CN114827360A - Voice response method, device, controller and computer readable storage medium - Google Patents
Voice response method, device, controller and computer readable storage medium Download PDFInfo
- Publication number
- CN114827360A CN114827360A CN202110110579.7A CN202110110579A CN114827360A CN 114827360 A CN114827360 A CN 114827360A CN 202110110579 A CN202110110579 A CN 202110110579A CN 114827360 A CN114827360 A CN 114827360A
- Authority
- CN
- China
- Prior art keywords
- information
- reply
- voice response
- caller
- terminal
- 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
- 230000004044 response Effects 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 title claims abstract description 79
- 230000000977 initiatory effect Effects 0.000 claims abstract description 15
- 238000013507 mapping Methods 0.000 claims description 26
- 230000006854 communication Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 4
- 206010048669 Terminal state Diseases 0.000 abstract description 5
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000010187 selection method Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000013519 translation Methods 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
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
Landscapes
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the application discloses a voice response method, a voice response device, a controller and a computer readable storage medium; according to the embodiment of the application, the terminal state can be acquired when the voice call request is received; if the terminal is in a state of being unable to answer, the voice call request is transferred to a voice response system, and caller information initiating the voice call request is obtained; acquiring corresponding reply information according to the caller information; and the voice response system calls the caller based on the reply message. Therefore, the intelligent degree of voice response is improved, and the user experience is improved.
Description
Technical Field
The present application relates to the field of voice response, and in particular, to a voice response method, apparatus, controller, and computer-readable storage medium.
Background
An example voice response (IVR) system is a part of artificial intelligence, and is more and more concerned by related enterprises in recent years, most of the roamers used in telecom, bank and other commodity sales systems are provided with an example voice response (IVR) system which can process the calling of a caller, while the existing example voice response system can only play the calling through fixed telephone technology, does not consider using a specific artificial intelligence mode, cannot deal with emergency situations, and has low intelligence degree.
Disclosure of Invention
The embodiment of the application provides a voice response method, a voice response device, a controller and a computer readable storage medium, and aims to improve the intelligent degree of voice response and improve user experience.
The embodiment of the application provides a voice response method, which is applied to a voice response system and comprises the following steps:
when a voice response request is received, acquiring a voice call request of a terminal corresponding to the voice response request;
acquiring caller information for initiating the voice call request;
acquiring corresponding reply information according to the caller information;
and calling the caller based on the reply message.
Correspondingly, the embodiment of the present application further provides a voice response apparatus, including:
the first acquisition unit is used for acquiring a voice call request of a terminal corresponding to a voice response request when the voice response request is received;
a second obtaining unit, configured to obtain caller information for initiating the voice call request;
a third obtaining unit, configured to obtain corresponding reply information according to the caller information;
and the communication unit is used for communicating with the caller based on the reply information.
Optionally, in some embodiments, the voice response apparatus further includes:
the terminal comprises a receiving unit, a processing unit and a processing unit, wherein the receiving unit is used for receiving a preset conversation journey and conversation information of the terminal, and the preset conversation journey comprises caller information and/or preset calling time;
and the storage unit is used for classifying the dialogue information, establishing a mapping relation between the classified dialogue information and the preset dialogue stroke, and storing the dialogue information as reply information.
Optionally, in some embodiments, the storage unit includes:
the extraction subunit is used for extracting necessary information in the dialogue information through a trained machine learning model and classifying the necessary information;
a first sharing subunit, configured to share the classified necessary information to the terminal;
a receiving subunit, configured to receive correction information fed back by the terminal based on the classified necessary information;
and the first storage subunit is used for correcting the classified necessary information based on the correction information, establishing a mapping relation between the corrected necessary information and a preset dialogue trip, and storing the corrected necessary information and the preset dialogue trip as reply information.
Optionally, in some embodiments, the storage unit further includes:
the translation subunit is used for translating the dialogue information into voice information when the dialogue information is text information;
and the second storage subunit is used for storing the voice information after establishing a mapping relation with a preset conversation process and taking the voice information as reply information.
Optionally, in some embodiments, the fourth obtaining unit includes:
the terminal comprises a first acquisition subunit, a second acquisition subunit and a third acquisition subunit, wherein the first acquisition subunit is used for acquiring preset conversation information of the terminal, and the preset conversation information comprises caller information and/or preset calling time;
the comparison subunit is used for comparing the preset calling time with the current time to obtain a time difference value;
and the second obtaining subunit is configured to obtain, if the time difference meets an obtaining condition, corresponding reply information according to the caller information.
Optionally, in some embodiments, the call unit includes:
the first reply subunit is used for replying based on the first reply information when the voice response system is switched on and the call of the caller is based on the reply information;
the second reply subunit is used for replying based on the second reply information if the inquiry of the caller is received and the reply information has a reply corresponding to the question inquired by the caller;
and the third reply subunit is used for replying based on the third reply information if the inquiry of the caller is received and the reply information does not have a reply corresponding to the question inquired by the caller.
Optionally, in some embodiments, the call unit includes:
a recording subunit, configured to record, as non-provided information, inquiry information corresponding to a reply based on the third reply information;
and the second sharing subunit is used for sharing the non-provided information with the terminal after the non-provided information is associated with the current call.
