CN113364920A - Incoming line request processing method and device and electronic equipment - Google Patents
Incoming line request processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN113364920A CN113364920A CN202110643784.XA CN202110643784A CN113364920A CN 113364920 A CN113364920 A CN 113364920A CN 202110643784 A CN202110643784 A CN 202110643784A CN 113364920 A CN113364920 A CN 113364920A
- Authority
- CN
- China
- Prior art keywords
- pronunciation
- incoming line
- navigation function
- line request
- user
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims description 16
- 238000000034 method Methods 0.000 claims abstract description 88
- 230000008569 process Effects 0.000 claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 48
- 230000006870 function Effects 0.000 claims description 118
- 230000008859 change Effects 0.000 claims description 36
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 abstract description 11
- 238000004891 communication Methods 0.000 description 3
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
-
- 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
- G10L25/60—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 measuring the quality of voice signals
-
- 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
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a method and a device for processing an incoming line request and electronic equipment, wherein under the condition of detecting the incoming line request, identity information of a target user generating the incoming line request is obtained, a pronunciation standard degree value corresponding to the identity information is determined, and under the condition of determining that the pronunciation standard degree value is smaller than a first preset threshold value, the user has poor pronunciation standard degree, an IVR key navigation function is called to process the incoming line request, the user can determine a service only by pressing a key without voice interaction, so that the problem that the service which needs to be processed cannot be determined due to nonstandard pronunciation can be solved, the service processing efficiency is low, and the user can be ensured to normally process the service.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to an incoming line request processing method and apparatus, and an electronic device.
Background
With the continuous development of voice communication services, the application of the intelligent voice navigation function is more and more extensive. After the user inputs voice, the intelligent voice navigation function identifies the voice, and positions a service node required to be handled by the user according to the identified voice, so that the user handles the service.
At present, after a telephone is accessed, an intelligent voice navigation function is preferentially used, and if the accuracy of voice recognition input by a user by the intelligent voice navigation function is low, a service node cannot be accurately positioned, so that the service handling efficiency is low.
Disclosure of Invention
In view of the above, the present invention provides an incoming line request processing method, an incoming line request processing device, and an electronic device, so as to solve the problem that if the accuracy of voice recognition input by a user by an intelligent voice navigation function is low, a service node cannot be accurately located, and the service handling efficiency is low.
In order to solve the technical problems, the invention adopts the following technical scheme:
an incoming request processing method, comprising:
under the condition that an incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and in the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for the continuous preset times is determined, calling an IVR key navigation function to continuously process the incoming line request.
Optionally, invoking an intelligent voice navigation function to process the incoming line request, including:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
Optionally, the generating of the pronunciation criterion degree value includes:
acquiring a plurality of pronunciation data of the target user when handling historical services;
determining a pronunciation label corresponding to each pronunciation data, and acquiring a grade value corresponding to each pronunciation label;
and calculating the sum of all grade values, and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
Optionally, calculating the sum of all rank values comprises:
determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data;
in the case where the change is not a change from the pronunciation basic standard label or the pronunciation non-standard label to the pronunciation standard label, the sum of all the rank values is calculated.
Optionally, in the case that the change condition is a change from a basic standard tag for pronunciation or a nonstandard tag for pronunciation to a standard tag for pronunciation, the method further includes:
determining the pronunciation standard degree value as a specified pronunciation standard degree value; the specified pronunciation standard degree value is larger than the second preset threshold value.
Optionally, after determining that the target service required to be transacted by the target user is successfully transacted, the method further includes:
and acquiring a voice tag corresponding to the target service, and outputting the target voice comprising the voice tag by voice.
An incoming request processing apparatus, comprising:
the system comprises a pronunciation information determining module, a pronunciation standard degree determining module and a pronunciation analyzing module, wherein the pronunciation information determining module is used for acquiring identity information of a target user generating an incoming line request under the condition of detecting the incoming line request and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
the first request processing module is used for calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and the second request processing module is used for calling an intelligent voice navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be not less than the first preset threshold value but less than the second preset threshold value, and calling an IVR key navigation function to continuously process the incoming line request under the condition that the intelligent voice navigation function cannot recognize the voice input by the target user in the incoming line request for the continuous preset times in the intelligent voice navigation function processing process.
Optionally, the second request processing module is configured to, when invoking an intelligent voice navigation function to process the incoming line request, specifically configured to:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
Optionally, the method further comprises:
a pronunciation data determination module; the pronunciation data determination module comprises:
the data acquisition submodule is used for acquiring a plurality of pronunciation data of the target user when handling historical services;
the grade value determining submodule is used for determining the pronunciation label corresponding to each pronunciation data and acquiring the grade value corresponding to each pronunciation label;
and the pronunciation data determining submodule is used for calculating the sum of all grade values and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that an incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and in the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for the continuous preset times is determined, calling an IVR key navigation function to continuously process the incoming line request.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method and a device for processing an incoming line request and electronic equipment, wherein under the condition of detecting the incoming line request, identity information of a target user generating the incoming line request is obtained, a pronunciation standard degree value corresponding to the identity information is determined, and under the condition of determining that the pronunciation standard degree value is smaller than a first preset threshold value, the user has poor pronunciation standard degree, an IVR key navigation function is called to process the incoming line request, the user can determine a service only by pressing a key without voice interaction, so that the problem that the service which needs to be processed cannot be determined due to nonstandard pronunciation can be solved, the service processing efficiency is low, and the user can be ensured to normally process the service. When the pronunciation standard degree value is determined to be not smaller than a first preset threshold value but smaller than a second preset threshold value, the pronunciation standard degree of a user is general, an intelligent voice navigation function can be called to process the incoming line request, when the intelligent voice navigation function is called to process the incoming line request, when the fact that the voice input by the target user cannot be recognized by the intelligent voice navigation function for continuous preset times is determined, the fact that the intelligent voice navigation function cannot recognize the service which the user wants to handle through voice interaction is indicated, the IVR key navigation function is called to continue processing the incoming line request, and normal handling of the service of the user is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for processing an incoming request according to an embodiment of the present invention;
fig. 2 is a flowchart of another incoming request processing method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an incoming request processing apparatus according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
At present, telephone business is continuously developed, intelligent voice navigation gradually becomes mainstream, and telephone access modes such as common telephone banking services, 10086 services, 10000 services and the like are set in many industries.
Some service terminals, such as servers, cancel the IVR key navigation, directly use the intelligent voice navigation to realize one-language direct service node, and directly use the intelligent voice navigation when a customer enters a telephone bank. After the user calls in, if the user has an abnormal pronunciation, a serious accent, and a mixed match (such as chinese, english, yue pu, etc.), the voice output by the user cannot be recognized by the service terminal, so that the service terminal cannot determine the service node based on the received voice, and cannot process the service in time. Moreover, the conversation time of the user is increased, so that the waiting time of the client is increased, the client is not good in use, and the experience of the client is influenced. In addition, the cost is also increased.
In order to solve the above technical problem, the inventor has found through research that if the pronunciation standard condition of the user of the incoming call is judged when the call is incoming, and the IVR key navigation is directly used under the condition that the pronunciation is not standard, the problem that the service handled by the user cannot be determined due to the use of intelligent voice navigation can be further avoided.
The method comprises the steps of acquiring identity information of a target user generating an incoming line request under the condition that the incoming line request is detected, determining a pronunciation standard degree value corresponding to the identity information, and indicating that the pronunciation standard degree of the user is poor under the condition that the pronunciation standard degree value is smaller than a first preset threshold value, calling an IVR key navigation function to process the incoming line request, wherein the user can determine a service only by pressing a key without voice interaction, so that the problem that the service processing efficiency is low because the service cannot be determined due to the fact that the pronunciation is not standard can be solved, and the user can be guaranteed to normally process the service. When the pronunciation standard degree value is determined to be not smaller than a first preset threshold value but smaller than a second preset threshold value, the pronunciation standard degree of a user is general, an intelligent voice navigation function can be called to process the incoming line request, when the intelligent voice navigation function is called to process the incoming line request, when the fact that the voice input by the target user cannot be recognized by the intelligent voice navigation function for continuous preset times is determined, the fact that the intelligent voice navigation function cannot recognize the service which the user wants to handle through voice interaction is indicated, the IVR key navigation function is called to continue processing the incoming line request, and normal handling of the service of the user is guaranteed.
On the basis of the above, another embodiment of the present invention provides an incoming line request processing method, which is applied to a service terminal, such as a server. Referring to fig. 1, an incoming line request processing method may include:
s11, under the condition that the incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information.
In practical application, a user can call in by dialing a telephone through a terminal, such as a mobile phone, specifically, the user can call in service numbers, 10086, 10000 and the like of a telephone bank. After the incoming call, the service terminal will detect the incoming line request, and in this embodiment, the whole service process for the user is referred to as a process for processing the incoming line request.
The identity information of the target user generating the incoming line request is obtained, specifically, the corresponding relation between the terminal and the identity information of the user can be preset, when the incoming line request exists, the terminal number of the incoming line terminal is obtained, and the corresponding relation between the terminal and the user is inquired, so that the identity information of the user can be obtained.
In addition, when a user dials a call, the user telephone number can be used, the corresponding relation between the telephone number and the identity information of the user is established in advance, when an incoming line request exists, the incoming line telephone number is determined, the corresponding relation between the telephone number and the identity information of the user is inquired, and the identity information of the user can be obtained.
In practical applications, the identity information of the user may be name, age, gender, user rating, and the like.
After the identity information of the user is determined, the pronunciation standard degree value corresponding to the identity information is inquired.
The pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical services, and in this embodiment, a pronunciation standard degree value of each user who has historically dialed a call may be predetermined.
The pronunciation criterion degree value in this embodiment may be a numerical value between 0 and 1, such as 0.5, 0.6, 0.8, 0.9, etc. The larger the value, the more standard the pronunciation of the user is.
S12, determining whether the pronunciation standard degree value is smaller than a first preset threshold value; if yes, go to step S13; if not, step S14 is executed.
In practical application, the first preset threshold may be 0.6, and if the pronunciation standard degree value is less than 0.6, it indicates that the pronunciation of the user is not standard, and at this time, the intelligent voice navigation is skipped, and the IVR key navigation is directly used.
If the pronunciation standard degree value is not less than 0.6, the basic standard or standard of the pronunciation of the user is stated, and at the moment, intelligent voice navigation is not skipped, and the incoming line request is processed by using the intelligent voice navigation.
And S13, calling an IVR key navigation function to process the incoming line request.
In this embodiment, some services are set with corresponding numerical identifiers in the IVR key navigation function, and are output in voice.
Such as credit card service, please press 1, bill inquiry, please press 2, etc.
S14, determining whether the pronunciation standard degree value is smaller than a second preset threshold value; if yes, go to step S15.
The second preset threshold may be 0.8, and if the pronunciation standard degree value is not less than the first preset threshold but less than the second preset threshold, that is, the pronunciation standard degree value is greater than or equal to 0.6 and less than 0.8.
And under the condition that the pronunciation standard degree value is more than or equal to 0.6 and less than 0.8, the pronunciation basic standard of the user is described, at the moment, the incoming line request can be tried to be processed by using the intelligent voice navigation function, and if the intelligent voice navigation function cannot identify the voice input by the user, the IVR key is used for navigation.
In this embodiment, the intelligent voice navigation function cannot recognize the voice input by the user, and may be that the intelligent voice navigation function cannot accurately recognize the service that the user wants to handle.
If the intelligent voice navigation function receives the voice input by the user, the intelligent voice navigation function replies to the user whether the user wants to transact the business, if yes, the user presses 1, if not, the user presses 2, and the voice explains the business that the user wants to transact.
If the user presses 2, it means that the intelligent voice navigation function cannot accurately identify the service that the user wants to handle, and at this time, the user needs to repeatedly speak the service that the user wants to handle.
In addition, after receiving the voice input by the user, the intelligent voice navigation function replies to the user, cannot recognize the voice, please speak the service that the user wants to handle again, and at this time, it is also considered that the intelligent voice navigation function cannot accurately recognize the service that the user wants to handle.
S15, calling an intelligent voice navigation function to process the incoming line request, and calling an IVR key navigation function to continue processing the incoming line request when determining that the voice input by the target user in the incoming line request cannot be recognized by the intelligent voice navigation function for a preset number of continuous times in the intelligent voice navigation function processing process.
Specifically, the intelligent voice navigation function in this embodiment may be a conventional intelligent voice navigation function, and at this time, the user is required to input voice, and the intelligent voice navigation function recognizes the voice input by the user and performs subsequent operations.
In addition, in order to improve the user experience, the intelligent voice navigation function is also improved, the service which the user wants to handle at this time can be presumed based on the historical service of the user, the digital identifier corresponding to the service is set, the digital identifier and the service name of the voice output service are set, the voice recognition accuracy of the number is higher than that of the character, if the service which the user wants to handle exists in the service predicted by the server, the user can directly say the numerical identifier when the user feels uncomfortable in own voice and considers that the pronunciation is not standard or is convenient, and the accurate recognition of the server is facilitated. In addition, the user may also speak the name of the service that the user wants to select.
Specifically, an intelligent voice navigation function is called, so that the intelligent voice navigation function obtains services handled by the target user, the services are sequenced according to the time sequence of service handling, a sequence number corresponding to each service ranked before a preset number is sequentially set, and the sequence number and the service corresponding to the sequence number are output in a voice mode.
When the server predicts the business, the historical transacted business of the user is referred to, specifically, for the user (the user with different phone numbers is identified), the summary is performed according to the historical service of the user in each channel, wherein each channel can be a counter, a telephone bank, an online bank, and the like. Acquiring the latest three times of business handled by the user, setting serial numbers for the business according to the time sequence of the handled business, wherein the business serial numbers of the business are closer to each other after the time is later, the intelligent voice navigation function acquires the incoming telephone number after the client enters the line, inquires the user corresponding to the telephone number, inquires the latest three times of historical business handled by the user and the serial number of the historical business, and outputs the historical business in a voice mode. Such as:
the client enters a line and broadcasts the content 'respectful client, you are good and please say your questions, such as {1. investment financing consultation, 2. card recovery, 3. overseas transfer remittance'. You can output the serial number of the service or can directly speak out the number.
The method for presetting the business which the client wants to handle can improve the efficiency of finding the business which the user wants to handle, can improve the convenience of the user speaking the business which the user wants to handle by setting the number sequence of the business, and avoids the problem that the server cannot identify the business which the user wants to handle due to inaccurate pronunciation under the condition that the pronunciation of the user is basically standard.
However, in this way, if the service of the user history consultation is not successfully processed, the user may continue to inquire the consulted service, but if the user wants to consult a new service, the service that the user wants to handle cannot be accurately identified based on the data of the user history consultation, at this time, the user is required to speak the service that the user wants to handle by voice, and therefore, the server cannot correctly identify the voice and cannot accurately locate the service node that the user wants to handle due to poor pronunciation standard degree of the user.
In the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for continuous preset times (such as 3 times) is determined, the incoming line request is continuously processed by calling an IVR key navigation function.
For the specific explanation process of the voice input by the target user in the incoming line request, please refer to the above corresponding description.
In another implementation manner of the present invention, under the condition that it is determined that the pronunciation standard degree value is not less than the second preset threshold, the incoming line request may be processed directly by using an intelligent voice navigation function, and the intelligent voice navigation function in this embodiment may be conventional intelligent voice navigation, or may be a manner of predicting a service that the user wants to handle based on the service handled historically.
Whether the incoming line request is processed by adopting the intelligent voice navigation function or the incoming line request is processed by calling the IVR key navigation function, if the incoming line request is successfully processed, the target service required to be processed by the target user is considered to be successfully processed. At this time, in order that the subsequent user can accurately describe the service, a voice tag capable of locating the service may be provided for the user, for example, the service is a credit card service, and the service may be located by means of a preset voice tag such as credit card transaction, credit card application, and the like.
Specifically, after it is determined that the target service required to be transacted by the target user is successfully transacted, the method further includes:
and acquiring a voice tag corresponding to the target service, and outputting the target voice comprising the voice tag by voice.
Such as: before hanging up, according to ivr service nodes switched in by customers, recommending users to use a voice navigation function, if incoming lines are next time, you can directly say 'XXXX', then a seat finishes the current telephone traffic, submits a pronunciation label, and finishes the current communication.
In the embodiment, under the condition that the incoming line request is detected, the identity information of a target user generating the incoming line request is obtained, the pronunciation standard degree value corresponding to the identity information is determined, under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value, the pronunciation standard degree of the user is relatively poor, an IVR key navigation function is called to process the incoming line request, the user can determine the service only by pressing a key without voice interaction, further, the problem that the service to be processed cannot be determined due to the fact that the pronunciation is not standard can be solved, the service processing efficiency is low is solved, and the user can normally process the service. When the pronunciation standard degree value is determined to be not smaller than a first preset threshold value but smaller than a second preset threshold value, the pronunciation standard degree of a user is general, an intelligent voice navigation function can be called to process the incoming line request, when the intelligent voice navigation function is called to process the incoming line request, when the fact that the voice input by the target user cannot be recognized by the intelligent voice navigation function for continuous preset times is determined, the fact that the intelligent voice navigation function cannot recognize the service which the user wants to handle through voice interaction is indicated, the IVR key navigation function is called to continue processing the incoming line request, and normal handling of the service of the user is guaranteed.
In another implementation of the present invention, a "generation process of pronunciation criterion degree value" is provided, and with reference to fig. 2, the method may include:
and S21, acquiring a plurality of pronunciation data of the target user when handling historical services.
Specifically, the user may use the voice conversation content of the user in each channel, such as various channels that may have voice conversation with the user, such as a counter, a mobile phone bank, a telephone bank, and a micro-bank, when transacting business, the voice conversation content of each transaction may be used as one pronunciation data, and when there are many businesses transacted by the user, a plurality of pronunciation data may be correspondingly obtained. And binding the acquired pronunciation data with the user, specifically binding the acquired pronunciation data with a telephone number used by the user.
And S22, determining the pronunciation label corresponding to each pronunciation data, and acquiring the grade value corresponding to each pronunciation label.
After the pronunciation data is acquired, the pronunciation data is calibrated, and the calibrated pronunciation label can be a pronunciation standard label, a pronunciation basic standard label or a pronunciation nonstandard label. Each pronunciation label has a corresponding grade value (also called score), for example, the grade values (also called score) corresponding to the pronunciation standard label, the pronunciation basic standard label and the pronunciation non-standard label are 2, 1 and 0 respectively.
During calibration, calibration can be performed by a manual calibration method, for example, manually determining the standard degree of the pronunciation data according to experience, and marking a corresponding label.
In addition, the pronunciation data can be calibrated automatically, specifically, the tags can be determined according to the character recognition rate of the pronunciation data, for example, the character recognition rate is greater than 80%, the corresponding tags are pronunciation standard tags, when the character recognition rate is between 60% and 80%, the corresponding tags are pronunciation basic standard tags, the character recognition rate is lower than 60%, and the corresponding tags are pronunciation nonstandard tags.
After the pronunciation label of each pronunciation data is determined, the corresponding grade value of each pronunciation label is obtained.
And S23, determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data.
In practical applications, the pronunciation tags are all pronunciation standard tags, all pronunciation basic standard tags, all pronunciation non-standard tags, change from pronunciation basic standard tags to pronunciation standard tags, change from pronunciation non-standard tags to pronunciation standard tags, and the like.
In this embodiment, the pronunciation of the user may not be changed, for example, the pronunciation is always within a certain standard degree, and the pronunciation of the user may also be changed, for example, the pronunciation becomes more and more standard, and generally, it is difficult to return to the situation that the pronunciation is not standard after the pronunciation standard, so in this embodiment, in order to avoid the problem of resource waste caused by acquiring the pronunciation data when the user transacts business and processing the pronunciation data for many times under the situation that the pronunciation standard of the user is used. In this embodiment, when the change is to change the pronunciation standard tag from the basic standard tag or the nonstandard tag to the pronunciation standard tag, or to continue to be the pronunciation standard tag, the pronunciation standard degree value of the user is not repeatedly determined.
S24, judging whether the change condition is that the pronunciation basic standard label or the pronunciation nonstandard label is changed into the pronunciation standard label; if not, go to step S25; if yes, go to step S27.
And S25, calculating the sum of all grade values.
And in the case that the change condition is not to change the pronunciation basic standard label or the pronunciation nonstandard label into the pronunciation standard label or to continue to be the pronunciation standard label, the method indicates that the user pronounces the basic standard or the pronunciation nonstandard and does not trend to pronounce more and more standard. At this time, a pronunciation criterion degree value of the user needs to be determined.
At this time, the sum of all the gradation values is calculated.
And S26, determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
Specifically, assuming that there are 5 pronunciation data in total, and the respective rank values are 1, 0, and 0, the pronunciation criterion degree value is (1+0+0+ 0)/5-0.2.
It should be noted that, in the present embodiment, the process of determining the pronunciation standard degree value needs to be determined once every predetermined time, so as to ensure the accuracy of the pronunciation standard degree value.
And S27, determining the pronunciation standard degree value as the designated pronunciation standard degree value.
Wherein, in the case that the change condition is to change from the basic standard label or the nonstandard label of pronunciation to the standard label of pronunciation, or to continue to be the standard label of pronunciation, the specified pronunciation standard degree value is larger than the second preset threshold value. The user pronunciation criteria are interpreted.
In the case where it is determined that the change is a change from the basic standard tag or the nonstandard tag of pronunciation to the standard tag of pronunciation, or a continuation of the standard tag of pronunciation, the pronunciation standard degree value may not be determined any more subsequently.
It should be noted that, in this embodiment, the process of determining the pronunciation standard degree value may be executed in the server, and in addition, may also be executed in other devices, and the server may directly obtain the pronunciation standard degree value, so that the processing amount of the server may be reduced, and the processing efficiency of the server is ensured.
In summary, the process of generating the pronunciation criterion degree value includes the following steps:
the generation process of the pronunciation standard degree value comprises the following steps: acquiring a plurality of pronunciation data of the target user when handling historical services;
determining a pronunciation label corresponding to each pronunciation data, and acquiring a grade value corresponding to each pronunciation label;
and calculating the sum of all grade values, and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
Wherein, calculating the sum of all grade values comprises:
determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data;
in the case where the change is not a change from the pronunciation basic standard label or the pronunciation non-standard label to the pronunciation standard label, the sum of all the rank values is calculated.
In addition, when the change condition is a change from a basic standard pronunciation tag or a nonstandard pronunciation tag to a standard pronunciation tag, the method further includes:
determining the pronunciation standard degree value as a specified pronunciation standard degree value; the specified pronunciation standard degree value is larger than the second preset threshold value.
It should be noted that, in addition to the above-mentioned implementation, other schemes for generating the pronunciation criterion degree value are also within the scope of the present invention.
In the embodiment, a generation process of the pronunciation standard degree value is provided, so that the pronunciation standard degree value can be generated according to the generation process in the embodiment, and incoming line access control is performed based on the pronunciation standard degree value.
Optionally, on the basis of the embodiment of the incoming request processing method, another embodiment of the present invention provides an incoming request processing apparatus, and with reference to fig. 3, the incoming request processing apparatus may include:
the system comprises a pronunciation information determining module 11, a pronunciation standard degree determining module and a pronunciation analyzing module, wherein the pronunciation information determining module is used for acquiring identity information of a target user generating an incoming line request under the condition that the incoming line request is detected, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
the first request processing module 12 is configured to, when it is determined that the pronunciation standard degree value is smaller than a first preset threshold, invoke an IVR key navigation function to process the incoming line request;
and the second request processing module 13 is configured to, when it is determined that the pronunciation standard degree value is not smaller than the first preset threshold but smaller than the second preset threshold, call an intelligent voice navigation function to process the incoming line request, and in the processing process of the intelligent voice navigation function, call an IVR key navigation function to continue processing the incoming line request when it is determined that the voice input by the target user cannot be recognized by the intelligent voice navigation function for the preset number of times.
Further, when the second request processing module is used for calling an intelligent voice navigation function to process the incoming line request, the second request processing module is specifically used for:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
Further, still include:
a pronunciation data determination module; the pronunciation data determination module comprises:
the data acquisition submodule is used for acquiring a plurality of pronunciation data of the target user when handling historical services;
the grade value determining submodule is used for determining the pronunciation label corresponding to each pronunciation data and acquiring the grade value corresponding to each pronunciation label;
and the pronunciation data determining submodule is used for calculating the sum of all grade values and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
Further, when the pronunciation data determination submodule is used for calculating the sum of all the rank values, the pronunciation data determination submodule is specifically used for:
determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data;
in the case where the change is not a change from the pronunciation basic standard label or the pronunciation non-standard label to the pronunciation standard label, the sum of all the rank values is calculated.
Further, the pronunciation data determination submodule is further configured to:
determining the pronunciation standard degree value as a specified pronunciation standard degree value under the condition that the change condition is that the pronunciation basic standard label or the pronunciation non-standard label is changed into the pronunciation standard label; the specified pronunciation standard degree value is larger than the second preset threshold value.
Further, still include:
and the voice tag output module is used for acquiring a voice tag corresponding to the target service after determining that the target service required to be transacted by the target user is successfully transacted, and outputting the target voice including the voice tag in a voice mode.
In the embodiment, under the condition that the incoming line request is detected, the identity information of a target user generating the incoming line request is obtained, the pronunciation standard degree value corresponding to the identity information is determined, under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value, the pronunciation standard degree of the user is relatively poor, an IVR key navigation function is called to process the incoming line request, the user can determine the service only by pressing a key without voice interaction, further, the problem that the service to be processed cannot be determined due to the fact that the pronunciation is not standard can be solved, the service processing efficiency is low is solved, and the user can normally process the service. When the pronunciation standard degree value is determined to be not smaller than a first preset threshold value but smaller than a second preset threshold value, the pronunciation standard degree of a user is general, an intelligent voice navigation function can be called to process the incoming line request, when the intelligent voice navigation function is called to process the incoming line request, when the fact that the voice input by the target user cannot be recognized by the intelligent voice navigation function for continuous preset times is determined, the fact that the intelligent voice navigation function cannot recognize the service which the user wants to handle through voice interaction is indicated, the IVR key navigation function is called to continue processing the incoming line request, and normal handling of the service of the user is guaranteed.
It should be noted that, for the working processes of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the embodiments of the incoming line request processing method and apparatus, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that an incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and in the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for the continuous preset times is determined, calling an IVR key navigation function to continuously process the incoming line request.
Further, calling an intelligent voice navigation function to process the incoming line request, comprising:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
Further, the generating process of the pronunciation standard degree value comprises the following steps:
acquiring a plurality of pronunciation data of the target user when handling historical services;
determining a pronunciation label corresponding to each pronunciation data, and acquiring a grade value corresponding to each pronunciation label;
and calculating the sum of all grade values, and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
Further, calculating the sum of all the rank values, including:
determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data;
in the case where the change is not a change from the pronunciation basic standard label or the pronunciation non-standard label to the pronunciation standard label, the sum of all the rank values is calculated.
Further, in the case that the change condition is a change from a basic standard pronunciation tag or a nonstandard pronunciation tag to a standard pronunciation tag, the method further comprises the following steps:
determining the pronunciation standard degree value as a specified pronunciation standard degree value; the specified pronunciation standard degree value is larger than the second preset threshold value.
Further, after determining that the target service required to be transacted by the target user is successfully transacted, the method further includes:
and acquiring a voice tag corresponding to the target service, and outputting the target voice comprising the voice tag by voice.
In the embodiment, under the condition that the incoming line request is detected, the identity information of a target user generating the incoming line request is obtained, the pronunciation standard degree value corresponding to the identity information is determined, under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value, the pronunciation standard degree of the user is relatively poor, an IVR key navigation function is called to process the incoming line request, the user can determine the service only by pressing a key without voice interaction, further, the problem that the service to be processed cannot be determined due to the fact that the pronunciation is not standard can be solved, the service processing efficiency is low is solved, and the user can normally process the service. When the pronunciation standard degree value is determined to be not smaller than a first preset threshold value but smaller than a second preset threshold value, the pronunciation standard degree of a user is general, an intelligent voice navigation function can be called to process the incoming line request, when the intelligent voice navigation function is called to process the incoming line request, when the fact that the voice input by the target user cannot be recognized by the intelligent voice navigation function for continuous preset times is determined, the fact that the intelligent voice navigation function cannot recognize the service which the user wants to handle through voice interaction is indicated, the IVR key navigation function is called to continue processing the incoming line request, and normal handling of the service of the user is guaranteed.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An incoming request processing method, comprising:
under the condition that an incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and in the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for the continuous preset times is determined, calling an IVR key navigation function to continuously process the incoming line request.
2. The incoming line request processing method of claim 1, wherein invoking an intelligent voice navigation function to process the incoming line request comprises:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
3. The incoming line request processing method as claimed in claim 1, wherein the generating process of the pronunciation criterion degree value comprises:
acquiring a plurality of pronunciation data of the target user when handling historical services;
determining a pronunciation label corresponding to each pronunciation data, and acquiring a grade value corresponding to each pronunciation label;
and calculating the sum of all grade values, and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
4. The incoming request processing method of claim 3, wherein calculating the sum of all rank values comprises:
determining the change condition of the pronunciation label corresponding to the pronunciation data according to the sequence of the acquired pronunciation data;
in the case where the change is not a change from the pronunciation basic standard label or the pronunciation non-standard label to the pronunciation standard label, the sum of all the rank values is calculated.
5. The incoming line request processing method as claimed in claim 4, wherein in case that the change condition is a change from a basic standard tag of pronunciation or a nonstandard tag of pronunciation to a standard tag of pronunciation, further comprising:
determining the pronunciation standard degree value as a specified pronunciation standard degree value; the specified pronunciation standard degree value is larger than the second preset threshold value.
6. The incoming line request processing method of claim 1, wherein after determining that the target service required to be transacted by the target user is successfully transacted, the method further comprises:
and acquiring a voice tag corresponding to the target service, and outputting the target voice comprising the voice tag by voice.
7. An incoming request processing apparatus, comprising:
the system comprises a pronunciation information determining module, a pronunciation standard degree determining module and a pronunciation analyzing module, wherein the pronunciation information determining module is used for acquiring identity information of a target user generating an incoming line request under the condition of detecting the incoming line request and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
the first request processing module is used for calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and the second request processing module is used for calling an intelligent voice navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be not less than the first preset threshold value but less than the second preset threshold value, and calling an IVR key navigation function to continuously process the incoming line request under the condition that the intelligent voice navigation function cannot recognize the voice input by the target user in the incoming line request for the continuous preset times in the intelligent voice navigation function processing process.
8. The incoming line request processing apparatus of claim 7, wherein the second request processing module is configured to, when invoking an intelligent voice navigation function to process the incoming line request, specifically:
calling an intelligent voice navigation function so that the intelligent voice navigation function acquires the services transacted by the target user, sequencing the services according to the time sequence of service transaction, sequentially setting a sequence number corresponding to each service ranked before a preset number, and outputting the sequence number and the services corresponding to the sequence number in a voice mode.
9. The incoming request processing apparatus of claim 7, further comprising:
a pronunciation data determination module; the pronunciation data determination module comprises:
the data acquisition submodule is used for acquiring a plurality of pronunciation data of the target user when handling historical services;
the grade value determining submodule is used for determining the pronunciation label corresponding to each pronunciation data and acquiring the grade value corresponding to each pronunciation label;
and the pronunciation data determining submodule is used for calculating the sum of all grade values and determining the ratio of the sum of the grade values to the number of the pronunciation data as a pronunciation standard degree value.
10. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that an incoming line request is detected, acquiring identity information of a target user generating the incoming line request, and determining a pronunciation standard degree value corresponding to the identity information; the pronunciation standard degree value is determined based on pronunciation data of the target user when handling historical business;
calling an IVR key navigation function to process the incoming line request under the condition that the pronunciation standard degree value is determined to be smaller than a first preset threshold value;
and in the intelligent voice navigation function processing process, when the situation that the voice input by the target user in the incoming line request cannot be identified by the intelligent voice navigation function for the continuous preset times is determined, calling an IVR key navigation function to continuously process the incoming line request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643784.XA CN113364920B (en) | 2021-06-09 | 2021-06-09 | Incoming line request processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643784.XA CN113364920B (en) | 2021-06-09 | 2021-06-09 | Incoming line request processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113364920A true CN113364920A (en) | 2021-09-07 |
| CN113364920B CN113364920B (en) | 2023-01-20 |
Family
ID=77533486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110643784.XA Active CN113364920B (en) | 2021-06-09 | 2021-06-09 | Incoming line request processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113364920B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004104520A1 (en) * | 2003-05-26 | 2004-12-02 | Philips Intellectual Property & Standards Gmbh | Method of operating a voice-controlled navigation system |
| CN107680588A (en) * | 2017-05-10 | 2018-02-09 | 平安科技（深圳）有限公司 | Intelligent sound air navigation aid, device and storage medium |
| CN107798341A (en) * | 2017-09-30 | 2018-03-13 | 平安科技（深圳）有限公司 | User view Forecasting Methodology, electronic equipment and computer-readable recording medium |
| CN109086429A (en) * | 2018-08-10 | 2018-12-25 | 携程旅游信息技术（上海）有限公司 | Method, system, equipment and the storage medium of IVR Voice Navigation |
| CN109525738A (en) * | 2018-12-28 | 2019-03-26 | 努比亚技术有限公司 | Telephone customer service method, telephone customer service equipment and readable storage medium storing program for executing |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| CN112347310A (en) * | 2020-11-05 | 2021-02-09 | 中国平安人寿保险股份有限公司 | Event processing information query method and device, computer equipment and storage medium |
-
2021
- 2021-06-09 CN CN202110643784.XA patent/CN113364920B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004104520A1 (en) * | 2003-05-26 | 2004-12-02 | Philips Intellectual Property & Standards Gmbh | Method of operating a voice-controlled navigation system |
| CN107680588A (en) * | 2017-05-10 | 2018-02-09 | 平安科技（深圳）有限公司 | Intelligent sound air navigation aid, device and storage medium |
| CN107798341A (en) * | 2017-09-30 | 2018-03-13 | 平安科技（深圳）有限公司 | User view Forecasting Methodology, electronic equipment and computer-readable recording medium |
| CN109086429A (en) * | 2018-08-10 | 2018-12-25 | 携程旅游信息技术（上海）有限公司 | Method, system, equipment and the storage medium of IVR Voice Navigation |
| CN109525738A (en) * | 2018-12-28 | 2019-03-26 | 努比亚技术有限公司 | Telephone customer service method, telephone customer service equipment and readable storage medium storing program for executing |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| CN112347310A (en) * | 2020-11-05 | 2021-02-09 | 中国平安人寿保险股份有限公司 | Event processing information query method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113364920B (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9992334B2 (en) | Multi-modal customer care system | |
| CN109981910B (en) | Service recommendation method and device | |
| US10027803B2 (en) | Enhanced automated attendant system | |
| US8117030B2 (en) | System and method for analysis and adjustment of speech-enabled systems | |
| US8976942B2 (en) | Method, system and software for implementing an automated call routing application in a speech enabled call center environment | |
| US20110171939A1 (en) | System, method and computer program product for providing customer service on a mobile device | |
| CN111988477A (en) | Incoming call processing method and device, server and storage medium | |
| CN112381256A (en) | Network node reservation method and device, electronic equipment and storage medium | |
| US6581035B1 (en) | System and method for voice-enabled transactions | |
| CN107105109B (en) | Voice broadcasting method and system | |
| CN111371793A (en) | Communication method and communication system | |
| CN110572524B (en) | User call processing method, device, storage medium and server | |
| WO2016169364A1 (en) | Method and apparatus for automatically processing self-service voice service, and mobile terminal | |
| CN113364920B (en) | Incoming line request processing method and device and electronic equipment | |
| EP3839848B1 (en) | Work processing-supporting system based on bi-directional voice and text communication | |
| CN111225115B (en) | Information providing method and device | |
| CN109101645B (en) | Voice call switching method and device, computer equipment and storage medium | |
| KR100977001B1 (en) | Automated response system for providing guidance classified by customer | |
| US8594281B2 (en) | Dynamic menu framework | |
| CN113284497A (en) | Method and device for urging collection of customers and intelligent collection urging system | |
| CN113283913A (en) | Client information processing method and device | |
| EP3053330B1 (en) | Method for an integrated interactive response system and mobile device | |
| US20220294903A1 (en) | Virtual private agent for machine-based interactions with a contact center | |
| CN110351414B (en) | Dialing method, dialing device and computer readable storage medium | |
| CN116645225A (en) | Marketing assistance method and device for insurance service, server and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |