WO2018099000A1 - 语音输入的处理方法、终端和网络服务器 - Google Patents

语音输入的处理方法、终端和网络服务器 Download PDF

Info

Publication number
WO2018099000A1
WO2018099000A1 PCT/CN2017/085051 CN2017085051W WO2018099000A1 WO 2018099000 A1 WO2018099000 A1 WO 2018099000A1 CN 2017085051 W CN2017085051 W CN 2017085051W WO 2018099000 A1 WO2018099000 A1 WO 2018099000A1
Authority
WO
WIPO (PCT)
Prior art keywords
tasks
terminal
executed
instruction
voice
Prior art date
Application number
PCT/CN2017/085051
Other languages
English (en)
French (fr)
Inventor
李颖
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2018099000A1 publication Critical patent/WO2018099000A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue

Definitions

  • the present disclosure relates to the field of communications, and in particular, to a method, a terminal, and a network server for processing voice input.
  • the voice assistant is an intelligent mobile phone application, which realizes helping the user to solve the problem through the intelligent interaction between the intelligent dialogue and the instant question and answer.
  • the main purpose is to help the user solve the life problem, and the application can greatly improve the application.
  • the user has a single use problem by operating the mobile phone through voice input, and there is currently no effective solution.
  • the embodiments of the present disclosure provide a method for processing voice input, a terminal, and a network server, so as to at least solve the problem that the user uses the voice input to operate the mobile phone in a related art.
  • a method for processing a voice input including:
  • the terminal receives the voice instruction of the user
  • the terminal acquires a plurality of tasks to be executed associated with the voice instruction, and executes the plurality of tasks to be executed.
  • the terminal acquires multiple to-be-executed tasks associated with the voice instruction, including one of the following:
  • the terminal searches for a task corresponding to the voice instruction from a local database of the terminal according to the voice instruction, and determines the found task as the plurality of tasks to be executed;
  • the terminal When the terminal does not find a task corresponding to the voice instruction from a local database of the terminal according to the voice instruction, the terminal sends the voice command to a network server, and receives the network.
  • the task obtained by the server corresponding to the voice instruction, and determining the task as the plurality of tasks to be executed.
  • the terminal acquires multiple to-be-executed tasks associated with the voice instruction, including:
  • the terminal converts the voice instruction into a character instruction, and acquires the plurality of to-be-executed tasks associated with the character instruction.
  • the method before the performing the plurality of tasks to be performed, the method further includes:
  • the terminal displays the plurality of tasks to be executed
  • executing the multiple to-be-executed tasks includes:
  • the terminal invokes multiple applications built in the terminal to execute the plurality of tasks to be executed according to a preset sequence.
  • a method for processing voice input including:
  • the network server receives the character instruction obtained by the terminal by converting the voice instruction
  • the network server After acquiring a plurality of to-be-executed tasks corresponding to the character instruction, the network server sends a first list that records the plurality of tasks to be executed to the terminal;
  • a terminal including:
  • a voice collection circuit configured to receive a voice command of the user, and transmit the voice command to the first processor
  • the first processor is configured to acquire a plurality of to-be-executed tasks associated with the voice instruction, and execute the plurality of to-be-executed tasks.
  • the first processor is further configured to acquire a plurality of tasks to be executed associated with the voice instruction in one of the following manners:
  • the first processor is configured to search for a task corresponding to the voice instruction from a local database of the terminal according to the voice instruction, and determine the found task as the plurality of tasks to be executed;
  • the first processor is further configured to send the voice instruction to the network server and receive the task if the task corresponding to the voice instruction is not found in the local database of the terminal according to the voice instruction. And the task obtained by the network server corresponding to the voice instruction, and determining the task as the multiple tasks to be executed.
  • the first processor is further configured to convert the voice instruction into a character instruction to acquire the plurality of tasks to be executed associated with the character instruction.
  • the first processor is further configured to display the multiple to-be-executed tasks by using a display of the terminal before performing the multiple to-be-executed tasks;
  • the first processor is further configured to receive an adjustment instruction input by the user, and manage the plurality of tasks to be executed according to the adjustment instruction.
  • the first processor is further configured to upload the adjusted multiple to-be-executed tasks to the network server after managing the plurality of to-be-executed tasks according to the adjustment instruction, where the network server stores There is a mapping relationship between the voice instruction and the plurality of tasks to be executed.
  • the first processor is configured to invoke the multiple applications built in the terminal to perform the multiple to-be-executed tasks according to a preset sequence.
  • a network server including:
  • a communication device configured to receive a character instruction obtained by converting a voice command uploaded by the terminal, and send a plurality of tasks to be executed acquired by the second processor to the terminal;
  • the second processor is configured to acquire the plurality of to-be-executed tasks corresponding to the character instruction.
  • the communication device is configured to send a first list that records the plurality of tasks to be executed to the terminal, and receive a second list sent by the terminal, where the second list is Said first list adjusted by the terminal according to the adjustment instruction of the user;
  • the second processor is further configured to establish a mapping relationship between the second list and the character instruction, and store the mapping relationship.
  • a storage medium is also provided.
  • the storage medium is set to store program code set to perform the following steps:
  • the terminal receives the voice instruction of the user
  • the terminal acquires a plurality of tasks to be executed associated with the voice instruction, and executes the plurality of tasks to be executed.
  • the storage medium is further arranged to store program code arranged to perform the following steps:
  • the network server receives the character instruction obtained by the terminal by converting the voice instruction
  • the terminal receives the voice input by the user, and after the voice is converted, recognizes the event expressed in the voice, and the terminal itself recognizes or resorts to the network server, and parses out multiple tasks that need to be performed during the execution of the event, and subsequently Perform the above multiple tasks.
