CN111770235A - Intelligent voice access method and system - Google Patents
Intelligent voice access method and system Download PDFInfo
- Publication number
- CN111770235A CN111770235A CN202010630058.XA CN202010630058A CN111770235A CN 111770235 A CN111770235 A CN 111770235A CN 202010630058 A CN202010630058 A CN 202010630058A CN 111770235 A CN111770235 A CN 111770235A
- Authority
- CN
- China
- Prior art keywords
- call
- probability
- intelligent voice
- model
- label
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
-
- 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
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
-
- 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)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the field of online services, in particular to an intelligent voice access method and an intelligent voice access system. It includes: acquiring background information of an initiator of a call; obtaining a first mark based on the background information; acquiring detailed information of a call; the detailed information at least comprises the type of the service to which the call belongs; obtaining a second mark based on the detailed information; obtaining a solution probability based on the first label and the second label; when the solving probability is larger than a preset value, accessing an intelligent voice response system matched with the service type of the call; and when the solving probability is smaller than the preset value, accessing the manual response system.
Description
Technical Field
The invention relates to the field of online services, in particular to an intelligent voice access method and an intelligent voice access system.
Background
Customer service, which mainly embodies a value view oriented to customer satisfaction, integrates and manages all elements of customer interface in a preset optimal cost-service combination. Broadly speaking, any content that improves customer satisfaction falls within the scope of customer service.
Telephone customer service is used as a main execution mode of customer service, and in the face of the condition that a large number of users need service and manual customer service staff is insufficient, intelligent voice response is increasingly used, but the particularity of intelligent voice causes that the intelligent voice is not suitable for all problems or all users.
Disclosure of Invention
The invention provides an intelligent voice access method and system, which are intelligent and humanized.
Some embodiments of the invention are implemented as follows:
an intelligent voice access method, comprising:
acquiring background information of an initiator of a call;
obtaining a first mark based on the background information;
acquiring detailed information of the call; the detailed information at least comprises the service type of the call;
obtaining a second label based on the detailed information;
obtaining a solution probability based on the first label and the second label;
when the solving probability is larger than a preset value, accessing an intelligent voice response system matched with the service type of the call; and when the solving probability is smaller than the preset value, accessing a manual response system.
In one embodiment of the invention:
the intelligent voice response system is based on a BERT model and is obtained through training of call history data of the service type of the call.
In one embodiment of the invention:
processing the first marker based on a first model to obtain a first probability value;
processing the second marker based on a second model to obtain a second probability value;
deriving the solution probability based on the first probability value and the second probability value.
In one embodiment of the invention:
the second model is an RNN model.
The invention also provides an intelligent voice access system, which comprises:
the first acquisition module is used for acquiring background information of an initiator of the call;
the first marking module is used for obtaining a first mark based on the background information;
the second acquisition module is used for acquiring detailed information of the call; the detailed information at least comprises the service type of the call;
the second marking module is used for obtaining a second mark based on the detailed information;
a processing module for deriving a solution probability based on the first label and the second label;
the access module is used for accessing an intelligent voice response system matched with the service type of the call when the solution probability is greater than a preset value; and when the solving probability is smaller than the preset value, accessing a manual response system.
The technical scheme of the invention at least has the following beneficial effects:
the intelligent voice access system is high in intelligent degree, intelligent voice response or artificial customer service is provided according to the user condition pertinence, and the access proportion can be properly adjusted according to the pressure of the artificial customer service.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is an exemplary block diagram of an intelligent voice access system according to some embodiments of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Fig. 1 is an exemplary block diagram of an intelligent voice access system according to some embodiments of the present application.
The user initiates a voice request through the user terminal, which may be that there is an operation problem that needs to be consulted or that there is a problem in use. The user terminal may include, but is not limited to, a mobile device, a tablet computer, a laptop computer, a desktop computer, etc., or any combination thereof. Further, in some embodiments, the user terminal may also be a device running APP, an applet, or the like.
In the existing response access system, users usually access intelligent voice, and the problem which cannot be solved after consultation and guidance is carried out is transferred to manual work, so that time is greatly delayed for the part of groups, and experience is reduced.
For this case, an intelligent voice access system 100 is provided, which includes:
the first obtaining module 110 is configured to obtain background information of an initiator of a call.
The background information of the call initiator is some information that can be quickly acquired by the platform, and particularly, the background information can be acquired before the call is connected, the information can be stored in the background of the platform, and the background information is acquired after being matched according to the user account or the telephone number when the call is initiated.
In some embodiments, the context information may include user age, gender, account status, and the like.
A first marking module 120, configured to obtain a first mark based on the context information.
The background information is processed, including but not limited to discretization, normalization, etc., and in some embodiments, the background information may be vectorized to obtain the first token.
In some embodiments, some of the background information is important (e.g., account status, age, etc.), and another part of the background information is less relevant to the entire call response (e.g., birthday), and some unimportant information may be directly marked in the first mark, so as to reduce the consideration of the information in the subsequent determination.
A second obtaining module 130, configured to obtain detailed information of the call; the detailed information at least comprises the service type of the call.
In order to better solve the call, a part of detailed information is acquired, and the situation is classified. The detailed information at least comprises the service types, and different question banks can be set for intelligent voice responses of different service types in actual processing.
And a second marking module 140 for obtaining a second mark based on the detailed information.
For subsequent processing, the detailed information is processed, for example, by vectorization as in the case of the first marker, to obtain the second marker.
A processing module 150 configured to obtain a solution probability based on the first label and the second label;
the solution probability is the probability of solving the problem of the user by the intelligent voice response, and when the probability is lower, the artificial customer service can be directly accessed to ensure the user experience.
The processing module 150 further includes:
a first processing unit 151 configured to process the first label based on a first model to obtain a first probability value.
The first model may be a classifier or a machine learning model, with which the first token is converted into a first probability value. In some embodiments, in addition to the aforementioned labeling of unimportant questions, individual more serious questions may be labeled, such as a large amount of money or a user older, increasing the probability of accessing human customer service.
A second processing unit 153, configured to process the second label based on a second model to obtain a second probability value;
the second model may be the same as the first model. In some embodiments, the second model is an RNN (Recurrent Neural Network) model. The model may be trained using the traffic type history data.
A probability output unit 155, configured to obtain the solution probability based on the first probability value and the second probability value.
The solution probability represents the composite influence of the first probability value and the second probability value, and in some embodiments, may be a product of the first probability value and the second probability value, and may also be weighted according to experience and model conditions, which is not limited herein.
The access module 160 is configured to access an intelligent voice response system matched with the service type to which the call belongs when the solution probability is greater than a preset value; and when the solving probability is smaller than the preset value, accessing a manual response system.
The preset value can be designed to be 60%, and when the solution probability is lower than 60%, the call is directly accessed to the manual customer service.
In some embodiments, the threshold may be adjusted according to the idle condition of the manual customer service, for example, if there is idle in the manual customer service, the threshold may be adjusted to 90%; and when the number of people in line in the manual customer service is more than 3 people or the predicted waiting time is more than 10 minutes, the threshold value can be adjusted to be 50%.
In some embodiments, the intelligent voice response system is based on a BERT model and is trained by call history data of the service type to which the call belongs.
The present application also provides an intelligent voice access method, wherein one or more steps can be executed by the intelligent voice access system 100, which includes:
s1, acquiring background information of the initiator of the call;
s2, obtaining a first mark based on the background information;
s3, acquiring the detailed information of the call; the detailed information at least comprises the service type of the call;
s4, obtaining a second mark based on the detailed information;
s5, obtaining a solution probability based on the first mark and the second mark;
s6, when the solution probability is larger than the preset value, accessing an intelligent voice response system matched with the service type of the call; and when the solving probability is smaller than the preset value, accessing a manual response system.
The intelligent voice access system is high in intelligent degree, intelligent voice response or artificial customer service is provided according to the user condition pertinence, and the access proportion can be properly adjusted according to the pressure of the artificial customer service.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present description may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of this description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present description may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
Claims (9)
1. An intelligent voice access method, comprising:
acquiring background information of an initiator of a call;
obtaining a first mark based on the background information;
acquiring detailed information of the call; the detailed information at least comprises the service type of the call;
obtaining a second label based on the detailed information;
obtaining a solution probability based on the first label and the second label;
when the solving probability is larger than a preset value, accessing an intelligent voice response system matched with the service type of the call; and when the solving probability is smaller than the preset value, accessing a manual response system.
2. The method of claim 1, wherein:
the intelligent voice response system is based on a BERT model and is obtained through training of call history data of the service type of the call.
3. The method of claim 1, deriving a solution probability based on the first label and the second label, wherein:
processing the first marker based on a first model to obtain a first probability value;
processing the second marker based on a second model to obtain a second probability value;
deriving the solution probability based on the first probability value and the second probability value.
4. The method of claim 3, wherein:
the second model is an RNN model.
5. An intelligent voice access system, comprising:
the first acquisition module is used for acquiring background information of an initiator of the call;
the first marking module is used for obtaining a first mark based on the background information;
the second acquisition module is used for acquiring detailed information of the call; the detailed information at least comprises the service type of the call;
the second marking module is used for obtaining a second mark based on the detailed information;
a processing module for deriving a solution probability based on the first label and the second label;
the access module is used for accessing an intelligent voice response system matched with the service type of the call when the solution probability is greater than a preset value; and when the solving probability is smaller than the preset value, accessing a manual response system.
6. The system of claim 5, wherein:
the intelligent voice response system is based on a BERT model and is obtained through training of call history data of the service type of the call.
7. The system of claim 5, the processing module comprising:
a first processing unit, configured to process the first marker based on a first model to obtain a first probability value;
the second processing unit is used for processing the second mark based on a second model to obtain a second probability value;
a probability output unit, configured to obtain the solution probability based on the first probability value and the second probability value.
8. The system of claim 7, wherein:
the second model is an RNN model.
9. An intelligent voice access apparatus, comprising a processor and a storage medium storing computer instructions, the processor being configured to execute at least a portion of the computer instructions to implement the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010630058.XA CN111770235A (en) | 2020-07-03 | 2020-07-03 | Intelligent voice access method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010630058.XA CN111770235A (en) | 2020-07-03 | 2020-07-03 | Intelligent voice access method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111770235A true CN111770235A (en) | 2020-10-13 |
Family
ID=72723497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010630058.XA Pending CN111770235A (en) | 2020-07-03 | 2020-07-03 | Intelligent voice access method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111770235A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60220652A (en) * | 1984-04-18 | 1985-11-05 | Nec Corp | Speech synthesizing system of exchange |
| US8755777B2 (en) * | 2000-12-19 | 2014-06-17 | At&T Intellectual Property I, L.P. | Identity blocking service from a wireless service provider |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
| CN108268555A (en) * | 2017-01-03 | 2018-07-10 | 中国移动通信有限公司研究院 | A kind of information processing method and device |
| CN110602333A (en) * | 2019-08-23 | 2019-12-20 | 绍兴文理学院 | Call center response system and method based on deep learning |
-
2020
- 2020-07-03 CN CN202010630058.XA patent/CN111770235A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60220652A (en) * | 1984-04-18 | 1985-11-05 | Nec Corp | Speech synthesizing system of exchange |
| US8755777B2 (en) * | 2000-12-19 | 2014-06-17 | At&T Intellectual Property I, L.P. | Identity blocking service from a wireless service provider |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
| CN108268555A (en) * | 2017-01-03 | 2018-07-10 | 中国移动通信有限公司研究院 | A kind of information processing method and device |
| CN110602333A (en) * | 2019-08-23 | 2019-12-20 | 绍兴文理学院 | Call center response system and method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109587360B (en) | Electronic device, method for coping with tactical recommendation, and computer-readable storage medium | |
| CN108509477B (en) | Method for recognizing semantics, electronic device and computer readable storage medium | |
| AU2018233014A1 (en) | Call center system having reduced communication latency | |
| WO2019080414A1 (en) | Customer label management method and system, computer device and storage medium | |
| CN111028007B (en) | User portrait information prompting method, device and system | |
| CN114120516B (en) | Method for optimizing business hall number calling sequence | |
| CN113627566A (en) | Early warning method and device for phishing and computer equipment | |
| US20230252486A1 (en) | Systems and methods for detecting complaint interactions | |
| CN111061948B (en) | User tag recommendation method and device, computer equipment and storage medium | |
| CN113239204A (en) | Text classification method and device, electronic equipment and computer-readable storage medium | |
| CN112330055A (en) | User complaint prediction method and device | |
| CN113434670A (en) | Method and device for generating dialogistic text, computer equipment and storage medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN115034886A (en) | Default risk prediction method and device | |
| CN116956896A (en) | Text analysis method, system, electronic equipment and medium based on artificial intelligence | |
| CN113438374B (en) | Intelligent outbound call processing method, device, equipment and storage medium | |
| CN112489628B (en) | Voice data selection method and device, electronic equipment and storage medium | |
| CN111770235A (en) | Intelligent voice access method and system | |
| CN110782119A (en) | Insurance agent selection method, device and equipment based on artificial intelligence | |
| CN112671984B (en) | Service mode switching method and device, robot customer service and storage medium | |
| CN112466337A (en) | Audio data emotion detection method and device, electronic equipment and storage medium | |
| WO2021073258A1 (en) | Task follow-up method, apparatus and device based on emotion analysis, and storage medium | |
| CN114969295A (en) | Dialog interaction data processing method, device and equipment based on artificial intelligence | |
| CN112367494A (en) | AI-based online conference communication method and device and computer equipment | |
| WO2023272833A1 (en) | Data detection method, apparatus and device and readable storage medium |
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: 20201013 |