When a call with a caller based on the reply information is connected, replying based on the leisure information;
optionally, in some embodiments, the call unit includes:
a fourth replying subunit, configured to reply based on the key information after replying based on the leisure information;
a fifth replying subunit, configured to reply based on the acquaintable information if a query from the caller is received and a reply corresponding to the question queried by the caller exists in the reply information;
and the sixth reply subunit is used for replying based on the standard information if the inquiry of the caller is received and the reply information does not have a reply corresponding to the question inquired by the caller.
Optionally, in some embodiments, the voice response apparatus further includes:
the summarizing unit is used for summarizing the call information in the call process after the voice response system finishes the call with the caller based on the reply information;
the sending unit is used for sending the summarized call information to a user;
and the storage unit is used for storing the call record of the communication between the voice response system and the caller based on the reply information so as to be inquired by the user.
In addition, an embodiment of the present application further provides a voice response method, which is applied to a terminal, and includes:
when a voice call request is received, detecting the answering state of the terminal;
and if the answering state of the terminal is in the non-answering state, sending a voice response request to a voice response system.
In addition, an embodiment of the present application further provides a voice response apparatus, including:
the terminal comprises a detection unit, a processing unit and a processing unit, wherein the detection unit is used for detecting the answering state of the terminal when receiving a voice call request;
and the sending unit is used for sending a voice response request to the voice response system if the answering state of the terminal is in the non-answering state.
In addition, an embodiment of the present application further provides a voice response controller, which includes: a processor and a memory; the memory stores a plurality of instructions, and the processor loads the instructions stored in the memory to execute the steps of any one of the voice response methods provided by the embodiments of the present application.
In addition, an embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to perform steps in any one of the voice response methods provided in the embodiments of the present application.
According to the embodiment of the application, when a voice response request is received, a voice call request of a terminal corresponding to the voice response request is obtained; acquiring caller information for initiating the voice call request; acquiring corresponding reply information according to the caller information; the call is carried out with the caller based on the reply information, even if the terminal is in a condition that the call cannot be answered, the call can be carried out through a voice response system, and the situation that the call cannot be carried out when the terminal is in a condition that the call cannot be answered is avoided, so that various emergency situations can be dealt with, such as sudden power failure of the terminal or no signal and the like; and when the terminal is in the state of unable answering, based on caller's information, carry out the pertinence conversation, avoid carrying out mechanical reply through fixed speech technology to improve the intelligent degree of voice response.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic scene diagram of a voice response method provided in an embodiment of the present application;
fig. 2 is a schematic structural diagram of a voice response controller provided in an embodiment of the present application;
fig. 3a is a schematic flow chart of a voice response method according to an embodiment of the present application;
FIG. 3b is a schematic diagram of key information provided by an embodiment of the present application;
fig. 3c is another schematic flow chart of a voice response method provided in the embodiment of the present application;
fig. 4 is a schematic flow chart of a voice response method according to an embodiment of the present application;
fig. 5a is a schematic structural diagram of a voice response device according to an embodiment of the present application;
fig. 5b is a schematic structural diagram of another voice response apparatus provided in the embodiment of the present application;
fig. 5c is a schematic view of another structure of the voice response apparatus according to the embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any inventive work, are within the scope of protection of the present application.
The embodiment of the invention provides a voice response method, a voice response device, a controller and a computer readable storage medium.
The controller may be a single controller integrated in the terminal or a controller independent from the terminal, and the terminal may be a mobile phone, a tablet Computer, an intelligent bluetooth device, a notebook Computer, or a Personal Computer (PC).
For example, referring to fig. 1, the terminal may be a smart phone communicatively coupled to the controller and the voice response system communicatively coupled to the controller. When the terminal receives the voice call request, if the terminal state is unavailable at the moment, the unavailable condition is that a user corresponding to the terminal is in an unavailable state, such as busy, and if the terminal can carry out communication at the moment, the terminal sends a voice response request to a voice response system so as to carry out communication through the voice response system. When the terminal receives the voice call request, if the terminal state is unavailable at the moment, for example, the terminal is in a power-off state or a signal-free state, and the voice call cannot be answered, the voice call request can be detected through a voice response system, and the voice call is performed when the situation that the terminal is not in a server is detected, and therefore, the voice response request can be obtained through receiving or actively acquiring. Specifically, in the voice call process, caller information is firstly acquired according to the voice response request, corresponding reply information is acquired according to the caller information, and then, the call is carried out with the caller based on the reply information through the voice response system, wherein the voice response system is arranged in the controller, namely, the voice response system is integrated in the controller, and the controller is in communication connection with the voice response system.
Fig. 2 shows a schematic structural diagram of a voice response controller according to an embodiment of the present application, and specifically:
in some embodiments, referring to fig. 2, the voice response controller 200 may include one or more processing cores of a processor 201, one or more computer-readable storage media of a memory 202, a power supply 203, and an input unit 204. Those skilled in the art will appreciate that the voice response controller configuration shown in fig. 2 does not constitute a limitation of the voice response controller and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 201 is a control center of the voice response controller, connects various parts of the entire apparatus using various interfaces and lines, and performs various functions of the apparatus and processes data by running or executing software programs and/or modules stored in the memory 202 and calling data stored in the memory 202, thereby performing overall monitoring of the voice response controller. Optionally, processor 201 may include one or more processing cores; preferably, the processor 201 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 201.
The memory 202 may be used to store software programs and modules, and the processor 201 executes various functional applications and data processing by operating the software programs and modules stored in the memory 202. The memory 202 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the device, and the like. Further, the memory 202 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 202 may also include a memory controller to provide the processor 201 access to the memory 202.
The voice response controller further comprises a power supply 203 for supplying power to each component, and preferably, the power supply 203 can be logically connected with the processor 201 through a power management system, so that the functions of charging, discharging, power consumption management and the like can be managed through the power management system. The power supply 203 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and any like components.
The voice response controller may also include an input unit 204. the input unit 204 may be used to receive input information and generate inputs for a screen, keyboard, mouse, etc. related to user settings and function control.
Specifically, in this embodiment, the processor 201 in the voice response controller loads the executable file corresponding to the process of one or more application programs into the memory 202 according to the following instruction, and the processor 201 runs the application program stored in the memory 202, thereby implementing the method according to any embodiment of the present application, for example, when a voice response request is received, a voice call request of a terminal corresponding to the voice response request is obtained; acquiring caller information for initiating the voice call request; acquiring corresponding reply information according to the caller information; the call is carried out with the caller based on the reply information, even if the terminal is in a condition that the call cannot be answered, the call can be carried out through a voice response system, and the situation that the call cannot be carried out when the terminal is in a condition that the call cannot be answered is avoided, so that various emergency situations can be dealt with, such as sudden power failure of the terminal or no signal and the like; and when the terminal is in the state of unable answering, based on caller's information, carry out the pertinence conversation, avoid carrying out mechanical reply through fixed speech technology to improve the intelligent degree of voice response.
The following are detailed below. It should be noted that the order of description of the following embodiments is not intended to limit the order of preference of the embodiments.
As shown in fig. 3a, the specific process of the voice response method applied to the voice response system may be as follows:
301, when receiving or obtaining a voice response request, obtaining a voice call request of a terminal corresponding to the voice response request.
Specifically, the voice response request may be obtained by terminal transmission, or by detecting a situation such as terminal communication. When the terminal receives the voice call request, if the terminal can communicate at the moment, and receives a rejection instruction, or does not answer after a preset time, such as 30s and 1 min, it indicates that the user is in a state of unable to answer due to reasons such as busy and the like at the moment, and at the moment, the voice response request can be triggered and sent to the voice response system, and at the moment, the voice response system can obtain the voice response request in a receiving mode. Optionally, when the terminal receives the voice call request, the terminal may first obtain information of a caller initiating the voice call request, and determine whether the information matches the information in the predetermined conversation process, if not, the terminal does not forward the voice call request to the voice response system; and when the matching is performed, the voice call request is transferred to the voice response system.
Or, when the other user initiates the voice call request and the terminal is in a no-signal state or a no-power state, the voice response request may be actively detected, where the specific detection includes detecting the terminal state, for example, detecting the signal condition of the terminal, detecting the battery power of the terminal, and determining that the voice response request is detected if the terminal detects that the terminal receives the voice call request and does not answer the voice call request for more than a preset time, such as 30s or 1 min.
Further, since it is necessary to obtain corresponding reply information according to the caller information when the terminal is in the non-answering state, before step 301, the method may further include:
a1, receiving a preset dialogue schedule and dialogue information of a terminal, wherein the preset dialogue schedule comprises caller information and/or preset calling time;
and A2, classifying the dialogue information, establishing a mapping relation between the classified dialogue information and the preset dialogue process, and storing the dialogue information as reply information.
The method comprises the steps of firstly receiving a preset conversation process sent by a terminal and conversation information input by a user, wherein the preset conversation process can comprise call time or caller information, for example, a 10 month 10 afternoon three-point call with Mr. client, and the conversation information is information that the user needs to interact with the caller when in a call, wherein the method for inputting the conversation information by the user can comprise voice input or text input. After the dialog information input by the user is obtained, the dialog information is firstly sorted, unnecessary interference information is frequently removed, then the dialog information is classified, and after a mapping relation is established between the classified dialog information and a preset dialog stroke, the classified dialog information is stored and used as reply information.
Further, the dialog information may be classified through a trained model, and at this time, the dialog information is classified, and after a mapping relationship is established between the classified dialog information and a predetermined dialog trip, the dialog information is stored and used as a reply information, including:
b1, extracting necessary information in the dialogue information through the trained machine learning model, and classifying the necessary information;
b2, sharing the classified necessary information to the terminal;
b3, receiving the correction information fed back by the terminal based on the classified necessary information;
and B4, correcting the classified necessary information based on the correction information, establishing a mapping relation between the corrected necessary information and a preset dialogue trip, storing the mapping relation, and using the mapping relation as reply information.