  • the invention solves the problem that the user realizes the single use of the mobile phone through voice input in the related art, and effectively expands the convenience of the user to control the terminal through voice.
  • FIG. 1 is a block diagram showing the hardware structure of a terminal according to an implementation of the present disclosure
  • FIG. 2 is a block diagram showing the hardware structure of a network server according to an embodiment of the present disclosure
  • FIG. 3 is a flowchart of a method of processing voice input according to an embodiment of the present disclosure
  • FIG. 4 is a flow diagram of the steps performed by the four modules in accordance with the voice in a preferred embodiment of the present disclosure.
  • the technical solutions in this application file can be run on terminals such as mobile phones and tablet computers.
  • the terminal 10 includes:
  • the voice collection circuit 102 is configured to receive a voice command of the user and transmit the voice command to the first processor 104.
  • the voice capture circuit may be a related circuit of a voice input device such as a microphone or a headset.
  • the voice command may be directly sent by the user, or may be played back in advance by the audio device.
  • the first processor 104 is configured to acquire a plurality of tasks to be executed associated with the voice instruction, and execute the plurality of tasks to be executed.
  • the first processor 104 is further configured to obtain, by one of the following manners, multiple to-be-executed tasks associated with the voice instruction:
  • the first processor 104 is configured to search for a task corresponding to the voice instruction from a local database of the terminal according to the voice instruction, and determine the found task as the plurality of tasks to be executed;
  • the first processor 104 is further configured to: when the task corresponding to the voice instruction is not found in the local database of the terminal according to the voice instruction, send the voice instruction to the network server, and receive the network server to obtain The task corresponding to the voice instruction, and the task is determined as the plurality of tasks to be executed.
  • the first processor 104 is further configured to convert the voice instruction into a character instruction, and acquire the plurality of to-be-executed tasks associated with the character instruction.
  • the first processor 104 is further configured to display the multiple to-be-executed tasks by using a display of the terminal before performing the multiple to-be-executed tasks;
  • the first processor 104 is further configured to receive an adjustment instruction input by the user, and manage the plurality of tasks to be executed according to the adjustment instruction.
  • the first processor 104 is further configured to upload the adjusted multiple to-be-executed tasks to the network server after managing the plurality of to-be-executed tasks according to the adjustment instruction, where the network server stores the voice A mapping relationship between the instruction and the plurality of tasks to be executed.
  • the first processor 104 is configured to invoke the multiple applications built in the terminal to perform the multiple to-be-executed tasks according to a preset sequence.
  • the network server 20 includes:
  • the communication device 202 is configured to receive a character instruction that is obtained by the terminal to be converted by the voice instruction, and send the plurality of to-be-executed tasks acquired by the second processor to the terminal;
  • the second processor 204 is configured to acquire the plurality of tasks to be executed corresponding to the character instruction.
  • the communication device 202 is configured to send a first list that records the multiple tasks to be executed to the terminal, and receive a second list sent by the terminal, where the second list is the terminal according to the user. Adjusting the first list adjusted by the instruction;
  • the second processor 204 is further configured to establish a mapping relationship between the second list and the character instruction, and store the mapping relationship.
  • FIG. 3 is a flowchart of a method for processing voice input according to an embodiment of the present disclosure. As shown in FIG. 3, the method includes the following steps:
  • Step S302 the terminal receives a voice instruction of the user
  • Step S304 the terminal acquires a plurality of tasks to be executed associated with the voice instruction, and executes the plurality of tasks to be executed.
  • the terminal receives the voice input by the user, and after the voice is converted, identifies the event expressed in the voice, and the terminal itself recognizes or resorts to the network server, and parses out multiple tasks that need to be performed during the execution of the event, and subsequently Perform the above multiple tasks in sequence.
  • the invention solves the problem that the user realizes the single use of the mobile phone through voice input in the related art, and effectively expands the convenience of the user to control the terminal through voice.
  • the terminal acquires multiple to-be-executed tasks associated with the voice instruction, including one of the following:
  • the terminal searches for a task corresponding to the voice instruction from the local database of the terminal according to the voice instruction, and determines the found task as the plurality of tasks to be executed;
  • the terminal When the terminal does not find a task corresponding to the voice instruction from the local database of the terminal according to the voice instruction, the terminal sends the voice command to the network server, and receives the voice command acquired by the network server.
  • the corresponding task is determined as the plurality of tasks to be executed.
  • the terminal converts the voice instruction into a character instruction, and acquires the plurality of to-be-executed tasks associated with the character instruction.
  • the terminal displays the multiple to-be-executed tasks
  • the terminal invokes multiple applications built in the terminal to perform the multiple to-be-executed tasks according to a preset sequence.
  • a method for processing voice input including:
  • the network server receives the character instruction obtained by the terminal by converting the voice instruction
  • the network server After acquiring a plurality of to-be-executed tasks corresponding to the character instruction, the network server sends a first list that records the plurality of tasks to be executed to the terminal;
  • the voice recognition terminal has the functions of the following modules: a voice recognition module (corresponding to the voice collection circuit 102 in the above embodiment), a requirement analysis module, a central processing module, and a demand recording module (following three)
  • the function of the module is equivalent to the first processor 104 in the above embodiment.
  • a voice recognition module for collecting and recognizing a user's voice and converting it into a character command, which is called a user here.
  • the matter is output to the demand resolution module.
  • the demand parsing module sends the user story data to the local demand database for analysis in advance, and if the parsing is unsuccessful, it is sent to the cloud demand parsing data server for parsing. The result of the demand analysis is sent to the central processing module.
  • the cloud demand data server establishes a demand classification database based on a large number of user behavior data statistics learning and combines a data mining system and a vector machine classifier, and continuously updates and upgrades.
