[go: up one dir, main page]

WO2018176705A1 - Appareil et procédé de réponse de service vocal - Google Patents

Appareil et procédé de réponse de service vocal Download PDF

Info

Publication number
WO2018176705A1
WO2018176705A1 PCT/CN2017/095057 CN2017095057W WO2018176705A1 WO 2018176705 A1 WO2018176705 A1 WO 2018176705A1 CN 2017095057 W CN2017095057 W CN 2017095057W WO 2018176705 A1 WO2018176705 A1 WO 2018176705A1
Authority
WO
WIPO (PCT)
Prior art keywords
function
service
voice
node
voice information
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.)
Ceased
Application number
PCT/CN2017/095057
Other languages
English (en)
Chinese (zh)
Inventor
吴震
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN201780058753.XA priority Critical patent/CN109964473B/zh
Publication of WO2018176705A1 publication Critical patent/WO2018176705A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a method and apparatus for voice service response.
  • the service provider When the user needs a service provider to provide a certain service service, the service call provided by the service provider is provided, and the service personnel of the service provider provide the service service to the user. Since the service personnel provide high cost to the user, and because the service personnel are limited, when a large number of users request the same service service at the same time, the service service is slow. Therefore, the service provider provides the user with a self-service voice service, which can provide the same service service to multiple users at the same time.
  • the user needs the communication service provider to provide the service service for the call charge inquiry, and the user dials the service phone of the communication carrier (for example, 10086, etc.).
  • the communication carrier provides the user with a self-service voice service
  • the self-service voice service first gives The user provides the following voice information: For Chinese service, press 1, For English service press 2, the user clicks the number 1 according to the above voice information; then, the self-service voice service provides the following voice information to the user: press 1 for the business inquiry. Please press 2 for mobile phone recharge, press 3 for business processing, and click the number 1 according to the above voice information; then, the self-service voice service will provide the following voice information to the user: press 1 for the phone bill and 2 for the package and traffic query. For historical billing inquiry, please press 3, and the user clicks the number 1 according to the above voice information.
  • the self-service voice service provides the user with a service for querying the call charge.
  • the self-service voice service when used, the user needs to perform multiple operations according to the voice information provided by the self-service voice service to implement the required service service processing.
  • the self-service voice service operation is cumbersome and has poor convenience.
  • the present application provides a method and apparatus for answering a voice service, which searches for a service processing path from a voice service function tree corresponding to a voice service, and automatically responds to a voice service by using a service processing path to implement an automatic response of the voice service.
  • a method for answering a voice service comprising:
  • the service processing path includes a function node and a node operation sequence required for processing the voice service, where the function node includes a function triggering operation, and the node operation sequence is used for Characterizing the function of the function node triggers the execution order of the operations;
  • the response of the voice service is automatically processed according to the service processing path.
  • creating the function node in the voice service function tree includes:
  • the voice service function tree includes a child function node corresponding to the first voice information
  • the child function node includes an identifier of a parent function node, the function identifier, and the function trigger
  • the identifier of the parent function node is used to represent a service function that can be implemented by the first input operation.
  • the first voice information function triggering operation includes a preset user attribute
  • the method further includes:
  • a correspondence between the sub-function node and a value of the preset user attribute is created.
  • the method further includes:
  • the acquiring the voice service function tree corresponding to the voice service includes:
  • Semantic analysis of the request for the voice service to find out whether there is a service processing path corresponding to the voice service;
  • the voice service function tree corresponding to the voice service is obtained.
  • the automatically responding to the voice service according to the service processing path includes:
  • the performing, by the target node, the processing of the second voice information includes:
  • the method further includes:
  • a device for answering a voice service comprising:
  • a receiving module configured to receive a request for a voice service
  • a first acquiring module configured to acquire a voice service function tree of a service provider to which the voice service belongs, where the voice service function tree is created according to voice information sent by a server of the service provider;
  • a search module configured to search for a service processing path from the voice service function tree, where the service processing path includes a function node and a node operation sequence required for processing the voice service, where the function node includes a function triggering operation,
  • the node operation sequence is used to characterize the execution order of the function triggering operation of the function node;
  • a processing module configured to automatically process the response of the voice service according to the service processing path.
  • the device further includes:
  • a sending module configured to send, according to a first input operation of the user, a function request corresponding to the first input operation to a server of the service provider;
  • a receiving module configured to receive first voice information that is sent by the server of the service provider according to the function request
  • a second obtaining module configured to obtain a function identifier and a function triggering operation of the first voice information, where the function identifier is used to represent a service function of the first voice information, and the function triggering operation is used to represent the implementation The operation to be triggered by the service function of the first voice message;
  • a first creating module configured to create a voice service function tree of the service provider, where the voice service function tree includes a child function node corresponding to the first voice information, where the child function node includes an identifier of a parent function node, and the function
  • the identifier, and the corresponding relationship of the function triggering operation, the identifier of the parent function node is used to represent a service function that can be implemented by the first input operation.
  • the first voice information function triggering operation includes a preset user attribute
  • the device further includes:
  • a third acquiring module configured to acquire a value of the preset user attribute in response to the second input operation of the user
  • a second creating module configured to create a correspondence between the sub-function node and a value of the preset user attribute.
  • the device further includes:
  • a storage module configured to store a correspondence between the voice service and the service processing path.
  • the first acquiring module includes:
  • An analyzing unit configured to perform semantic analysis on the request for the voice service, to find whether a service processing path corresponding to the voice service exists;
  • the first obtaining unit is configured to acquire a voice service function tree corresponding to the voice service when the service processing path corresponding to the voice service does not exist.
  • the processing module includes:
  • a receiving unit configured to receive second voice information sent by the service provider