Specifically, feature extraction is performed on the dialogue information through a trained Machine Learning model, and specifically, feature selection can be performed based on a filtering feature selection method, wherein the filtering feature selection method is to calculate the probability of each feature in the dialogue information through a certain statistical measurement method, and then select or reject the features in the dialogue information according to the probability, so as to achieve the purpose of feature selection. And then, identifying necessary information in the dialogue information according to the selected characteristics, removing the unnecessary information, and classifying the necessary information. In the specific implementation process, the necessary information may be divided into 5 categories, as shown in fig. 3b, which specifically include: (a) critical information, which is important information that the caller may need to know or the user needs to communicate, that the caller needs to be informed proactively even if the caller does not make a request; (b) the voice response system can not inform the caller actively and only provides the information when the caller asks actively; (c) the leisure information is information for providing leisure and conversation etiquettes, has no practical significance, and is information interspersed in the conversation process for showing the etiquettes and improving the conversation experience of callers. Further, standard information can be added to the reply information, wherein (d) the standard information is the standard expression for replying when the caller asks a question but there is no corresponding reply answer in the reply information, wherein a plurality of standard expressions can be set for correspondingly replying the callers with different roles, so that the caller can communicate with the caller through the standard information when there is no corresponding reply answer in the reply information. The reply message may also include query message, and (e) query message is an active query from the user terminal and is provided only when the user terminal actively queries. Further, after the call is ended, the category of the unavailable information can be further increased according to the actual situation of the call, (f) no information is provided, and the unavailable information is a problem that the caller asks but does not provide information in the call process. Therefore, after the call of the caller is finished, when the user checks the call record, the corresponding information is timely provided for the caller according to the information which is not provided.
And then, the classified necessary information is shared to the terminal, the terminal can provide feedback information according to the classification condition of the necessary information, and at the moment, the machine learning model changes the feedback information of the terminal and records and learns the feedback information, such as changing or adding and deleting the classification information, so that the classification accuracy of the dialogue information is improved during subsequent classification. It can be understood that the process of the machine learning model based on the corrected information fed back by the terminal is also the process of the machine learning model training in real time. And then establishing a mapping relation between the corrected necessary information and the preset dialogue journey, and storing the information as reply information. Therefore, the conversation between the voice response system and the caller is more orderly, the mechanical playing is avoided, the omission of key information is also avoided, the intelligent degree of voice response is improved, and the user experience is improved.
Further, it can be understood that the manner of inputting the dialog information by the user may include voice input and text input, and when the manner of inputting the dialog information by the user is text input, the classifying the dialog information, establishing a mapping relationship between the classified dialog information and a predetermined dialog trip, storing the dialog information, and using the dialog information as the reply information, the method further includes:
c1, when the dialogue information is text information, translating the dialogue information into voice information;
and C2, storing the voice information after establishing a mapping relation with a preset dialogue trip, and using the voice information as reply information.
When the dialogue information is text information, the dialogue information can be classified and then converted into voice information through a voice synthesis technology, the voice information can be expressed by user accent learned by a machine, and then the voice information is stored and used as reply information after a mapping relation is established between the voice information and a preset dialogue stroke, so that the dialogue information can be played conveniently in a conversation process.
And 302, obtaining caller information for initiating the voice call request.
Wherein the caller's information may be obtained through the communication number, or personal account, from which the caller originated the call.
303, obtaining the corresponding reply information according to the caller information.
After the caller information is obtained, the corresponding reply information can be obtained through the caller information according to the mapping relation between the voice information and the preset conversation journey which is established in advance.
Further, in order to improve the accuracy of acquiring the reply information, the acquiring may further be performed in combination with time, and in this case, the acquiring the corresponding reply information according to the caller information includes:
d1, obtaining a preset conversation travel of the terminal, wherein the preset conversation travel comprises caller information and preset calling time;
d2, comparing the preset calling time with the current time to obtain a time difference value;
d3, if the time difference value accords with the obtaining condition, obtaining the corresponding reply information according to the caller information.
The method comprises the steps of firstly obtaining a preset conversation travel stored by a terminal, wherein the preset conversation travel comprises caller information and preset calling information, comparing preset calling time with current time to obtain a time difference value, and if the time difference value meets an obtaining condition, obtaining corresponding reply information according to the caller information, wherein the obtaining condition can include that the time difference value is within a preset value range, the preset value can be 10 minutes, 30 minutes and the like, the preset value can be set by a system or can be set by a user, when the preset value is 10 minutes, if the time difference value is 0-10 minutes, the time difference value is determined to meet the obtaining condition, at the moment, the corresponding reply information can be obtained according to the caller information, and therefore the accuracy of obtaining the conversation information is improved.
304. And calling the caller based on the reply message.
After obtaining the reply message, the voice response system can communicate with the caller based on the reply message.
During the call, the call in order can be made based on the category of the reply message, specifically, referring to fig. 3c, the call with the caller based on the reply message includes:
305, when the voice response system is connected to the call of the caller based on the reply information, replying based on the first reply information;
306, if the inquiry of the caller is received and the reply information has a reply corresponding to the question inquired by the caller, replying based on the second reply information;
307, if the caller's inquiry is received and there is no reply corresponding to the question asked by the caller in the reply message, then reply is performed based on the third reply message.
Specifically, the first reply message includes key information, leisure information and inquiry information; the second reply information comprises learnable information; the third reply message includes standard information, and referring to fig. 3c, the talking with the caller based on the reply message includes:
e1, when the call with the caller based on the reply information is connected, replying based on the leisure information;
e2, replying based on the key information after replying based on the leisure information;
e3, if the inquiry of the caller is received and the reply information has the reply corresponding to the question inquired by the caller, replying based on the acquaintability information;
e4, if the caller's inquiry is received and there is no reply corresponding to the question inquired by the caller in the reply message, then reply is performed based on the standard message.
