 | 2020-12-31 | Intelligent customer service dialogue method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011622221.4A CN112820316A (en) | 2020-12-31 | 2020-12-31 | Intelligent customer service dialogue method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112820316A true CN112820316A (en) | 2021-05-18 |
Family
ID=75854560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011622221.4A Pending CN112820316A (en) | 2020-12-31 | 2020-12-31 | Intelligent customer service dialogue method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112820316A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113934825A (en) * | 2021-12-21 | 2022-01-14 | 北京云迹科技有限公司 | Question answering method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107026940A (en) * | 2017-05-18 | 2017-08-08 | 北京神州泰岳软件股份有限公司 | A kind of method and apparatus for determining session feedback information |
| CN109712646A (en) * | 2019-02-20 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Voice broadcast method, device and terminal |
| US20200005772A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Interactive method and device of robot, and device |
| CN110661927A (en) * | 2019-09-18 | 2020-01-07 | 平安科技（深圳）有限公司 | Voice interaction method and device, computer equipment and storage medium |
| CN111881273A (en) * | 2020-07-13 | 2020-11-03 | 北京捷通华声科技股份有限公司 | Question and answer processing method and device |
-
2020
- 2020-12-31 CN CN202011622221.4A patent/CN112820316A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107026940A (en) * | 2017-05-18 | 2017-08-08 | 北京神州泰岳软件股份有限公司 | A kind of method and apparatus for determining session feedback information |
| US20200005772A1 (en) * | 2018-06-28 | 2020-01-02 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Interactive method and device of robot, and device |
| CN109712646A (en) * | 2019-02-20 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Voice broadcast method, device and terminal |
| CN110661927A (en) * | 2019-09-18 | 2020-01-07 | 平安科技（深圳）有限公司 | Voice interaction method and device, computer equipment and storage medium |
| CN111881273A (en) * | 2020-07-13 | 2020-11-03 | 北京捷通华声科技股份有限公司 | Question and answer processing method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113934825A (en) * | 2021-12-21 | 2022-01-14 | 北京云迹科技有限公司 | Question answering method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020024389A1 (en) | Method for collecting overdue payment, device, computer apparatus, and storage medium | |
| US20200329144A1 (en) | Automated communications over multiple channels | |
| CN111223485A (en) | Intelligent interaction method and device, electronic equipment and storage medium | |
| CN110381221B (en) | Call processing method, device, system, equipment and computer storage medium | |
| CN112487810B (en) | Intelligent customer service method, device, equipment and storage medium | |
| CN111696558A (en) | Intelligent outbound method, device, computer equipment and storage medium | |
| CN111583931A (en) | Service data processing method and device | |
| CN111462726B (en) | Method, device, equipment and medium for answering out call | |
| CN113011159A (en) | Artificial seat monitoring method and device, electronic equipment and storage medium | |
| CN112529585A (en) | Interactive awakening method, device, equipment and system for risk transaction | |
| CN112383667A (en) | Call data processing method, device, equipment and storage medium | |
| CN112820316A (en) | Intelligent customer service dialogue method and system | |
| CN111291157A (en) | Response method, response device, terminal and storage medium | |
| CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
| CN111309882B (en) | Method and device for realizing intelligent customer service question and answer | |
| CN109871129B (en) | Human-computer interaction method and device, customer service equipment and storage medium | |
| CN111858874A (en) | Conversation service processing method, device, equipment and computer readable storage medium | |
| CN114138943A (en) | Dialog message generation method and device, electronic equipment and storage medium | |
| CN111556096B (en) | Information pushing method, device, medium and electronic equipment | |
| CN112651526A (en) | Method, device, equipment and storage medium for reserving target service | |
| CN113868396A (en) | Task intelligent dialogue construction method and system based on knowledge graph | |
| CN113099054A (en) | Voice interaction method, device, equipment and computer readable medium | |
| CN113782022B (en) | Communication method, device, equipment and storage medium based on intention recognition model | |
| CN115129847B (en) | Intelligent answering method and device | |
| CN115393077B (en) | Data processing method based on loan transaction man-machine conversation system and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |