WO2015154447A1 - 一种交互式语音应答方法及装置 - Google Patents
一种交互式语音应答方法及装置 Download PDFInfo
- Publication number
- WO2015154447A1 WO2015154447A1 PCT/CN2014/090167 CN2014090167W WO2015154447A1 WO 2015154447 A1 WO2015154447 A1 WO 2015154447A1 CN 2014090167 W CN2014090167 W CN 2014090167W WO 2015154447 A1 WO2015154447 A1 WO 2015154447A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- service
- voice
- menu node
- voice response
- Prior art date
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
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
Definitions
- the present invention relates to the field of communications technologies, and in particular, to an interactive voice response method and apparatus.
- the user when a user calls a customer service phone for help, the user generally selects different services by pressing a button according to a voice prompt.
- this method can provide The menu options are limited, so the user has to choose which menu option the problem of the desired consultation belongs to before the button can be selected.
- the menu option level is more complicated, even if the user listens to the complicated menu option, it may not be able to get the menu option corresponding to the question that needs to be consulted.
- the mobile phone When the user uses the mobile phone to dial the customer service number, the mobile phone must be frequently removed from the ear to press the voice indication, which undoubtedly increases the operation time and cumbersomeness of the user, resulting in inconvenience to the user.
- the embodiment of the invention provides an interactive voice response method and device, which is used to solve the problem that the IVR mode in the prior art is inconvenient for the user.
- An interactive voice response method includes: receiving voice information input by a user; acquiring service information according to the received voice information; and performing voice response according to the service information.
- the acquiring the service information according to the received voice information includes: acquiring the service type information and the service parameter when the received voice information includes the service type information and the service parameter; and only the service type is included in the received voice information.
- obtaining the service information according to the received voice information includes: converting the received voice information into text information; and extracting the service information from the text information.
- extracting the service information from the text information includes: splitting the text information into multiple phrases; Matching the plurality of phrases obtained by the splitting with the preset service type information to obtain the service type information; performing semantic analysis on the plurality of phrases obtained by the splitting, and acquiring corresponding business parameters when detecting that multiple phrases contain service parameters .
- performing a voice response according to the service information includes: determining, according to a preset relationship between the preset menu node and the service category information, a menu node corresponding to the service category information in the service information; performing a voice response according to the determined menu node, or When the acquired service information includes the service parameter, the voice response is performed according to the determined menu node and the service parameter.
- the above menu node types include a main menu node and a sub-service content sub-menu node for processing the main menu node.
- An interactive voice response device includes: a receiving module configured to receive voice information input by a user; an obtaining module configured to acquire service information according to the received voice information; and a response module configured to perform voice according to the service information Answer.
- the obtaining module includes: a first acquiring unit, configured to acquire service type information and service parameters when the received voice information includes the service type information and the service parameter; and the second acquiring unit is configured to be The service type information obtained when only the service type information is included in the received voice information.
- the obtaining module includes: a converting unit configured to convert the received voice information into text information; and an extracting unit configured to extract the business information from the text information.
- the extracting unit is configured to split the text information into a plurality of phrases; and match the plurality of phrases obtained by the splitting with the preset service category information to obtain the service type information;
- the phrase performs semantic analysis and acquires the business parameter when detecting that multiple phrases contain business parameters.
- the response module includes: a determining unit configured to determine a menu node corresponding to the service category information in the service information according to a correspondence between the preset menu node and the service category information;
- the response unit is configured to perform a voice response according to the determined menu node, or, when the acquired service information includes the service parameter, perform a voice response according to the determined menu node and the service parameter.
- the menu node type includes a main menu node and a sub-service content sub-menu node for processing the main menu node.
- Embodiments of the present invention also provide a computer program comprising program instructions that, when executed by a computer, cause the computer to perform the above method.
- Embodiments of the present invention also provide a computer readable storage medium carrying the computer program.
- the service keyword is obtained according to the voice information input by the user, and the voice response is performed according to the service keyword, thereby achieving the purpose of directly performing the IVR response process according to the user voice, thereby reducing user operations and improving the user experience.
- FIG. 1 is a flowchart of an interactive voice response method according to an embodiment of the present invention
- FIG. 2 is a flow chart of a preferred interactive voice response method according to an embodiment of the present invention.
- FIG. 3 is a flow chart of another preferred interactive voice response method in accordance with an embodiment of the present invention.
- FIG. 4 is a structural block diagram of an interactive voice response apparatus according to an embodiment of the present invention.
- FIG. 1 is a flowchart of an interactive voice response method according to an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:
- Step 101 Receive voice information input by a user
- Step 102 Obtain service information according to the received voice information.
- the obtaining the service information according to the received voice information may include: acquiring the service category information and the service parameter when the received voice information includes the service category information and the service parameter; and only receiving the voice information
- the service type information is included, the service type information is obtained; the received voice information can be converted into text information, and the business information is extracted from the text information. interest.
- the step of converting the received voice information into text information may convert the received voice information into text information through an ASR (Automatic Speech Recognition) module, and the voice information received by the ASR module is described. The conversion is only a preferred mode of the embodiment of the present invention, and the received voice information can also be converted into text information by using voice recognition software, for example, the Android voice recognition software iris.
- the service information includes service type information and service parameters
- the step of extracting service information from the text information may include the following processing:
- the text information is divided into a plurality of phrases; the plurality of phrases obtained by the splitting are matched with the preset service type information to obtain the service type information; and the plurality of phrases obtained by the splitting are semantically analyzed to detect whether the business parameters are included. When included, obtain the corresponding business parameters. If the phrase with the same service type information exists in the multiple phrases obtained by the splitting, the matching is successful.
- the service category information database includes a preset service type information name for indicating different service types, for example, a network traffic package, or a short message package or a call charge package.
- the service parameter is the parameter information related to the service requested by the user. For example, if the user needs to obtain the call charge information for a period of time, the time period is the parameter information related to the service.
- Step 103 Perform a voice response according to the service information.
- This step 103 can include the following processing:
- the call center platform can transfer the current IVR process to the corresponding menu node according to the menu node corresponding to the service type information, and continue the voice response.
- the menu node referred to above is a physical node for processing different services or different transactions.
- the node code of the menu node can be sent to the call center platform, that is, The menu node is coded to identify the menu node.
- the menu node may specifically include a main menu node and a sub-menu node, and the sub-menu node is used for The lower-level service content of the main menu node; based on this, the voice response according to the service information may specifically include the following processing:
- the main menu IV flow is entered, that is, the main menu navigation sound is played, and the user is allowed to input the voice for confirmation or selection;
- the process jumps to the sub-menu IVR flow, plays the sub-menu navigation sound, and waits for the user to input the voice for confirmation or selection.
- FIG. 2 is a flow chart of a preferred interactive voice response method in accordance with an embodiment of the present invention. The method is elaborated from the user's interaction with the call center platform through the client:
- Step 201 The user dials an IVR access code through the client.
- Step 202 After receiving the user request, the call center platform executes the IVR service process in the IVR process module, and plays the voice prompting user;
- Step 203 The user speaks the voice content that needs to be consulted;
- Step 204 The call center platform invokes ASR to convert the voice content of the user into text content, that is, text information.
- Step 205 The call center platform invokes the semantic analysis module to analyze the text content, and returns the processing result to the IVR.
- the processing result includes the service information, and the service information includes the service type information and the service parameter.
- the analysis module can be a hardware module having a hardware structure or a software module;
- Step 206 The IVR performs the next process according to the received processing result from the call center platform, such as playing a menu node or performing corresponding service processing;
- Step 207 Determine whether there is service type information matching the preset menu node code. If not, go to step 208, and if yes, go to step 209.
- Step 208 Return to the preset error menu node code
- Step 209 Return the corresponding menu node code.
- FIG. 3 is a flow chart of another preferred interactive voice response method according to an embodiment of the present invention, the flow being different from the flow shown in FIG. 2 in that the process includes the call center platform determining a menu according to voice information input by a user. Node encoding, and the specific menu node continues the specific IVR process step:
- Step 301 After the customer dials the IVR access code, the system plays the main menu navigation sound, for example: "Good morning, may I help you?"
- Step 302 The customer speaks the business that he wants to handle, for example, the customer answers "call charge inquiry". If the client does not make a voice response, step 303 is performed; if the service type information is successfully matched with the code of the large class service menu node, that is, the main menu node, step 303 is performed as well;
- the call center platform collects the voice of the customer, and the ASR converts the voice content into text content, that is, text information.
- the call center platform calls the semantic analysis module to analyze the text content, obtains the service information, and uses the service type information and the pre-process in the obtained service information. Set the menu node code to match.
- Step 303 If the service type information is successfully matched with the code of the main service menu node, that is, the main menu node, the system plays a large menu selection prompt tone, and after the user performs voice selection according to the prompt tone, the call center platform receives the user's voice. Go to step 302 to continue the menu type node determination. Then, according to the judgment result, the prompt tone is played, for example, "OK, the xxx service includes yyy and zzz, which business to choose?"
- Step 304 If the service category key matches the sub-menu node encoding, the call center platform performs preset business logic processing, and performs voice prompting user confirmation. After the user voice input, the user jumps to step 302 to perform menu node judgment, if the execution is finished. After the step 304, the user continues to input the voice, then the process goes to step 302, and the voice analysis is continued on the voice input by the user. Similarly, if the user does not make any voice response, the process returns to step 303 to continue playing the main menu voice.
- the sub-menu node may be used for processing, querying, etc., and if the voice information input by the user through the ASR semantic analysis module matches the preset sub-menu node code, the user may directly jump. Go to the IVR process of the submenu and play the submenu navigation voice, which eliminates the need for unnecessary operations that the user needs to make a selection from the main menu. Based on this, the matching relationship between the preset menu node code and the service type information needs to set the correspondence between the sub-menu node code and the service type information, so that the IVR process can be implemented after the user directly inputs the statement containing the sub-menu voice. The process of jumping directly to the specified submenu node greatly simplifies the user's operation.
- Step 305 If the obtained service category information does not match any menu node code, then the language The semantic analysis module returns the preset error menu code, and the call center platform prompts the user to input a voice error prompt tone, and the system proceeds to the next processing flow.
- FIG. 4 is a structural block diagram of an interactive voice response apparatus according to an embodiment of the present invention. As shown in Figure 4, the device 40 includes the following components:
- a receiving module 41 configured to receive voice information input by a user
- An obtaining module 42 configured to obtain service information according to the received voice information
- the answering module 43 is arranged to perform a voice response based on the service information.
- the obtaining module 42 may include: a first acquiring unit, configured to acquire the service type information and the service parameter when the received voice information includes the service type information and the service parameter; and the second acquiring unit is configured to receive the The service type information obtained when the voice information contains only the service type information.
- the obtaining module 42 may further include: a converting unit configured to convert the received voice information into text information; and an extracting unit configured to extract the business information from the text information.
- the extracting unit may be configured to: split the text information into a plurality of phrases; match the plurality of phrases obtained by the splitting with the preset service category information to obtain the service type information; and perform semantics on the plurality of phrases obtained by the splitting Analyze whether the service parameter is included in the test. When it is included, the corresponding service parameter is obtained.
- the response module 43 may include: a determining unit configured to determine a menu node corresponding to the service category information in the service information according to a correspondence relationship between the preset menu node and the service category information; and a response unit configured to be according to the determined menu
- the node performs a voice response, or, when the acquired service information includes a service parameter, performs a voice response according to the determined menu node and the service parameter.
- the above menu node types include a main menu node and a sub-service content sub-menu node for processing the main menu node.
- the service information is obtained according to the voice information input by the user, and the voice response is performed according to the service information, thereby achieving the purpose of directly performing the IVR response process according to the user voice, thereby reducing user operations and improving the user experience.
- all or part of the steps of the above embodiments may also be implemented by using an integrated circuit. These steps may be separately fabricated into individual integrated circuit modules, or multiple modules or steps may be fabricated into a single integrated circuit module. achieve. Thus, the invention is not limited to any specific combination of hardware and software.
- the devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.
- each device/function module/functional unit in the above embodiment When each device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium.
- the above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
- the service keyword is obtained according to the voice information input by the user, and the voice response is performed according to the service keyword, thereby achieving the purpose of directly performing the IVR response process according to the user voice, thereby reducing user operations and improving the user experience.
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
一种交互式语音应答方法及装置，其中，交互式语音应答方法包括：接收用户输入的语音信息；根据接收到的语音信息获取业务信息；根据业务关信息进行语音应答；该交互式语音应答装置包括：接收模块，设置为接收用户输入的语音信息；获取模块，设置为根据接收到的语音信息获取业务信息；应答模块，设置为根据所述业务信息进行语音应答。
Description
本发明涉及通信技术领域，尤其涉及一种交互式语音应答方法及装置。
目前，在IVR(Interactive Voice Response，交互式语音应答)流程应用中，当用户拨打客服电话寻求帮助时，一般是用户根据语音提示，通过按键来选择不同服务，然而，这种方式所能提供的菜单选项有限，使用户不得不在分辨所需咨询的问题属于哪个菜单选项后，才能对按键进行选择。同时，菜单选项层次较为复杂，即使用户在听取复杂的菜单选项后，也并不一定可以得到与其需要咨询的问题对应的菜单选项。且当用户使用手机拨打客服号码时，必须频繁地将手机从耳边拿开，以便按照语音指示进行按键，这无疑增加了用户的操作时间与繁琐程度，导致用户使用不便。
发明内容
本发明实施例提供一种交互式语音应答方法及装置，用以解决现有技术中的IVR方式不便于用户使用的问题。
一种交互式语音应答方法，包括：接收用户输入的语音信息；根据接收到的语音信息获取业务信息；根据业务信息进行语音应答。
可选地，根据接收到的语音信息获取业务信息包括：在接收到的语音信息中包含业务种类信息以及业务参数时，获取业务种类信息以及业务参数；在接收到的语音信息中仅包含业务种类信息时，获取的业务种类信息。
可选地，根据接收到的语音信息获取业务信息包括：将接收到的语音信息转化为文字信息；并从文字信息中提取业务信息。
可选地，从文字信息中提取业务信息包括：将文字信息拆分为多个词组；
将拆分得到的多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的多个词组进行语义分析，当检测多个词组包含业务参数时，获取对应的业务参数。
可选地，根据业务信息进行语音应答包括：根据预先设置的菜单节点与业务种类信息的对应关系，确定与业务信息中业务种类信息对应的菜单节点；根据确定的菜单节点进行语音应答，或者，当获取的业务信息中包含业务参数时，根据确定的菜单节点并结合业务参数进行语音应答。
上述菜单节点类型包括主菜单节点以及用于处理主菜单节点的下级业务内容子菜单节点。
一种交互式语音应答装置，包括：接收模块，其设置为接收用户输入的语音信息；获取模块，其设置为根据接收到的语音信息获取业务信息；应答模块，其设置为根据业务信息进行语音应答。
可选地，上述获取模块包括：第一获取单元，其设置为在接收到的语音信息中包含业务种类信息以及业务参数时，获取业务种类信息以及业务参数；第二获取单元，其设置为在接收到的语音信息中仅包含业务种类信息时，获取的业务种类信息。
可选地，上述获取模块包括：转化单元，其设置为将接收到的语音信息转化为文字信息；提取单元，其设置为并从文字信息中提取业务信息。
可选地，提取单元是设置为，将文字信息拆分为多个词组；将拆分得到的多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的多个词组进行语义分析，当检测多个词组包含业务参数时，获取该业务参数。
可选地，应答模块包括：确定单元，其设置为根据预先设置的菜单节点与业务种类信息的对应关系，确定与业务信息中业务种类信息对应的菜单节点；
应答单元，其设置为根据确定的菜单节点进行语音应答，或者，当获取的业务信息中包含业务参数时，根据确定的菜单节点并结合业务参数进行语音应答。
可选地，上述菜单节点类型包括主菜单节点以及用于处理主菜单节点的下级业务内容子菜单节点。
本发明实施例还提供一种计算机程序，包括程序指令，当该程序指令被计算机执行时，使得该计算机可执行上述方法。
本发明实施例还提供一种载有所述计算机程序的计算机可读存储介质。
本发明实施例提供的方案，根据用户输入的语音信息获取业务关键词，根据业务关键词进行语音应答，实现了直接根据用户语音进行IVR应答流程的目的，减少了用户操作，提高了用户体验。
附图概述
图1是本发明实施例提供的交互式语音应答方法的流程图；
图2为本发明实施例的一种优选的交互式语音应答方法的流程图；
图3是本发明实施例的另一种优选的交互式语音应答方法的流程图；
图4为本发明实施例的交互式语音应答装置的结构框图。
本发明的较佳实施方式
下面结合附图对技术方案的实施作详细描述，在不冲突的情况下，本发明实施例和实施例中的特征可以相互任意组合。
图1是本发明实施例提供的交互式语音应答方法的流程图。如图1所示，该方法包括以下步骤：
步骤101：接收用户输入的语音信息；
步骤102：根据接收到的语音信息获取业务信息；
在该步骤102中，根据接收到的语音信息获取业务信息可以包括：在接收到的语音信息中包含业务种类信息以及业务参数时，获取业务种类信息以及业务参数；在接收到的语音信息中仅包含业务种类信息时，获取业务种类信息；可以将接收到的语音信息转化为文字信息，从文字信息中提取业务信
息。将接收到的语音信息转化为文字信息的步骤可以通过ASR(Automatic Speech Recognition，自动语音识别)模块将接收到的语音信息转化为文字信息，需要说明的是，通过ASR模块对接收到的语音信息进行转化仅为本发明实施例的一种优选方式，还可以通过语音识别软件将接收到的语音信息转化为文字信息，例如，安卓语音识别软件iris。
其次，业务信息中包括业务种类信息以及业务参数，从文字信息中提取业务信息的步骤可以包括如下处理：
将文字信息拆分为多个词组；将拆分得到的多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的多个词组进行语义分析，检测是否包含业务参数，当包含时，获取对应的业务参数。其中，如果拆分得到的多个词组中存在与业务种类信息相同的词组，则表明匹配成功。其中，业务种类信息库中包括预先设置的用于表示不同业务种类的业务种类信息名称，例如，网络流量套餐、或短信套餐、话费套餐的关键词。同时，业务参数即为与用户所请求的业务相关的参数信息，例如，用户需要获取一段时间内的话费信息，则这一段时间即为与业务相关的参数信息。
步骤103：根据业务信息进行语音应答。
该步骤103可以包括以下处理：
根据预先设置的菜单节点与业务种类信息的对应关系，确定与业务信息中业务种类信息对应的菜单节点；根据确定的菜单节点进行语音应答，或者，当获取的所述业务信息中包含业务参数时，根据确定的菜单节点并结合所述业务参数进行语音应答。需要说明的是，在用户输入的语音所转换的文字信息中，可能只包含业务种类信息，这时只能获取到与菜单节点对应的业务种类信息，这时仅根据业务种类信息进行应答即可，即呼叫中心平台可以根据业务种类信息对应的菜单节点，将当前IVR流程转到相应的菜单节点，继续进行语音应答。
上述所指的菜单节点，即为用于处理不同业务或不同事务的物理节点，业务种类信息与预先设置的菜单节点匹配成功后，可以将菜单节点的节点编码发送给呼叫中心平台，即，可以用菜单节点编码来标识菜单节点。其中，上述菜单节点具体可以包括主菜单节点以及子菜单节点，子菜单节点用于处
理主菜单节点的下级业务内容；基于此，根据业务信息进行语音应答具体可以包括如下处理：
在业务种类信息对应的菜单节点为主菜单节点时，进入主菜单IV流程，即播放主菜单导航音，等待用户输入语音进行确认或选择；
在业务种类信息对应的菜单节点为子菜单节点时，跳转到子菜单IVR流程，播放子菜单导航音，等待用户输入语音进行确认或选择。
图2为本发明实施例的一种优选的交互式语音应答方法的流程图。以下从用户通过客户端与呼叫中心平台的交互来对该方法进行详细阐述：
步骤201：用户通过客户端拨打IVR接入码；
步骤202：呼叫中心平台收到用户请求后，执行IVR流程模块中的IVR业务流程，播放语音提示用户；
步骤203：用户说出需要咨询的语音内容；
步骤204：呼叫中心平台调用ASR把用户的语音内容转化为文本内容，即文字信息；
步骤205：呼叫中心平台调用语义分析模块分析文本内容，并返回处理结果给IVR，该处理结果中包括业务信息，业务信息又包括业务种类信息以及业务参数，需要说明的是，该处所涉及的语义分析模块可以为具有硬件结构的硬件模块，也可以为软件模块；
步骤206：IVR根据接收到的来自呼叫中心平台的处理结果进行下一步流程处理，比如播放菜单节点或者进行相应的业务处理；
步骤207：判断是否有业务种类信息与预设菜单节点编码匹配，如果否，转入步骤208，如果是，转入步骤209
步骤208：返回预设的错误菜单节点编码；
步骤209：返回对应的菜单节点编码。
图3是本发明实施例的另一种优选的交互式语音应答方法的流程图，该流程与上述图2中所示流程的区别在于，该流程包括呼叫中心平台根据用户输入的语音信息确定菜单节点编码，并由指定菜单节点继续IVR流程的具体
步骤：
步骤301：客户拨打IVR接入码后，系统播放主菜单导航音，例如：“上午好，请问有什么可以帮你”？
步骤302：客户说出想要处理的业务，例如客户回答“话费查询…”。如果客户并未做出语音回应，则执行步骤303；如果业务种类信息与大类业务菜单节点，即，主菜单节点的编码匹配成功，同样执行步骤303；
呼叫中心平台收集客户的语音，ASR把语音内容转化为文本内容，即文本信息，呼叫中心平台调用语义分析模块对文本内容进行分析，得到业务信息，使用得到的业务信息中的业务种类信息与预设菜单节点编码进行匹配。
步骤303：如果业务种类信息与大类业务菜单节点，即，主菜单节点的编码匹配成功，则系统播放大类菜单选择提示音，用户根据提示音进行语音选择后，呼叫中心平台接收用户的语音，跳转到步骤302继续进行菜单类型节点判断。然后根据判断结果播放提示音，例如，“好的，xxx业务包含yyy和zzz，请问选择哪一个业务？”
步骤304：如果业务种类关键匹配上子菜单节点编码，则呼叫中心平台进行预设业务逻辑处理，并进行语音提示用户确认，用户语音输入后跳转到步骤302进行菜单节点判断，如果在执行完步骤304后，用户继续输入语音，则跳转到步骤302，继续对用户输入的语音进行语音分析，同样如果用户并未做出任何语音应答，则返回步骤303，继续播放主菜单语音。
在步骤304中，子菜单节点可以为用于业务办理、查询等的处理，如果用户输入的语音信息通过ASR语义分析模块得到的业务种类信息与预设的子菜单节点编码匹配，则可以直接跳转到子菜单的IVR流程中，播放子菜单导航语音，这样可以免去用户需要从主菜单依次进行选择，所需做出的不必要的操作。基于此，预先设置的菜单节点编码与业务种类信息的匹配关系中需要设置子菜单节点编码与业务种类信息的对应关系，这样即可以实现在用户直接输入包含子菜单语音的语句后，IVR流程可以直接跳转到指定子菜单节点的流程，大大简化了用户的操作。
步骤305：如果得到的业务种类信息没有匹配上任何菜单节点编码，则语
义分析模块返回预设的错误菜单编码，呼叫中心平台向用户提示输入语音错误的提示音，系统进入下一处理流程。
图4为本发明实施例的交互式语音应答装置的结构框图。如图4所示，该装置40包括以下组成部分：
接收模块41，其设置为接收用户输入的语音信息；
获取模块42，其设置为根据接收到的语音信息获取业务信息；
应答模块43，其设置为根据业务信息进行语音应答。
上述获取模块42可以包括：第一获取单元，其设置为在接收到的语音信息中包含业务种类信息以及业务参数时，获取业务种类信息以及业务参数；第二获取单元，其设置为在接收到的语音信息中仅包含业务种类信息时，获取的业务种类信息。
上述获取模块42还可以包括：转化单元，其设置为将接收到的语音信息转化为文字信息；提取单元，其设置为并从文字信息中提取业务信息。
上述提取单元可以设置为：将文字信息拆分为多个词组；将拆分得到的多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的多个词组进行语义分析，检测是否包含业务参数，当包含时，获取对应的业务参数。
上述应答模块43可以包括：确定单元，其设置为根据预先设置的菜单节点与业务种类信息的对应关系，确定与业务信息中业务种类信息对应的菜单节点；应答单元，其设置为根据确定的菜单节点进行语音应答，或者，当获取的业务信息中包含业务参数时，根据确定的菜单节点并结合业务参数进行语音应答。
上述菜单节点类型包括主菜单节点以及用于处理主菜单节点的下级业务内容子菜单节点。
本发明实施例提供的方案，根据用户输入的语音信息，获取业务信息，根据业务信息进行语音应答，实现了直接根据用户语音进行IVR应答流程的目的，减少了用户操作，提高了用户体验。
通过具体实施方式的说明，应当可对本发明为达成预定目的所采取的技
术手段及功效得以更加深入且具体的了解，然而所附图示仅是提供参考与说明之用，并非用来对本发明加以限制。
本领域普通技术人员可以理解上述实施例的全部或部分步骤可以使用计算机程序流程来实现，所述计算机程序可以存储于一计算机可读存储介质中，所述计算机程序在相应的硬件平台上(如系统、设备、装置、器件等)执行，在执行时，包括方法实施例的步骤之一或其组合。
可选地，上述实施例的全部或部分步骤也可以使用集成电路来实现，这些步骤可以被分别制作成一个个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。
上述实施例中的各装置/功能模块/功能单元可以采用通用的计算装置来实现，它们可以集中在单个的计算装置上，也可以分布在多个计算装置所组成的网络上。
上述实施例中的各装置/功能模块/功能单元以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。上述提到的计算机可读取存储介质可以是只读存储器，磁盘或光盘等。
任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求所述的保护范围为准。
本发明实施例提供的方案，根据用户输入的语音信息获取业务关键词，根据业务关键词进行语音应答，实现了直接根据用户语音进行IVR应答流程的目的，减少了用户操作，提高了用户体验。
Claims (14)
- 一种交互式语音应答方法，包括：接收用户输入的语音信息；根据接收到的所述语音信息获取业务信息；根据所述业务信息进行语音应答。
- 根据权利要求1所述的方法，其中，根据接收到的所述语音信息获取业务信息包括：在接收到的所述语音信息中包含业务种类信息以及业务参数时，获取所述业务种类信息以及所述业务参数；在接收到的所述语音信息中仅包含业务种类信息时，获取所述业务种类信息。
- 根据权利要求1所述的方法，其中，根据接收到的语音信息获取所述业务信息包括：将接收到的所述语音信息转化为文字信息；从所述文字信息中提取业务信息。
- 根据权利要求3所述的方法，其中，所述从所述文字信息中提取业务信息包括：将所述文字信息拆分为多个词组；将拆分得到的所述多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的所述多个词组进行语义分析，当检测所述多个词组包含业务参数信息时，获取所述业务参数信息。
- 根据权利要求2所述的方法，其中，根据所述业务信息进行语音应答包括：根据预先设置的菜单节点与业务种类信息的对应关系，确定与所述业务信息中业务种类信息对应的菜单节点；根据确定的所述菜单节点进行语音应答，或者，当获取的所述业务信息中包含业务参数时，根据确定的菜单节点并结合所述业务参数进行语音应答。
- 根据权利要求5所述的方法，其中，所述菜单节点的类型包括主菜单节点以及用于处理所述主菜单节点的下级业务内容的子菜单节点。
- 一种交互式语音应答装置，包括：接收模块，其设置为接收用户输入的语音信息；获取模块，其设置为根据所述接收模块接收到的所述语音信息获取业务信息；以及应答模块，其设置为根据所述业务信息进行语音应答。
- 根据权利要求7所述的装置，其中，所述获取模块包括：第一获取单元，其设置为在接收到的语音信息中包含业务种类信息以及业务参数时，获取所述业务种类信息以及业务参数；第二获取单元，其设置为在接收到的语音信心中仅包含业务种类信息时，获取所述业务种类信息。
- 根据权利要求7所述的装置，其中，所述获取模块包括：转化单元，其设置为将接收到的语音信息转化为文字信息；提取单元，其设置为并从所述文字信息中提取业务信息。
- 根据权利要求9所述的装置，其中，所述提取单元是设置为：将所述文字信息拆分为多个词组；将拆分得到的多个词组与预先设置的业务种类信息进行匹配，获取业务种类信息；对拆分得到的多个词组进行语义分析，当检测所述多个词组包含业务参数信息时，获取所述业务参数信息。
- 根据权利要求8所述的装置，其中，所述应答模块包括：确定单元，其设置为根据预先设置的菜单节点与业务种类信息的对应关系，确定与所述业务信息中业务种类信息对应的菜单节点；应答单元，其设置为根据确定的所述菜单节点进行语音应答，或者，当获取的所述业务信息中包含业务参数时，根据确定的菜单节点并结合所述业务参数进行语音应答。
- 根据权利要求11所述的装置，其中，所述菜单节点的类型包括主菜单节点以及用于处理所述主菜单节点的下级业务内容的子菜单节点。
- 一种计算机程序，包括程序指令，当该程序指令被计算机执行时，使得该计算机可执行权利要求1-6任一项所述的方法。
- 一种载有权利要求13所述计算机程序的计算机可读存储介质。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410401919.1 | 2014-08-15 | ||
| CN201410401919.1A CN105338204A (zh) | 2014-08-15 | 2014-08-15 | 一种交互式语音应答方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2015154447A1 true WO2015154447A1 (zh) | 2015-10-15 |
Family
ID=54287207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2014/090167 WO2015154447A1 (zh) | 2014-08-15 | 2014-11-03 | 一种交互式语音应答方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105338204A (zh) |
| WO (1) | WO2015154447A1 (zh) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516520A (zh) * | 2016-02-04 | 2016-04-20 | 平安科技（深圳）有限公司 | 一种互动式语音应答装置 |
| WO2019153533A1 (zh) * | 2018-02-12 | 2019-08-15 | 平安科技（深圳）有限公司 | 动态路由控制方法、装置、计算机设备及存储介质 |
| CN113223518A (zh) * | 2021-04-16 | 2021-08-06 | 讯飞智联科技(江苏)有限公司 | 一种基于ai语音分析的边缘计算网关的人机互动的方法 |
| CN113990305A (zh) * | 2020-07-27 | 2022-01-28 | 广东美的厨房电器制造有限公司 | 一种语音交互方法、装置、设备 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107995376A (zh) * | 2017-11-07 | 2018-05-04 | 平安科技（深圳）有限公司 | 一种用户报案处理方法及终端设备 |
| CN111031185A (zh) * | 2019-12-19 | 2020-04-17 | 易谷网络科技股份有限公司 | 一种基于人工智能导航的坐席分配方法及相关装置 |
| CN111355853A (zh) * | 2020-03-17 | 2020-06-30 | 集奥聚合(北京)人工智能科技有限公司 | 呼叫中心数据处理方法及装置 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100239075A1 (en) * | 2009-03-23 | 2010-09-23 | Paul Kobylevsky | System and Method for Providing Local Interactive Voice Response Services |
| CN102369568A (zh) * | 2009-02-03 | 2012-03-07 | 索夫特赫斯公司 | 使用语音通信交互式地访问托管服务的系统和方法 |
| CN101431573B (zh) * | 2007-11-08 | 2013-02-20 | 上海撼世网络科技有限公司 | 通过人机交互技术实现自动客户服务的方法和设备 |
| CN103533186A (zh) * | 2013-09-23 | 2014-01-22 | 安徽科大讯飞信息科技股份有限公司 | 一种基于语音呼叫的业务流程实现方法及系统 |
-
2014
- 2014-08-15 CN CN201410401919.1A patent/CN105338204A/zh active Pending
- 2014-11-03 WO PCT/CN2014/090167 patent/WO2015154447A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101431573B (zh) * | 2007-11-08 | 2013-02-20 | 上海撼世网络科技有限公司 | 通过人机交互技术实现自动客户服务的方法和设备 |
| CN102369568A (zh) * | 2009-02-03 | 2012-03-07 | 索夫特赫斯公司 | 使用语音通信交互式地访问托管服务的系统和方法 |
| US20100239075A1 (en) * | 2009-03-23 | 2010-09-23 | Paul Kobylevsky | System and Method for Providing Local Interactive Voice Response Services |
| CN103533186A (zh) * | 2013-09-23 | 2014-01-22 | 安徽科大讯飞信息科技股份有限公司 | 一种基于语音呼叫的业务流程实现方法及系统 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516520A (zh) * | 2016-02-04 | 2016-04-20 | 平安科技（深圳）有限公司 | 一种互动式语音应答装置 |
| WO2019153533A1 (zh) * | 2018-02-12 | 2019-08-15 | 平安科技（深圳）有限公司 | 动态路由控制方法、装置、计算机设备及存储介质 |
| CN113990305A (zh) * | 2020-07-27 | 2022-01-28 | 广东美的厨房电器制造有限公司 | 一种语音交互方法、装置、设备 |
| CN113223518A (zh) * | 2021-04-16 | 2021-08-06 | 讯飞智联科技(江苏)有限公司 | 一种基于ai语音分析的边缘计算网关的人机互动的方法 |
| CN113223518B (zh) * | 2021-04-16 | 2024-03-22 | 讯飞智联科技(江苏)有限公司 | 一种基于ai语音分析的边缘计算网关的人机互动的方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105338204A (zh) | 2016-02-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2015154447A1 (zh) | 一种交互式语音应答方法及装置 | |
| US11809686B1 (en) | Voice communication targeting user interface | |
| CN107895578B (zh) | 语音交互方法和装置 | |
| CN108962233B (zh) | 用于语音对话平台的语音对话处理方法及系统 | |
| JP6351562B2 (ja) | 情報処理システム、受付サーバ、情報処理方法及びプログラム | |
| US10244111B1 (en) | System for providing data to an interactive response system | |
| CN105814535B (zh) | 呼叫中的虚拟助理 | |
| CN106548788B (zh) | 一种智能情绪确定方法及系统 | |
| US6601029B1 (en) | Voice processing apparatus | |
| US7317789B2 (en) | Method and apparatus for automatic telephone menu navigation | |
| US20080273672A1 (en) | Automated attendant grammar tuning | |
| WO2017016104A1 (zh) | 问答信息的处理方法、装置、存储介质及设备 | |
| KR102421668B1 (ko) | 패킷화된 오디오 신호의 인증 | |
| WO2017175363A1 (ja) | 情報処理システム、受付サーバ、情報処理方法及びプログラム | |
| KR20190037363A (ko) | 음성 정보를 처리하기 위한 방법 및 장치 | |
| CN109005303A (zh) | 交互语音应答方法及装置 | |
| US10402434B1 (en) | Interface between a virtual personal assistant and an interactive voice response system | |
| US9088655B2 (en) | Automated response system | |
| KR20140055502A (ko) | 방송 수신 장치, 서버 및 그 제어 방법 | |
| CN107624177B (zh) | 用于提高用户效率和交互性能的可听呈现的选项的自动视觉显示 | |
| CN105897686A (zh) | 智能电视语音管理用户账号方法及智能电视 | |
| US20230353671A1 (en) | Indicating callers for incoming voice calls on a shared speech-enabled device | |
| US8301452B2 (en) | Voice activated application service architecture and delivery | |
| JP2018120203A (ja) | 情報処理方法及びプログラム | |
| CN111048091A (zh) | 一种语音识别方法、设备及计算机可读存储介质 |
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: 14888784 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: 14888784 Country of ref document: EP Kind code of ref document: A1 |