CN110275948B - Free jump method, device and medium for self-service - Google Patents
Free jump method, device and medium for self-service Download PDFInfo
- Publication number
- CN110275948B CN110275948B CN201910463012.0A CN201910463012A CN110275948B CN 110275948 B CN110275948 B CN 110275948B CN 201910463012 A CN201910463012 A CN 201910463012A CN 110275948 B CN110275948 B CN 110275948B
- Authority
- CN
- China
- Prior art keywords
- service
- dimension
- service request
- nodes
- voice
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000009191 jumping Effects 0.000 claims abstract description 10
- 230000014509 gene expression Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims 6
- 230000005540 biological transmission Effects 0.000 description 8
- 238000012546 transfer Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012550 audit Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/954—Navigation, e.g. using categorised browsing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to voice semantics, and provides a free jump method for self-service, which comprises the following steps: setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service; identifying a service request input by voice of a user side; identifying an exit node corresponding to the service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting an exit node query result to a user side; broadcasting a next voice instruction corresponding to the query result to the user terminal; when the next service request input by the user end is not matched with the next voice instruction, the user end is judged to be re-hearing refusal; and taking the next service determined as the re-listening refused service as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next service request in a question-answer matching mode, and directly jumping to the outlet node. The invention also provides an electronic device and a storage medium. The invention avoids repeated incoming lines.
Description
Technical Field
The invention relates to the technical field of voice semantics, in particular to a free jump method, a device and a medium for self-service.
Background
With the development and application of intelligent voice recognition technology, various scenes can deeply mine the operation intention of a user aiming at a credit card telephone voice incoming channel. In the voice interaction, when a user inquires about one item of information, the user does not want to reburn the voice, but suddenly wants to inquire about another item of information, and must return to the first layer to reburn to inquire about another item of information, so that the user can inquire about another item of information, for example, when the user inquires about "credit card bill", inquires about the current bill information and reports the current bill information to the user, and simultaneously reports the voice "whether to reburn once or to continue to listen to the next item? The user does not want to listen to the voice again, but suddenly wants to inquire about the available credit, and the user must return to the first layer, and can enter the available credit inquiry after re-speaking the credit card available credit inquiry, repeatedly enter the line, and the time for the user to navigate to the target node is longer, so that the user service experience is reduced.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a free jump method, an electronic device and a storage medium for self-service, which can reduce the time for a user to navigate a target node, improve the user service experience, and avoid repeated incoming lines.
In order to achieve the above object, the present invention provides an electronic device, including a memory and a processor, where the memory includes a self-service free jump program, and the self-service free jump program when executed by the processor implements the following steps:
setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service;
identifying a service request input by voice of a user side;
Identifying an exit node corresponding to the service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting a query result of the exit node to a user side;
broadcasting a next voice instruction corresponding to the query result to a user terminal;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
and taking the next service determined as the re-listening refused service as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next service request in a question-answer matching mode, and directly jumping to the outlet node.
In addition, in order to achieve the above object, the present invention further provides a free jump method for self-service, including:
setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service;
identifying a service request input by voice of a user side;
Identifying an exit node corresponding to the service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting a query result of the exit node to a user side;
broadcasting a next voice instruction corresponding to the query result to a user terminal;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
and taking the next service determined as the re-listening refused service as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next service request in a question-answer matching mode, and directly jumping to the outlet node.
Preferably, the method for configuring the question-answer matching mode includes:
And providing the webpage user side for service personnel, and adding or deleting different questions or expressions of the user side by the service personnel to corresponding nodes.
Further, preferably, the method for configuring the question-answer matching manner further includes: by adding service dimensions in the webpage user side, the user side obtains answers of a plurality of service dimensions of the corresponding node of the service request by inquiring the service request.
In addition, preferably, the method for configuring the question-answer matching mode further includes:
Taking keywords of query service as standard questions;
Setting other problems similar to the standard problem;
setting answers corresponding to the standard questions and the similar questions, wherein the answers are nodes with service dimensions corresponding to the standard questions and the similar questions.