When the voice response system is switched on and the call is made with the caller based on the reply information, replying is carried out based on first reply information, wherein the first reply information is leisure information and key information, namely the caller is politely chatted with the leisure information, and then if the caller does not ask a question at the moment, replying is carried out based on the key information, namely the caller is informed of the key information. If the inquiry of the caller is received and the reply information has the reply corresponding to the question inquired by the caller, the reply is carried out based on the second reply information, the second reply information is the acquainted information, and the information is provided only when the caller asks the question. If the inquiry of the caller is received and the reply information does not have a reply corresponding to the question inquired by the caller, replying based on third reply information, wherein the third reply information is standard information, for example, the question I needs to inquire and then replies to you and the like.
Further, after the calling with the caller based on the reply message, the method further includes:
f1, recording the inquiry information corresponding to the reply based on the third reply information as the non-provided information;
and F2, associating the non-provided information with the current call, and then sharing the non-provided information with the terminal.
After answering based on the standard information, the caller is asked, the question corresponding to the specific answer which does not correspond is recorded as the non-provided information, and the non-provided information is associated with the current call and then is shared to the terminal, so that the terminal can perform the corresponding answer.
Further, after the calling with the caller based on the reply message, the method further includes:
g1, after the communication with the caller is completed based on the reply information, summarizing the communication information in the communication process;
g2, sharing the collected call information to the terminal;
g3, saving the call record of the call with the caller based on the reply message for the user to inquire.
After the call is finished, the call information is further gathered, and the gathered call information is shared to the terminal, wherein the call information can comprise provided information, non-provided information and the like, and can also comprise non-provided information only, so that a user can specifically contact a caller aiming at the call information when the terminal is in an available state, or the caller is not required to be contacted according to the judgment of the call information, thereby reducing unnecessary reply, reducing repeated communication, improving the user efficiency and improving the intelligent degree of voice response. And further saving a call record of the call with the caller based on the reply message for the user to inquire.
The method comprises the steps of acquiring a voice call request of a terminal corresponding to a voice response request when the voice response request is received; acquiring caller information for initiating the voice call request; acquiring corresponding reply information according to the caller information; the call is carried out with the caller based on the reply information, even if the terminal is in a condition that the call cannot be answered, the call can be carried out through a voice response system, and the situation that the call cannot be carried out when the terminal is in a condition that the call cannot be answered is avoided, so that various emergency situations can be dealt with, for example, the terminal is suddenly powered off or has no signal and the like; and when the terminal is in the state of unable answering, based on caller's information, carry on the pertinence conversation, avoid carrying on the mechanical reply through the fixed speech technology, thus improve the intelligent degree of the voice response, and facilitate users to arrange the conversation business more flexibly.
Further, the embodiment of the application can also provide a voice response method, which is applied to a terminal. As shown in fig. 4, the specific flow of the voice response method may be as follows:
401, when receiving a voice call request, detecting the answering state of the terminal;
402, if the answering state of the terminal is in the non-answering state, sending a voice response request to the voice response system.
When the terminal receives a voice call request, detecting the answering state of the terminal, if the terminal is in an unavailable answering state at the moment, such as receiving a refusing instruction, or the terminal does not answer after a preset time, such as 30s and 1 minute, determining that the user is in an unavailable answering state due to busy and other reasons at the moment, determining that the terminal is in an unavailable answering state, triggering a voice response request at the moment, and sending the voice response request to a voice response system. Optionally, when the terminal receives the voice call request, the terminal may first obtain information of a caller initiating the voice call request, determine whether the information matches the information in the predetermined conversation process, and if the information does not match, not forward the voice response request to the voice response system; and when the matching is carried out, the voice response request is transferred to the voice response system.
Further, before receiving the voice call, the session schedule and the session information may be received in advance, that is, before step 401, the method further includes:
h1, receiving a predetermined dialog trip and dialog information, wherein the predetermined dialog trip comprises caller information and/or a predetermined calling time;
h2, sending the preset dialogue journey and the dialogue information to the voice response system.
Receiving a predetermined dialog trip including caller information or a predetermined call time and dialog information, which may be in a text form or a voice form, and then transmitting the predetermined dialog trip and the dialog information to a voice response system.
In order to better implement the above method, the embodiment of the present application may further provide a voice response device.
For example, as shown in fig. 5a, the voice response apparatus may include a first obtaining unit 501, a second obtaining unit 502, a third obtaining unit 503 and a talking unit 504, as follows:
(1) first acquisition unit 501
A first obtaining unit 501, configured to obtain, when a voice response request is received, a voice call request of a terminal corresponding to the voice response request.
Specifically, the voice response request may be obtained by terminal transmission, or by detecting a situation such as terminal communication. When the terminal receives the voice call request, if the terminal can communicate at the moment, and receives a rejection instruction, or does not answer after a preset time, such as 30s and 1 min, it indicates that the user is in a state of unable to answer due to reasons such as busy and the like at the moment, and at the moment, the voice response request can be triggered and sent to the voice response system, and at the moment, the voice response system can obtain the voice response request in a receiving mode. Optionally, when the terminal receives the voice call request, the terminal may first obtain information of a caller initiating the voice call request, and determine whether the information matches the information in the predetermined conversation process, if not, the terminal does not forward the voice call request to the voice response system; and when the matching is performed, the voice call request is transferred to the voice response system.
Or, when the other user initiates the voice call request and the terminal is in a no-signal state or a no-power state, the voice response request may be actively detected, where the specific detection includes detecting the terminal state, for example, detecting the signal condition of the terminal, detecting the battery power of the terminal, and determining that the voice response request is detected if the terminal detects that the terminal receives the voice call request and does not answer the voice call request for more than a preset time, such as 30s or 1 min.
(2) Second acquisition unit 502
A second obtaining unit 502, configured to obtain caller information for initiating the voice call request.
Wherein the caller's information may be obtained through the communication number, or personal account, from which the caller originated the call.
(3) Third acquisition unit 503
A second obtaining unit 503, configured to obtain corresponding reply information according to the caller information.
After the caller information is obtained, the corresponding reply information can be obtained through the caller information according to the mapping relation between the voice information and the preset conversation journey which is established in advance.
(4) Talking unit 504
A talking unit 504 for talking with the caller based on the reply message.
After obtaining the reply message, the voice response system can communicate with the caller based on the reply message.
Specifically, as shown in fig. 5b, the voice response apparatus further includes a receiving unit 505 and a storing unit 506, specifically:
a receiving unit 505, configured to receive a predetermined conversation process of a terminal and conversation information, where the predetermined conversation process includes caller information and/or a predetermined call time;
the storage unit 506 is configured to classify the dialog information, establish a mapping relationship between the classified dialog information and the predetermined dialog travel, and store the dialog information as a reply information.
The method comprises the steps of firstly receiving a preset conversation process sent by a terminal and conversation information input by a user, wherein the preset conversation process can comprise call time or caller information, for example, a 10 month 10 afternoon three-point call with Mr. client, and the conversation information is information that the user needs to interact with the caller when in a call, wherein the method for inputting the conversation information by the user can comprise voice input or text input. After the dialog information input by the user is obtained, the dialog information is firstly sorted, unnecessary interference information is frequently removed, then the dialog information is classified, and after a mapping relation is established between the classified dialog information and a preset dialog stroke, the classified dialog information is stored and used as reply information.
Specifically, as shown in fig. 5c, the storage unit includes an extracting sub-unit 507, a first sharing sub-unit 508, a receiving sub-unit 509, and a first storage sub-unit 510, specifically:
an extracting subunit 507, configured to extract necessary information in the dialog information through a trained machine learning model, and classify the necessary information;
a first sharing subunit 508, configured to share the classified necessary information to the terminal;
a receiving subunit 509, configured to receive correction information fed back by the terminal based on the classified necessary information;
the first storage subunit 510 is configured to correct the classified necessary information based on the correction information, and store the corrected necessary information and a predetermined dialog trip after establishing a mapping relationship, and use the mapping relationship as a reply information.
Specifically, feature extraction is performed on the dialogue information through a trained Machine Learning model, and specifically, feature selection can be performed based on a filtering feature selection method, wherein the filtering feature selection method is to calculate the probability of each feature in the dialogue information through a certain statistical measurement method, and then select or reject the features in the dialogue information according to the probability, so as to achieve the purpose of feature selection. And then, identifying necessary information in the dialogue information according to the selected characteristics, removing the unnecessary information, and classifying the necessary information. In the specific implementation process, the necessary information can be divided into 5 types, which specifically include: (a) key information, which is important information that the caller may need to know or the user needs to deliver, and that the caller needs to be informed proactively even if the caller does not make a request; (b) the system can acquire information which can be acquired by a caller, and the voice response system can not actively inform the caller and only provides the information when the caller actively inquires; (c) the leisure information is information for providing leisure and conversation etiquettes, has no practical significance, and is information interspersed in the conversation process for showing the etiquettes and improving the conversation experience of callers. Further, standard information can be added to the reply information, wherein (d) the standard information is standard terms for replying when the caller asks a question but there is no corresponding reply answer in the reply information, wherein a plurality of standard terms can be set for replying the caller with different roles correspondingly, so that communication can be performed with the caller through the standard information when there is no corresponding reply answer in the reply information. The reply message may further include query message, (e) the query message is a query from the user terminal and is provided only when the user terminal queries. Further, after the call is finished, the category of the unavailable information can be further increased according to the actual situation of the call, (f) the unavailable information is a problem that the caller asks but does not provide information in the call process. Therefore, after the caller finishes the call, when the user checks the call record, the corresponding information is provided to the caller in time according to the unavailable information.
And then, the classified necessary information is shared to the terminal, the terminal can provide feedback information according to the classification condition of the necessary information, and at the moment, the machine learning model changes the feedback information of the terminal and records and learns the feedback information, such as changing or adding and deleting the classification information, so that the classification accuracy of the dialogue information is improved during subsequent classification. It can be understood that the process of the machine learning model based on the corrected information fed back by the terminal is also the process of the machine learning model training in real time. And then establishing a mapping relation between the corrected necessary information and the preset dialogue journey, and storing the information as reply information. Therefore, the conversation between the voice response system and the caller is more orderly, the mechanical playing is avoided, the omission of key information is also avoided, the intelligent degree of voice response is improved, and the user experience is improved.