  • the parsed demand data is output to the central processing module in a specified format.
  • the implementation process is as follows: A user instruction is “I am going to Beijing for business trip on October 15th”, and the cloud demand resolution server will first extract the key data “October 15, Beijing, business trip” from the instruction, and the key data will be in demand. Analyze the database for demand matching, and finally deep analysis of a series of requirements: booking air tickets / train tickets, booking hotels, getting up the alarm clock, timing car calls and other needs.
  • the central processing module is configured to receive the demand data, and arrange them into a list in chronological order, and present to the user in the form of a UI interface, and the user can modify and configure (by voice or manual), and after the user confirms, the demand list of the story is Output to the requirements record module for saving. Then start the list of requirements for the story in order.
  • a user story may contain multiple requirements.
  • the central processor needs to collaborate to call each application module to fulfill these requirements. It can also provide an interface or voice to allow the user to select according to requirements. Whenever a requirement for the story is executed, the notification requirements record module removes the requirement from the list of requirements. The user can be prompted by voice or interface when performing each requirement.
  • a demand record module that receives and saves a list of user-confirmed requirements.
  • a voice command of the user is called a story, and the story corresponds to a list of requirements.
  • An operational interface is provided to the central processing module to delete completed requirements, all requirements are completed, and the story is automatically deleted.
  • the first step the speech recognition module collects voice commands, recognizes and converts them into character commands (ie, a user story), and outputs them to the demand parsing module.
  • the second step the requirement analysis module sends the user story data to the local demand database for parsing, and if the parsing is unsuccessful, it is sent to the cloud demand parsing data server for parsing. The result of the demand analysis is sent to the central processing module.
  • the cloud demand data server establishes a demand classification database based on a large number of user behavior data statistics learning and combines a data mining system and a vector machine classifier, and continuously updates and upgrades.
  • the parsed demand data is output to the central processing module in a specified format.
  • a user instruction is “I am going to Beijing for business trip on October 15th”
  • the cloud demand resolution server will first extract the key data “October 15, Beijing, business trip” from the instruction, and the key data is in demand. Analyze the database for requirements analysis and matching.
  • the keyword "business trip” analyzes the needs of: booking a ticket / train ticket, booking a hotel, setting a schedule alarm clock, timing a car, etc., and then combining with the "time”, “destination” and other keywords, the final output
  • the demand is:
  • the third step the central processing module
  • the user can say "modify the Xth article" or manually click the demand item, and enter the sub-interface to modify.
  • the user can modify the booking ticket or train ticket, book the start and end date of the hotel, the time of the alarm clock, and the time and destination of the taxi, or delete a certain demand, and then confirm the execution.
  • the central processing module outputs the demand list of the story to the demand record module for saving.
  • a requirement may correspond to multiple functions, and the central processor needs to collaboratively call each application module to complete the requirement.
  • Example 1 Booking a ticket (October 15th), the module that needs to be linked has
  • the central processing module is triggered to read the demand number in the schedule, and the demand module is called and executed from the demand module.
  • the central processor will automatically check whether it will affect other requirements in the list, find out the requirements that may be affected, perform automatic adjustment, and pop up the relevant demand items. Please confirm with the user:
  • the central processing module removes the requirement from the requirements record module each time a requirement is executed.
  • the fourth step the demand record module records the demand list corresponding to each user story, provides an operation interface to the central processing module, so as to delete the completed requirements, all the requirements are completed, and the story is automatically deleted.
  • the user is provided with an entry to delete the demand list at any time, thereby interrupting the execution of the demand task.
  • the central processor can jointly control the plurality of modules on the left side of FIG. 4 to perform the above tasks, the most important.
  • the central processing module and the cloud demand resolution server the central processing module is responsible for parsing the requirements and calling all other modules to work together, which can be likened to an intelligent robot.
  • the local and cloud demand resolution server intelligently mines and analyzes user requirements, and the cloud server can continuously learn and update.
  • the technical solution in the above preferred embodiment is used to provide a set of intelligent voice service system for the user, which can be accurately and Deeply parsing the requirements contained in a short instruction of the user, and coordinating the linkage of each application module to provide services for the user to complete the series of requirements that the user desires. Greatly save time for users and provide users with more convenient and user-friendly voice experience services.
  • Embodiments of the present disclosure also provide a storage medium.
  • the foregoing storage medium may be configured to store program code for performing the following steps:
  • the terminal receives a voice instruction of the user.
  • the terminal acquires multiple to-be-executed tasks associated with the voice instruction, and executes the multiple to-be-executed tasks.
  • the storage medium is further arranged to store program code for performing the following steps:
  • the network server receives a character instruction that is obtained by the terminal and is converted by the voice instruction.
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the processor performs the method steps in the foregoing embodiments according to the stored program code in the storage medium.
  • modules or steps of the present disclosure described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein.
  • the steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. As such, the disclosure is not limited to any specific combination of hardware and software.
  • the present disclosure is applicable to the field of communication, and solves the problem that the user realizes a single use of the mobile phone through voice input in the related art, and effectively expands the convenience of the user to control the terminal through voice.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Transfer Between Computers (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本公开提供了一种语音输入的处理方法、终端和网络服务器，其中，该方法包括：终端接收到用户输入的语音，将语音转换之后，识别出语音中表达的事件，终端自身识别或者求助于网络服务器，解析出执行该事件过程中需要进行的多个任务，后续依次执行上述多个任务。采用上述方案，解决了相关技术中用户通过语音输入来操作手机实现的用途单一的问题，有效扩展了用户通过语音来操控终端的便捷性。