Preferably, the step of determining that the re-hearing is refusal further includes:
Judging whether the next service request is in a valid dimension, wherein the valid dimension is the service dimension in which an exit node of the last service request corresponding to the next service request is located;
If the service request is in the effective dimension, matching with the next service request in other outlet nodes to obtain an outlet node corresponding to the next service request;
and if the service dimension is not in the effective dimension, matching other service dimensions with the next service request to obtain the service dimension and the outlet node corresponding to the next service request.
Further, preferably, the step of determining that the re-hearing is refusal includes:
judging whether the next step of service request input by the user terminal is matched with nodes of other service dimensions or other nodes of effective dimensions;
if the result is not matched, the user terminal judges that the user terminal completely re-listens for refusal, and sends an alarm signal of the result which is not found to the user terminal.
In addition, preferably, the step of directly skipping to the exit node further includes the steps of taking the next service determined as refusal as a question, taking other exit nodes as answers, searching the exit node corresponding to the next service request in a question-answer matching manner:
And returning a query result corresponding to the next service request, and returning a query pointer to an original skip position, wherein the query pointer is a query starting service dimension of the service query input by the user side, and the original skip position is a position corresponding to the next voice indication corresponding to the service request before the next service.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, where the computer readable storage medium includes a self-service free jump program, and when the self-service free jump program is executed by a processor, the steps of the self-service free jump method are implemented.
The free jump method, the electronic device and the computer readable storage medium for self-service provided by the invention have the advantages that the judgment of re-listening rejection is set, the self-service method, the electronic device and the computer readable storage medium can quickly jump to the service node of the target in a configurable 'question-answer' mode, the regret is supported, the self-service path time of a user entering the target is reduced, the user satisfaction is improved, and repeated incoming lines are avoided.
Drawings
FIG. 1 is a schematic view of an application environment of a preferred embodiment of a free jump method of self-service according to the present invention;
FIG. 2 is a block diagram of a preferred embodiment of the free jump procedure of the self-service of FIG. 1;
FIG. 3 is a flow chart of a preferred embodiment of the free jump method of self-service of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention provides a free jump method for self-service, which is applied to an electronic device 1. Referring to fig. 1, an application environment of a preferred embodiment of a free jump method for self-service according to the present invention is shown.
In this embodiment, the electronic device 1 may be a terminal having an operation function, such as a server, a mobile phone, a tablet computer, a portable computer, or a desktop computer.
The electronic device 1 comprises a memory 11, a processor 12, a network interface 13 and a communication bus 14.
The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as flash memory, a hard disk, a multimedia card, a card memory, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. In other embodiments, the readable storage medium may also be an external memory of the electronic device 1, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1.
In the present embodiment, the readable storage medium of the memory 11 is generally used for storing a self-service free-jump program 10 or the like installed in the electronic apparatus 1. The memory 11 may also be used for temporarily storing data that has been output or is to be output.
The processor 12 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as the free-jump program 10 for performing self-service, etc.
The network interface 13 may optionally comprise a standard wired interface, a wireless interface (e.g. WI-FI interface), typically used to establish a communication connection between the electronic device 1 and other electronic clients.
The communication bus 14 is used to enable connected communication between these components.
Fig. 1 shows only an electronic device 1 with components 11-14, but it is understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
Optionally, the electronic device 1 may further include a user interface, which may include an input unit such as a Keyboard (Keyboard), a voice input device such as a microphone (microphone) and the like, a user terminal with a voice recognition function, a voice output device such as a sound box, a headset and the like, and optionally, a standard wired interface, a wireless interface.
Optionally, the electronic device 1 may also comprise a display, which may also be referred to as a display screen or display unit.
In some embodiments, the display may be an LED display, a liquid crystal display, a touch-control liquid crystal display, an Organic Light-Emitting Diode (OLED) touch device, or the like. The display is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
Optionally, the electronic device 1 further comprises a touch sensor. The area provided by the touch sensor for the user to perform a touch operation is referred to as a touch area. Further, the touch sensors described herein may be resistive touch sensors, capacitive touch sensors, and the like. The touch sensor may include not only a contact type touch sensor but also a proximity type touch sensor. Furthermore, the touch sensor may be a single sensor or may be a plurality of sensors arranged in an array, for example.
Optionally, the electronic device 1 may further include logic gates, sensors, audio circuits, etc., which are not described herein.
In the embodiment of the apparatus shown in fig. 1, a memory 11, which is a computer storage medium, may include an operating system and a self-service free jump program 10; the processor 12, executing the self-service free jump program 10 stored in the memory 11, implements the following steps:
setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service;
identifying a service request input by voice of a user side;
identifying an exit node corresponding to a service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting a query result of the exit node to a user side, wherein the exit node is a destination node of a data packet of the service dimension corresponding to the service request;
broadcasting a next voice instruction corresponding to the query result to a user terminal;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
and taking the next service determined as the re-listening refused service as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next service request in a question-answer matching mode, and directly jumping to the outlet node.
Preferably, the question-answer matching method includes:
a standard problem submodule taking keywords of the query service as a standard question;
A similar problem sub-module for setting other problems similar to the standard problem;
And the answer sub-module is used for storing answers corresponding to the questions of the standard question sub-module and the similar question sub-module, wherein the answers are nodes with service dimensions corresponding to the standard questions and the similar questions.
In other embodiments, the self-service free-jump program 10 may also be partitioned into one or more modules, one or more modules being stored in the memory 11 and executed by the processor 12 to complete the present invention. The invention may refer to a series of computer program instruction segments capable of performing a specified function. Referring to FIG. 2, a functional block diagram of a preferred embodiment of the self-service free-jump program 10 of FIG. 1 is shown. The self-service free jump program 10 performs dynamic configuration of the document at the front end according to the application program at the background, and may be divided into:
The self-service system 100 comprises a first layer 110 and a lower layer 120, wherein:
The first layer 110 includes a voice recognition module 111, a navigation module 112, a first transmission module 113 and a broadcasting module 114, where the voice recognition module recognizes a service request input by a user end by voice, the navigation module recognizes an exit node through voice navigation, the first transmission module transfers a speech path to a lower layer, sends the exit node to the lower layer and transmits a query result of the lower layer and a next voice instruction to the broadcasting module, and the broadcasting module broadcasts the query result to the user end;
The lower layer 120 includes a storage module 121, a second transmission module 122, a question-answer module 123, and a judgment module 124, where:
The storage module 121 stores a service dimension and a plurality of nodes corresponding to each service dimension, wherein the service dimension comprises one or more of a credit card dimension, a debit card dimension, a fund dimension, a stock dimension and a policy dimension, and the nodes are divided according to the service;
The question-answer module 123 includes an answer corresponding to the question, and matches the answer with the exit node as the exit information;
the second transmission module 122 receives the exit node of the first transmission module 113, transfers the speech path to the service dimension corresponding to the exit node of the storage module, enters the exit node in the service dimension, and returns the query result and the next voice instruction to the first layer;
The judging module 124 judges whether the next service request input by the user end is matched with the next voice prompt, if so, sends a signal to the second transmission module, transfers the voice channel to the exit node corresponding to the next service request, and returns the query result to the upper layer; and if the next service request is not matched with the next voice prompt, judging that the next service request is refused to be reinitiated, sending a signal to a question-answer module, wherein the question-answer module takes the next service request judged to be reinitiated to be refused as a question to obtain corresponding outlet information, sending the outlet information to a second transmission module, and directly jumping to a corresponding outlet node by the second transmission module according to the outlet information.
Preferably, the question-answer module 123 includes:
a standard problem submodule taking keywords of the query service as a standard question;
A similar problem sub-module for setting other problems similar to the standard problem;
And the answer sub-module is used for storing the export information corresponding to each question of the standard question sub-module and the similar question sub-module.
Preferably, the method for configuring the question-answer module includes:
And providing the webpage user end for service personnel of the self-service system, and adding or deleting different questions or expressions by the service personnel to the target node of the lower layer.
In addition, the invention also provides a free jump method for self-service. Referring to FIG. 3, a flow chart of a preferred embodiment of a free jump method for self-service according to the present invention is shown. The method may be performed by an apparatus, which may be implemented in software and/or hardware.
In this embodiment, the free jump method of self-service includes:
Step S1, a plurality of service dimensions are set, each service dimension corresponds to a plurality of nodes, the service dimensions comprise one or more of credit card dimensions, debit card dimensions, fund dimensions, stock dimensions, policy keeping dimensions and the like, the nodes are divided according to services, such as bill inquiring nodes, balance inquiring nodes, card handling inquiring nodes, card clearing inquiring nodes and the like, preferably, the nodes are arranged in a layered mode, such as credit card dimensions are head nodes, the child nodes under the head nodes comprise bill nodes, credit limit nodes and password nodes, the child nodes under the bill nodes comprise home bill nodes, history bill nodes and non-bill nodes, the child nodes under the credit limit nodes comprise available credit nodes, fixed credit nodes and temporary credit nodes, the child nodes under the password nodes comprise password setting nodes, password inquiring nodes and secret modifying nodes, different service dimensions can be provided with different nodes according to different services, such as debit card dimensions can also comprise account transfer nodes and policy keeping nodes;
Step S2, identifying a service request input by voice of a user terminal;
Step S3, identifying an exit node corresponding to the service request through voice navigation, transferring a voice channel to a service dimension corresponding to the exit node, entering the exit node in the service dimension, broadcasting a query result of the exit node to a user side, wherein, for example, a credit card dimension and a debit card dimension are respectively provided with a bill query node and a balance query node, when the service request input by the user side through voice is 'credit card present bill query', the credit card dimension is reached, and when the service request reaches the bill query node in the credit card dimension, the bill query sub-node in the present bill is further reached;
When the user side obtains a broadcasted query result corresponding to a service request through the self-service system, in step S4, broadcasting a next voice instruction corresponding to the query result to the user side, where the voice instruction includes one or more of "whether to listen again for one time", "whether to listen to the next piece", "whether to query an x service request related to the query result", and the like;
When the next service request input by the user side does not match the next voice prompt, in step S5, it is determined that the next voice prompt is inauthentic, for example, "whether to re-listen once or continue listening to the next voice prompt? The user side says "yes", "no" or "next" intention, finally recognizes as re-hearing or not re-hearing, and continues to hear, and the user side says "credit card available credit inquiry" as re-hearing refusal;
And S6, taking the next service determined as refused as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next service request in a question-answer matching mode, and directly jumping to the outlet node.
In one embodiment of the present invention, the method for configuring the question-answer matching manner includes:
And providing the webpage user side for service personnel, and adding or deleting different questions or expressions of the user side by the service personnel to corresponding nodes.
Preferably, the method for configuring the question-answer matching mode further includes: by adding service dimensions to the webpage user side, the user side obtains answers of a plurality of service dimensions of a node corresponding to the service request by inquiring one service request, for example, the user side can obtain bills of different dimensions such as credit card, debit card and the like of the user side through the service request of credit card bill.
In addition, preferably, the method for configuring the question-answer matching mode further includes:
taking keywords of the query service as standard questions, for example, the standard questions are "available credit query";
Other questions similar to the standard questions are set, as for example, the similar question may be "i want to check the available credit? "," what the my available credit is, "etc.;
And setting answers corresponding to the standard questions and the similar questions, wherein the answers are nodes with service dimensions corresponding to the standard questions and the similar questions, and for example, the available quota is x.
In one embodiment of the present invention, after the step of determining that the re-listening is refusal, the method further includes:
Judging whether the next service request is in a valid dimension, wherein the valid dimension is the service dimension in which an exit node of the last service request corresponding to the next service request is located;
If the service request is matched with the next service request in other outlet nodes of the lower layer in the effective dimension, an outlet node corresponding to the next service request is obtained;
and if the service dimension is not in the effective dimension, matching other service dimensions of the lower layer with the next service request to obtain the service dimension and the outlet node corresponding to the next service request.
Preferably, the step of determining that the re-hearing is refusal includes:
Judging whether the next step of service request input by the user terminal is matched with the nodes of other service dimensions of the lower layer or other nodes of effective dimensions;
If the two voice instructions are not matched, the judgment is that the voice instructions are completely re-listened and refused, an alarm signal of the result which is not found is sent to the user side, and the step that the lower layer reports the voice instructions of the next step corresponding to the inquiry result to the user side through the first layer can be returned, for example, "I don't know what you mean, please ask for a report for you again.