As can be seen from the above, in the voice response apparatus of this embodiment, when receiving a voice response request, the first obtaining unit 501 obtains a voice call request of a terminal corresponding to the voice response request; acquiring caller information for initiating the voice call request through a second acquiring unit 502; acquiring corresponding reply information according to the caller information through a third acquiring unit 503; the call unit 504 is used for making a call with the caller based on the reply information, so that even if the terminal cannot answer, the call can be made through the voice response system, and the situation that the terminal cannot answer is avoided, so that the call can be made under various emergency situations, such as sudden power failure of the terminal or no signal and the like; and when the terminal is in the state of being unable to answer, based on the caller information, the terminal carries on the pertinence conversation, avoid carrying on the mechanical reply through the fixed talk skill, thus improve the intelligent degree of the voice response, and facilitate users to arrange the conversation business more flexibly.
It will be understood by those skilled in the art that all or part of the steps in the methods of the above embodiments may be performed by instructions or by instructions controlling associated hardware, and the instructions may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application provide a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the voice response methods provided by the embodiments of the present application. For example, the instructions may perform the steps of:
when a voice response request is received or acquired, acquiring a voice call request of a terminal corresponding to the voice response request;
acquiring caller information for initiating the voice call request;
acquiring corresponding reply information according to the caller information;
and carrying out a call with the caller based on the reply message.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the computer-readable storage medium can execute the steps in any voice response method provided in the embodiments of the present application, the beneficial effects that can be achieved by any voice response method provided in the embodiments of the present application can be achieved, for details, see the foregoing embodiments, and are not described herein again.
The voice response method, the voice response device, the voice response controller, and the computer-readable storage medium provided in the embodiments of the present application are described in detail above, and a specific example is applied to illustrate the principles and implementations of the present application, and the description of the embodiments above is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (15)
1. A voice response method is applied to a voice response system and is characterized by comprising the following steps:
when a voice response request is received, acquiring a voice call request of a terminal corresponding to the voice response request;
acquiring caller information for initiating the voice call request;
acquiring corresponding reply information according to the caller information;
and calling the caller based on the reply message.
2. The voice response method according to claim 1, wherein when detecting the voice response request and before acquiring the voice call request of the terminal corresponding to the voice response request, the method further comprises:
receiving a preset conversation travel and conversation information of a terminal, wherein the preset conversation travel comprises caller information and/or preset calling time;
and classifying the dialogue information, establishing a mapping relation between the classified dialogue information and the preset dialogue stroke, and storing the dialogue information to be used as reply information.
3. The voice response method according to claim 2, wherein the classifying the dialogue information, and storing and using the classified dialogue information as the reply information after establishing a mapping relationship with a predetermined dialogue trip comprises:
extracting necessary information in the dialogue information through a trained machine learning model, and classifying the necessary information;
sharing the classified necessary information to the terminal;
receiving correction information fed back by the terminal based on the classified necessary information;
and correcting the classified necessary information based on the correction information, establishing a mapping relation between the corrected necessary information and a preset dialogue trip, and storing the mapping relation to be used as reply information.
4. The voice response method according to claim 2, wherein the classifying the dialogue information, and storing the classified dialogue information as the reply information to the voice response system after establishing a mapping relationship with a predetermined dialogue trip, further comprises:
when the dialogue information is text information, translating the dialogue information into voice information;
and establishing a mapping relation between the voice information and a preset conversation stroke, and then storing the voice information and the preset conversation stroke as reply information.
5. The voice response method according to claim 1, wherein the obtaining of the corresponding reply information according to the caller information comprises:
acquiring preset conversation information of the terminal, wherein the preset conversation information comprises caller information and/or preset calling time;
comparing the preset calling time with the current time to obtain a time difference value;
and if the time difference value meets the acquisition condition, acquiring corresponding reply information according to the caller information.
6. The voice response method according to claim 1, wherein the reply message includes a first reply message, a second reply message and a third reply message, and the calling party is conversed with based on the reply message, including:
when the call with the caller based on the reply information is connected, replying based on the first reply information;
if the inquiry of the caller is received and the reply information has the reply corresponding to the question inquired by the caller, replying based on the second reply information;
and if the inquiry of the caller is received and the reply information does not have a reply corresponding to the question inquired by the caller, replying based on the third reply information.
7. The voice response method according to claim 6, further comprising, after said calling the caller based on the reply message:
recording inquiry information corresponding to reply based on the third reply information as non-provided information;
and sharing the information which is not provided with the information to the terminal after the information which is not provided with the information is associated with the current call.
8. The voice response method according to claim 6, wherein the first reply information includes key information, leisure information, and inquiry information; the second reply message comprises an acquaintance message; the third reply message comprises standard information, and the conversation with the caller based on the reply message comprises:
when a call with a caller based on the reply information is connected, replying based on the leisure information;
after replying based on the leisure information, replying based on the key information;
if the inquiry of the caller is received and the reply information has the reply corresponding to the question inquired by the caller, replying based on the acquaintable information;
and if the inquiry of the caller is received and the reply information does not have the reply corresponding to the question inquired by the caller, replying based on the standard information.
9. The voice response method according to any one of claims 1 to 8, further comprising, after having made a call with the caller based on the reply message:
gathering call information in the call process;
sharing the summarized call information to the terminal;
and saving the call record of the call with the caller based on the reply information for the user to inquire.
10. A voice response method is applied to a terminal, and is characterized by comprising the following steps:
when a voice call request is received, detecting the answering state of the terminal;
and if the answering state of the terminal is in the non-answering state, sending a voice response request to a voice response system.
11. The voice response method according to claim 10, wherein before detecting the listening state of the terminal when the voice call request is received, further comprising:
receiving a predetermined conversation schedule and conversation information, wherein the predetermined conversation schedule comprises caller information and/or a predetermined call time;
and sending the preset conversation journey and the conversation information to the voice response system.
12. A voice response apparatus, comprising:
the first acquisition unit is used for acquiring a voice call request of a terminal corresponding to a voice response request when the voice response request is received;
a second obtaining unit, configured to obtain caller information for initiating the voice call request;
a third obtaining unit, configured to obtain corresponding reply information according to the caller information;
and the communication unit is used for communicating with the caller based on the reply information.
13. A voice response apparatus, comprising:
the detection unit is used for detecting the answering state of the terminal when receiving a voice call request;
and the sending unit is used for sending a voice response request to the voice response system if the answering state of the terminal is in the non-answering state.
14. A voice response controller, comprising: a processor and a memory; the memory stores a plurality of instructions that the processor loads to perform the voice response method of any of claims 1-9, or 10-11.
15. A computer-readable storage medium storing instructions adapted to be loaded by a processor to perform the voice response method of any of claims 1-9 or 10-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110579.7A CN114827360A (en) | 2021-01-27 | 2021-01-27 | Voice response method, device, controller and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110579.7A CN114827360A (en) | 2021-01-27 | 2021-01-27 | Voice response method, device, controller and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114827360A true CN114827360A (en) | 2022-07-29 |
Family
ID=82524935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110110579.7A Pending CN114827360A (en) | 2021-01-27 | 2021-01-27 | Voice response method, device, controller and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827360A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030068693A (en) * | 2002-02-15 | 2003-08-25 | 남기식 | Auto response telephone by using voice recognition |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103179524A (en) * | 2013-04-15 | 2013-06-26 | 陈财淦 | Intelligent response system based on intelligent communication terminal |
| CN105162980A (en) * | 2015-08-31 | 2015-12-16 | 小米科技有限责任公司 | Call processing method and device |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| CN111818213A (en) * | 2020-07-22 | 2020-10-23 | 维沃移动通信有限公司 | Call response method and device and electronic equipment |
| CN112069801A (en) * | 2020-09-14 | 2020-12-11 | 深圳前海微众银行股份有限公司 | Sentence backbone extraction method, equipment and readable storage medium based on dependency syntax |
-
2021
- 2021-01-27 CN CN202110110579.7A patent/CN114827360A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030068693A (en) * | 2002-02-15 | 2003-08-25 | 남기식 | Auto response telephone by using voice recognition |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103179524A (en) * | 2013-04-15 | 2013-06-26 | 陈财淦 | Intelligent response system based on intelligent communication terminal |
| CN105162980A (en) * | 2015-08-31 | 2015-12-16 | 小米科技有限责任公司 | Call processing method and device |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| CN111818213A (en) * | 2020-07-22 | 2020-10-23 | 维沃移动通信有限公司 | Call response method and device and electronic equipment |
| CN112069801A (en) * | 2020-09-14 | 2020-12-11 | 深圳前海微众银行股份有限公司 | Sentence backbone extraction method, equipment and readable storage medium based on dependency syntax |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104202491B (en) | Method for handling customer service telephone call and device thereof | |
| CN110891124A (en) | System for artificial intelligence pick-up call | |
| CN109672786B (en) | Incoming call answering method and device | |
| CN103888581B (en) | A kind of communication terminal and its method for recording call-information | |
| CN107995360A (en) | Call handling method and Related product | |
| CN105578439A (en) | Incoming call transfer intelligent answering method and system for call transfer platform | |
| CN109995953A (en) | A kind of system and method for intelligence electricity pin | |
| CN107920154A (en) | The processing method and terminal of Stranger Calls | |
| CN108683810A (en) | Call processing method, device, intelligent sound box and storage medium | |
| CN103634448A (en) | Method for intelligently responding to incoming calls by voice | |
| US20120077469A1 (en) | Automated electronic messaging to a person with whom another form of communication is exchanged | |
| CN112153223B (en) | Method for voice assistant to recognize and execute called user instruction and voice assistant | |
| CN113779217A (en) | Intelligent voice outbound service method and system based on human-computer interaction | |
| CN114827360A (en) | Voice response method, device, controller and computer readable storage medium | |
| CN108182942B (en) | Method and device for supporting interaction of different virtual roles | |
| CN115118820A (en) | Call processing method and device, computer equipment and storage medium | |
| CN112261234B (en) | Method for voice assistant to execute local task and voice assistant | |
| CN112291432B (en) | Method for voice assistant to participate in call and voice assistant | |
| CN108769277A (en) | Contact person adding method and device of address list, communication terminal and storage medium | |
| JP2007336237A (en) | Speech-recording control system for call center and its method | |
| CN107864262A (en) | Incoming call screen method and device | |
| CN101170789A (en) | Method for mobile terminal to record failure path | |
| CN113744741B (en) | Method and device for recognizing telephone answering behavior | |
| CN110300229A (en) | Call answering method, device and terminal | |
| CN109587346A (en) | Call management method, mobile terminal 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 |