  • a second acquiring unit configured to acquire a function node corresponding to the second voice information from the service processing path, and use the function node as a target node;
  • a processing unit configured to process the second voice information according to the target node.
  • the processing unit includes:
  • a third acquiring unit configured to acquire a function identifier and a function triggering operation in the target node
  • An analyzing unit configured to perform semantic analysis on the second voice information, to identify whether the function identifier of the second voice information matches the second voice information
  • an execution unit configured to: when the function identifier of the second voice information matches the second voice information, perform a function triggering operation of the second voice information, and respond to the second voice information.
  • the device further includes:
  • a playing unit configured to: when the function identifier of the second voice information does not match the second voice information, play the second voice information to a user;
  • an updating unit configured to generate a new function node according to the second voice information, and update the voice service function tree by using the new function node.
  • a device for answering a voice service comprising:
  • a receiver, a processor, a memory, a communication bus, the receiver, and the memory are respectively connected to the processor through the communication bus;
  • the receiver is configured to receive a request for a voice service
  • the memory is configured to store instructions
  • the processor is configured to invoke instruction execution from the memory, the instructions comprising:
  • the service processing path includes a function node and a node operation sequence required for processing the voice service, where the function node includes a function triggering operation, and the node operation sequence is used for Characterizing the function of the function node triggers the execution order of the operations;
  • the response of the voice service is automatically processed according to the service processing path.
  • the voice service processing path includes processing the voice service
  • the function node that is required to be triggered according to the function in the function node can learn the operation required to process the voice service; on the other hand, the voice service processing path further includes a node operation sequence, which can be determined according to the operation sequence of the node.
  • the execution sequence of the operations required for the voice service is implemented, so that the voice service can be automatically responded according to the service processing path, the operations performed by the user when processing the voice service are reduced, and the convenience of the user to use the voice service is improved.
  • FIG. 1 is a flowchart of a method for creating a function node in a voice service function tree according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a voice service function tree according to an embodiment of the present application.
  • FIG. 3 is a flowchart of a method for answering a voice service according to an embodiment of the present application
  • FIG. 4 is a schematic diagram of a service processing path provided by an embodiment of the present application.
  • FIG. 5 is a flowchart of a method for answering a voice service according to an embodiment of the present application
  • FIG. 6 is a sequence diagram of a scenario example of a method for voice response according to an embodiment of the present disclosure
  • FIG. 7 is a schematic structural diagram of an apparatus for answering a voice service according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of hardware of a device for answering a voice service according to an embodiment of the present disclosure.
  • the embodiment of the present application provides a voice service response method and apparatus.
  • the embodiments of the present application are described below with reference to the accompanying drawings.
  • the user uses a terminal device, such as a mobile phone, to dial a service call provided by the service provider.
  • the server of the service provider provides a self-service voice service to the user, and sends a voice message to the terminal device.
  • the terminal device plays the voice information to the user, and the user performs an input operation according to the voice information, and the terminal device returns the input operation to the server of the service provider.
  • the server of the service provider sends another piece of voice information to the terminal device according to the input operation.
  • the present application provides a voice service response method, which searches for a service processing path from a voice service function tree corresponding to a voice service, and implements a voice service according to a function node and a node operation sequence in the service processing path.
  • Automatic response reducing the number of times users perform input operations when using self-service voice services, simplifying user operations and improving user experience.
  • the voice service function tree in the embodiment of the present application is created by performing voice recognition on the voice information sent by the server of the service provider, and the specific creation method is as follows.
  • FIG. 1 is a flowchart of a method for creating a function node in a voice service function tree according to an embodiment of the present disclosure, including:
  • the user performs a first input operation on the human-computer interaction interface of the terminal device.
  • the terminal device receives the first input operation, analyzes the function request corresponding to the first input operation, and sends the function request to the server of the service provider.
  • the server of the service provider searches for the first voice information corresponding to the function request from the provided self-service voice service according to the function request, and sends the first voice information to the terminal device.
  • the function request corresponding to the first input operation may be implemented by sending a digital code corresponding to the first input operation, and the digital code may be a digital or dual tone. Multi-frequency, DTMF) The digital code represented by the signal.
  • sending the function request corresponding to the first input operation may also be implemented by sending an operation signal corresponding to the first input operation.
  • it can also be implemented in other manners, and can be specifically set according to actual conditions, and will not be described here.
  • the function request corresponding to the first input operation of the user is to establish a call connection between the terminal device and the server of the service provider.
  • the user's first input operation that is, dialing the service phone of the service provider on the terminal device.
  • the terminal device sends a function request to establish a call connection to the service provider's service.
  • the first voice information corresponding to the function request is sent to the terminal device.
  • the first voice information is the first voice information of the self-service voice service.
  • the user dials China Mobile's service phone 10086 on the mobile terminal.
  • the mobile terminal sends a request to establish a call connection to the China Mobile server in response to the user dialing the operation of 10086.
  • China Mobile's server mobile terminal establishes a call connection and obtains the first voice from the self-service voice service. “Welcome to China Mobile, Chinese service, please press 1, For English Service, Press 2” to send to the terminal device.
  • the terminal device plays a piece of voice information sent by the server of the service provider to the user, and the user performs a first input operation according to the voice information, and the function request corresponding to the first input operation is to request the voice information.
  • the terminal device transmits the function request to the server of the service provider in response to the first input operation of the user.
  • the server of the service provider After receiving the function request, the server of the service provider provides the service function indicated by the first input operation.
  • the service provider's server obtains a piece of voice information under the service function from the provided self-service voice service, and records it as the first voice information, and sends the first voice information to the terminal device.
  • the voice message sent by the China Mobile server to the terminal device is “For Chinese Service, Press 2”
  • the first input operation performed by the user on the terminal device is “Press 1” according to the above voice information.
  • the function request sent by the terminal device to China Mobile's server that is, the server requesting China Mobile, provides the Chinese service indicated by "1".
  • China Mobile's server provides Chinese services, and obtains the voice information under the Chinese service in the self-service voice service provided by China Mobile. Please press 1 for mobile phone recharge, 2 for business inquiry, 3 for business processing, and the above voice information.
  • the first voice information is sent to the terminal device.
  • the function identifier is used to represent a service function of the first voice information
  • the function triggering operation is used to represent an operation to be triggered by the service function that implements the first voice information.
  • the terminal device After receiving the first voice information, the terminal device performs voice recognition on the first voice information by using voice recognition technology, obtains a keyword that represents a service function in the first voice information, and uses the keyword as a function identifier to obtain the
  • the first voice information represents a keyword that implements an operation to be triggered by the service function, and the keyword is used as a function trigger operation.
  • the voice recognition of the first voice information can obtain multiple function identifiers and multiple function trigger operations, one function identifier corresponds to one function trigger operation, and one function identifier represents the service function, which can only be executed.
  • the function corresponding to the function identifier triggers the operation.
  • the specific function, the function identifier It may be a character or a character string obtained by performing speech recognition on the first voice information.
  • the first voice message is "Chinese service, please press 1, For English Service, Press 2", and the first voice information is voice-recognized.
  • Another function identifier obtained is "For English Service”, which identifies that the service function represented is an English service.
  • the function triggering operation “press 1” is obtained, and the function triggering operation corresponds to the function identifier “Chinese”, that is, the function triggering operation required to implement the Chinese service is “press 1”.
  • Another function obtained triggers the operation "Press 2”, which triggers the operation corresponding to the function identifier "For English Service”, that is, the function triggering operation for implementing the English service mainly is "Press 2".
  • the terminal device After the terminal device receives the first voice information, if the terminal device can provide the voice recognition technology, the terminal device uses the voice recognition technology to perform voice recognition on the first voice information; if the terminal device cannot The voice recognition technology is provided, and the terminal device can send the first voice information to a voice recognition device.
  • the first voice information is voice-recognized by the voice recognition device, and the voice recognition result of the first voice information is returned to the terminal device.
  • the voice service function tree includes a child function node corresponding to the first voice information, where the child function node includes an identifier of the parent function node, a function identifier, and a corresponding relationship of the function triggering operation, the parent
  • the identity of the function node is used to characterize the service functions that the first input operation can implement.
  • each function node has a unique parent function node corresponding to the function node, and the function node is a child function node of the corresponding parent function node.
  • each function node has at least one child function node corresponding to the function node, and the function node is a parent function node of the corresponding child function node.
  • the parent function node and the child function node are a relative concept.
  • other functional nodes may be used as a parent function node or a child function node.
  • the voice service function tree shown in FIG. 2 is the parent node of the function node 202 "Chinese, press 1", and the function node 203 "For English Service, Press 2". That is to say, the function node 202 "Chinese, press 1", and the function node 203 "For English Service, Press2" are the sub-function nodes of the root node 201 "China Mobile”.
  • the function node 202 "Chinese, press 1” is a sub-function node of the root node 201 "China Mobile”
  • function node 205 service query, press 2
  • function node 206 Business processing, press 3" parent function node.
  • an identifier of a parent function node of the child function node in the voice service function tree of the service provider to be created where the identifier of the parent function node may be a function identifier in the parent function node, or may be An identifier customized for the parent function node, as long as it can identify the parent function node.
  • the identifier of the parent function node corresponds to a service function that can be implemented by the first input operation.
  • a function node can be uniquely determined as a parent function node.
  • the functional service that the first input operation can implement is to establish a call connection between the terminal device and the server of the service provider.
  • the parent function node of the child function node to be established is the root node, and the identifier of the root node is obtained.
  • the service function that can be implemented by the first input operation it is possible to determine a function identifier and a function triggering operation corresponding to the function identifier, thereby being able to uniquely determine a created function.
  • the node acts as a parent function node.
  • the identity of the parent function node is the identifier of the root node "China Mobile”.
  • the first input operation is “press 1”
  • the service function implemented by the first input operation is “Chinese service”
  • it can be determined that one function identifier is “Chinese”
  • the function identifier corresponding to the function trigger operation It is "press 1”, which can uniquely identify a function node “Chinese, press 1”
  • the identity of the parent function node is the function node "Chinese, press 1" Logo.
  • the function node has the same number of sub-function nodes created as the number of function identifiers.
  • Each sub-function node includes the identity of the parent function node, the function identifier, and the corresponding relationship of the function-triggered operations.
  • the sub-function nodes corresponding to the created first voice information are all sub-function nodes of the parent function node.
  • Each sub-function node includes an identifier of the parent function node, a function identifier, and a function triggering operation corresponding to the function identifier, and a correspondence between the three.
  • the content of the root node can be customized.
  • the name of the service provider to which the voice service function tree belongs may be the root node, and the root node is “China Mobile”; for example, the service phone of the service provider to which the voice service function tree belongs may be set as the root node and the root node. 10086".
  • the first piece of voice information sent by the server of the service provider may be voice-recognized, and the content of the root node is set according to the voice recognition result.
  • the recognition result of the voice part is taken as a root node, and the root node “Welcome to call China Mobile”; for example, After the first piece of voice information is voice-recognized, the voice part that does not include the function identifier and the function triggering operation is obtained, and the keyword is extracted as the root node from the recognition result of the voice part, and the root node is “China Mobile”.
  • the root node may be set in other manners according to actual needs, as long as the root node can uniquely correspond to the self-service voice service provided by the service provider.
  • the function triggering operation of the first voice information includes a preset user attribute
  • the method further includes:
  • the first voice information indicates a keyword that is to be triggered by the service function, that is, the function triggering operation
  • keywords indicating the preset user attribute such as an account number, an ID number, a card number, and the like.
  • the user performs a second input operation on the user interaction interface of the terminal device.
  • the terminal device obtains a value of the preset user attribute in the function triggering operation in response to the second input operation. Create a correspondence between the child function node and the value of the preset user attribute.
  • the sub-function node When the sub-function node is included in the service processing path, when the function triggering operation of the sub-function node is performed, the value of the preset user attribute corresponding to the sub-function node is obtained, and the input operation of the value of the preset user attribute is automatically implemented. .
  • the first voice message includes “Please enter the ID card number and end with the # key”
  • the “110123199006225678” input by the user on the terminal device is obtained, and the sub-function node “Entering the identity” of the first voice information is created.
  • the certificate number enter the ID number to end with the # key," and the corresponding value of the user attribute value "110123199006225678".
  • the sub-function node is used, the value of the user attribute "110123199006225678" is obtained and is automatically input.
  • the above content describes a method for creating a function node corresponding to the voice information after receiving a piece of voice information.
  • a service provider's voice service function tree you need to receive multiple voice messages sent by the server of the service provider.
  • the function node corresponding to each piece of voice information is created by the above method, and finally the voice service function tree of the service provider is obtained.
  • a voice service function tree of multiple service providers can be created to implement automatic response to voice services of multiple service providers.
  • the voice service function tree used is created based on voice recognition technology, and performs voice recognition on the voice information sent by the server.
  • the voice service function tree is matched with the self-service voice service provided by the service provider, and the automatic response of the voice service provided by the service provider can be better realized.
  • the voice service function tree of the service provider After the voice service function tree of the service provider is described in detail, the following describes the method for implementing the voice service automatic response by using the voice service function tree.
  • FIG. 3 is a flowchart of a method for answering a voice service according to an embodiment of the present disclosure, including:
  • the user inputs a request for a voice service through a user interaction interface provided by the terminal device.
  • the terminal device can provide a voice input function on the user interaction interface, and the user inputs the voice service request by using the voice input function.
  • the terminal device can also provide a text input function on the user interaction interface, and the user inputs the voice service request by using the text input function.
  • the terminal After receiving the request for the voice service, if the request for the voice service is voice, the terminal first performs voice recognition on the voice service request, and performs semantic analysis on the text result obtained by the voice recognition; if the voice service request is The text directly analyzes the request of the voice service, analyzes the service provider to which the voice service belongs, and searches for the voice service function tree of the service provider.
  • the request for voice service input by the user is "query call balance, China Mobile”.
  • the mobile phone performs semantic analysis on the request of the voice service, and analyzes that the voice service is “query balance”, and the service provider belongs to “China Mobile”. Only the semantic analysis of the request for the voice service can be used to know the voice service and the service provider to which the voice service belongs.
  • the request for the voice service input by the user is “query the balance of the mobile phone credit”, and the mobile phone performs a semantic analysis on the request for the voice service, and analyzes that the voice service is “query balance”.
  • the mobile phone can also automatically analyze the mobile phone number used by the mobile phone belonging to China Mobile.
  • the request to be able to determine the voice service is "query the phone message”
  • the service provider to which the fee balance belongs is “China Mobile.”
  • the request for the voice service is semantically analyzed to obtain the voice service; and the other information that the terminal device can provide is further determined to determine the service provider to which the voice service belongs.
  • the voice service function tree corresponding to the service provider is found in the mobile terminal. If not, the voice service function tree of the service provider is created according to the method shown in FIG. If yes, obtain the voice service function tree of the service provider.
  • 303 Query a service processing path from a voice service function tree, where the service processing path includes a function node and a node operation sequence required for processing the voice service, the function node includes a function triggering operation, and the node operation sequence is used to represent the function triggering operation of the function node. Execution order.
  • the voice service function tree of the service provider After obtaining the voice service function tree of the service provider, starting from the root node, traversing each function node of the voice service function tree to find a function node that matches the semantics of the voice service.
  • the voice service is semantically matched with the function node, mainly the voice service, and matches the function identification voice of the function node.
  • the function identifier of the function node is used to indicate the service function that the function node can provide.
  • the function node is a leaf node in the voice service function tree.
  • the voice service function tree of the service provider can represent the processing logic of the self-service voice service provided by the service provider. After finding the function node of the voice service semantic matching, a unique service processing path from the root node to the function node can be found from the service function tree.
  • the service processing path includes functional nodes required for processing the voice service, and also includes a node operation sequence.
  • the operation sequence of the node is used to represent the execution sequence of the function triggering operation of each functional node when the service processing path processes the voice service. It can be understood that, in general, the root node in the voice service function tree is not included in the service processing path.
  • each function node corresponds to a piece of voice information sent by the service provider when the voice service is provided.
  • the terminal device When the service processing path is found, the terminal device automatically establishes a voice connection with the server of the service provider.
  • the voice service request input by the user is "query the phone credit balance", and the voice service analyzed is the "check balance", and the service provider belongs to "China Mobile”. .
  • the function node is "balance inquiry, press 1".
  • From the voice service function tree look for the service processing path from the root node "Welcome to China Mobile" to the function node "balance inquiry, press 1".
  • the service processing path as shown in FIG.
  • the service processing path shown in FIG. 4 includes not only the function nodes required for processing the voice service of “query balance”, but also the function triggering operation of each function node, and the execution sequence of the function triggering operation of each function node. , press 2, press 1".
  • the response of the voice service is automatically processed according to the execution order of the function triggering operation of each function node in the service processing path.
  • the terminal device establishes a voice connection with the server of the service provider, receives the second voice information sent by the server, obtains a function node corresponding to the second voice information from the service processing path as a target node, and processes the second node by using the target node. voice message.
  • the service processing path includes only function triggered operations of the functional nodes.
  • the processing path automatically processes the response of the voice service
  • the service processing path that the terminal device finds from the voice service function tree is: "Press 1, press 2, press 1".
  • the terminal device establishes a voice connection with the server of China Mobile, and the terminal device receives the first piece of voice information sent by the server of China Mobile, and obtains the function of the first function node from the service processing path, and triggers the operation “press 1”, and automatically executes the button 1
  • the operation of the China Mobile server sends a second piece of voice information to the terminal device according to the operation of 1, the terminal device receives the second piece of voice information, and obtains the function trigger of the second function node in sequence from the service processing path.
  • the operation "press 2" automatically performs the operation of pressing 2; the server of China Mobile transmits the third piece of voice information to the terminal device according to the operation of 2, and the terminal device receives the third piece of voice information, from the service processing path,
  • the function of acquiring the third function node in sequence is triggered to "press 1", and the operation of pressing 1 is automatically performed; the server of China Mobile obtains the balance of the mobile phone according to the operation of pressing 1, and returns to the mobile terminal.
  • the balance of the mobile phone may be sent to the terminal device in the form of voice, and played by the terminal device to the user; or may be sent to the terminal device in the form of a short message, and displayed by the terminal device to the user.
  • the service processing path includes not only the function triggering operation of the function node but also the function identifier of the function node.
  • the terminal device acquires a function node from the service processing path in order, and compares the received second node first. Whether the voice information matches the semantics of the function identifier of the function node, that is, whether the function node is a function node that responds to the service function of the second voice information. If the semantic matching, the function node is a function node that answers the service function of the second voice information, and then performs a function triggering operation of the function node to automatically answer the second voice information.
  • the function node is not a function node that answers the service function of the second voice information, and the terminal device plays the second voice information to the user, and the user performs an operation of answering the second voice information.
  • a new function node is generated according to the second voice information, and the voice service function tree of the service provider is updated by the new function node.
  • voice recognition is performed on the received second voice information, and the voice recognition result of the second voice information is compared with whether the semantics of the function identifier of the function node match, thereby improving the accuracy of the automatic response of the voice service.
  • the terminal device triggers the operation only according to the function of the function node in the service processing path, and an automatic response error occurs when the automatic response is performed in the order of the function-triggered operation.
  • the voice service function tree of the service provider can be automatically updated when the processing logic of the self-service voice service provided by the service provider is changed.
  • the service processing path that the terminal device finds from the voice service function tree is: "Chinese, press 1", “service query, press 2", "balance inquiry, press 1".
  • the terminal device establishes a voice connection with the server of China Mobile, and the terminal device receives the first piece of voice information sent by the server of China Mobile, and obtains the first function node “Chinese, press 1” from the service processing path, and compares the first segment first. Whether the voice information matches the semantics of the function identifier "Chinese" of the first function node, and if it matches, the function trigger operation of the first function node is "pressed 1", and the operation of pressing 1 is automatically performed.
  • China Mobile's server sends a second paragraph to the terminal device according to the operation of 1.
  • the terminal device To receive the second piece of voice information, the terminal device obtains the second function node “Service Query, Press 2” from the service processing path, and compares the second segment of the voice information with the function identifier of the second function node. Whether the "business query” semantics match, if it matches, the function of the second function node is triggered to "press 2", and the operation of pressing 2 is automatically performed. According to the operation of 2, China Mobile's server sends a third piece of voice information to the terminal device, and the terminal device receives the third piece of voice information, and obtains a third function node from the service processing path, “balance inquiry, press 1”.
  • the method for creating a voice service function tree of the service provider is shown in FIG. 1 , and the method for automatically answering the voice service as shown in FIG. 3 is provided, and the service processing path for processing the voice service is obtained from the voice service function tree created by the preselection.
  • the function processing path of the function node the function triggering operation of the function node and the execution sequence of the function triggering operation, realizing an automatic response to the voice service, reducing the operation performed by the user when processing the voice service, and improving the convenience of the user using the voice service. Sex.
  • the voice service response method further includes: storing a correspondence between the voice service and the service processing path, and searching for a service processing path corresponding to the voice service before acquiring the voice service function tree of the service provider, if If the voice service function tree of the service provider is obtained, the service processing path corresponding to the voice service can be directly obtained.
  • the method shown includes:
  • the service processing path includes a function node and a node operation sequence required for processing the voice service
  • the function node includes a function triggering operation
  • the node operation sequence is used to represent the function triggering operation of the function node. Execution order.
  • Step 501, step 503, step 504, and step 506 are similar to the method shown in FIG. 3, with reference to the description of the method shown in FIG. 3, and details are not described herein again.
  • the voice service function tree of the service provider to which the voice service belongs is not immediately obtained, but the service processing path corresponding to the voice service is first found. If the service processing path exists, the voice service function tree of the service provider is not required to be obtained, and the service processing path corresponding to the voice service is directly used to automatically process the response of the voice service. If the service processing path corresponding to the voice service is not found, the network service path is obtained again. The voice service function tree of the service provider is taken, and the service processing path for processing the voice service is searched from the voice service function tree.
  • the request for the voice service input by the user needs to be semantically matched with the stored voice service, so as to find the service processing path corresponding to the voice service.
  • the user is required to input according to the standard expression of the voice service, so as to improve the accuracy of the service processing path corresponding to the voice service.
  • the user inputs a request for a voice service of "checking the mobile phone balance" on the mobile phone.
  • the mobile phone queries whether there is a service processing path corresponding to the voice service of “checking the mobile phone balance”, and if yes, executing 604; if not, executing 603.
  • the mobile phone obtains the voice service function tree of China Mobile according to the voice service of the “check balance” and the communication carrier to which the mobile phone number belongs, and obtains the service processing path from the voice service function tree of China Mobile.
  • the mobile phone establishes a voice connection with China Mobile's server.
  • China Mobile's server sends the first voice message to the mobile phone. “Welcome to China Mobile, Chinese service, please press 1. For English Service, Press 2”.
  • the function identifier “Chinese” of the first function node is matched with the first piece of voice information, and then the function triggering operation “press 1” of the first function node is performed.
  • the function identifier “service query” of the second function node is matched with the second piece of voice information, and then the function triggering operation “press 2” of the second function node is performed.
  • the function identifier “balance inquiry” of the third function node is matched with the third segment voice information, and then the function triggering operation “press 1” of the third function node is performed.
  • the mobile phone feeds back the balance information to the user.
  • FIG. 6 is a scenario example of a method for answering a voice service provided by the present application.
  • the specific implementation is similar to the method shown in FIG. 3 and FIG. 5, and is described in the method shown in FIG. 3 and FIG. I won't go into details here.
  • FIG. 7 is a schematic structural diagram of an apparatus for answering a voice service according to an embodiment of the present disclosure, including:
  • the receiving module 701 is configured to receive a request for a voice service.
  • the first obtaining module 702 is configured to acquire a voice service function tree of a service provider to which the voice service belongs, The voice service function tree is created according to voice information sent by the server of the service provider.
  • the searching module 703 is configured to search for a service processing path from the voice service function tree, where the service processing path includes a function node and a node operation sequence required for processing the voice service, where the function node includes a function triggering operation, where The node operation sequence is used to characterize the execution order of the function triggering operations of the function nodes.
  • the processing module 704 is configured to automatically process the response of the voice service according to the service processing path.
  • the device further includes:
  • a sending module configured to send, according to a first input operation of the user, a function request corresponding to the first input operation to a server of the service provider;
  • a receiving module configured to receive first voice information that is sent by the server of the service provider according to the function request
  • a second obtaining module configured to obtain a function identifier and a function triggering operation of the first voice information, where the function identifier is used to represent a service function of the first voice information, and the function triggering operation is used to represent the implementation The operation to be triggered by the service function of the first voice message;
  • a first creating module configured to create a voice service function tree of the service provider, where the voice service function tree includes a child function node corresponding to the first voice information, where the child function node includes an identifier of a parent function node, and the function
  • the identifier, and the corresponding relationship of the function triggering operation, the identifier of the parent function node is used to represent a service function that can be implemented by the first input operation.
  • the first voice information function triggering operation includes a preset user attribute
  • the device further includes:
  • a third acquiring module configured to acquire a value of the preset user attribute in response to the second input operation of the user
  • a second creating module configured to create a correspondence between the sub-function node and a value of the preset user attribute.
  • the device further includes:
  • a storage module configured to store a correspondence between the voice service and the service processing path.
  • the first obtaining module 702 includes:
  • An analyzing unit configured to perform semantic analysis on the request for the voice service, to find whether a service processing path corresponding to the voice service exists;
  • the first obtaining unit is configured to acquire a voice service function tree corresponding to the voice service when the service processing path corresponding to the voice service does not exist.
  • processing module 704 includes:
  • a receiving unit configured to receive second voice information sent by the service provider
  • a second acquiring unit configured to acquire a function node corresponding to the second voice information from the service processing path, and use the function node as a target node;
  • a processing unit configured to process the second voice information according to the target node.
  • the processing unit includes:
  • a third acquiring unit configured to acquire a function identifier and a function triggering operation in the target node
  • An analyzing unit configured to perform semantic analysis on the second voice information, to identify whether the function identifier of the second voice information matches the second voice information
  • An execution unit configured to: when a function identifier of the second voice information matches the second voice information, The function of the second voice information triggers an operation in response to the second voice information.
  • the device further includes:
  • a playing unit configured to: when the function identifier of the second voice information does not match the second voice information, play the second voice information to a user;
  • an updating unit configured to generate a new function node according to the second voice information, and update the voice service function tree by using the new function node.
  • the device shown in FIG. 7 is a device corresponding to the method shown in FIG. 1 to FIG. 6 , and the specific implementation method is similar. Referring to the description of the method shown in FIG. 1 to FIG. 6 , details are not described herein again.
  • FIG. 8 is a schematic structural diagram of a hardware device of a voice service response according to an embodiment of the present disclosure, including:
  • Receiver 801, processor 802, memory 803, communication bus 804, said receiver 801, said memory 803 are coupled to said processor 802 via said communication bus 804, respectively.
  • the receiver 801 is configured to receive a request for a voice service.
  • the memory 803 is configured to store instructions, and the processor 802 is configured to invoke instruction execution from the memory 803, where the instructions include:
  • the service processing path includes a function node and a node operation sequence required for processing the voice service, where the function node includes a function triggering operation, and the node operation sequence is used for Characterizing the function of the function node triggers the execution order of the operations;
  • the response of the voice service is automatically processed according to the service processing path.
  • the device shown in FIG. 8 is a device corresponding to the method shown in FIG. 1 to FIG. 6 , and the specific implementation method is similar. Referring to the description of the method shown in FIG. 1 to FIG. 6 , details are not described herein again.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)

Abstract

La présente invention concerne un appareil et un procédé de réponse de service vocal, le procédé consistant : à recevoir une demande pour un service vocal ; à acquérir un arbre fonctionnel de service vocal correspondant au service vocal ; et à rechercher, dans l'arbre fonctionnel de service vocal, un trajet de traitement de service pour traiter le service vocal, le trajet de traitement de service vocal comprenant un nœud fonctionnel requis afin de traiter le service vocal, et une opération devant être exécutée pour traiter le service vocal peut être obtenue conformément à une opération de déclenchement fonctionnelle du nœud fonctionnel ; et le trajet de traitement de service vocal comprend en outre une séquence d'opération de nœud, et une séquence d'exécution d'opération requise afin de traiter le service vocal peut être déterminée conformément à la séquence d'opération de nœud, ce qui permet d'obtenir, conformément au trajet de traitement de service, une réponse automatique au service vocal, de réduire les opérations exécutées par un utilisateur lorsque le service vocal est traité, et d'améliorer la commodité de l'utilisateur utilisant le service vocal.
PCT/CN2017/095057 2017-04-01 2017-07-28 Appareil et procédé de réponse de service vocal Ceased WO2018176705A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201780058753.XA CN109964473B (zh) 2017-04-01 2017-07-28 语音业务应答的方法及装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710213583.X 2017-04-01
CN201710213583 2017-04-01

Publications (1)

Publication Number Publication Date
WO2018176705A1 true WO2018176705A1 (fr) 2018-10-04

Family

ID=63674117

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/095057 Ceased WO2018176705A1 (fr) 2017-04-01 2017-07-28 Appareil et procédé de réponse de service vocal

Country Status (2)

Country Link
CN (1) CN109964473B (fr)
WO (1) WO2018176705A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110837914A (zh) * 2019-09-26 2020-02-25 深圳市保臻社区服务科技有限公司 提升物管费催缴率的方法、装置和计算机可读存储介质
CN110807542A (zh) * 2019-09-26 2020-02-18 深圳市保臻社区服务科技有限公司 智能编排系统业务能力的方法、装置和计算机可读存储介质
CN112259090A (zh) * 2020-09-10 2021-01-22 北京百度网讯科技有限公司 基于语音交互的业务办理方法、装置和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7027572B2 (en) * 2001-08-30 2006-04-11 Aspect Software, Inc. System and method for associating interactive voice response unit data to a telephone call using automatic number identifiers
CN101686286A (zh) * 2008-09-26 2010-03-31 中兴通讯股份有限公司 一种具有全语音服务的自动业务流程实现方法及系统
CN102724345A (zh) * 2012-06-01 2012-10-10 广东欧珀移动通信有限公司 一种自助语音服务电话的智能拨号方法
CN103188407A (zh) * 2011-12-31 2013-07-03 中国移动通信集团广东有限公司 交互式语音应答ivr的处理方法、终端、拨测服务器和系统
CN106302915A (zh) * 2016-10-18 2017-01-04 深圳市金立通信设备有限公司 一种自助语音服务的智能拨号方法及终端

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6389126B1 (en) * 1998-05-07 2002-05-14 Mci Communications Corporation Service provisioning system for interactive voice response services
US20060146992A1 (en) * 2004-12-30 2006-07-06 Sbc Knowledge Ventures L.P. System and method for real time monitoring an interactive voice response system
CN101141526B (zh) * 2006-09-08 2011-08-10 中国电信股份有限公司 实现语音导航的方法
CN101039353B (zh) * 2007-05-09 2012-04-04 华为技术有限公司 交互式语音应答流程节点定位方法及系统
CN101132444B (zh) * 2007-09-21 2011-06-22 中兴通讯股份有限公司 用于智能网的ivr流程主菜单的配置方法及配置系统
CN101729694A (zh) * 2008-10-29 2010-06-09 中兴通讯股份有限公司 一种自动业务实现流程配置及运行的方法及系统
CN101834953B (zh) * 2010-04-08 2012-12-26 中国农业大学 Ivr流程可配置的语音服务方法及系统
CN104410637B (zh) * 2014-11-28 2018-01-05 科大讯飞股份有限公司 互动式语音应答ivr可视化流程的开发系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7027572B2 (en) * 2001-08-30 2006-04-11 Aspect Software, Inc. System and method for associating interactive voice response unit data to a telephone call using automatic number identifiers
CN101686286A (zh) * 2008-09-26 2010-03-31 中兴通讯股份有限公司 一种具有全语音服务的自动业务流程实现方法及系统
CN103188407A (zh) * 2011-12-31 2013-07-03 中国移动通信集团广东有限公司 交互式语音应答ivr的处理方法、终端、拨测服务器和系统
CN102724345A (zh) * 2012-06-01 2012-10-10 广东欧珀移动通信有限公司 一种自助语音服务电话的智能拨号方法
CN106302915A (zh) * 2016-10-18 2017-01-04 深圳市金立通信设备有限公司 一种自助语音服务的智能拨号方法及终端

Also Published As

Publication number Publication date
CN109964473A (zh) 2019-07-02
CN109964473B (zh) 2021-03-05

Similar Documents

Publication Publication Date Title
CN104142964B (zh) 信息匹配的方法及装置
US9843908B2 (en) Method, client, server and system for intelligent recognizing contents of short message
US20200401645A1 (en) Processor-implemented method, computing system and computer program for invoking a search
US20240370516A1 (en) Processor-implemented method, computing system and computer program for invoking a search
WO2016183378A1 (fr) Communication instantanée
CN105491127A (zh) 通话界面信息展示、推送方法和装置及其系统
CN107168599B (zh) 一种即时通信方法和装置
CN106649488A (zh) 多数据源交互接口的调用方法及装置
WO2020038145A1 (fr) Procédé et appareil de traitement de données de service, et dispositif associé
CN105279168A (zh) 支持自然语言的数据查询方法、开放平台及用户终端
WO2018176705A1 (fr) Appareil et procédé de réponse de service vocal
WO2018145574A1 (fr) Procédé et dispositif de traitement d'informations, terminal, serveur et support d'informations
CN113470631B (zh) 语音信号处理方法及装置、电子设备及存储介质
WO2013010477A1 (fr) Procédé et dispositif pour rappel de texte
CN110045378A (zh) 终端设备的查找方法、装置及其相关设备
CN104239371B (zh) 一种指令信息处理方法及装置
CN115329181A (zh) 一种信息查询方法、查询服务端及客户端
CN108234781B (zh) 通信方法及装置
WO2016086488A1 (fr) Procédé et système de recherche de contacts spéciaux
EP3193559B1 (fr) Procédé et dispositif de traitement d'informations
EP2712162B1 (fr) Procédé et système pour entrer des informations dans un terminal mobile et terminal mobile
CN117528736A (zh) 能耗限制方法、nef网元、通信系统及存储介质
CN112182177B (zh) 一种用户问题处理方法、装置、电子设备及存储介质
CN110472254A (zh) 语音翻译方法、通信终端、及计算机可读存储介质
JP5389867B2 (ja) 情報検索システム及び方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17903135

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17903135

Country of ref document: EP

Kind code of ref document: A1