In one embodiment of the present invention, the step of directly jumping to the corresponding exit node according to the exit information further includes:
Returning a query result corresponding to the next service request, returning a query pointer to a first layer or returning the query pointer to an original skip position, wherein the query pointer is a query starting service dimension of the service query input by the user side, the original skip position is a next voice indication corresponding to the service request, for example, after the user skips from the application progress query to the available credit query, two return modes exist after completing the self-service of the available credit query, and the method comprises the following steps: returning to the original jump position, i.e. apply for progress inquiry and broadcast, "do please ask you to broadcast one more time? "place; second,: returns directly to the first layer.
In one embodiment of the present invention, a free jump method of self-service includes:
after a user side (for example, a mobile phone or a landline) dials a hotline to input a service request, the user enters a credit card service dimension of a lower layer through first-layer voice recognition of a self-service system, and searches an exit node corresponding to the service request in the credit card service dimension, for example, the service request is "credit card application progress inquiry", after entering the credit card service dimension, the credit card service dimension can also comprise a transfer manual node, an inquiry limit node, a card sending node and the like;
Returning the query result in the application progress node To the first layer, and broadcasting the query result To the user side, wherein the query result comprises passing of the audit, passing of the express delivery, in-process of the audit, audit rejection, to-be-repaired and the like, and broadcasting can be realized through a sip protocol-based interaction flow and broadcasting voice, and can also be realized through voice synthesis TTS (Text-To-specific);
After the query result is broadcast to the user side, continuing to broadcast a next voice instruction, for example, continuing to broadcast whether to listen again;
The first layer transmits a next service request of the user side for the voice input after the next voice instruction to the credit card service dimension, at this time, the credit card service dimension will call the voice recognition module to convert the service request of the user voice input into text, for example Automatic Speech Recognition (ASR) recognition, including acoustic model training, linguistic model training, word segmentation, dictionary, and, for example, natural Language Understanding (NLU): performing word segmentation by adopting a forward maximum matching method, scoring according to the matching degree of different words, comprehensively scoring the highest to obtain a final matching output result, and converting the text into semantics (NLP semantic parsing), wherein the meaning is "good" representing "yes";
judging whether to re-listen rejection or not through a judging module;
if refusal is to be found, the text is sent to a question-answer module, the exit information corresponding to the semantics is obtained, the user directly jumps to an exit node corresponding to the exit information, if the next step of service request input by the user side is 'I want to inquire the available credit', the text is sent to the question-answer module (a supporting configurable matching system based on some matching algorithms) when the judgment module is the refusal of the description of the text, all the descriptions containing 'available credit' are matched into available credit nodes, and the user directly jumps to the available credit nodes;
if the inquiry result is not the re-listening refusal, the first layer carries out repeated broadcasting of set times on the inquiry result, and when the repeated broadcasting times exceeds the set times, voice indication broadcasting of 'turning manual' is carried out.
The credit card service dimension can jump to an available limit node module in the credit card service dimension according to the return result of the question-answer module, thereby achieving the function of free jump.
The question-answer module may also provide a web page client to the service, i.e. the service may be manually configured to add or delete different questions or comments to the target node, for example, such as standard question configuration [ query available credit ], similar questions may be configured [ i want to query available credit? What are my cards available? Etc., and on the answer, the available credit flow names, such as ccsrSubQryAvailableLimit, for the desired jump are configured.
When the re-hearing refusal is carried out, the credit card dimension continuously broadcasts a next voice instruction through the first layer, and when the user terminal does not carry out next service inquiry beyond the set time or the next service inquiry is carried out, the last next service inquiry is sent to the question-answer module.
In addition, the embodiment of the invention also provides a computer readable storage medium, which comprises a self-service free jump program, wherein the self-service free jump program realizes the following steps when being executed by a processor:
The method comprises the steps that a self-service system is built, the self-service system comprises a first layer and a lower layer, the lower layer is used for storing service dimensions and a plurality of nodes corresponding to each service dimension and configuring a question-answer module, the service dimensions comprise one or more of credit card dimensions, debit card dimensions, fund dimensions, stock dimensions and policy dimensions, the nodes are divided according to services, the question-answer module comprises answers corresponding to questions, the answers are used as outlet information and are matched with outlet nodes, the first layer recognizes service requests input by a user side through voice, recognizes the outlet nodes through voice navigation, transfers a speech path to the service dimensions corresponding to the outlet nodes at the lower layer and enters the outlet nodes in the service dimensions, and the lower layer returns query results of the outlet nodes to the first layer and reports the query results of the outlet nodes to the user side through the first layer;
When a user side obtains a broadcasted query result corresponding to a service request through the self-service system, a lower layer broadcasts a next voice instruction corresponding to the query result to the user side through a first layer;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
And obtaining corresponding outlet information of the next service request judged as re-listening refusal through a question-answer module, and directly jumping to a corresponding outlet node according to the outlet information.
