CN106686267A - Method and system for implementing personalized voice service - Google Patents
Method and system for implementing personalized voice service Download PDFInfo
- Publication number
- CN106686267A CN106686267A CN201510763305.2A CN201510763305A CN106686267A CN 106686267 A CN106686267 A CN 106686267A CN 201510763305 A CN201510763305 A CN 201510763305A CN 106686267 A CN106686267 A CN 106686267A
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- voice
- incoming call
- preferred
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000006243 chemical reaction Methods 0.000 claims description 26
- 230000004044 response Effects 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention provides a method and a system for implementing personalized voice service. The method comprises the following steps: receiving a call request; determining the user to which the call belongs according to the call request; determining the type of voice preferred by the user based on the user to which the call belongs; and responding to the call request in a customer service prompt voice matching the type of voice preferred by the user.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and a system for implementing a personalized voice service.
Background
At present, the matching mode of customer service and users in the intelligent voice customer service system is mainly determined based on the self-ability of the customer service, the problem of user consultation and the VIP level of the users, and the matching mode can improve the user experience to a certain extent.
However, voice is an important way for person-to-person communication, individual preference to voice affects subjective thinking and emotion of users, and traditional matching modes of customer service and users do not consider preference of different users to customer service voice, seriously affects impression and loyalty of users to enterprises, and is poor in user experience.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and a system for implementing personalized voice service, which can select a most similar customer service seat for a user according to a voice preference of the user, thereby improving user experience.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
in one aspect, an embodiment of the present invention provides a method for implementing a personalized voice service, where the method includes:
receiving an incoming call request;
determining a user to which the incoming call belongs according to the incoming call request;
determining a sound type preferred by a user based on the user to which the incoming call belongs;
and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
In the foregoing solution, the determining a preferred sound type of a user based on a user to which the incoming call belongs includes:
searching user information matched with the user to which the incoming call belongs in an information database;
inputting the user information into a voice preference model;
determining a user preferred sound type based on the sound preference model.
In the foregoing solution, the determining a preferred sound type of a user based on a user to which the incoming call belongs includes:
and determining the voice type preferred by the user to which the incoming call belongs based on the preset corresponding relation between the user and the voice preference type.
In the above solution, responding to the incoming call request with a customer service alert tone matching the sound type preferred by the user includes:
adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to approve entering manual customer service;
and when a response instruction that the user agrees to enter the artificial customer service is received, selecting a customer service seat matched with the sound type preferred by the user to connect the artificial customer service.
In the above scheme, the selecting a customer service seat matched with the sound type preferred by the user to connect with manual customer service includes:
detecting whether a customer service seat which is in an idle state and meets the requirement of the sound type matched with the user preference exists;
and when the detection result shows that the customer service seat in the idle state and matched with the sound type preferred by the user is met, selecting the customer service seat matched with the sound type preferred by the user to be communicated with manual customer service.
In the above scheme, the method further comprises:
when the detection result shows that no customer service seat in an idle state is available and the customer service seat matched with the sound type preferred by the user is met, adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to agree to select a language conversion function;
when receiving a response instruction that a user agrees to select a language conversion function, selecting a customer service seat in an idle state;
converting the voice of the selected customer service seat to a voice type preferred by the user using a voice conversion technique.
On the other hand, the embodiment of the invention also provides a system for realizing the personalized voice service, which comprises a receiving module, a first determining module, a second determining module and a response module; wherein,
the receiving module is used for receiving an incoming call request;
the first determining module is used for determining a user to which the incoming call belongs according to the incoming call request;
the second determining module is used for determining the sound type preferred by the user based on the user to which the incoming call belongs;
and the response module is used for responding the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
In the above scheme, the second determining module includes a searching unit, an input unit, and a first determining unit; wherein,
the searching unit is used for searching user information matched with the user to which the incoming call belongs in an information database;
the input unit is used for inputting the user information into a voice preference model;
the first determining unit is used for determining the voice type preferred by the user based on the voice preference model.
In the foregoing solution, the second determining module includes a second determining unit; wherein,
the second determining unit is configured to determine a voice type preferred by the user to whom the incoming call belongs, based on a preset correspondence between the user and the voice preference type.
In the above scheme, the response module includes a reminding unit and an execution unit; wherein,
the reminding unit is used for reminding the user whether to approve to enter the artificial customer service by adopting a customer service reminding sound matched with the sound type preferred by the user;
and the execution unit is used for selecting a customer service seat matched with the sound type preferred by the user to be communicated with the artificial customer service when receiving a response instruction that the user agrees to enter the artificial customer service.
In the above scheme, the execution unit includes a detection subunit and a first selection subunit; wherein,
the detection subunit is used for detecting whether a customer service seat which is in an idle state and meets the sound type matched with the user preference exists;
and the first selection subunit is used for selecting the customer service seat matched with the sound type preferred by the user to be communicated with manual customer service when the detection result shows that the customer service seat is in an idle state and meets the customer service seat matched with the sound type preferred by the user.
In the above scheme, the execution unit further includes a reminding subunit, a second selecting subunit and a converting subunit; wherein,
the reminding subunit is configured to, when the detection result indicates that the service seat matching the sound type preferred by the user does not exist in the idle state and meets the requirement, remind the user of agreeing to select the language conversion function by using a service reminding tone matching the sound type preferred by the user;
the second selection subunit is used for selecting the customer service seat in an idle state when receiving a response instruction of agreeing to select the language conversion function by the user;
and the conversion subunit is used for converting the sound of the selected customer service seat into the sound type preferred by the user by using a voice conversion technology.
In the embodiment of the invention, after receiving an incoming call request, a voice customer service center determines a user to which the incoming call belongs according to the incoming call request, and determines a sound type preferred by the user based on the user to which the incoming call belongs; and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user. Therefore, the most similar customer service seat can be selected for the user according to the voice preference of the user, the user experience is improved, and the service quality of customer service is optimized.
Drawings
Fig. 1 is a first flowchart illustrating a method for implementing a personalized voice service according to an embodiment of the present invention;
FIG. 2a is a flowchart illustrating a second method for implementing a personalized voice service according to an embodiment of the present invention;
FIG. 2b is a schematic flow chart of inputting the user information into the voice preference model and inputting the user information into the voice preference model according to the embodiment of the present invention;
FIG. 3 is a third flowchart illustrating a method for implementing personalized voice service according to an embodiment of the present invention;
fig. 4 is a fourth flowchart illustrating a method for implementing a personalized voice service according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a system for implementing personalized voice services according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an execution unit according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
In the embodiment of the invention, after receiving an incoming call request, a voice customer service center determines a user to which the incoming call belongs according to the incoming call request, and determines a sound type preferred by the user based on the user to which the incoming call belongs; and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
Example one
Fig. 1 is a first schematic flow chart of a method for implementing a personalized voice service according to an embodiment of the present invention, and as shown in fig. 1, the method for implementing a personalized voice service according to an embodiment of the present invention includes:
step 101: receiving an incoming call request;
wherein the incoming call request at least comprises identity information of the user.
Specifically, the voice customer service center receives an incoming call request initiated by a user. In practical application, when a user needs to consult the voice customer service center for tariff information or other information related to communication service, the user calls the voice customer service center to enable the voice customer service center to receive an incoming call request.
Step 102: determining a user to which the incoming call belongs according to the incoming call request;
specifically, after receiving the incoming call request, the voice customer service center analyzes the incoming call request to obtain the identity information of the user included in the incoming call request, so as to determine the user to which the incoming call belongs.
Step 103: determining a sound type preferred by a user based on the user to which the incoming call belongs;
specifically, in order to fully consider the preferences of different users for customer service voice, the voice customer service center can input the user information into a voice preference model by searching the user information matched with the user to which the incoming call belongs in an information database, and determine the voice type preferred by the user based on the voice preference model; the voice customer service center can also directly determine the voice type preferred by the user to which the incoming call belongs based on the preset corresponding relation between the user and the voice preferred type.
Step 104: and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
Specifically, the responding to the incoming call request by adopting the customer service prompt tone matched with the sound type preferred by the user comprises:
step 1, adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to approve entering artificial customer service;
and 2, when a response instruction that the user agrees to enter the artificial customer service is received, selecting a customer service seat matched with the sound type preferred by the user to connect the artificial customer service.
According to the method for realizing the personalized voice service, after receiving an incoming call request, a voice customer service center determines a user to which the incoming call belongs according to the incoming call request, and determines a sound type preferred by the user based on the user to which the incoming call belongs; and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user. Therefore, the most similar customer service seat can be selected for the user according to the voice preference of the user, the user experience is improved, and the service quality of customer service is optimized.
Example two
Fig. 2a is a schematic flow chart of a method for implementing a personalized voice service according to an embodiment of the present invention, and as shown in fig. 2a, the method for implementing a personalized voice service according to an embodiment of the present invention includes:
step 101: receiving an incoming call request;
step 102: determining a user to which the incoming call belongs according to the incoming call request;
step 1031: searching user information matched with the user to which the incoming call belongs in an information database;
here, the user information includes information of the user's sex, age, income level, attribution, and the like.
Step 1032: inputting the user information into a voice preference model;
here, the voice preference model is pre-established by the voice customer service center.
Specifically, the process of the voice customer service center inputting the user information into the voice preference model and inputting the user information into the voice preference model is shown in fig. 2b, and includes:
step 1032 a: marking the class label for the customer service sound;
specifically, taking K-Means as an example, the process of labeling class labels for customer service sounds by using a machine learning method is as follows: firstly, acquiring a section of normal customer service recording information of each customer service, wherein the recording time is 60 seconds, extracting the acoustic characteristics of each recording by using a voice processing technology, then putting the acoustic characteristics of the recording data of all the customer services together to form a cluster sample set, clustering the samples into K classes by using a K-means method, wherein each sample belongs to a certain class, and further obtaining the sound type of the customer service corresponding to the sample.
Step 1032 b: synthesizing a typical sound set with class characteristics by using the customer service sound and the class label;
specifically, synthesizing a typical sound set having a category feature using the customer service sound and the category label includes: based on the results of the aforementioned K-means, the sound of the customer service can be classified into K categories; for the ith class of the K classes, i is 1,2, … K, and corresponds to a sound sample containing Ni customer services, and by using the sound features of the Ni customer services, the characteristics of the representative sound of the ith class are found by using an intelligent speech processing technology to perform sound synthesis, so as to form the ith class in the typical sound set, thereby obtaining the typical sound set with class features.
Step 1032 c: establishing an empirical data set of user information and sound preference types as a training set of the model;
specifically, to establish a voice preference prediction model by using a machine learning method, an empirical data set with user information characteristics related to user preference types needs to be constructed as a training set of the model. The acquisition process of the training set can be obtained in the form of an outbound user or a questionnaire, and by taking the mode of the outbound user as an example, a detailed acquisition process is as follows: firstly, preparing a typical audio set for trial listening of a user, wherein the set can be a synthesized K typical sound set, or a set of K sound sets randomly selected from each class of customer service sound; then randomly selecting a user from a database of a customer service center, extracting information data of the user, and calling the user; the user is switched on and indicates a willingness to play the prepared K audio sounds to the user for listening when the user is under investigation, and the user informs his sound preference by key input. After the collection process is repeated for a plurality of times, a training data set with user information characteristics matched with the user voice preference can be obtained.
Here, each training data includes two parts of data: the user information data and the user voice preference type are respectively represented by X and y, wherein the user information data take sex, age, income level and attribution information as examples, X (sex, age, income level and attribution information) is four-dimensional characteristic data, the user preference type is discrete one-dimensional data, the value of y is 1 to K, and y i represents that the voice type preferred by the user is the ith type.
Step 1032 d: establishing a voice preference model by using a data analysis method;
specifically, after the training data set is collected, the user voice preference model can be established through a plurality of machine learning methods. Here, taking the decision tree as an example, the modeling process of the model is briefly introduced: 1) all samples are taken as a node; 2) traversing each segmentation mode of each attribute, and finding the best segmentation point (the optimal attribute and the optimal segmentation threshold); 3) the split point may split the M samples into two nodes M1 and M2; 4) and (3) continuing to perform 2) and 3) on the M1 and the M2 respectively until the number of records in the current node is lower than the minimum threshold value or the depth of the tree exceeds D, stopping segmentation, and taking the classification corresponding to max (P (i)) as the classification of the current leaf node.
Step 1032 e: and inputting the user information into the established voice preference model.
Of course, in practical applications, steps 1032a to 1032d are processes of establishing a voice preference model; the establishment of the voice preference model may be completed in advance, so that after the user information matched with the user to which the incoming call belongs is searched in the information database through step 1031, the user information may be directly input into the pre-established voice preference model.
Step 1033: determining a user preferred sound type based on the sound preference model;
specifically, taking the decision tree model as an example, the information features of the user are moved from the parent node of the decision tree to a leaf node according to the trained decision rule, and the category represented by the leaf node is the sound type preferred by the current user.
Step 104: and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
According to the method for realizing the personalized voice service, after receiving an incoming call request, a voice customer service center determines a user to which the incoming call belongs according to the incoming call request; searching user information matched with the user to which the incoming call belongs in an information database; inputting the user information into a voice preference model; determining a user preferred sound type based on the sound preference model; and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user. Therefore, the most similar customer service seat can be selected for the user according to the voice preference of the user, the user experience is improved, and the service quality of customer service is optimized.
EXAMPLE III
Fig. 3 is a third schematic flowchart of a method for implementing a personalized voice service according to an embodiment of the present invention, and as shown in fig. 3, the method for implementing a personalized voice service according to an embodiment of the present invention includes:
step 101: receiving an incoming call request;
step 102: determining a user to which the incoming call belongs according to the incoming call request;
step 103 a: determining a voice type preferred by a user to which the incoming call belongs based on a preset corresponding relation between the user and the voice preference type;
specifically, the voice customer service center may pre-establish a voice preference model based on steps 1032a to 1032d shown in fig. 2b, and further set the corresponding relationship between the user and the voice preference type according to the established voice preference model. Thus, after the user to which the incoming call belongs is determined, the voice type preferred by the user to which the incoming call belongs can be directly determined based on the preset corresponding relation between the user and the voice preference type.
Step 104: and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
According to the method for realizing the personalized voice service, after receiving an incoming call request, a voice customer service center determines a user to which the incoming call belongs according to the incoming call request; determining a voice type preferred by a user to which the incoming call belongs based on a preset corresponding relation between the user and the voice preference type; and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user. Therefore, the most similar customer service seat can be selected for the user according to the voice preference of the user, the user experience is improved, and the service quality of customer service is optimized.
Example four
Fig. 4 is a fourth schematic flowchart of a method for implementing a personalized voice service according to an embodiment of the present invention, as shown in fig. 4, the method for implementing a personalized voice service according to an embodiment of the present invention includes:
step 101: receiving an incoming call request;
step 102: determining a user to which the incoming call belongs according to the incoming call request;
step 103: determining a sound type preferred by a user based on the user to which the incoming call belongs;
step 1041: adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to approve entering manual customer service;
step 1042: when a response instruction that a user agrees to enter artificial customer service is received, whether a customer service seat which is in an idle state and meets the sound type matched with the user preference exists is detected;
here, when the detection result is that there is a customer service seat in an idle state and that matches the sound type preferred by the user, the subsequent step 1043 is performed; otherwise, the subsequent step 1044 is executed.
It should be noted that, when receiving a response instruction that the user disagrees with entering the manual customer service, the flow is ended, that is, the automatic service consultation is ended.
Step 1043: and selecting a customer service seat matched with the sound type preferred by the user to connect with manual customer service.
Step 1044: adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to agree to select a language conversion function;
step 1045: when receiving a response instruction that a user agrees to select a language conversion function, selecting a customer service seat in an idle state;
it should be noted that, when receiving a response instruction that the user disagrees with the language conversion function, the voice customer service center is required to select the customer service according to the queue to connect the manual customer service.
Step 1046: converting the voice of the selected customer service seat to a voice type preferred by the user using a voice conversion technique.
According to the method for realizing the personalized voice service, a voice customer service center adopts a customer service prompt tone matched with a preferred sound type of a user to remind the user whether to agree to enter artificial customer service or not on the basis that the user to which the incoming call belongs determines the preferred sound type of the user, when the user selects to enter the artificial customer service, the idle customer service meeting the preferred sound type of the user in a customer service queue is preferentially connected, and if the idle customer service meeting the sound condition does not exist, one customer service is selected from the idle customer service in the queue to serve the user; before the call is connected, the user feels whether to use the voice conversion function, if the voice conversion function is selected, the current customer service voice is converted into the user preference type by using the voice conversion technology in the call, otherwise, the voice of the customer service original is used for serving the user. Therefore, the most similar customer service seat can be selected for the user according to the voice preference of the user, the user experience is improved, and the service quality of customer service is optimized.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a system for implementing a personalized voice service according to an embodiment of the present invention, and as shown in fig. 5, the system for implementing a personalized voice service according to an embodiment of the present invention includes a receiving module 51, a first determining module 52, a second determining module 53, and a responding module 54; wherein,
the receiving module 51 is configured to receive an incoming call request;
the first determining module 52 is configured to determine, according to the incoming call request, a user to which the incoming call belongs;
the second determining module 53 is configured to determine a preferred sound type of the user based on the user to which the incoming call belongs;
the response module 54 is configured to respond to the incoming call request with a customer service alert tone matching the user's preferred voice type.
In one embodiment, as shown in fig. 5, the second determining module 53 includes a searching unit 531, an input unit 532, and a first determining unit 533; wherein,
the searching unit 531 is configured to search, in an information database, user information matched with a user to which the incoming call belongs;
the input unit 532 is used for inputting the user information into a voice preference model;
the first determining unit 533 is configured to determine a voice type preferred by the user based on the voice preference model.
In one embodiment, as shown in fig. 5, the second determining module 53 includes a second determining unit 534; wherein,
the second determining unit 534 is configured to determine, based on a preset correspondence between a user and a voice preference type, a voice type preferred by the user to whom the incoming call belongs.
In one embodiment, as shown in fig. 5, the response module 54 includes a reminding unit 541 and an execution unit 542; wherein,
the reminding unit 541 is configured to remind the user whether to approve entering of manual customer service by using a customer service reminding sound matched with the sound type preferred by the user;
the execution unit 542 is configured to select a customer service seat matching the sound type preferred by the user to communicate with the manual customer service when receiving a response instruction that the user agrees to enter the manual customer service.
In one embodiment, as shown in fig. 6, the execution unit 542 includes a detection subunit 5421 and a first selection subunit 5422; wherein,
the detecting subunit 5421 is configured to detect whether there is a customer service seat that is in an idle state and satisfies a sound type matching the user preference;
the first selecting subunit 5422 is configured to, when the detection result indicates that there is a customer service seat in an idle state and that meets the sound type matching the sound type preferred by the user, select a customer service seat matching the sound type preferred by the user to connect to manual customer service.
In an embodiment, as shown in fig. 6, the execution unit 542 further includes a reminding sub-unit 5423, a second selecting sub-unit 5424, and a converting sub-unit 5425; wherein,
the reminding subunit 5423 is configured to, when the detection result indicates that there is no customer service seat in an idle state and that the sound type matching the sound type preferred by the user is satisfied, remind the user of agreeing to select a language conversion function by using a customer service reminding sound matching the sound type preferred by the user;
the second selecting subunit 5424 is configured to select a customer service seat in an idle state when receiving a response instruction that the user agrees to select the language conversion function;
the conversion subunit 5425 is configured to convert the sound of the selected customer service seat into the sound type preferred by the user by using a voice conversion technology.
In practical applications, each module, the unit included in each module, and the sub-unit thereof for forming the system for implementing the personalized voice service according to the embodiments of the present invention may be implemented by a processor in the system for implementing the personalized voice service, or may be implemented by a specific logic circuit; for example, in practical applications, the personalized voice service can be implemented by a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), or a Field Programmable Gate Array (FPGA) located in the system for implementing the personalized voice service.
Here, it should be noted that: the description of the system embodiment for implementing the personalized voice service is similar to the description of the method, and has the same beneficial effects as the method embodiment, and therefore, the description thereof is omitted. For technical details that are not disclosed in the embodiment of the system for implementing personalized voice service according to the present invention, those skilled in the art should refer to the description of the embodiment of the method of the present invention to understand that, for brevity, detailed description is omitted here.
The foregoing is merely an example of the embodiments of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the embodiments of the present invention, and these modifications and decorations should also be regarded as the protection scope of the embodiments of the present invention.
Claims (12)
1. A method for implementing personalized voice services, the method comprising:
receiving an incoming call request;
determining a user to which the incoming call belongs according to the incoming call request;
determining a sound type preferred by a user based on the user to which the incoming call belongs;
and responding to the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
2. The method of claim 1, wherein the determining a preferred voice type for the user based on the user to which the incoming call belongs comprises:
searching user information matched with the user to which the incoming call belongs in an information database;
inputting the user information into a voice preference model;
determining a user preferred sound type based on the sound preference model.
3. The method of claim 1, wherein the determining a preferred voice type for the user based on the user to which the incoming call belongs comprises:
and determining the voice type preferred by the user to which the incoming call belongs based on the preset corresponding relation between the user and the voice preference type.
4. The method of any of claims 1 to 3, wherein responding to the incoming call request with a customer service alert tone matching the user's preferred voice type comprises:
adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to approve entering manual customer service;
and when a response instruction that the user agrees to enter the artificial customer service is received, selecting a customer service seat matched with the sound type preferred by the user to connect the artificial customer service.
5. The method of claim 4, wherein selecting a customer service seat matching the user preferred sound type to engage manual customer service comprises:
detecting whether a customer service seat which is in an idle state and meets the requirement of the sound type matched with the user preference exists;
and when the detection result shows that the customer service seat in the idle state and matched with the sound type preferred by the user is met, selecting the customer service seat matched with the sound type preferred by the user to be communicated with manual customer service.
6. The method of claim 5, further comprising:
when the detection result shows that no customer service seat in an idle state is available and the customer service seat matched with the sound type preferred by the user is met, adopting a customer service prompt tone matched with the sound type preferred by the user to remind the user whether to agree to select a language conversion function;
when receiving a response instruction that a user agrees to select a language conversion function, selecting a customer service seat in an idle state;
converting the voice of the selected customer service seat to a voice type preferred by the user using a voice conversion technique.
7. A system for realizing personalized voice service is characterized by comprising a receiving module, a first determining module, a second determining module and a response module; wherein,
the receiving module is used for receiving an incoming call request;
the first determining module is used for determining a user to which the incoming call belongs according to the incoming call request;
the second determining module is used for determining the sound type preferred by the user based on the user to which the incoming call belongs;
and the response module is used for responding the incoming call request by adopting customer service prompt tones matched with the sound types preferred by the user.
8. The system of claim 7, wherein the second determination module comprises a lookup unit, an input unit, and a first determination unit; wherein,
the searching unit is used for searching user information matched with the user to which the incoming call belongs in an information database;
the input unit is used for inputting the user information into a voice preference model;
the first determining unit is used for determining the voice type preferred by the user based on the voice preference model.
9. The system of claim 7, wherein the second determination module comprises a second determination unit; wherein,
the second determining unit is configured to determine a voice type preferred by the user to whom the incoming call belongs, based on a preset correspondence between the user and the voice preference type.
10. The system according to any one of claims 7 to 9, wherein the response module comprises a reminding unit and an execution unit; wherein,
the reminding unit is used for reminding the user whether to approve to enter the artificial customer service by adopting a customer service reminding sound matched with the sound type preferred by the user;
and the execution unit is used for selecting a customer service seat matched with the sound type preferred by the user to be communicated with the artificial customer service when receiving a response instruction that the user agrees to enter the artificial customer service.
11. The system of claim 10, wherein the execution unit comprises a detection subunit and a first selection subunit; wherein,
the detection subunit is used for detecting whether a customer service seat which is in an idle state and meets the sound type matched with the user preference exists;
and the first selection subunit is used for selecting the customer service seat matched with the sound type preferred by the user to be communicated with manual customer service when the detection result shows that the customer service seat is in an idle state and meets the customer service seat matched with the sound type preferred by the user.
12. The system of claim 11, wherein the execution unit further comprises a reminder subunit, a second selection subunit, and a conversion subunit; wherein,
the reminding subunit is configured to, when the detection result indicates that the service seat matching the sound type preferred by the user does not exist in the idle state and meets the requirement, remind the user of agreeing to select the language conversion function by using a service reminding tone matching the sound type preferred by the user;
the second selection subunit is used for selecting the customer service seat in an idle state when receiving a response instruction of agreeing to select the language conversion function by the user;
and the conversion subunit is used for converting the sound of the selected customer service seat into the sound type preferred by the user by using a voice conversion technology.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510763305.2A CN106686267A (en) | 2015-11-10 | 2015-11-10 | Method and system for implementing personalized voice service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510763305.2A CN106686267A (en) | 2015-11-10 | 2015-11-10 | Method and system for implementing personalized voice service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106686267A true CN106686267A (en) | 2017-05-17 |
Family
ID=58865237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510763305.2A Pending CN106686267A (en) | 2015-11-10 | 2015-11-10 | Method and system for implementing personalized voice service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106686267A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109413289A (en) * | 2018-10-19 | 2019-03-01 | 中国银行股份有限公司 | A kind of data processing method and system |
| CN110033129A (en) * | 2019-03-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for determining feedback for the report of user |
| CN111145721A (en) * | 2019-12-12 | 2020-05-12 | 科大讯飞股份有限公司 | Personalized prompt language generation method, device and equipment |
| CN112418673A (en) * | 2020-11-23 | 2021-02-26 | 平安普惠企业管理有限公司 | Case allocation method, device and medium |
| CN113920984A (en) * | 2021-09-13 | 2022-01-11 | 上海仪电数字技术股份有限公司 | Processing method and processing system for voice message of television terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1172804A1 (en) * | 2000-07-13 | 2002-01-16 | Rockwell Electronic Commerce Corporation | Voice filter for normalizing an agent's emotional response |
| CN102802114A (en) * | 2012-06-20 | 2012-11-28 | 北京语言大学 | Method and system for screening seat by using voices |
| CN103167174A (en) * | 2013-02-25 | 2013-06-19 | 广东欧珀移动通信有限公司 | Output method, device and mobile terminal of mobile terminal greetings |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN103377651A (en) * | 2012-04-28 | 2013-10-30 | 北京三星通信技术研究有限公司 | Device and method for automatic voice synthesis |
| CN105761720A (en) * | 2016-04-19 | 2016-07-13 | 北京地平线机器人技术研发有限公司 | Interaction system based on voice attribute classification, and method thereof |
-
2015
- 2015-11-10 CN CN201510763305.2A patent/CN106686267A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1172804A1 (en) * | 2000-07-13 | 2002-01-16 | Rockwell Electronic Commerce Corporation | Voice filter for normalizing an agent's emotional response |
| CN103377651A (en) * | 2012-04-28 | 2013-10-30 | 北京三星通信技术研究有限公司 | Device and method for automatic voice synthesis |
| CN102802114A (en) * | 2012-06-20 | 2012-11-28 | 北京语言大学 | Method and system for screening seat by using voices |
| CN103167174A (en) * | 2013-02-25 | 2013-06-19 | 广东欧珀移动通信有限公司 | Output method, device and mobile terminal of mobile terminal greetings |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN105761720A (en) * | 2016-04-19 | 2016-07-13 | 北京地平线机器人技术研发有限公司 | Interaction system based on voice attribute classification, and method thereof |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109413289A (en) * | 2018-10-19 | 2019-03-01 | 中国银行股份有限公司 | A kind of data processing method and system |
| CN110033129A (en) * | 2019-03-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for determining feedback for the report of user |
| CN111145721A (en) * | 2019-12-12 | 2020-05-12 | 科大讯飞股份有限公司 | Personalized prompt language generation method, device and equipment |
| CN111145721B (en) * | 2019-12-12 | 2024-02-13 | 科大讯飞股份有限公司 | Personalized prompt generation method, device and equipment |
| CN112418673A (en) * | 2020-11-23 | 2021-02-26 | 平安普惠企业管理有限公司 | Case allocation method, device and medium |
| WO2022105136A1 (en) * | 2020-11-23 | 2022-05-27 | 平安普惠企业管理有限公司 | Case allocation method and apparatus, and medium |
| CN113920984A (en) * | 2021-09-13 | 2022-01-11 | 上海仪电数字技术股份有限公司 | Processing method and processing system for voice message of television terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN106372059B (en) | Data inputting method and device | |
| CN107832286B (en) | Intelligent interaction method, equipment and storage medium | |
| CN109344237B (en) | Information processing method and device for man-machine interaction | |
| CN106782615B (en) | Voice data emotion detection method, device and system | |
| CN105590626B (en) | Continuous voice man-machine interaction method and system | |
| CN106686267A (en) | Method and system for implementing personalized voice service | |
| CN108874895B (en) | Interactive information pushing method and device, computer equipment and storage medium | |
| US20210280172A1 (en) | Voice Response Method and Device, and Smart Device | |
| WO2020238209A1 (en) | Audio processing method, system and related device | |
| CN106294774A (en) | User individual data processing method based on dialogue service and device | |
| CN109961786B (en) | Product recommendation method, device, equipment and storage medium based on voice analysis | |
| CN109254669A (en) | A kind of expression picture input method, device, electronic equipment and system | |
| CN109271550A (en) | A kind of music personalization classification recommended method based on deep learning | |
| CN114297365B (en) | Intelligent customer service system and method based on Internet | |
| CN101867742A (en) | Television system based on sound control | |
| CN105893562A (en) | Conversation message processing method and device and terminal | |
| CN108595406A (en) | User state reminding method and device, electronic equipment and storage medium | |
| CN112242135A (en) | Voice data processing method and intelligent customer service device | |
| CN105550361B (en) | Log processing method and device and question and answer information processing method and device | |
| JP2020160425A (en) | Evaluation system, evaluation method, and computer program | |
| CN114328867A (en) | Intelligent interruption method and device in man-machine conversation | |
| CN117332062A (en) | Data processing method and related device | |
| CN107807949A (en) | Intelligent interactive method, equipment and storage medium | |
| CN111354350A (en) | Voice processing method and device, voice processing equipment and electronic equipment |
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: 20170517 |