Description

语音输入的处理方法、终端和网络服务器 技术领域
本公开涉及通信领域，具体而言，涉及一种语音输入的处理方法、终端和网络服务器。
背景技术
在相关技术中，语音助手是一款智能型的手机应用，通过智能对话与即时问答的智能交互，实现帮助用户解决问题，其主要是帮助用户解决生活类问题，通过此类应用，可以大大提高在不同场景下操作手机的便利性。自2011年苹果将Siri带进手机市场开创语音助手先河之后，语音助手类应用可谓火的一塌糊涂。随着技术发展，人们需求的不断提高，手机语音功能的广泛使用是一种必然趋势。
但目前语音的使用场景还比较单一，主要是对话形式或者转化为一条指令。
针对相关技术中，用户通过语音输入来操作手机实现的用途单一的问题，目前还没有有效的解决方案。
发明内容
本公开实施例提供了一种语音输入的处理方法、终端和网络服务器，以至少解决相关技术中用户通过语音输入操作手机用途单一的问题。
根据本公开的一个实施例，提供了一种语音输入的处理方法，包括：
终端接收用户的语音指令；
所述终端获取与所述语音指令关联的多个待执行任务，并执行所述多个待执行任务。
可选地，所述终端获取与所述语音指令关联的多个待执行任务，包括以下之一：
所述终端依据所述语音指令从所述终端的本地数据库中查找与所述语音指令对应的任务，并将查找到的任务确定为所述多个待执行任务；
在所述终端依据所述语音指令从所述终端的本地数据库中没有查找到与所述语音指令对应的任务的情况下，所述终端将所述语音指令发送到网络服务器，并接收所述网络服务器获取的与所述语音指令对应的任务，并将该任务确定为所述多个待执行任务。
可选地，所述终端获取与所述语音指令关联的多个待执行任务，包括：
所述终端将所述语音指令转换为字符指令，获取与所述字符指令关联的所述多个待执行任务。
可选地，执行所述多个待执行任务之前，所述方法还包括：
所述终端显示所述多个待执行任务；
接收用户输入的调整指令，并依据所述调整指令管理所述多个待执行任务。
可选地，在依据所述调整指令管理所述多个待执行任务之后，将所述调整后的多个待执行任务上传至网络服务器，其中，所述网络服务器存储有所述语音指令与所述多个待执行任 务的映射关系。
可选地，执行所述多个待执行任务，包括：
所述终端依据预设顺序调用所述终端内置的多个应用程序分别执行所述多个待执行任务。
根据本公开的另一个实施例，还提供了一种语音输入的处理方法，包括：
网络服务器接收终端上传的通过转换语音指令得到的字符指令；
获取与所述字符指令对应的多个待执行任务，并将所述多个待执行任务下发到所述终端。
可选地，在获取与所述字符指令对应的多个待执行任务之后，所述网络服务器将记录有所述多个待执行任务的第一列表发送到所述终端；
接收所述终端发送的第二列表，其中，所述第二列表是所述终端依据用户的调整指令调整过的所述第一列表；
建立所述第二列表与所述字符指令的映射关系，并存储所述映射关系。
根据本公开的另一个实施例，还提供了一种终端，包括：
语音采集电路，设置为接收用户的语音指令，并将所述语音指令传输到第一处理器；
第一处理器，设置为获取与所述语音指令关联的多个待执行任务，并执行所述多个待执行任务。
可选地，所述第一处理器还设置为通过以下方式之一获取与所述语音指令关联的多个待执行任务：
所述第一处理器设置为依据所述语音指令从所述终端的本地数据库中查找与所述语音指令对应的任务，并将查找到的任务确定为所述多个待执行任务；
所述第一处理器还设置为在依据所述语音指令从所述终端的本地数据库中没有查找到与所述语音指令对应的任务的情况下，将所述语音指令发送到网络服务器，并接收所述网络服务器获取的与所述语音指令对应的任务，并将该任务确定为所述多个待执行任务。
可选地，所述第一处理器还设置为将所述语音指令转换为字符指令，获取与所述字符指令关联的所述多个待执行任务。
可选地，所述第一处理器还设置为在执行所述多个待执行任务之前，通过所述终端的显示器显示所述多个待执行任务；
所述第一处理器还设置为接收用户输入的调整指令，并依据所述调整指令管理所述多个待执行任务。
可选地，所述第一处理器还设置为在依据所述调整指令管理所述多个待执行任务之后，将调整后的多个待执行任务上传至网络服务器，其中，所述网络服务器存储有所述语音指令与所述多个待执行任务的映射关系。
可选地，所述第一处理器设置为依据预设顺序调用所述终端内置的多个应用程序分别执行所述多个待执行任务。
根据本公开的另一个实施例，还提供了一种网络服务器，包括：
通信装置，设置为接收终端上传的通过转换语音指令得到的字符指令，并将第二处理器获取的多个待执行任务下发到所述终端；
所述第二处理器，设置为获取与所述字符指令对应的所述多个待执行任务。
可选地，所述通信装置设置为将记录有所述多个待执行任务的第一列表发送到所述终端，并接收所述终端发送的第二列表，其中，所述第二列表是所述终端依据用户的调整指令调整过的所述第一列表；
所述第二处理器，还设置为建立所述第二列表与所述字符指令的映射关系，并存储所述映射关系。
根据本公开的又一个实施例，还提供了一种存储介质。该存储介质设置为存储设置为执行以下步骤的程序代码：
终端接收用户的语音指令；
所述终端获取与所述语音指令关联的多个待执行任务，并执行所述多个待执行任务。
可选地，存储介质还设置为存储设置为执行以下步骤的程序代码：
网络服务器接收终端上传的通过转换语音指令得到的字符指令；
获取与所述字符指令对应的多个待执行任务，并将所述多个待执行任务下发到所述终端。
通过本公开，终端接收到用户输入的语音，将语音转换之后，识别出语音中表达的事件，终端自身识别或者求助于网络服务器，解析出执行该事件过程中需要进行的多个任务，后续依次执行上述多个任务。解决了相关技术中用户通过语音输入来操作手机实现的用途单一的问题，有效扩展了用户通过语音来操控终端的便捷性。
附图说明
此处所说明的附图用来提供对本公开的进一步理解，构成本申请的一部分，本公开的示意性实施例及其说明用于解释本公开，并不构成对本公开的不当限定。在附图中：
图1是根据本公开实施的一种终端的硬件结构框图；
图2是根据本公开实施例的一种网络服务器的硬件结构框图；
图3是根据本公开实施例的一种语音输入的处理方法流程图；
图4是跟本公开优选实施例中四大模块依据语音执行后续步骤的流程图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本公开。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
实施例一
本申请文件中的技术方案可以运行于手机、平板电脑等终端上。
图1是根据本公开实施的一种终端的硬件结构框图，如图1所示，该终端10包括：
语音采集电路102，用于接收用户的语音指令，并将该语音指令传输到第一处理器104；需要补充的是，语音采集电路可以是麦克风或者耳机等语音输入设备的相关电路。语音指令可以是用户直接发出的，也可以是音频设备预先存储的再播放出来的。
第一处理器104，用于获取与该语音指令关联的多个待执行任务，并执行该多个待执行任务。
可选地，该第一处理器104还用于通过以下方式之一获取与该语音指令关联的多个待执行任务：
该第一处理器104用于依据该语音指令从该终端的本地数据库中查找与该语音指令对应的任务，并将查找到的任务确定为该多个待执行任务；
该第一处理器104还用于在依据该语音指令从该终端的本地数据库中没有查找到与该语音指令对应的任务的情况下，将该语音指令发送到网络服务器，并接收该网络服务器获取的与该语音指令对应的任务，并将该任务确定为该多个待执行任务。
可选地，该第一处理器104还用于将该语音指令转换为字符指令，获取与该字符指令关联的该多个待执行任务。
可选地，该第一处理器104还用于在执行该多个待执行任务之前，通过该终端的显示器显示该多个待执行任务；
该第一处理器104还用于接收用户输入的调整指令，并依据该调整指令管理该多个待执行任务。
可选地，该第一处理器104还用于在依据该调整指令管理该多个待执行任务之后，将调整后的多个待执行任务上传至网络服务器，其中，该网络服务器存储有该语音指令与该多个待执行任务的映射关系。
可选地，该第一处理器104用于依据预设顺序调用该终端内置的多个应用程序分别执行该多个待执行任务。
图2是根据本公开实施例的一种网络服务器的硬件结构框图，如图2所示，该网络服务器20包括：
通信装置202，用于接收终端上传的通过转换语音指令得到的字符指令，并将第二处理器获取的多个待执行任务下发到该终端；
该第二处理器204，用于获取与该字符指令对应的该多个待执行任务。
可选地，该通信装置202用于将记录有该多个待执行任务的第一列表发送到该终端，并接收该终端发送的第二列表，其中，该第二列表是该终端依据用户的调整指令调整过的该第一列表；
该第二处理器204，还用于建立该第二列表与该字符指令的映射关系，并存储该映射关系。
实施例二
图3是根据本公开实施例的一种语音输入的处理方法流程图，如图3所示，该方法包括以下步骤：
步骤S302，终端接收用户的语音指令；
步骤S304，该终端获取与该语音指令关联的多个待执行任务，并执行该多个待执行任务。
采用上述技术方案，终端接收到用户输入的语音，将语音转换之后，识别出语音中表达的事件，终端自身识别或者求助于网络服务器，解析出执行该事件过程中需要进行的多个任务，后续依次执行上述多个任务。解决了相关技术中用户通过语音输入来操作手机实现的用途单一的问题，有效扩展了用户通过语音来操控终端的便捷性。
可选地，该终端获取与该语音指令关联的多个待执行任务，包括以下之一：
该终端依据该语音指令从该终端的本地数据库中查找与该语音指令对应的任务，并将查找到的任务确定为该多个待执行任务；
在该终端依据该语音指令从该终端的本地数据库中没有查找到与该语音指令对应的任务的情况下，该终端将该语音指令发送到网络服务器，并接收该网络服务器获取的与该语音指令对应的任务，并将该任务确定为该多个待执行任务。
可选地，该终端将该语音指令转换为字符指令，获取与该字符指令关联的该多个待执行任务。
可选地，执行该多个待执行任务之前，该终端显示该多个待执行任务；
接收用户输入的调整指令，并依据该调整指令管理该多个待执行任务。
可选地，在依据该调整指令管理该多个待执行任务之后，将该调整后的多个待执行任务上传至网络服务器，其中，该网络服务器存储有该语音指令与该多个待执行任务的映射关系。
可选地，该终端依据预设顺序调用该终端内置的多个应用程序分别执行该多个待执行任务。
根据本公开的另一个实施例，还提供了一种语音输入的处理方法，包括：
网络服务器接收终端上传的通过转换语音指令得到的字符指令；
获取与该字符指令对应的多个待执行任务，并将该多个待执行任务下发到该终端。
可选地，在获取与该字符指令对应的多个待执行任务之后，该网络服务器将记录有该多个待执行任务的第一列表发送到该终端；
接收该终端发送的第二列表，其中，该第二列表是该终端依据用户的调整指令调整过的该第一列表；
建立该第二列表与该字符指令的映射关系，并存储该映射关系。
下面结合本公开的优选实施例进行详细说明。
在本申请文件中提供的语音识别的终端具有以下各个模块的功能：语音识别模块(相当于上述实施例中的语音采集电路102)，需求解析模块，中央处理模块，需求记录模块(后续三个模块的功能相当于上述实施例中的第一处理器104)。
语音识别模块，用于采集和识别用户的语音并转化为一条字符指令,这里称为一个用户故 事，输出给需求解析模块。(需要补充的是，本优选实施例中记载的用户故事包括多个需求，该多个需求即上述实施例中的多个待执行任务)。
需求解析模块，预先将用户故事数据发送到本地需求数据库进行解析，若解析无果再发送到云端需求解析数据服务器进行解析。并将需求解析结果发送到中央处理模块。
该云端需求数据服务器，根据大量用户的行为数据统计学习并结合数据挖掘系统以及采用向量机分类器等方法，建立需求分类数据库，并不断更新和升级。并将解析出的需求数据以指定格式，输出到中央处理模块。
实现过程如下：一条用户指令为“我10月15号要去北京出差”，云端需求解析服务器会先从指令中提取出关键数据“10月15号，北京，出差”，并将关键数据在需求解析数据库中进行需求匹配，最终深度解析出一系列需求：订机票/火车票，订酒店，起床闹钟，定时叫车等一系列需求。
中央处理模块，用于接收需求数据，并以时间顺序排列成列表，以UI界面的形式呈现给用户，用户可(用语音或手动)进行修改和配置，待用户确认后，将故事的需求列表输出到需求记录模块进行保存。然后按顺序开始执行该故事的需求列表。一个用户故事可能包含多条需求，中央处理器需要协作调用各个应用模块完成这些需求，还可根据需求提供界面或语音让用户进行选择。每当执行完该故事的一条需求，通知需求记录模块从需求列表中移除该条需求。执行每条需求时可通过语音或界面提示用户。
需求记录模块，该模块接收并保存用户确认的需求列表，用户的一个语音指令我们称之为一个故事，该故事对应一个需求列表。提供操作接口给中央处理模块，以便删除已完成的需求，所有需求完成，该故事也自动删除。
本公开优选实施例中的具体技术方案如下：
第一步：语音识别模块，采集语音指令，识别并转化为字符指令(即一个用户故事)，输出给需求解析模块。
第二步：需求解析模块，将用户故事数据发送到本地需求数据库进行解析，若解析无果再发送到云端需求解析数据服务器进行解析。并将需求解析结果发送到中央处理模块。
该云端需求数据服务器，根据大量用户的行为数据统计学习并结合数据挖掘系统以及采用向量机分类器等方法，建立需求分类数据库，并不断更新和升级。并将解析出的需求数据以指定格式，输出到中央处理模块。
一个示例如下：一条用户指令为“我10月15号要去北京出差”，云端需求解析服务器会先从指令中提取出关键数据“10月15号，北京，出差”，并将关键数据在需求解析数据库中进行需求分析和匹配。关键字“出差”解析出的需求有：订机票/火车票，订酒店，设置日程闹钟，定时叫车等一系列需求，再与“时间”“目的地”等关键字进行组合，最终输出的需求为：
1)订机票/火车票(10月15号到达)
2)订北京的酒店(10月15号起)
3)日程闹钟(10月15号7点)
4)定时叫车(10月15号8点)
这些需求可能会转换为已协议预定的字符或格式返回.
第三步：中央处理模块，
(1)接收需求数据，并以时间顺序排列成列表，以UI界面的形式呈现给用户，用户可以说“修改第X条”或手动点击需求条目，进入子界面进行修改。例如在上述例子中，用户可以修改订机票还是火车票，订酒店的起止日期，闹钟的时间，以及打车的时间和目的地，或者删除某一条需求，然后确认执行。待用户确认后，中央处理模块将该故事的需求列表输出到需求记录模块进行保存。
(2)然后按顺序开始执行该故事的需求列表。一条需求可能对应多个功能，中央处理器需要协作调用各个应用模块完成该需求。
例子1:订机票(10月15号),需要联动的模块有
a)打开定位开关，获取当前城市信息。
b)用语音助手播报“正在为你预定去北京的机票，请您确认航班”。
c)打开订票软件(若没有即打开订票网站)，并将起点终点城市信息进行搜索，等待用户选择和预定搜索出来的航班。
例子2：叫车去机场(10月15号8点)
a)设置一个10月15号8点的需求型日程闹钟，并将该需求的编号保存到日程闹钟内容里。
b)日程闹钟到时，触发中央处理模块去读取日程中的需求编号，并从需求模块查找和执行该需求“叫车去机场”。
c)打开定位开关获取当前起点位置。
d)将起止地点输入打车软件开始查询价格，等待用户确认叫车。
(3)当一条需求执行完成，中央处理器会自动检查是否会影响列表中的其他需求，找出可能受到影响的需求，进行自动调整，并弹出相关的需求条目请用户确认：
(a)日程闹钟(10月15号12点)
(b)定时叫车(10月15号13点)
(4)每当执行完一条需求，中央处理模块即从需求记录模块中移除该条需求。
第四步：需求记录模块,记录各个用户故事对应的需求列表，提供操作接口给中央处理模块，以便删除已完成的需求，所有需求完成，该故事也自动删除。同时也为用户提供了入口可以随时删除需求列表，从而中断需求任务的执行。
图4是跟本公开优选实施例中四大模块依据语音执行后续步骤的流程图，如图4所示，中央处理器可以联动控制图4中左侧的多个模块分别执行上述任务，最重要的是中央处理模块和云端需求解析服务器,中央处理模块负责解析需求并调用其他所有模块共同联动工作，可以比喻为一台智能化机器人。本地和云端需求解析服务器，对用户需求进行智能挖掘和分析，云端服务器可以不断学习和更新升级。
采用上述优选实施例中的技术方案，为用户提供一套智能化语音服务系统，可以准确和 深度解析用户一句简短指令中包含的需求,并协调各个应用模块联动为用户提供服务，以完成用户希望的系列需求。极大程度为用户节约时间，给用户提供更方便和人性化的语音体验服务。
实施例三
本公开的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的程序代码：
S1，终端接收用户的语音指令；
S2，该终端获取与该语音指令关联的多个待执行任务，并执行该多个待执行任务。
可选地，存储介质还被设置为存储用于执行以下步骤的程序代码：
S3，网络服务器接收终端上传的通过转换语音指令得到的字符指令；
S4，获取与该字符指令对应的多个待执行任务，并将该多个待执行任务下发到该终端。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
可选地，在本实施例中，处理器根据存储介质中已存储的程序代码执行上述实施例中的方法步骤。
可选地，本实施例中的示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本公开的各模块或各步骤可以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，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，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，本公开不限制于任何特定的硬件和软件结合。
以上所述仅为本公开的优选实施例而已，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。
工业实用性
本公开适用于通信领域，用以解决相关技术中用户通过语音输入来操作手机实现的用途单一的问题，并有效扩展了用户通过语音来操控终端的便捷性。

Claims (16)

  1. 一种语音输入的处理方法，包括：
    终端接收语音指令；
    所述终端获取与所述语音指令关联的多个待执行任务，并执行所述多个待执行任务。
  2. 根据权利要求1所述的方法，其中，所述终端获取与所述语音指令关联的多个待执行任务，包括以下之一：
    所述终端依据所述语音指令从所述终端的本地数据库中查找与所述语音指令对应的任务，并将查找到的任务确定为所述多个待执行任务；
    在所述终端依据所述语音指令从所述终端的本地数据库中没有查找到与所述语音指令对应的任务的情况下，所述终端将所述语音指令发送到网络服务器，并接收所述网络服务器获取的与所述语音指令对应的任务，并将该任务确定为所述多个待执行任务。
  3. 根据权利要求1所述的方法，其中，所述终端获取与所述语音指令关联的多个待执行任务，包括：
    所述终端将所述语音指令转换为字符指令，获取与所述字符指令关联的所述多个待执行任务。
  4. 根据权利要求1所述的方法，其中，执行所述多个待执行任务之前，所述方法还包括：
    所述终端显示所述多个待执行任务；
    接收输入的调整指令，并依据所述调整指令管理所述多个待执行任务。
  5. 根据权利要求4所述的方法，其中，在依据所述调整指令管理所述多个待执行任务之后，将所述调整后的多个待执行任务上传至网络服务器，其中，所述网络服务器存储有所述语音指令与所述多个待执行任务的映射关系。
  6. 根据权利要求1所述的方法，其中，执行所述多个待执行任务，包括：
    所述终端依据预设顺序调用所述终端的多个应用程序分别执行所述多个待执行任务。
  7. 一种语音输入的处理方法，包括：
    网络服务器接收终端上传的通过转换语音指令得到的字符指令；
    获取与所述字符指令对应的多个待执行任务，并将所述多个待执行任务下发到所述终端。
  8. 根据权利要求7所述的方法，其中，在获取与所述字符指令对应的多个待执行任务之后，所述网络服务器将记录有所述多个待执行任务的第一列表发送到所述终端；
    接收所述终端发送的第二列表，其中，所述第二列表是所述终端依据用户的调整指令调整过的所述第一列表；
    建立所述第二列表与所述字符指令的映射关系，并存储所述映射关系。
  9. 一种终端，包括：
    语音采集电路，设置为接收语音指令，并将所述语音指令传输到第一处理器；
    第一处理器，设置为获取与所述语音指令关联的多个待执行任务，并执行所述多个待执行任务。
  10. 根据权利要求9所述的终端，其中，所述第一处理器还设置为通过以下方式之一获取与所述语音指令关联的多个待执行任务：
    所述第一处理器设置为依据所述语音指令从所述终端的本地数据库中查找与所述语音指令对应的任务，并将查找到的任务确定为所述多个待执行任务；
    所述第一处理器还设置为在依据所述语音指令从所述终端的本地数据库中没有查找到与所述语音指令对应的任务的情况下，将所述语音指令发送到网络服务器，并接收所述网络服务器获取的与所述语音指令对应的任务，并将该任务确定为所述多个待执行任务。
  11. 根据权利要求9所述的终端，其中，所述第一处理器还设置为将所述语音指令转换为字符指令，获取与所述字符指令关联的所述多个待执行任务。
  12. 根据权利要求9所述的终端，其中，所述第一处理器还设置为在执行所述多个待执行任务之前，通过所述终端的显示器显示所述多个待执行任务；
    所述第一处理器还设置为接收用户输入的调整指令，并依据所述调整指令管理所述多个待执行任务。
  13. 根据权利要求12所述的终端，其中，所述第一处理器还设置为在依据所述调整指令管理所述多个待执行任务之后，将调整后的多个待执行任务上传至网络服务器，其中，所述网络服务器存储有所述语音指令与所述多个待执行任务的映射关系。
  14. 根据权利要求9所述的终端，其中，所述第一处理器设置为依据预设顺序调用所述终端内置的多个应用程序分别执行所述多个待执行任务。
  15. 一种网络服务器，包括：
    通信装置，设置为接收终端上传的通过转换语音指令得到的字符指令，并将第二处理器获取的多个待执行任务下发到所述终端；
    所述第二处理器，设置为获取与所述字符指令对应的所述多个待执行任务。
  16. 根据权利要求15所述的网络服务器，其中，所述通信装置设置为将记录有所述多个待执行任务的第一列表发送到所述终端，并接收所述终端发送的第二列表，其中，所述第二列表是所述终端依据用户的调整指令调整过的所述第一列表；
    所述第二处理器，还设置为建立所述第二列表与所述字符指令的映射关系，并存储所述映射关系。
PCT/CN2017/085051 2016-12-01 2017-05-19 语音输入的处理方法、终端和网络服务器 WO2018099000A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611094261.XA CN108132768A (zh) 2016-12-01 2016-12-01 语音输入的处理方法，终端和网络服务器
CN201611094261.X 2016-12-01

Publications (1)

Publication Number Publication Date
WO2018099000A1 true WO2018099000A1 (zh) 2018-06-07

Family

ID=62241152

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/085051 WO2018099000A1 (zh) 2016-12-01 2017-05-19 语音输入的处理方法、终端和网络服务器

Country Status (2)

Country Link
CN (1) CN108132768A (zh)
WO (1) WO2018099000A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111124348A (zh) * 2019-12-03 2020-05-08 北京蓦然认知科技有限公司 一种生成交互引擎簇的方法及装置
CN112820284A (zh) * 2020-12-28 2021-05-18 恒大新能源汽车投资控股集团有限公司 语音交互方法、装置、电子设备及计算机可读存储介质
CN113192490A (zh) * 2021-04-14 2021-07-30 维沃移动通信有限公司 语音处理方法、装置和电子设备
CN114915513A (zh) * 2021-12-17 2022-08-16 山西三友和智慧信息技术股份有限公司 一种具有语音控制的人工智能家居控制系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200019370A1 (en) * 2018-07-12 2020-01-16 Disney Enterprises, Inc. Collaborative ai storytelling
CN109542216B (zh) 2018-10-11 2022-11-22 平安科技（深圳）有限公司 人机交互方法、系统、计算机设备及存储介质
CN111048078A (zh) * 2018-10-15 2020-04-21 阿里巴巴集团控股有限公司 语音复合指令处理方法和系统及语音处理设备和介质
CN109262617A (zh) * 2018-11-29 2019-01-25 北京猎户星空科技有限公司 机器人控制方法、装置、设备及存储介质
CN110706705A (zh) * 2019-10-22 2020-01-17 青岛海信移动通信技术股份有限公司 一种语音控制方法、终端及计算机存储介质
CN110853645A (zh) * 2019-12-02 2020-02-28 三星电子（中国）研发中心 一种识别语音命令的方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103474068A (zh) * 2013-08-19 2013-12-25 安徽科大讯飞信息科技股份有限公司 实现语音命令控制的方法、设备及系统
CN105120373A (zh) * 2015-09-06 2015-12-02 上海智臻智能网络科技股份有限公司 语音传输控制方法及系统
US20160078864A1 (en) * 2014-09-15 2016-03-17 Honeywell International Inc. Identifying un-stored voice commands
CN105739940A (zh) * 2014-12-08 2016-07-06 中兴通讯股份有限公司 存储方法及装置
WO2016184095A1 (zh) * 2015-10-16 2016-11-24 中兴通讯股份有限公司 操作事件的执行方法及装置、终端

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9043703B2 (en) * 2012-10-16 2015-05-26 Facebook, Inc. Voice commands for online social networking systems
CN103000175A (zh) * 2012-12-03 2013-03-27 深圳市金立通信设备有限公司 一种语音识别的方法及移动终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103474068A (zh) * 2013-08-19 2013-12-25 安徽科大讯飞信息科技股份有限公司 实现语音命令控制的方法、设备及系统
US20160078864A1 (en) * 2014-09-15 2016-03-17 Honeywell International Inc. Identifying un-stored voice commands
CN105739940A (zh) * 2014-12-08 2016-07-06 中兴通讯股份有限公司 存储方法及装置
CN105120373A (zh) * 2015-09-06 2015-12-02 上海智臻智能网络科技股份有限公司 语音传输控制方法及系统
WO2016184095A1 (zh) * 2015-10-16 2016-11-24 中兴通讯股份有限公司 操作事件的执行方法及装置、终端

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111124348A (zh) * 2019-12-03 2020-05-08 北京蓦然认知科技有限公司 一种生成交互引擎簇的方法及装置
CN111124348B (zh) * 2019-12-03 2023-12-05 光禹莱特数字科技(上海)有限公司 一种生成交互引擎簇的方法及装置
CN112820284A (zh) * 2020-12-28 2021-05-18 恒大新能源汽车投资控股集团有限公司 语音交互方法、装置、电子设备及计算机可读存储介质
CN113192490A (zh) * 2021-04-14 2021-07-30 维沃移动通信有限公司 语音处理方法、装置和电子设备
CN114915513A (zh) * 2021-12-17 2022-08-16 山西三友和智慧信息技术股份有限公司 一种具有语音控制的人工智能家居控制系统

Also Published As

Publication number Publication date
CN108132768A (zh) 2018-06-08

Similar Documents

Publication Publication Date Title
WO2018099000A1 (zh) 语音输入的处理方法、终端和网络服务器
CN110235154B (zh) 使用特征关键词将会议与项目进行关联
US10311877B2 (en) Performing tasks and returning audio and visual answers based on voice command
CN106406806A (zh) 一种用于智能设备的控制方法及装置
US20120330662A1 (en) Input supporting system, method and program
CN104813311A (zh) 用于多人的虚拟代理推荐的系统和方法
KR102220945B1 (ko) 휴대 기기에서 연관 정보 표시 방법 및 장치
CN104378441A (zh) 日程创建方法和装置
CN108701127A (zh) 电子设备及其操作方法
CN104035995A (zh) 群标签生成方法及装置
CN110992937B (zh) 语言离线识别方法、终端及可读存储介质
WO2014101416A1 (zh) 一种文件展示方法及装置
CN104461446B (zh) 基于语音交互的软件运行方法及系统
CN113705943B (zh) 基于语音对讲功能的任务管理方法、系统与移动装置
CN109271503A (zh) 智能问答方法、装置、设备及存储介质
US20180211669A1 (en) Speech Recognition Based on Context and Multiple Recognition Engines
US20120185417A1 (en) Apparatus and method for generating activity history
CN104702758B (zh) 一种终端及其管理多媒体记事本的方法
WO2019062705A1 (zh) 信息输出方法、装置及电子设备
JP5220451B2 (ja) 電話受付システム、電話受付方法、プログラム、及び記録媒体
CN109658070B (zh) 备忘事件的备忘提醒方法、终端及存储介质
CN112700770A (zh) 语音控制方法、音箱设备、计算设备和存储介质
EP3979162A1 (en) Systems, methods, and apparatuses for improving performance of executing a workflow operation
CN109981490B (zh) 具备行动加值服务的智能网络交换机系统
CN115550502A (zh) 日程记录及提示方法、装置、智能设备及存储介质

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: 17875330

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: 17875330

Country of ref document: EP

Kind code of ref document: A1