Preferably, the method for configuring the question-answer module includes:
And providing the webpage user end for service personnel of the self-service system, and adding or deleting different questions or expressions by the service personnel to the target node of the lower layer.
Further, preferably, the method for configuring the question-answer module further includes: by adding service dimensions in the webpage user side, the user side obtains answers of a plurality of service dimensions of the corresponding node of the service request by inquiring the service request.
In addition, preferably, the method for configuring the question-answer module further includes:
setting a standard problem sub-module, wherein keywords of query service are used as standard problems;
setting a similar problem sub-module and setting other problems similar to the standard problem;
And setting an answer submodule corresponding to the standard question submodule and the similar question submodule, wherein the answer submodule is provided with export information.
Preferably, the step of determining that the re-hearing is refusal further includes:
Judging whether the next service request is in a valid dimension, wherein the valid dimension is the service dimension in which an exit node of the last service request corresponding to the next service request is located;
If the service request is matched with the next service request in other outlet nodes of the lower layer in the effective dimension, an outlet node corresponding to the next service request is obtained;
and if the service dimension is not in the effective dimension, matching other service dimensions of the lower layer with the next service request to obtain the service dimension and the outlet node corresponding to the next service request.
Further, preferably, the step of determining that the re-hearing is refusal includes:
Judging whether the next step of service request input by the user terminal is matched with the nodes of other service dimensions of the lower layer or other nodes of effective dimensions;
if the result is not matched, the user terminal judges that the user terminal completely re-listens for refusal, and sends an alarm signal of the result which is not found to the user terminal.
In addition, preferably, the step of directly skipping to the corresponding exit node according to the exit information further includes:
and returning a query result corresponding to the next service request, wherein a query pointer returns to the first layer or returns to the original jump position, the query pointer is the query starting service dimension of the service query input by the user terminal, and the original jump position is the next voice indication corresponding to the service request.
The embodiments of the computer readable storage medium of the present invention are substantially the same as the embodiments of the free jump method and the electronic device for self-service, and will not be described herein.
The free jump method, the electronic device and the computer readable storage medium for self-service judge the new intention of the service, and additionally add the free jump function, such as the user suddenly wants to inquire the available credit, at the moment, the user conveniently transfers to the available credit node, even if the current operation is at a certain link of inquiring the application progress, that is, the judgment of re-listening rejection is set, the service can rapidly configure questions and answers, and the path time of the user entering the target self-service is reduced through rapid jump during voice interaction, so that the user satisfaction is improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing an end user terminal (which may be a mobile phone, a computer, a server, or a network user terminal, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (5)
1. A method of free jump for self-service, comprising:
setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service; the business dimension comprises one or more of credit card dimension, debit card dimension, fund dimension, stock dimension and policy dimension, and the nodes are divided and arranged in layers according to the business;
identifying a service request input by voice of a user side;
Identifying an exit node corresponding to the service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting a query result of the exit node to a user side;
broadcasting a next voice instruction corresponding to the query result to a user terminal;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
Taking the next step of service judged as re-listening refusal as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next step of service request in a question-answer matching mode, and directly jumping to the outlet node; the method comprises the following steps: judging whether the next step of service request input by the user terminal is matched with the nodes of other service dimensions of the lower layer or other nodes of effective dimensions; if the voice response is not matched with the voice response, judging that the voice response is completely re-listened, sending an alarm signal of a non-found result to the user side, and returning to the lower layer to broadcast a next voice instruction corresponding to the query result to the user side through the first layer;
Returning a query result corresponding to a next service request, and returning a query pointer to an original skip position, wherein the query pointer is a query starting service dimension of a service query input by a user side, and the original skip position is a position of a next voice indication corresponding to a service request before the next service;
the method for configuring the question-answer matching mode further comprises the following steps:
Taking keywords of query service as standard questions;
Setting other problems similar to the standard problem;
Setting answers corresponding to standard questions and similar questions, wherein the answers are nodes with service dimensions corresponding to the standard questions and the similar questions;
the step of determining that the re-hearing is refusal further comprises the following steps:
Judging whether the next service request is in a valid dimension, wherein the valid dimension is the service dimension in which an exit node of the last service request corresponding to the next service request is located;
If the service request is in the effective dimension, matching with the next service request in other outlet nodes to obtain an outlet node corresponding to the next service request;
and if the service dimension is not in the effective dimension, matching other service dimensions with the next service request to obtain the service dimension and the outlet node corresponding to the next service request.
2. The method of claim 1, wherein the method of configuring the question-answer matching means comprises:
And providing the webpage user side for service personnel, and adding or deleting different questions or expressions of the user side by the service personnel to corresponding nodes.
3. The method of claim 2, wherein the method of configuring the question-answer matching means further comprises: by adding service dimensions in the webpage user side, the user side obtains answers of a plurality of service dimensions of the corresponding node of the service request by inquiring the service request.
4. An electronic device comprising a memory and a processor, wherein a self-service free jump program is stored in the memory, and the self-service free jump program when executed by the processor realizes the following steps:
setting a plurality of service dimensions, wherein each service dimension corresponds to a plurality of nodes, and the nodes are divided according to the service; the business dimension comprises one or more of credit card dimension, debit card dimension, fund dimension, stock dimension and policy dimension, and the nodes are divided and arranged in layers according to the business;
identifying a service request input by voice of a user side;
Identifying an exit node corresponding to the service request through voice navigation, transferring a speech path to a service dimension corresponding to the exit node, entering the exit node in the service dimension, and broadcasting a query result of the exit node to a user side;
broadcasting a next voice instruction corresponding to the query result to a user terminal;
When the next step of service request input by the user terminal is not matched with the next step of voice instruction, the user terminal is judged to be refused to be re-listened;
Taking the next step of service judged as re-listening refusal as a question, taking other outlet nodes as answers, searching the outlet node corresponding to the next step of service request in a question-answer matching mode, and directly jumping to the outlet node; the method comprises the following steps: judging whether the next step of service request input by the user terminal is matched with the nodes of other service dimensions of the lower layer or other nodes of effective dimensions; if the voice response is not matched with the voice response, judging that the voice response is completely re-listened, sending an alarm signal of a non-found result to the user side, and returning to the lower layer to broadcast a next voice instruction corresponding to the query result to the user side through the first layer;
Returning a query result corresponding to a next service request, and returning a query pointer to an original skip position, wherein the query pointer is a query starting service dimension of a service query input by a user side, and the original skip position is a position of a next voice indication corresponding to a service request before the next service;
Wherein, the question-answer matching mode comprises:
a standard problem submodule taking keywords of the query service as a standard question;
A similar problem sub-module for setting other problems similar to the standard problem;
The answer sub-module stores answers corresponding to the questions of the standard question sub-module and the similar question sub-module, wherein the answers are nodes with service dimensions corresponding to the standard questions and the similar questions;
the step of determining that the re-hearing is refusal further comprises the following steps:
Judging whether the next service request is in a valid dimension, wherein the valid dimension is the service dimension in which an exit node of the last service request corresponding to the next service request is located;
If the service request is in the effective dimension, matching with the next service request in other outlet nodes to obtain an outlet node corresponding to the next service request;
and if the service dimension is not in the effective dimension, matching other service dimensions with the next service request to obtain the service dimension and the outlet node corresponding to the next service request.
5. A computer readable storage medium, comprising a self-service free-jump program, which when executed by a processor, implements the steps of the self-service free-jump method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463012.0A CN110275948B (en) | 2019-05-30 | 2019-05-30 | Free jump method, device and medium for self-service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463012.0A CN110275948B (en) | 2019-05-30 | 2019-05-30 | Free jump method, device and medium for self-service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110275948A CN110275948A (en) | 2019-09-24 |
| CN110275948B true CN110275948B (en) | 2024-06-25 |
Family
ID=67961182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910463012.0A Active CN110275948B (en) | 2019-05-30 | 2019-05-30 | Free jump method, device and medium for self-service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110275948B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626706A (en) * | 2020-05-27 | 2020-09-04 | 中国联合网络通信集团有限公司 | User intention identification method and device |
| CN112084315B (en) * | 2020-09-07 | 2024-06-11 | 腾讯科技（深圳）有限公司 | Question-answer interaction method, device, storage medium and equipment |
| CN113470649A (en) * | 2021-08-18 | 2021-10-01 | 三星电子（中国）研发中心 | Voice interaction method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680588A (en) * | 2017-05-10 | 2018-02-09 | 平安科技（深圳）有限公司 | Intelligent sound air navigation aid, device and storage medium |
| CN108090177A (en) * | 2017-12-15 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | The generation methods of more wheel question answering systems, equipment, medium and take turns question answering system more |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1723539A4 (en) * | 2004-03-03 | 2009-02-25 | Packetvideo Network Solutions | System and method for retrieving digital multimedia content from a network node |
| CN101867893B (en) * | 2010-06-29 | 2014-09-10 | 中兴通讯股份有限公司 | Method for processing value added service instruction and service management platform equipment |
| CN106407198A (en) * | 2015-07-28 | 2017-02-15 | 百度在线网络技术（北京）有限公司 | Question and answer information processing method and device |
| CN107800897B (en) * | 2017-03-13 | 2020-09-18 | 平安科技（深圳）有限公司 | Dispatching task allocation method and device |
| CN107943878B (en) * | 2017-11-14 | 2022-03-15 | 北京思特奇信息技术股份有限公司 | Business rule engine implementation method and system |
| CN109040485B (en) * | 2018-08-30 | 2020-08-28 | 山东高速股份有限公司 | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing |
-
2019
- 2019-05-30 CN CN201910463012.0A patent/CN110275948B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680588A (en) * | 2017-05-10 | 2018-02-09 | 平安科技（深圳）有限公司 | Intelligent sound air navigation aid, device and storage medium |
| CN108090177A (en) * | 2017-12-15 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | The generation methods of more wheel question answering systems, equipment, medium and take turns question answering system more |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110275948A (en) | 2019-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10389880B1 (en) | Short message service (SMS) response and interpretation application | |
| US9202247B2 (en) | System and method utilizing voice search to locate a product in stores from a phone | |
| US7450698B2 (en) | System and method of utilizing a hybrid semantic model for speech recognition | |
| CN110275948B (en) | Free jump method, device and medium for self-service | |
| US20190035400A1 (en) | Systems and methods to present voice message information to a user of a computing device | |
| CN100578614C (en) | Semantic object synchronous understanding implemented with speech application language tags | |
| US7966176B2 (en) | System and method for independently recognizing and selecting actions and objects in a speech recognition system | |
| US8328089B2 (en) | Hands free contact database information entry at a communication device | |
| US20090304161A1 (en) | system and method utilizing voice search to locate a product in stores from a phone | |
| US20080019496A1 (en) | Method And System For Providing Directory Assistance | |
| US20070047718A1 (en) | System and method to access content from a speech-enabled automated system | |
| CN101292282A (en) | Mobile systems and methods of supporting natural language human-machine interactions | |
| US20010053977A1 (en) | System and method for responding to email and self help requests | |
| US20050124322A1 (en) | System for communication information from a server via a mobile communication device | |
| CN1658635A (en) | Method and system for navigating applications | |
| CN111583931A (en) | Service data processing method and device | |
| JP7481475B2 (en) | Method and device for determining functional areas of dialogue text | |
| CN107105109B (en) | Voice broadcasting method and system | |
| KR20200079107A (en) | Method for providing customized public knowledge information based on chatbot communication and System of the Same | |
| US20050069122A1 (en) | System and method for operator assisted automated call handling | |
| WO2015188454A1 (en) | Method and device for quickly accessing ivr menu | |
| EP1875730A1 (en) | Method and system for searching and ranking entries stored in a directory | |
| KR102406518B1 (en) | Apparatus for filtering received information automatically, system having the same and method thereof | |
| CN104732982A (en) | Method and device for recognizing voice in interactive voice response (IVR) service | |
| JP2009187163A (en) | Questioning and responding apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |