WO2024098878A1 - 信息输出通道选择方法、信息的输出方法、装置及设备 - Google Patents

信息输出通道选择方法、信息的输出方法、装置及设备 Download PDF

Info

Publication number
WO2024098878A1
WO2024098878A1 PCT/CN2023/113728 CN2023113728W WO2024098878A1 WO 2024098878 A1 WO2024098878 A1 WO 2024098878A1 CN 2023113728 W CN2023113728 W CN 2023113728W WO 2024098878 A1 WO2024098878 A1 WO 2024098878A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
output
channel
optional
determining
Prior art date
Application number
PCT/CN2023/113728
Other languages
English (en)
French (fr)
Inventor
孙明明
曾理
张晓帆
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2024098878A1 publication Critical patent/WO2024098878A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00—Arrangements affording multiple use of the transmission path
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00—Arrangements affording multiple use of the transmission path
    • H04L5/02—Channels characterised by the type of signal
    • 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
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer

Definitions

  • the present application relates to human-computer interaction technology, and in particular to an information output channel selection method, an information output method, a device and equipment.
  • UI user interface
  • structured information such as cards and lists can be presented to users in a more concise, efficient, beautiful and rich style.
  • Users can conduct human-computer interaction through UI and complete information transmission.
  • the selection of a transmission channel usually depends on a single electronic device or a single scene mode, and cannot be effectively matched to different types of electronic devices or different types of scenes.
  • the embodiment of the present application provides a method for selecting an information output channel, which is applied in an electronic device and includes:
  • An output channel is determined according to the classification information and the data collected by the sensor; wherein the output channel includes an output device and an output mode corresponding to the output device.
  • the present application provides a method for outputting information, which is applied to an output device and includes:
  • the output information is determined based on the notification information, and the output information is output based on the output modality.
  • the embodiment of the present application provides an information output channel selection device, which is arranged in an electronic device and includes:
  • an acquisition module configured to acquire notification information and data collected by sensors
  • a classification module configured to determine classification information corresponding to the notification information based on the notification information
  • a determination module is configured to determine an output channel according to the classification information and the data collected by the sensor; wherein the output device includes an output device and an output mode corresponding to the output device.
  • the present application provides an information output device, which is arranged in an output device and includes:
  • a receiving module configured to receive information and output a modality
  • a first output module configured to output the output information based on the output modality when the received information is output information
  • the second output module is configured to determine the output information based on the notification information and output the output information based on the output modality when the received information is notification information.
  • An embodiment of the present application provides an electronic device, comprising: a processor and a storage medium storing instructions executable by the processor, wherein the storage medium relies on the processor to perform operations via a communication bus, and when the instructions are executed by the processor, the information output channel selection method described in one or more of the above embodiments is executed.
  • An embodiment of the present application provides an output device, including: a processor and a storage medium storing instructions executable by the processor, wherein the storage medium relies on the processor to perform operations via a communication bus, and when the instructions are executed by the processor, the information output method described in one or more of the above embodiments is executed.
  • An embodiment of the present application provides a computer storage medium storing executable instructions.
  • the processor executes the information output channel selection method described in one or more embodiments, or executes the information output method described in one or more embodiments.
  • FIG1 is a schematic diagram of a flow chart of an optional information output channel selection method provided in an embodiment of the present application.
  • FIG2 is a schematic diagram of a flow chart of an optional information output method provided in an embodiment of the present application.
  • FIG3 is a schematic diagram of an example of an optional network structure composed of multiple devices provided in an embodiment of the present application.
  • FIG4 is a flow chart of an example of an optional information output channel selection method and information output method provided in an embodiment of the present application
  • FIG5 is a schematic diagram of an optional UI card design architecture provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of an example of an optional UI interface provided in an embodiment of the present application.
  • FIG7 is a schematic diagram of the structure of an optional information output channel selection device provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of the structure of an optional information output device provided in an embodiment of the present application.
  • FIG9 is a schematic diagram of the structure of an optional electronic device provided in an embodiment of the present application.
  • FIG. 10 is a schematic diagram of the structure of an optional output device provided in an embodiment of the present application.
  • An embodiment of the present application provides a method for selecting an information output channel, which is applied in an electronic device and includes:
  • Acquire notification information and data collected by sensors based on the notification information, determine classification information corresponding to the notification information; determine an output channel according to the classification information and the data collected by the sensors; wherein the output channel includes an output device and an output mode corresponding to the output device.
  • determining the classification information corresponding to the notification information based on the notification information includes: determining the classification information corresponding to the notification information based on a result of semantic analysis of the notification information.
  • the classification information includes one or more of the following: privacy information, urgency information, and importance information.
  • determining the output channel according to the classification information and the data collected by the sensor includes: determining channel quality information of the optional output channel based on the data collected by the sensor; and determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channel.
  • the channel quality information includes one or more of the following: availability information, interference information, channel capacity information, privacy information and adaptability information.
  • the determining of the channel quality information of the optional output channel based on the data collected by the sensor includes: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; re-determining the channel capacity information of the optional output channel based on the availability information of the optional output channel and the channel capacity information of the optional output channel; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the optional output channel, the preset privacy information of the optional channel and the preset adaptability information of the optional output channel as the channel quality information of the optional output channel.
  • the determining of the channel quality information of the optional output channel based on the data collected by the sensor includes: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the preset channel capacity information of the optional output channel, the preset privacy information of the optional channel and the preset adaptability information of the optional output channel as the channel quality information of the optional output channel.
  • determining the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels includes: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; and when the number of the selected output channels is one, determining the selected output channel as the output channel.
  • determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when the number of the selected output channels is a first number, selecting the output channel based on the selected channel.
  • the channel quality information of the output channels is retrieved, a second number of output channels are selected from the selected output channels, and the selected second number of output channels are determined as the output channels, wherein the second number is greater than 1 and less than the first number.
  • the output channel is determined from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when there are multiple output channels to be selected, based on the channel quality information of the selected output channels, performing evaluation processing on the selected output channels to obtain evaluation values of the selected output channels; and determining the output channel corresponding to the maximum value of the evaluation values among the selected output channels as the output channel.
  • the output channel is determined from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when there are multiple output channels selected, determining the number of priorities of privacy information, availability information, and channel capacity information in the channel quality information of each output channel in the selected output channels that are higher than or equal to a preset priority; and determining the output channel corresponding to the maximum value of the number as the output channel.
  • the first preset condition refers to that the level of the classification information reaches a preset level.
  • selecting an output channel satisfying a second preset condition from the optional output channels includes: selecting an output channel satisfying the second preset condition from the optional output channels based on channel quality information of the optional output channels.
  • determining the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels includes: when the privacy information in the classification information is of the first priority, selecting from the optional output channels an output channel whose privacy information in the channel quality information is of the highest priority; wherein the first priority is the highest priority of the privacy information in the classification information; and determining the selected output channel as the output channel.
  • the output channel is determined from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the importance information in the classification information is the first priority or the urgency information is the first priority, selecting from the optional output channels an output channel whose interference information in the channel quality information is anti-interference and whose availability information in the channel quality information is the highest priority; wherein the first priority is the highest priority among the importance information in the classification information, and is the highest priority among the urgency information in the classification information; and determining the selected output channel as the output channel.
  • determining the output channel based on the classification information and the data collected by the sensor includes: performing scene analysis processing on the data collected by the sensor to obtain scene information of the sensor; inputting the classification information, the scene information of the sensor and the optional output channel into a preset neural network model to select multiple output channels to obtain the output channel.
  • the method further includes: sending the notification information and the output mode to the output device.
  • the method further includes: outputting the notification information based on the output modality.
  • the output device comprises a master device in a network architecture of multiple devices.
  • the method when the electronic device is a server or a main device in a network architecture of multiple devices, the method further includes: determining output information based on the notification information; and sending the output information and the output mode to the output device.
  • the method further includes: outputting the output information based on the output modality.
  • determining the output information based on the notification information includes: when the output mode is a tactile mode, based on a preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • determining the output information based on the notification information includes: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on the key information of the notification information.
  • determining the output information based on the notification information includes: when the output modality is a visual modality or an auditory modality, and when the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information; wherein the second capacity range is different from a preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the determining of the output information based on the notification information includes: when the output mode is auditory In the modal mode, the notification information is converted into voice, and the converted voice data is determined as the output information.
  • the determining of the output information based on the key information of the notification information includes: when the output modality is an auditory modality, performing voice conversion on the key information, and determining the converted voice data as the output information.
  • determining the output information based on the notification information includes: when the output modality is a visual modality, performing UI adaptation on the notification information based on an output device corresponding to the output channel to obtain the output information.
  • determining the output information based on the key information of the notification information includes: when the output modality is a visual modality, performing UI adaptation on the key information based on an output device corresponding to the output channel to obtain the output information.
  • determining the output channel according to the classification information and the data collected by the sensor includes: determining the output device according to the classification information and the data collected by the sensor; and determining the output mode from the modes corresponding to the output device.
  • determining the output channel according to the classification information and the data collected by the sensor includes: determining the output mode according to the classification information and the data collected by the sensor; and determining the output device from devices corresponding to the output mode.
  • An embodiment of the present application provides a method for selecting an information output channel, which is applied in an electronic device and includes:
  • Receiving information and an output mode when the received information is output information, outputting the output information based on the output mode;
  • the output information is determined based on the notification information, and the output information is output based on the output modality.
  • determining the output information based on the notification information includes: when the output modality is a tactile modality, based on a preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • determining the output information based on the notification information includes: when the output modality is a visual modality or an auditory modality, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on key information of the notification information.
  • determining the output information based on the notification information includes: when the output modality is a visual modality or an auditory modality, and the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information; wherein the second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • determining the output information based on the notification information includes: when the output modality is an auditory modality, converting the notification information into voice, and determining the converted voice data as the output information.
  • the determining of the output information based on the key information of the notification information includes: when the output modality is an auditory modality, performing voice conversion on the key information, and determining the converted voice data as the output information.
  • determining the output information based on the notification information includes: when the output modality is a visual modality, performing UI adaptation on the notification information based on an output device corresponding to the output channel to obtain the output information.
  • determining the output information based on the key information of the notification information includes: when the output modality is a visual modality, performing UI adaptation on the key information based on an output device corresponding to the output channel to obtain the output information.
  • the embodiment of the present application further provides a device for selecting an information output channel, the device being arranged in an electronic device, comprising:
  • an acquisition module configured to acquire notification information and data collected by a sensor
  • a classification module configured to determine classification information corresponding to the notification information based on the notification information
  • a determination module configured to determine an output device according to the classification information and the data collected by the sensor; wherein the output channel includes an output device and an output mode corresponding to the output device
  • the classification module is configured to: determine classification information corresponding to the notification information based on a result of a semantic analysis of the notification information.
  • the classification information includes one or more of the following: privacy information, urgency information, and importance information.
  • the determination module is configured to: determine the channel quality information of the optional output channel based on the data collected by the sensor; and determine the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channel.
  • the channel quality information includes one or more of the following: availability information, interference information, channel capacity information, privacy information and adaptability information.
  • the determination module determines the channel quality of the optional output channel based on the data collected by the sensor.
  • the information includes: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; re-determining the channel capacity information of the optional output channel based on the availability information of the optional output channel and the channel capacity information of the optional output channel; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the optional output channel, the preset privacy information of the optional channel and the preset adaptability information of the optional output channel as the channel quality information of the optional output channel.
  • the determination module determines the channel quality information of the optional output channel based on the data collected by the sensor, including: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the preset channel capacity information of the optional output channel, the preset privacy information of the optional channel and the preset adaptability information of the optional output channel as the channel quality information of the optional output channel.
  • a determination module determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when the number of the selected output channels is a first number, based on the channel quality information of the selected output channels, selecting a second number of output channels from the selected output channels, and determining the selected second number of output channels as the output channels, the second number being greater than 1 and less than the first number.
  • a determination module determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when there are multiple output channels to be selected, based on the channel quality information of the selected output channels, performing evaluation processing on the selected output channels to obtain an evaluation value of the selected output channels; and determining the output channel corresponding to the maximum value of the evaluation value among the selected output channels as the output channel.
  • a determination module determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies a first preset condition, selecting an output channel that satisfies a second preset condition from the optional output channels; when there are multiple output channels selected, determining the number of priorities of privacy information, availability information, and channel capacity information in the channel quality information of each output channel in the selected output channels that are higher than or equal to a preset priority; and determining the output channel corresponding to the maximum value of the number as the output channel.
  • the first preset condition refers to that the level of the classification information reaches a preset level.
  • the determination module selects an output channel that meets a second preset condition from the optional output channels, including: based on channel quality information of the optional output channels, selecting an output channel that meets the second preset condition from the optional output channels.
  • a determination module determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the privacy information in the classification information is of the first priority, selecting from the optional output channels an output channel whose privacy information in the channel quality information is of the highest priority; wherein the first priority is the highest priority of the privacy information in the classification information; and determining the selected output channel as the output channel.
  • a determination module determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the importance information in the classification information is the first priority or the urgency information is the first priority, selecting from the optional output channels an output channel whose interference information in the channel quality information is anti-interference and whose availability information in the channel quality information is the highest priority; wherein the first priority is the highest priority in the importance information in the classification information, and is the highest priority in the urgency information in the classification information; and determining the selected output channel as the output channel.
  • the determination module is configured to: perform scene analysis processing on the data collected by the sensor to obtain scene information of the sensor; input the classification information, the scene information of the sensor and the optional output channel into a preset neural network model to select multiple output channels to obtain the output channel.
  • the apparatus when the electronic device is a master device in a multi-device network architecture, the apparatus is further configured to: send the notification information and the output mode to the output device
  • the apparatus when the output device is the master device, the apparatus is further configured to: output the notification information based on the output modality.
  • the output device comprises a master device in a network architecture of multiple devices.
  • the apparatus when the electronic device is a server or a main device in a network architecture of multiple devices, the apparatus is further configured to: determine output information based on the notification information; and send the output information and the output modality to the output device.
  • the apparatus when the output device is the master device, the apparatus is further configured to: The output information is output in a state.
  • the device determines the output information based on the notification information, including: when the output mode is a tactile mode, based on a preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • the device determines the output information based on the notification information, including: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on the key information of the notification information.
  • the device determines the output information based on the notification information, including: when the output modality is a visual modality or an auditory modality, and when the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information; wherein the second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the device determines the output information based on the notification information, including: when the output modality is an auditory modality, performing voice conversion on the notification information, and determining the converted voice data as the output information.
  • the device determines the output information based on the notification information, including: when the output modality is a visual modality, based on the output device corresponding to the output channel, performing UI adaptation on the notification information to obtain the output information.
  • the device determines the output information based on the key information of the notification information, including: when the output modality is a visual modality, based on the output device corresponding to the output channel, performing UI adaptation on the key information to obtain the output information.
  • the determination module is configured to: determine the output device according to the classification information and the data collected by the sensor; and determine the output mode from the modes corresponding to the output device.
  • the determination module is configured to: determine the output modality according to the classification information and the data collected by the sensor; and determine the output device from the devices corresponding to the output modality.
  • the present application provides an information output device, which is arranged in an output device and includes:
  • a receiving module is configured to receive information and an output mode; a first output module is configured to output the output information based on the output mode when the received information is output information; and a second output module is configured to determine the output information based on the notification information and output the output information based on the output mode when the received information is notification information.
  • the second output module determines the output information based on the notification information, including: when the output modality is a tactile modality, based on a preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • the second output module determines the output information based on the notification information, including: when the output modality is a visual modality or an auditory modality, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on the key information of the notification information.
  • the second output module determines the output information based on the notification information, including: when the output modality is a visual modality or an auditory modality, and the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the key information of the notification information; wherein the second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the second output module determines the output information based on the notification information, including: when the output modality is an auditory modality, converting the notification information into voice, and determining the converted voice data as the output information.
  • the device determines the output information based on the key information of the notification information, including: when the output modality is an auditory modality, performing voice conversion on the key information, and determining the converted voice data as the output information.
  • the device determines the output information based on the notification information, including: when the output modality is a visual modality, based on the output device corresponding to the output channel, performing UI adaptation on the notification information to obtain the output information.
  • the device determines the output information based on the key information of the notification information, including: when the output modality is a visual modality, based on the output device corresponding to the output channel, performing UI adaptation on the key information to obtain the output information.
  • the embodiment of the present application provides an electronic device, comprising: a processor and a storage medium storing instructions executable by the processor, wherein the storage medium relies on the processor to perform operations through a communication bus, and when the instructions are executed by the processor, the above-mentioned The information output channel selection method described in one or more embodiments.
  • An embodiment of the present application provides an output device, including: a processor and a storage medium storing instructions executable by the processor, wherein the storage medium relies on the processor to perform operations through a communication bus, and when the instructions are executed by the processor, the information output channel selection method described in one or more of the above embodiments is executed.
  • An embodiment of the present application provides a computer storage medium storing executable instructions.
  • the processor executes the information output channel selection method described in one or more of the above embodiments, or executes the information output method described in one or more of the above embodiments.
  • An embodiment of the present application provides an information output channel selection method, which can be applied to a single device or to a network architecture consisting of multiple devices.
  • the embodiment of the present application does not make any specific limitations on this.
  • the single device executes the information output channel selection method, and after determining the output channel and the output mode corresponding to the output device, executes the following information output method.
  • the device that executes the information output channel selection method can be any device in the network architecture, or a master device in the network architecture, or a server connected to any device in the network architecture.
  • the embodiments of the present application do not make specific limitations on this.
  • FIG. 1 is a flow chart of an optional information output channel selection method provided in an embodiment of the present application. As shown in FIG. 1 , the information output channel selection method may include:
  • S101 Acquire notification information and data collected by sensors
  • S102 Determine, based on the notification information, classification information corresponding to the notification information
  • S103 Determine an output channel according to the classification information and the data collected by the sensor.
  • smart cars can provide visual and auditory channels
  • smart phones, watches, and bracelets can provide visual, auditory, and tactile (vibration) channels
  • smart TVs can provide visual and auditory channels
  • smart headphones can provide auditory channels.
  • more new devices may emerge to provide similar channel services.
  • the properties of various channels are different (such as channel capacity, privacy, interference, etc.), and they rely on different devices.
  • the accessibility and availability of different channels are different.
  • the mobile phone UI interface channel has the highest channel capacity and high privacy, and is generally used as the main channel, but in environments such as strong light and motion, the anti-interference ability is poor, and the screen-off availability is poor in scenarios such as sports and driving.
  • Smart car interconnected voice, smart watch vibration, and smart headset voice are generally weaker than mobile phone UI interfaces in terms of privacy and channel capacity, but in the above-mentioned scenarios where the mobile phone's anti-interference ability or availability is insufficient, the anti-interference ability and availability of these devices are higher than the mobile phone UI interface, and can be used as auxiliary channels to provide users with convenient, natural, and ubiquitous services.
  • the selection of a transmission channel usually depends on a single device or a single scene mode, and cannot be effectively matched to different types of electronic devices or different types of scenes.
  • An embodiment of the present application provides an information output channel selection method to obtain notification information.
  • the notification information can be a text message received by a smartphone, a prompt message generated by a smartphone, or UI interface information or graphical user interface (GUI) interface information.
  • GUI graphical user interface
  • UI interface information is interface information stored in the architecture of UI Tree.
  • UI Tree refers to the tree-like hierarchical structure of UI element content in the system, which is similar to HTML.
  • GUI interface information is interface information stored in the architecture of GUI Tree.
  • GUI Tree refers to the tree-like hierarchical structure of GUI element content in the system, which is similar to HTML.
  • a UI interface information or a GUI interface information in the interface of a third-party application (Application, APP) in a smart phone both UI interface information and GUI interface information include attribute information of controls.
  • the senor refers to a sensor related to a single device, which can be a sensor connected to a single device or a sensor on a single device.
  • a sensor is a sensor related to multiple devices. It can be a sensor connected to multiple devices or a sensor on multiple devices. Each of the multiple devices receives data collected by the sensor related to it, and each device sends the received data collected by the sensor to the main device or server, so that the main device or server in the network architecture can obtain the data collected by the sensor.
  • the above sensors may include position sensors, environmental sensors, motion sensors, etc.
  • this application This embodiment does not specifically limit this.
  • the sensor may include a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, etc.
  • the pressure sensor is used to sense the pressure signal and can convert the pressure signal into an electrical signal.
  • the pressure sensor can be set on the display screen.
  • the capacitive pressure sensor can be a parallel plate including at least two conductive materials. When a force acts on the pressure sensor, the capacitance between the electrodes changes. The intensity of the pressure is determined according to the change in capacitance. When a touch operation acts on the display screen, the touch operation intensity is detected according to the pressure sensor. The touch position can also be calculated according to the detection signal of the pressure sensor. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities can correspond to different operation instructions.
  • Gyroscope sensors can be used to determine the motion posture of electronic devices.
  • the angular velocity of electronic devices around three axes i.e., X, Y, and Z axes
  • Gyroscope sensors can be used for anti-shake shooting. For example, when the shutter is pressed, the gyroscope sensor detects the angle of the electronic device's shaking, calculates the distance that the lens module needs to compensate based on the angle, and allows the lens to offset the shaking of the electronic device through reverse movement to achieve anti-shake.
  • Gyroscope sensors can also be used for navigation and somatosensory game scenes.
  • the accelerometer can detect the magnitude of the acceleration of an electronic device in all directions (generally three axes). When the electronic device is stationary, it can detect the magnitude and direction of gravity. It can also be used to identify the posture of the electronic device and is applied to applications such as horizontal and vertical screen switching and pedometers.
  • the ambient light sensor is used to sense the brightness of the ambient light.
  • the ambient light sensor can also work with the proximity light sensor to detect whether the electronic device is in the pocket to prevent accidental touches.
  • the fingerprint sensor is used to collect fingerprints.
  • the collected fingerprint characteristics can be used to implement fingerprint unlocking.
  • the temperature sensor is used to detect the temperature.
  • a touch sensor is also called a "touch panel”.
  • a touch sensor can be set on a display screen.
  • the touch sensor and the display screen form a touch screen, also called a "touch screen”.
  • a touch sensor is used to detect a touch operation on or near it.
  • the touch sensor can detect the touch operation.
  • the touch sensor can also be set on the surface of the electronic device, which is different from the position of the display screen.
  • the notification information is classified to obtain classification information corresponding to the notification information, wherein the classification information includes one or more of the following: privacy information, urgency information, and importance information; wherein, here, the notification information can be classified using preset classification rules to obtain classification information corresponding to the notification information, and can also be classified using a neural network model to obtain classification information corresponding to the notification information.
  • the embodiment of the present application does not make specific limitations on this.
  • the output channel includes the output device and the output mode corresponding to the output device, that is, the output device and the output mode corresponding to the output device can be determined based on the classification information and the data collected by the sensor.
  • the output channel can be determined by a preset determination rule, or by a neural network model.
  • the embodiment of the present application does not make any specific limitations on this.
  • the above-mentioned output channels can be used for the output of information; wherein the above-mentioned output devices may include: smart phones, smart TVs, smart headphones, smart watches, smart bracelets, sweeping robots, etc.; the output modalities corresponding to the above-mentioned output devices may include: visual modality, auditory modality and tactile modality.
  • the above-mentioned privacy information, urgency information, and importance information can be represented by priorities.
  • low, medium, and high can be used to represent different levels of priorities.
  • S102 may include:
  • the classification information corresponding to the notification information is determined.
  • the notification information can be processed according to the specific form of the notification information to obtain the classification information corresponding to the notification information. For example, when the notification information is a picture, it is necessary to perform image recognition processing on the notification information to obtain the text content, and then perform semantic analysis and multi-label classification on the text content in turn, so as to obtain the classification information corresponding to the notification information.
  • the attribute information of each control in the UI interface information can be processed to obtain the classification information corresponding to the notification information.
  • the attribute information of each control in the UI interface information can be processed by the following neural network model:
  • the semantic vector of the first UI is input into a preset fourth neural network model for multi-label classification to obtain classification information corresponding to the UI interface information.
  • the attribute information of each control of the UI interface information may include: text position, control position (position in the UI), interaction properties and position information of the control in the UI Tree (UI Tree is a storage structure for UI interface information), wherein the position information of the control in the UI Tree may be the corresponding index of the pre-order, in-order and post-order traversal of the control in the UI Tree, etc.
  • preset first neural network model preset second neural network model
  • preset third neural network model preset fourth neural network model
  • preset fourth neural network model can be four independent neural network models or four sub-neural network models of a neural network model.
  • embodiment of the present application does not make any specific limitation on this.
  • one or more of the privacy information, urgency information and importance information corresponding to the UI interface information can be obtained.
  • S103 may include:
  • An output channel is determined from the optional output channels according to the classification information and the channel quality information of the optional output channels.
  • the optional output channel refers to the output channel corresponding to the electronic device corresponding to the sensor, and the optional output channel includes the optional output device and the output mode corresponding to the optional output device.
  • the above-mentioned sensor is a sensor related to a single device, then the electronic device corresponding to the above-mentioned sensor is a single device, and the optional output channel is the output channel corresponding to the single device;
  • the above-mentioned sensor is a sensor related to multiple devices, then the electronic device corresponding to the above-mentioned sensor is multiple devices, and the optional output channel is the output channel corresponding to multiple devices.
  • the channel quality of the optional output channel is evaluated based on the data collected by the sensor, so that the channel quality information of the optional output channel can be obtained; wherein, for the network architecture of multiple devices, based on the data collected by the sensor related to each device, the channel quality evaluation is performed on each optional output channel corresponding to each device, so that the channel quality information of each optional output channel can be obtained; for a single device, based on the data collected by the sensor, the channel quality evaluation is performed on each optional output channel corresponding to the single device, so that the channel quality information of each optional output channel can be obtained.
  • the channel quality information of the optional output channel is determined from the optional output channels, wherein the channel quality information includes one or more of the following: availability information, interference information, channel capacity information, privacy information, and adaptability information; in this way, when selecting the output device and the output mode corresponding to the output device, the classification information corresponding to the notification information and the channel quality information of the optional output channel are combined, so that the selected output device and the output mode corresponding to the output device can effectively match the classification information corresponding to the notification information and the current scene.
  • the above-mentioned availability information is used to reflect the availability of the channel, which is usually expressed in terms of priority.
  • the above-mentioned interference information is used to reflect whether the channel is anti-interference and the level of anti-interference ability, for example, it may include: non-interference resistance, anti-interference, anti-interference ability level, channel capacity information is used to reflect the capacity of information that can be transmitted by the channel, which can be expressed in a numerical value or divided into different levels. The higher the level, the larger the capacity of transmittable information, and the lower the level, the smaller the capacity of transmittable information; privacy information is used to reflect the privacy level of the channel.
  • adaptive capability information is used to reflect the adaptive capability of the channel, which may include: whether it has UI adaptive capability, whether it has concise natural voice broadcast capability, whether it has information compression capability, whether it has vibration mode adaptive capability, etc.; it should be noted that the embodiments of the present application are not limited to this.
  • determining the channel quality information of the optional output channel based on the data collected by the sensor includes:
  • the availability information of the optional output channels, the interference information of the optional output channels, and the channel capacity of the preset optional output channels are transmitted. At least one of the information, the privacy information of the preset optional channel and the adaptability information of the preset optional output channel is determined as the channel quality information of the optional output channel.
  • a sensor state detection mechanism is adopted to perform state detection on the optional output channel, so that availability information of the optional output channel and interference information of the optional output channel can be obtained.
  • the channel capacity information, privacy information and adaptability information of each optional output channel are pre-stored, after obtaining the availability information and interference information of the optional output channel, at least one of the availability information, interference information, channel capacity information, privacy information and adaptability information of the optional output channel is determined as the channel quality information of the optional output channel. In this way, the channel quality information of the optional output channel can be used to determine the output device and the output mode corresponding to the output device.
  • determining the channel quality information of the optional output channel based on data collected by the sensor includes:
  • At least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the optional output channel, the privacy information of the preset optional output channel, and the adaptability information of the preset optional output channel is determined as the channel quality information of the optional output channel.
  • a sensor status detection mechanism is adopted to perform status detection on the optional output channel, so as to obtain the availability information of the optional output channel and the interference information of the optional output channel. Since the availability information of the optional output channel has a certain influence on the channel capacity information of the optional output channel, here, the channel capacity information of the optional output channel is corrected based on the availability information of the optional output channel.
  • the preset correction rules can be used for correction, so that the channel capacity information of the optional output channel can be re-determined.
  • the correction coefficient is 1, and the channel capacity information of the re-determined optional output channel is the preset channel capacity information of the optional output channel; if the availability information is of the second priority, the correction coefficient is 0.8, and the value of the preset channel capacity information of the optional output channel is multiplied by 0.8 to regain the channel capacity information of the optional output channel; if the availability information is of the third priority, the correction coefficient is 0.5, and the value of the preset channel capacity information of the optional output channel is multiplied by 0.5 to regain the channel capacity information of the optional output channel, wherein the first priority is greater than the second priority, and the second priority is greater than the third priority.
  • the privacy information of each optional output channel and the adaptive capability information of the optional output channel are pre-stored, after obtaining the availability information, interference information and channel capacity information of the optional output channel, at least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the optional output channel, the privacy information of the optional output channel and the adaptive capability information of the optional output channel is determined as the channel quality information of the optional output channel. In this way, the channel quality information of the optional output channel can be used to determine the output device and the output mode corresponding to the output device.
  • determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channel includes:
  • the selected output channel is determined as the output channel.
  • the first preset condition means that the level of the classified information reaches the preset level.
  • the privacy information, urgency information and importance information of the classified information all meet the preset levels, or at least one or two of the privacy information, urgency information and importance information of the classified information meet the preset levels.
  • the preset level can be the highest level or the second highest level.
  • selecting the output channel that satisfies the second preset condition from the optional output channels includes:
  • an output channel that meets the second preset condition is selected from the optional output channels.
  • the output channel that meets the second preset condition is selected from the optional output channel, wherein the output channel whose channel quality information reaches the preset channel quality information is selected.
  • the output channel whose privacy information in the channel quality information reaches the preset level, the availability information reaches the preset level, the interference information reaches the anti-interference level, the channel capacity information reaches the preset capacity value, and the adaptability information includes the output channel of the UI adaptability can be selected.
  • an output channel whose privacy information has the highest priority and whose availability information in the channel quality information is not the lowest priority may also be selected from the optional output channels.
  • the selected output channel is directly determined as the output channel.
  • one or more output channels can be arbitrarily selected from the selected output channels, or one or more output channels can be selected using a preset selection rule, thereby determining the selected output channel as the output channel.
  • the embodiments of the present application do not specifically limit this.
  • determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes:
  • the number of the selected output channels is a first number
  • a second number of output channels are selected from the selected output channels, and the selected second number of output channels are determined as output channels; wherein the second number is greater than 1 and less than the first number.
  • a second number of output channels can be selected from the selected output channels based on the channel quality information of the selected output channels.
  • the selection method can be based on one or more information in the channel quality information, such as privacy information, and sorting from high to low priority. For the same priority, sorting from high to low priority based on availability information, so as to obtain the sorting result according to the channel quality information, select the second number of output channels ranked in front in the sorting result, and finally determine the selected second number of output channels as the output channels.
  • the number of determined output channels can be one or more, and this is not specifically limited in the embodiments of the present application.
  • determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes:
  • the selected output channels are evaluated to obtain evaluation values of the selected output channels;
  • the output channel corresponding to the maximum value of the evaluation value among the selected output channels is determined as the output channel.
  • a weighted summation algorithm can be used for evaluation. For example, the availability information, interference information, privacy information, channel capacity information and adaptability information in the channel quality information of each selected output channel can be scored, and the scores are weighted and summed with the corresponding weight values. In this way, the evaluation value of each selected output channel can be obtained, and the output channel corresponding to the maximum evaluation value can be determined as the output channel.
  • determining the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes:
  • the output channel corresponding to the maximum number is determined as the output channel.
  • the priority of privacy information, the priority of availability information and the priority of channel capacity information in the channel quality information of each output channel in the selected output channels can be compared and counted with the preset priority, so as to determine the number of these three priorities in the channel quality information of each output channel that are higher than or equal to the preset priority.
  • the privacy information of A is the first priority
  • the availability information is the first priority
  • the channel capacity information is the first priority
  • the privacy information of B is the first priority
  • the availability information is the first priority
  • the channel capacity information is the second priority.
  • the output channel corresponding to the maximum number is used for outputting information.
  • determining an output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes:
  • the selected output channel is determined as the output channel.
  • the first priority is the highest priority of the privacy information in the classified information, that is, for the notification information with the privacy information as the highest priority, in order to ensure the privacy of the information, here, the output channel with the privacy information as the highest priority in the channel quality information in the optional output channel is directly used for the output of the information, that is to say, the information with the privacy information as the highest priority uses the output channel with the privacy information as the highest priority to output the information.
  • the availability information and interference information can be compared to select the optimal output channel for information output.
  • determining an output channel from the optional output channels according to the classification information and the channel quality information of the optional output channels includes:
  • the importance information in the classification information is of the first priority or the urgency information is of the first priority, selecting from the optional output channels an output channel in which the interference information in the channel quality information is anti-interference and the availability information in the channel quality information is of the highest priority;
  • the selected output channel is determined as the output channel.
  • the output channel in which the interference information in the channel quality information in the optional output channel is anti-interference and the availability information in the channel quality information is the highest priority is directly used for the output of the information.
  • the information with the importance information or the urgency information as the highest priority uses the output channel with the anti-interference and the highest priority availability information to output the information, so that the information is output in a timely and safe manner.
  • the output channel in addition to selecting the output channel from the optional output channels according to the classification information and the channel quality information, the output channel may also be selected by using the following neural network model.
  • S103 may include:
  • the classification information, scene information of the sensor and optional output channels are input into the preset neural network model for multi-output channel selection to obtain the output channel.
  • the data collected by the sensor is first subjected to scene analysis processing to obtain data that can be input into the preset neural network model.
  • the data collected by the sensor is subjected to scene analysis processing to obtain the scene information of the sensor.
  • the classification information, the scene information of the sensor and the optional output channel are then input into a preset neural network model together, so that an output channel is selected from the optional output channels.
  • the preset neural network model can be used to select an output channel from the optional output channels.
  • scene analysis processing is performed on the data collected by the sensor to obtain the scene information of the sensor, including:
  • the data collected by the sensor is input into the preset fifth neural network model for digital encoding to obtain the digital vector of each sensor;
  • the scene representation vector of each sensor is input into the preset seventh neural network model for information extraction and fusion to obtain the scene information of the sensor.
  • the fifth neural network model, the sixth neural network model and the seventh neural network model can be three independent neural network models or three sub-neural network models of one neural network model.
  • the embodiment of the present application does not make any specific limitation on this.
  • the electronic device can implement different processing methods for the notification information for different scenarios; here, for the scenario of a single device, after determining the output channel, the output information can be determined based on the notification information.
  • the output information can be output using the output modality.
  • the electronic device may be a master device or a server of the network architecture of the multiple devices.
  • the method further includes:
  • the main device which undertakes more computing work in the network architecture, in order to reduce the load of the main device, here, after determining the output device and the output mode corresponding to the output device, the notification information and the output mode are sent to the output device, so that the output device determines the output information based on the notification information, and the output device outputs the output information based on the output mode.
  • the method further includes:
  • notification information can be directly output based on the output modality.
  • notification information is output based on the output modality.
  • the method further includes:
  • the server can be used to centrally process computing work in the network architecture and share the computing load for each device in the network architecture. Therefore, here, after the server determines the output device and the output mode corresponding to the output device, it can determine the output information based on the notification information, and then send the output information and output mode to the output device. In other words, the output device only needs to output the output information based on the output mode.
  • main device can also be responsible for determining the output information, thereby obtaining the output information, and then sending the output information and the output mode to the output device.
  • the method further includes:
  • the output information is determined based on the notification information, and the output information is output based on the output modality.
  • the output information is output based on the output modality.
  • the output device includes a master device in a network architecture of multiple devices.
  • the main device is the device that interacts most frequently with other devices in the network architecture and is generally pre-set by the user.
  • the output device includes the main device.
  • the main device is used as the output device for information of different types of electronic devices and different types of scenarios, which is conducive to timely output of information.
  • the output information is determined based on the notification information, including:
  • the output mode is the tactile mode
  • the tactile category corresponding to the classification information is determined as the output information.
  • the modality may include at least: visual modality, auditory modality and tactile modality
  • the method of determining output information for different modalities is different.
  • the output modality is a tactile modality
  • the server pre-stores a mapping relationship between tactile categories and classification information. Taking the classification information as importance information and the tactile as vibration as an example, the higher the priority of the importance information, the stronger the intensity of the vibration, and the longer the vibration lasts; the lower the priority of the importance information, the weaker the intensity of the vibration, and the shorter the vibration lasts.
  • the tactile category corresponding to the classified information can be used as the output information.
  • the higher the priority of the classified information the stronger the vibration intensity and the longer the vibration duration.
  • the lower the priority of the classified information the weaker the vibration intensity and the shorter the vibration duration.
  • the notification information is flight cancellation information.
  • After classification it is determined that the priority of the urgency information of the information is the highest priority. Then, when determining to use the tactile channel, the strongest intensity of the vibration is used and the longest duration of the vibration is used.
  • output information is determined based on the notification information, including:
  • the output information is determined based on the key information of the notification information.
  • the output information is determined based on the notification information.
  • the output mode is a visual mode or an auditory mode
  • the channel capacity information of the output channel falls within a preset second capacity range
  • the output information is determined based on the notification information.
  • the channel capacity information of the output channel constituted by the output device and the output mode corresponding to the output device is combined to determine whether to use the notification information or the key information of the notification information to determine the output information.
  • the methods of determining the output information can be divided into two categories.
  • One category is the situation where the channel capacity information of the output channel falls within the preset first capacity range. That is to say, when using an output channel with a smaller channel capacity to output information, it is necessary to control the capacity of the output information. Therefore, the key information of the notification information can be used to determine the output information.
  • the key information is extracted from the notification information, which can briefly reflect the main content of the notification information.
  • Another case is when the channel quality of the output channel falls within the preset second capacity range.
  • the notification information can be used to determine the output information.
  • the key information of the notification information can be used to determine the output information, or the output information can be determined by using the notification information.
  • the embodiment of the present application does not make specific limitations on this.
  • determining the output information based on the notification information includes:
  • the notification information is converted into voice, and the converted voice data is determined as the output information.
  • the output information is determined based on the key information of the notification information, including:
  • the output mode is the auditory mode
  • the key information is converted into speech, and the converted speech data is determined as the output information.
  • the output mode being the auditory mode
  • the notification information is converted into voice
  • the converted voice data is determined as the output information
  • the key information is converted into voice
  • the converted voice data is determined as the output information
  • determining the output information based on the notification information includes:
  • UI adaptation is performed on the notification information based on the output device corresponding to the output channel to obtain output information.
  • the output information is determined based on the key information of the notification information, including:
  • UI adaptation is performed on the key information based on the output device corresponding to the output channel to obtain output information.
  • the UI when it is determined that the output information is determined based on the notification information, the UI is adapted to the notification information based on the output device corresponding to the output channel, so that the output information can be obtained; when it is determined that the output information is determined based on the key information, the UI is adapted to the notification information based on the output device corresponding to the output channel, so that the output information can be obtained.
  • UI adaptation is relative adaptation of UI elements, which means that the relative positions of two UI elements remain unchanged.
  • UI element A is always 50 pixels to the right of UI element B.
  • a UI background frame no matter how the screen size changes, the left edge of the frame is always 100 pixels away from the left side of the screen, and the right edge of the frame is always 100 pixels away from the right side of the screen.
  • the key information of the UI interface may include: attribute information of the control of the task theme and attribute information of the control of the key information, and the output information may be obtained in the following manner:
  • the semantic vector of the second UI is processed by using a text generation algorithm and a text summary generation algorithm to obtain a text description of the UI.
  • the UI interface may include: attribute information of visible controls, and the text description of the UI may be obtained in the following manner:
  • the attribute information of the visible control is input into the preset first neural network model for data encoding to obtain the data of the visible control.
  • Value vector
  • the semantic vector of the third UI is processed by using a text generation algorithm and a text summary generation algorithm to obtain a text description of the UI.
  • the output information is determined based on the text description of the UI, including:
  • the output mode is a visual mode
  • a text description of the UI is determined as output information
  • the output mode is an auditory mode
  • the text description of the UI is converted into speech, and the converted speech data is determined as output information.
  • the output modality is first determined to be a visual modality or an auditory modality. If it is a visual modality, that is, the output channel can output a text description of the UI, so the text description of the UI is directly determined as the output information; if it is an auditory modality, that is, the output channel cannot directly output the text description of the UI, so the text description of the UI can be converted into speech using a text-to-speech (TTS) algorithm, and the converted voice data is determined as the output information, so that the output device can successfully output the output information.
  • TTS text-to-speech
  • determining the output channel according to the classification information and the data collected by the sensor includes:
  • the output mode is determined from the corresponding mode of the output device.
  • the output device when determining the output channel, can be first determined based on the classification information and the data collected by the sensor, and then the output mode can be determined from the mode corresponding to the output device, thereby determining the output channel; for example, the data collected by the sensor can obtain the state of each optional device (which can be used as availability information), and the state includes an on state and a off state, so that the output device can be determined based on the classification information and the state of the optional device; the data collected by the sensor can obtain the distance between each optional device and the user (which can be used as availability information), so that the output device can be determined based on the classification information and the distance between the optional device and the user; when the data collected by the sensor can obtain the state of the user (which can be used as availability information), the state can be inaudible, invisible and intangible, so that the output device can be determined based on the classification information and the state of the user.
  • the data collected by the sensor can obtain the state of each optional device (which can be used as availability information), and the state includes
  • the output modality can still be selected in combination with the classification information and the data collected by the sensor.
  • the data collected by the sensor can obtain the state of the environment (which can be used as interference information), and the state includes light and noise, etc.
  • the output modality can be selected according to the classification information and the environmental state; the data collected by the sensor can obtain the time dimension (which can be used as availability information), and the time dimension includes: morning, noon and evening.
  • the output modality can be selected according to the classification information and the time dimension;
  • the data collected by the sensor can obtain the occasion where the user is (which can be used as privacy information), and the occasion can include public occasions or private occasions, and the output modality can be selected according to the classification information and the occasion where the user is;
  • the data collected by the sensor can obtain the state of the user, and the state can include motion state and static state (which can be used as interference information), and the output modality can be selected according to the classification information and the state of the user; in this way, the output device and the output modality corresponding to the output device can be determined.
  • determining the output channel according to the classification information and the data collected by the sensor includes:
  • the output device is determined from the devices corresponding to the output modality.
  • the output mode can be first determined based on the classification information and the data collected by the sensor, and then the output device can be determined from the devices corresponding to the output mode, so as to determine the output channel; for example, the data collected by the sensor can obtain the state of the environment, which includes light and noise, etc., so the output mode can be selected according to the classification information and the environmental state; the data collected by the sensor can obtain the time dimension, and the time dimension includes: morning, noon and evening, so the output mode can be selected according to the classification information and the time dimension; the data collected by the sensor can obtain the occasion where the user is, which can include public occasions or private occasions, and the output mode can be selected according to the classification information and the occasion where the user is; the data collected by the sensor can obtain the user's state, which can include motion state and still state, and the output mode can be selected according to the classification information and the user's state.
  • the output device can be selected by combining the classification information and the data collected by the sensor.
  • the data collected by the sensor can obtain the state of each optional device, which includes an on state and a off state.
  • the output device is selected according to the classification information and the state of the optional device.
  • the data collected by the sensor can obtain the distance between each optional device and the user, so that the output device can be selected according to the classification information and the distance between the optional device and the user;
  • the data collected by the sensor can obtain the state of the user, where the state can be inaudible, invisible and intangible, so that the output device can be selected according to the classification information and the state of the user. In this way, the output device and the output mode corresponding to the output device can be determined.
  • FIG. 2 is a flow chart of an optional information output method provided by the embodiment of the present application. As shown in FIG. 2, the information output method may include:
  • S203 When the received information is notification information, determine output information based on the notification information, and output the output information based on the output modality.
  • the above-mentioned received information can be notification information or output information, wherein the notification information is the notification information in the information output channel selection method, and the output information is output information determined based on the notification information, or output information determined based on the key information of the notification information.
  • the output device After the output device receives the information and output mode, it needs to be divided into two situations.
  • One situation is that the server or main device determines the output information after executing the information output channel selection method. Then, the information received by the output device at this time is output information, which can be directly based on the information output in the output mode.
  • Another situation is that after the main device executes the information output channel selection method, it directly sends the notification information and output mode to the output device. Then, the information received by the output device is the notification information, and the output device needs to further process the notification information to obtain the output information, and then output the output information based on the output mode.
  • the output information is determined based on the notification information, including:
  • the output mode is the tactile mode
  • the tactile category corresponding to the classification information is determined as the output information.
  • the method for the output device side to determine the output information based on the notification information when the output mode is the tactile mode is the same as the method for the server side or the main device side to determine the output information based on the notification information when the output mode is the tactile mode, and will not be repeated here.
  • determining the output information based on the notification information includes:
  • the output information is determined based on the key information of the notification information.
  • determining output information based on the notification information includes:
  • the output mode is a visual mode or an auditory mode
  • the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information
  • the preset second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the method for the output device side to determine the output information based on the notification information when the output mode is a visual mode or an auditory mode is the same as the method for the server side or the main device side to determine the output information based on the notification information when the output mode is a visual mode or an auditory mode, and will not be repeated here.
  • determining the output information based on the notification information includes:
  • the notification information or key information of the notification information is converted into voice, and the converted voice data is determined as the output information.
  • determining the output information based on the key information of the notification information includes:
  • the output mode is the auditory mode
  • the key information is converted into speech, and the converted speech data is determined as the output information.
  • the method in which the output device side performs voice conversion on the notification information or the key information of the notification information when the output mode is the auditory mode, and determines the converted voice data as the output information is the same as the method in which the server side or the main device side performs voice conversion on the notification information or the key information of the notification information when the output mode is the auditory mode, and determines the converted voice data as the output information, and will not be repeated here.
  • the output information is determined based on the notification information, including include:
  • UI adaptation is performed on the notification information based on the output device corresponding to the output channel to obtain output information.
  • determining the output information based on the key information of the notification information includes:
  • UI adaptation is performed on the key information based on the output device corresponding to the output channel to obtain output information.
  • the output device side performs UI adaptation on the notification information or the key information of the notification information based on the output device corresponding to the output channel when the output mode is the visual mode to obtain the method of output information, which is the same as the method for the server side or the main device side to perform UI adaptation on the notification information or the key information of the notification information based on the output device corresponding to the output channel when the output mode is the visual mode to obtain the output information, and will not be repeated here.
  • information output channel selection method and information output method provided in the embodiments of the present application can be applied to meeting scenes, in-car scenes, bathing scenes and sports scenes, but the embodiments of the present application are not limited to this.
  • a user's smartphone receives a message
  • the network architecture composed of multiple devices includes: smartphones, smart watches, smart headphones and smart glasses.
  • Data collected by sensors of the user's smartphone, smart watches, smart headphones and smart glasses are obtained, and the received information is classified and processed using the above-mentioned information output channel selection method, and the importance information in the classified information is given the highest priority, the privacy information is given the highest priority, and the urgency information is given the highest priority.
  • an output channel (set) (equivalent to the above-mentioned output channel) can be selected from all output channels (equivalent to the above-mentioned optional output channels) included in the smartphone, smart watch, smart headphones and smart glasses.
  • the obtained output channel (set) is: smartphone-card, smart glasses-card, smart watch-vibration; for selecting smart
  • the channel capacity information of the output channel can be based on the channel capacity information.
  • the UI adaptation is performed on the received information based on the output device to determine the output information, and the output information is displayed on the smart phone;
  • the UI adaptation is performed based on the key information of the received information to determine the output information, and finally the output information is displayed on the smart glasses, for example, the key information is the sender and the title information;
  • the vibration intensity of the received information can be determined based on the classification information corresponding to the received information and from the mapping relationship between the classification information and the vibration intensity.
  • the smart watch vibrates with the vibration intensity of the received information.
  • Figure 3 is a structural diagram of an example of an optional network architecture composed of multiple devices provided in an embodiment of the present application.
  • the network structure includes: a server, a smart TV, smart glasses, a smart watch, a smart phone and a smart headset, wherein the server is connected to the smart TV, smart glasses, a smart watch, a smart phone and a smart headset, respectively.
  • the optional output channels in the network architecture may include: a smart phone-card, a smart watch-card, a smart car-card, and a smart TV-card, which belong to visual channels, smart headsets-voice, smart phones-voice, smart car-voice, smart watches-voice, and smart TV-voice, which belong to auditory channels, and smart watches-vibration and smart phones-vibration, which belong to tactile channels.
  • the server when a smartphone receives a text message, the server obtains the text message (equivalent to the above-mentioned notification information), the sensor collection data of each device in the smart TV, smart glasses, smart watch, smartphone and smart headset, and the server obtains the data collected by the sensor of each device, thereby obtaining the data collected by the sensor.
  • the notification information is processed to obtain the classification information corresponding to the notification information, including the importance information, urgency information and privacy information corresponding to the notification information.
  • the above-mentioned information output channel selection method can be used to select the optimal output channel (set) that best matches the classification information corresponding to the notification information and the current scene reflected by the data collected by the sensor from the optional output channels.
  • the information output channel selection method if important information is received, in order to notify the user in a timely and accurate manner, when the user is wearing a smart headset and other devices are far away from the user, the information can be output through the smart headset-voice output channel; if more urgent information is received, in order to notify the user in a timely manner, when the user is wearing smart glasses and other devices are turned off, the information can be output through the smart glasses-card output channel; if information that is inconvenient to be made public is received, in order to ensure privacy, when the user is wearing smart glasses, the information can be output through the smart glasses-card output channel.
  • the user wears a smart watch, and the smart watch and smart phone are turned on, the smart TV, smart headphones and smart glasses are turned off, and the output can be output through the output channel of smart phone-card and smart watch-card.
  • FIG. 4 is a flow chart of an example of an optional information output channel selection method and an information output method provided in an embodiment of the present application.
  • the server obtains UI interface information of a UI interface in multiple devices (equivalent to the card information in Figure 4), wherein Figure 5 is a schematic diagram of an optional UI card design architecture provided in an embodiment of the present application.
  • the set of information displayed on the card includes: required items and optional items, wherein the set of information is presented in a gradient manner and is divided into necessary information (corresponding to required items) and optional information (corresponding to optional items) according to priority.
  • the required items include ubiquitous icons + suggestions, application icons + names, auxiliary information and core information, and the optional items include: image display and button entry; it should be noted that the small card carries all necessary information, and the large card carries more auxiliary information, providing a clear template to facilitate information extraction and presentation.
  • FIG. 6 is a schematic diagram of an example of an optional UI interface provided in an embodiment of the present application. As shown in Figure 6, it is a UI interface for flight information.
  • the UI interface includes: XX travel, flight assistant, flight number, X month X day, flight scheduled to take off at Shenzhen Bao'an T3 at 07:15 and arrive at Shanghai Pudong T1 at 09:35, with an punctuality rate of 90%, check-in counters E01-E18, and class gate F28.
  • the UI interface also includes controls: flight assistant, view orders, and book hotels.
  • Each node in the UI Tree represents a representation element or operation control (Control/Widget/Element) in the UI, which gives the relevant attributes of the element.
  • the element attribute information of the UI Tree includes: text description, interaction attributes (whether it is clickable, whether text can be entered, whether it is slidable, etc.), element position, etc.
  • the first is to obtain image interface elements through the Accessibility Service related interface of the Android system; the second is to directly obtain interface elements through UI interactive software; among them, when obtaining UI interface information through the Android Accessibility Service related interface, a screenshot of the interface is required to assist in obtaining the relevant image information of the control.
  • UI interactive software card information can generally be directly obtained.
  • the classification information may include at least one of the following: privacy information, urgency information and importance information; wherein, the classification information is generally expressed in terms of priority, privacy information can reflect the degree to which the content of the card information involves user privacy, urgency information can reflect the degree to which the content of the card information needs to be output in a timely manner, and importance information can reflect the importance of the amount of information contained in the content of the card information.
  • the privacy information, urgency information, and importance information in the classified information can be realized by constructing a multimodal neural network 1 for the card information to perform multi-label classification reasoning.
  • the specific process is as follows:
  • SA01 Extract the attribute information of each control visible to the user in the card information
  • the attribute information of each control includes but is not limited to text description, control position, interaction properties, and the position information of the control in the UI Tree (such as the corresponding index of the control in the pre-order, in-order, and post-order traversal in the UI Tree, etc.);
  • SA02 Input the attribute information of each control into the first neural network model in sequence for numerical encoding to obtain a numerical vector for each control;
  • SA03 Input the numerical vectors of each control into the second neural network model in sequence to obtain the semantic vectors of each control;
  • SA04 inputting the semantic vectors of each control into the third neural network model in sequence for information extraction and fusion to obtain the semantic vector of the first UI;
  • SA05 Input the semantic vector of the first UI into the fourth neural network model for multi-label classification to extract the privacy information, importance information, and urgency information of the card information.
  • SA06 extracting a text list of key controls from the card information according to the UI element specification. If the text contained in the text list of key controls is too long, inputting the semantic vector of the first UI into a neural network model to extract key information and obtain key information.
  • SA07 Extract attribute information of user-visible and interactive response controls from the card information, that is, response information.
  • the control elements of the card information are also extracted and data mined, so as to obtain the key information and auxiliary information of the card information, wherein the key information includes the task subject, which is the task name corresponding to the card information, for example, the UI interface of the flight information, the task subject is the flight information, and the task subject can be obtained through the specified control element in the card information; in addition to the above method, the key information can also specify the control element list composition; the auxiliary information can be response information, including the response methods that can be supported for the information presented on the UI interface, and the response information is obtained through the card information.
  • Interactive control elements are obtained; wherein, interactive controls may include clickable and/or inputtable controls.
  • the network model mentioned in SA02 above can be any network type and is not limited to a specific model.
  • the network model mentioned in SA03 above can be any network model and is not limited to a specific model.
  • the neural network model mentioned in SA04 above can be any model that can accept sequence input, such as RNN[1,2,3], Transformer[4], Bert[5], etc., and is not limited to a specific model.
  • the network model mentioned in SA03-SA06 above can be a separate model or different network modules in the same model.
  • the network model used for multi-label classification mentioned in SA05 is a network model with multiple output labels, each label carrying category information.
  • the sensors in the ubiquitous service involve motion sensors, position sensors, environmental sensors, and other sensors.
  • the motion sensor is used to monitor the movement of the device, such as tilting, shaking, rotating or swinging, and the motion sensor includes an acceleration sensor, a gyroscope/angular velocity sensor, a gravity sensor, a linear acceleration sensor, a rotation vector sensor, etc.;
  • the position sensor is used to determine the physical position of the device in the world reference system, and the position sensor includes a geomagnetic sensor, a direction sensor, a distance/proximity sensor, etc.;
  • the environmental sensor is used to monitor various properties of the environment in which the device is located, and the environmental sensor includes a light/infrared sensor, air pressure, temperature, etc.; there are other types of sensors, such as optical heart rate sensors and optical blood oxygen sensors in smart watches and smart bracelets, and bone vibration sensors in smart headphones.
  • the channel quality of multiple channels can be evaluated through sensor perception of multiple devices to obtain channel quality information of the channels.
  • the channel quality information of all optional output channels involved in each device can be realized through the sensor status detection mechanism of each device.
  • the channel quality information of each output channel is different.
  • the channel quality information is summarized as shown in the following Table 1:
  • smartphone-card, smart watch-card, smart car-card, and smart TV-card belong to the visual channel
  • smart headset-voice, smartphone-voice, smart car-voice, smart watch-voice, and smart TV-voice belong to the auditory channel
  • smart watch-vibration and smartphone-vibration belong to the tactile channel
  • the channel capacity information of the visual channel, auditory channel, and tactile channel generally decreases in sequence.
  • the best channel will be selected according to the channel capacity information while ensuring privacy and accessibility.
  • the tactile channel has the weakest information capacity and is generally used as a prompt for the arrival of information from the corresponding device. It does not serve as the main information transmission channel. Transmission channel.
  • the availability information, interference information, channel capacity information, etc. of the output channel are evaluated on the output channel corresponding to each device using a state detection mechanism based on data collected by sensors of each device.
  • the ubiquitous interactive rules can be used to select the channel.
  • this example proposes an intelligently perceived automatic channel selection solution based on the classification information and channel quality information corresponding to the card information; specifically, the ubiquitous interactive rules can be manually compiled to select the channel. This method is flexible and can adapt to many scenarios.
  • the specific interaction process refer to the following process:
  • SB01 Calculate the privacy information, urgency information and importance information corresponding to the card information
  • SB02 Based on the calculated privacy information, urgency information, and importance information, use the interaction rules to determine whether to perform channel transmission;
  • SB03 Based on the privacy information corresponding to the card information, exclude channels where the privacy information cannot be reached;
  • SB04 Based on the channel quality requirements, exclude channels with poor availability information or interference information;
  • SB05 If there are multiple channels remaining, retain the channel with the best channel quality information and privacy information to obtain the optimal channel (set) for information output.
  • the classification information corresponding to the card information and the scene information obtained from the output of the sensor can be combined and input into the multimodal interaction model with the optional output channel to select the channel.
  • the interaction design is intelligent and can avoid incomplete consideration of manual preset.
  • SC01 Extract the relevant attribute information of each control visible to the user in the card information
  • the attribute information includes but is not limited to text description, control location, interaction properties, and the location information of the control in the UI Tree (such as the corresponding index of the control in the pre-order, in-order, and post-order traversal in the UI Tree, etc.);
  • SC02 Input the attribute information of each control into the first neural network model in sequence for numerical encoding to obtain a numerical vector for each control;
  • SC03 Input the numerical vectors of each control into the second neural network model in sequence to obtain the semantic vectors of each control;
  • SC04 Input the semantic vectors of each control into the third neural network model in sequence for information extraction and fusion to obtain the semantic vector of the second UI;
  • SC05 Extract data collected by multiple device sensors in sequence
  • SC06 The data collected by each sensor is sequentially input into the fifth neural network model for numerical encoding to obtain a numerical vector for each sensor;
  • SC07 Input the digitized vectors of each sensor into the sixth neural network model in sequence to obtain the scene representation vector of each sensor;
  • SC08 Input the scene representation vectors of each sensor into the seventh neural network model in sequence for information extraction and fusion to obtain the scene representation vector of the sensor state;
  • SC09 Input the semantic vector of the second UI (equivalent to the above notification information) and the sensor state scene representation vector (equivalent to the scene information of the above sensor) into the preset neural network model (equivalent to the above multimodal interaction model) for multi-classification to obtain the optimal channel (set).
  • the network model mentioned in SC03 and SC06 above can be any network model, not limited to a specific model;
  • the neural network model mentioned in SC04 and SC08 can be any model that can accept sequence input, such as RNN[1,2,3], Transformer[4], Bert[5], etc., not limited to a specific model;
  • the network model mentioned in SC03-SC09 above can be a separate model or different network modules in the same model.
  • the channel quality information of the selectable output channels is presented in different forms. Therefore, as shown in FIG4 , after the channel selection is completed, this example will perform channel adaptation design, for example, adapting the amount of notification information to the channel capacity.
  • the optional output channels can be divided into vision, hearing, and touch.
  • information can be output for different modes:
  • the card information is mapped to the vibration pattern, and the mapping of the vibration pattern can be adapted according to the urgency information, importance information, and privacy information of the classified information.
  • channels with larger display spaces can display all information, and channels with smaller display spaces can display compressed information, i.e., key information.
  • UI adaptation is then performed on each device. Specifically, visually, UI adaptation is performed. For channels whose channel capacity information falls within the preset first capacity range, UI adaptation is performed on the key information of the card information based on the selected optimal channel (set) and then output. For channels whose channel capacity information falls within the preset second capacity range, the card information is selected and output after UI adaptation.
  • SD01 Extract the attribute information of each control visible to the user in the card information
  • SD02 Input the attribute information of each control into the first neural network model in sequence for numerical encoding to obtain a numerical vector for each control;
  • SD03 Input the numerical vectors of each control into the second neural network model in sequence to obtain the semantic vectors of each control;
  • SD04 Input the semantic vectors of each control into the third neural network model in sequence to extract and fuse information, and obtain the semantic vector of the third UI;
  • SD05 The semantic vector of the third UI is transmitted to the text generation/text summarization model to generate fluent text.
  • SD06 Convert text into speech through the TTS algorithm and output it to the selected channel.
  • the numerical encoding method mentioned in the above step SD02 is not limited to a specific algorithm;
  • the network model mentioned in the above SD02 and SD03 can be any network model, not limited to a specific model;
  • the neural network model mentioned in SD04 can be any model that can accept sequence input, such as RNN[1,2,3], Transformer[4], Bert[5], etc., not limited to a specific model;
  • the network model mentioned in the above SD02-SD06 can be a single model or different network modules in the same model.
  • sensors and related image and voice technologies can also be used to identify the user's static information (inherent physical characteristics such as gender and age group) and dynamic emotions (facial expressions, crying, anger) and behavioral states (lying on the sofa, driving, sleeping), and add additional prompt information to the text, affecting the generation style of TTS and making it more natural.
  • the optimal channel (set) in the current scenario is automatically selected for the user without user operation, and the optimal channel (set) is adapted for the card information, and the information is output to the user in the form of the optimal channel (set), thereby completing the design of a new ubiquitous interaction framework.
  • the optimal channel (set) can be automatically selected for seamless and imperceptible information output, which can effectively improve communication reliability, provide users with seamless and convenient ubiquitous services, and enhance user experience.
  • the embodiment of the present application provides a method for selecting an information output channel, including: obtaining notification information and data collected by a sensor, determining classification information corresponding to the notification information based on the notification information, and determining an output channel according to the classification information and the data collected by the sensor, wherein the output channel includes an output device and an output mode corresponding to the output device; that is, in the embodiment of the present application, by obtaining notification information and data collected by the sensor, and after obtaining the classification information corresponding to the notification information, determining the output channel based on the classification information and the data collected by the sensor, so as to know the output device and the output mode corresponding to the output device.
  • the output channel can be determined, that is, in the case of having the notification information and the data collected by the sensor, the output device and the output mode corresponding to the output device that best match the classification information corresponding to the notification information and the current scene reflected by the sensor can be determined.
  • the information output channel selection method is applicable to different types of electronic devices and different types of scenes, and for the classification information corresponding to the notification information, combined with the data collected by the sensor, the effective matching of transmission channels for different types of electronic devices or different types of scenes is achieved.
  • FIG7 is a schematic structural diagram of an optional information output channel selection device provided by an embodiment of the present application.
  • the information output channel selection device includes: an acquisition module 71, configured to acquire notification information and data collected by a sensor; a classification module 72, configured to determine classification information corresponding to the notification information based on the notification information; a determination module 73, configured to determine the output channel according to the classification information and the data collected by the sensor; wherein the output channel includes an output device and an output mode corresponding to the output device.
  • the classification module 72 is configured to: determine the classification information corresponding to the notification information based on the semantic analysis result of the notification information.
  • the classification information includes one or more of the following: privacy information, urgency information, and importance information.
  • the determination module 73 is configured to: determine channel quality information of the optional output channel based on data collected by the sensor; and determine the output channel from the optional output channels according to the classification information and the channel quality information of the optional output channel.
  • the channel quality information includes one or more of the following: availability information, interference information, channel capacity information, privacy information, and adaptability information.
  • the determination module 73 determines the channel quality information of the optional output channel based on the data collected by the sensor, including: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; re-determining the channel capacity information of the optional output channel based on the availability information of the optional output channel and the channel capacity information of the optional output channel; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the optional output channel, the preset privacy information of the optional channel and the preset adaptability information of the optional output channel as the channel quality information of the optional output channel.
  • the determination module 73 determines the channel quality information of the optional output channel based on the data collected by the sensor, including: obtaining the availability information of the optional output channel and the interference information of the optional output channel based on the data collected by the sensor; and determining at least one of the availability information of the optional output channel, the interference information of the optional output channel, the channel capacity information of the preset optional output channel, the privacy information of the preset optional channel and the adaptability information of the preset optional output channel as the channel quality information of the optional output channel.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies the first preset condition, selecting an output channel that meets the second preset condition from the optional output channels; when the number of the selected output channels is one, determining the selected output channel as the output channel.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies the first preset condition, selecting an output channel that meets the second preset condition from the optional output channels; when the number of the selected output channels is one, determining the selected output channel as the output channel.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies the first preset condition, selecting the output channel that satisfies the second preset condition from the optional output channels; when the number of the selected output channels is multiple, based on the channel quality information of the selected output channels, selecting multiple output channels from the selected output channels, and determining the selected multiple output channels as the output channels.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies the first preset condition, selecting an output channel that satisfies the second preset condition from the optional output channels; when there are multiple output channels to be selected, based on the channel quality information of the selected output channels, evaluating the selected output channels to obtain an evaluation value of the selected output channels; and determining the output channel corresponding to the maximum value of the evaluation value among the selected output channels as the output channel.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the classification information satisfies the first preset condition, selecting an output channel that satisfies the second preset condition from the optional output channels; when there are multiple output channels selected, determining that the priority of the privacy information, the priority of the availability information, and the priority of the channel capacity information in the channel quality information of each output channel in the selected output channels are higher than or equal to the preset priority number; and determining the output channel corresponding to the maximum number as the output channel.
  • the first preset condition refers to that the level of the classified information reaches a preset level.
  • the determination module 73 selects an output channel satisfying the second preset condition from the optional output channels, including: selecting an output channel satisfying the second preset condition from the optional output channels based on channel quality information of the optional output channels.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the privacy information in the classification information is the first priority, selecting the output channel whose privacy information in the channel quality information is the highest priority from the optional output channels; wherein the first priority is the highest priority of the privacy information in the classification information; and determining the selected output channel as the output channel.
  • the determination module 73 determines the output channel from the optional output channels based on the classification information and the channel quality information of the optional output channels, including: when the importance information in the classification information is the first priority or the urgency information is the first priority, selecting from the optional output channels an output channel whose interference information in the channel quality information is anti-interference and whose availability information in the channel quality information is the highest priority; wherein the first priority is the highest priority in the importance information in the classification information, and is the highest priority in the urgency information in the classification information; and determining the selected output channel as the output channel.
  • the determination module 73 is configured to: perform scene analysis processing on the data collected by the sensor to obtain scene information of the sensor; input the classification information, scene information of the sensor and optional output channels into a preset neural network model to select multiple output channels to obtain output channels.
  • the above-mentioned apparatus is further configured to: send notification information and output mode to the output device.
  • the apparatus when the output device is a master device, the apparatus is further configured to: output notification information based on the output modality.
  • the output device comprises a master device in a network architecture of multiple devices.
  • the above-mentioned apparatus is further configured to: determine output information based on the notification information; and send the output information and output mode to the output device.
  • the apparatus when the output device is a master device, the apparatus is further configured to: output output information based on the output modality.
  • the above-mentioned device determines the output information based on the notification information, including: when the output mode is a tactile mode, based on a preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • the above-mentioned device determines the output information based on the notification information, including: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on the key information of the notification information.
  • the above-mentioned device determines the output information based on the notification information, including: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information; wherein the preset second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the apparatus determines the output information based on the notification information, including: when the output mode is an auditory mode, performing voice conversion on the notification information, and determining the converted voice data as the output information.
  • the above-mentioned device determines the output information based on the key information of the notification information, including: when the output mode is an auditory mode, converting the key information into voice, and determining the converted voice data as the output information.
  • the above-mentioned device determines the output information based on the notification information, including: when the output mode is a visual mode, based on the output device corresponding to the output channel, performing UI adaptation on the notification information to obtain the output information.
  • the above-mentioned device determines the output information based on the key information of the notification information, including: when the output mode is a visual mode, based on the output device corresponding to the output channel, performing UI adaptation on the key information to obtain the output information.
  • the determination module 73 is configured to: determine the output device according to the classification information and the data collected by the sensor; and determine the output mode from the modes corresponding to the output device.
  • the determination module 73 is configured to: determine the output modality according to the classification information and the data collected by the sensor; and determine the output device from the devices corresponding to the output modality.
  • the acquisition module 71, classification module 72 and determination module 73 mentioned above can be implemented by a processor located on the information output channel selection device, specifically a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA).
  • a processor located on the information output channel selection device, specifically a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA).
  • CPU central processing unit
  • MPU microprocessor
  • DSP digital signal processor
  • FPGA field programmable gate array
  • FIG8 is a schematic diagram of the structure of an optional information output device provided by an embodiment of the present application.
  • the information output device includes: a receiving module 81, configured to receive information and output mode; a first output module 82, configured to output output information based on the output mode when the received information is output information; and a second output module 83, configured to determine output information based on the notification information and output the output information based on the output mode when the received information is notification information.
  • the second output module 83 determines the output information based on the notification information, including: when the output mode is the tactile mode, based on the preset mapping relationship between the tactile category and the classification information, determining the tactile category corresponding to the classification information as the output information.
  • the second output module 83 determines the output information based on the notification information, including: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset first capacity range, determining the output information based on the key information of the notification information.
  • the second output module 83 determines the output information based on the notification information, including: when the output mode is a visual mode or an auditory mode, and the channel capacity information of the output channel falls within a preset second capacity range, determining the output information based on the notification information; wherein the preset second capacity range is different from the preset first capacity range, and the second capacity range is larger than the first capacity range.
  • the second output module 83 determines the output information based on the notification information, including: when the output mode is the auditory mode, converting the notification information into voice, and determining the converted voice data as the output information.
  • the second output module 83 determines the output information based on the key information of the notification information, including:
  • the output mode is the auditory mode
  • the key information is converted into speech, and the converted speech data is determined as the output information.
  • the second output module 83 determines the output information based on the notification information, including: when the output mode is a visual mode, performing UI adaptation on the notification information based on the output device corresponding to the output channel to obtain the output information.
  • the second output module 83 determines the output information based on the key information of the notification information, including: when the output mode is a visual mode, based on the output device corresponding to the output channel, performing UI adaptation on the key information to obtain the output information.
  • the above-mentioned receiving module 81, the first output module 82 and the second output module 83 can be implemented by a processor located on the information output device, specifically a CPU, MPU, DSP or FPGA.
  • FIG. 9 is a schematic diagram of the structure of an optional electronic device provided in an embodiment of the present application.
  • an embodiment of the present application provides an electronic device 900, including: a processor 91 and a storage medium 92 storing executable instructions of the processor 91, the storage medium 92 relies on the processor 91 to perform operations through a communication bus 93, and when the instructions are executed by the processor 91, the information output channel selection method described in one or more of the above embodiments is executed.
  • the various components in the terminal are coupled together via the communication bus 93. It is understandable that the communication bus 93 is used to realize the connection and communication between these components.
  • the communication bus 93 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, various buses are marked as the communication bus 93 in FIG. 9.
  • FIG 10 is a structural schematic diagram of an optional output device provided in an embodiment of the present application.
  • an embodiment of the present application provides an output device 1000, including: a processor 101 and a storage medium 102 storing executable instructions of the processor 101, the storage medium 102 relies on the processor 101 to perform operations through a communication bus 103, and when the instructions are executed by the processor 101, the output method of the information described in one or more of the above embodiments is executed.
  • the various components in the terminal are coupled together through the communication bus 103.
  • the communication bus 103 is used to realize the connection and communication between these components.
  • the communication bus 103 also includes a power bus, a control bus and a status signal bus.
  • various buses are marked as communication buses 103 in FIG. 10.
  • An embodiment of the present application provides a computer storage medium storing executable instructions.
  • the processor executes the information output channel selection method described in one or more of the above embodiments, or executes the information output method described in one or more of the above embodiments.
  • the computer readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc (CD-ROM) and other memories.
  • FRAM magnetic random access memory
  • ROM read-only memory
  • PROM programmable read-only memory
  • EPROM erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash Memory Flash Memory
  • magnetic surface memory an optical disc
  • CD-ROM compact disc
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.
  • a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.
  • These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
  • an information output channel selection method is applied to an electronic device, comprising: obtaining notification information and data collected by a sensor, determining classification information corresponding to the notification information based on the notification information, and determining an output channel according to the classification information and the data collected by the sensor, wherein the output channel comprises an output device and an output mode corresponding to the output device.
  • the information output channel selection method is applicable to different types of electronic devices and different types of scenarios, and for the classification information corresponding to the notification information, combined with the data collected by the sensor, effective matching of transmission channels for different types of electronic devices or under different types of scenarios is achieved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Alarm Systems (AREA)

Abstract

本申请实施例公开了一种信息输出通道选择方法，该方法应用于电子设备中，包括：获取通知信息和传感器采集的数据，基于通知信息，确定通知信息对应的分类信息，根据分类信息和传感器采集的数据确定输出通道，输出通道包括输出设备和输出设备对应的输出模态。本申请实施例还同时提供了一种信息输出通道选择装置、信息的输出方法、装置及设备。

Description

信息输出通道选择方法、信息的输出方法、装置及设备
相关申请的交叉引用
本申请基于申请号为202211407206.7、申请日为2022年11月10日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以全文引用的方式引入本申请。
技术领域
本申请涉及人机交互技术，尤其涉及一种信息输出通道选择方法、信息的输出方法、装置及设备。
背景技术
目前，得益于近年来智能设备的技术进步，用户交互界面(User Interface，UI)作为人机交互的媒介得到了很好的发展，信息的呈现形式也更加丰富，例如卡片、列表等结构化信息能够以更加简洁、高效、美观、丰富的样式呈现给用户，用户能够通过UI进行人机交互，完成信息传输。
电子设备和其支持的交互模态共同构成传输通道。相关技术中，在人机交互时，传输通道的选择通常依赖于单一电子设备或者单一场景模式，而不能够针对不同类型的电子设备或者不同类型场景做到有效匹配。
发明内容
本申请实施例提供一种信息输出通道选择方法，所述方法应用于电子设备中，包括：
获取通知信息和传感器采集的数据；
基于所述通知信息，确定所述通知信息对应的分类信息；
根据所述分类信息和所述传感器采集的数据确定输出通道；其中，所述输出通道包括输出设备和所述输出设备对应的输出模态。
本申请实施例提供一种信息的输出方法，所述方法应用于输出设备中，包括：
接收信息和输出模态；
当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；
当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
本申请实施例提供一种信息输出通道选择装置，所述装置设置于电子设备中，包括：
获取模块，配置成获取通知信息和传感器采集的数据；
分类模块，配置成基于所述通知信息，确定所述通知信息对应的分类信息；
确定模块，配置成根据所述分类信息和所述传感器采集的数据确定输出通道；其中，所述输出设备包括输出设备和所述输出设备对应的输出模态。
本申请实施例提供一种信息的输出装置，所述装置设置于输出设备中，包括：
接收模块，配置成接收信息和输出模态；
第一输出模块，配置成当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；
第二输出模块，配置成当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
本申请实施例提供一种电子设备，包括：处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述一个或多个实施例中所述的信息输出通道选择方法。
本申请实施例提供一种输出设备，包括：处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述一个或多个实施例中所述的信息的输出方法。
本申请实施例提供一种计算机存储介质，存储有可执行指令，当所述可执行指令被一个或多个处理器执行的时候，所述处理器执行如一个或多个实施例所述的信息输出通道选择方法，或者，执行如一个或多个实施例所述的信息的输出方法。
附图说明
图1为本申请实施例提供的一种可选的信息输出通道选择方法的流程示意图；
图2为本申请实施例提供的一种可选的信息的输出方法的流程示意图；
图3为本申请实施例提供的一种可选的多个设备构成的网络结构的实例的结构示意图；
图4为本申请实施例提供的一种可选的信息输出通道选择方法和信息的输出方法的实例的流程示意图；
图5为本申请实施例提供的一种可选的UI卡片设计架构示意图；
图6为本申请实施例提供的一种可选的UI界面的实例的示意图；
图7为本申请实施例提供的一种可选的信息输出通道选择装置的结构示意图；
图8为本申请实施例提供的一种可选的信息的输出装置的结构示意图；
图9为本申请实施例提供的一种可选的电子设备的结构示意图；
图10为本申请实施例提供的一种可选的输出设备的结构示意图。
具体实施方式
本申请实施例提供了一种信息输出通道选择方法，所述方法应用于电子设备中，包括：
获取通知信息和传感器采集的数据；基于所述通知信息，确定所述通知信息对应的分类信息；根据所述分类信息和所述传感器采集的数据确定输出通道；其中，所述输出通道包括输出设备和所述输出设备对应的输出模态。
在一种可选的实施例中，所述基于所述通知信息，确定所述通知信息对应的分类信息，包括：基于所述通知信息的语义分析结果，确定所述通知信息对应的分类信息。
在一种可选的实施例中，所述分类信息包括以下一项或多项：隐私性信息、紧急性信息和重要性信息。
在一种可选的实施例中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：基于所述传感器采集的数据，确定可选输出通道的信道质量信息；根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道。
在一种可选的实施例中，所述信道质量信息包括以下一项或多项：可用性信息、干扰性信息、信道容量信息、隐私性信息和自适应能力信息。
在一种可选的实施例中，所述基于所述传感器采集的数据，确定所述可选输出通道的信道质量信息，包括：基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；基于所述可选输出通道的可用性信息和所述可选输出通道的信道容量信息，重新确定所述可选输出通道的信道容量信息；将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
在一种可选的实施例中，所述基于所述传感器采集的数据，确定所述可选输出通道的信道质量信息，包括：基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、预设的所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为一个时，将选取出的输出通道确定为所述输出通道。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为第一数量个时，基于选 取出的输出通道的信道质量信息，从选取出的输出通道中选取第二数量个输出通道，将选取出的第二数量个输出通道确定为所述输出通道，所述第二数量大于1且小于所述第一数量。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，基于选取出的输出通道的信道质量信息，对选取出的输出通道进行评估处理，得到选取出的输出通道的评估值；将选取出的输出通道中评估值的最大值对应的输出通道确定为所述输出通道。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，确定出选取出的输出通道中每个输出通道的信道质量信息中隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级高于等于预设优先级的个数；将所述个数的最大值对应的输出通道确定为所述输出通道。
在一种可选的实施例中，所述第一预设条件是指所述分类信息的等级达到预设等级。
在一种可选的实施例中，所述从所述可选输出通道中选取出满足第二预设条件的输出通道，包括：基于所述可选输出通道的信道质量信息，从所述可选输出通道中选取出满足所述第二预设条件的输出通道。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息中的隐私性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中隐私性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中隐私性信息中最高的优先级；将选取出的输出通道确定为所述输出通道。
在一种可选的实施例中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：当所述分类信息中的重要性信息为第一优先级或者紧急性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中重要性信息中最高的优先级，且为所述分类信息中紧急性信息中最高的优先级；将选取出的输出通道确定为所述输出通道。
在一种可选的实施例中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：对所述传感器采集的数据进行场景分析处理，得到所述传感器的场景信息；将所述分类信息、所述传感器的场景信息和可选输出通道输入至预设神经网络模型中进行多输出通道选取，得到所述输出通道。
在一种可选的实施例中，当所述电子设备为多设备的网络架构中的主设备，所述方法还包括：将所述通知信息和所述输出模态，发送至所述输出设备。
在一种可选的实施例中，当所述输出设备为所述主设备，所述方法还包括：基于所述输出模态输出所述通知信息。
在一种可选的实施例中，所述输出设备包括多个设备的网络架构中的主设备。
在一种可选的实施例中，当所述电子设备为多个设备的网络架构中的服务器或主设备，所述方法还包括：基于所述通知信息确定输出信息；将所述输出信息和所述输出模态，发送至所述输出设备。
在一种可选的实施例中，当所述输出设备为所述主设备，所述方法还包括：基于所述输出模态输出所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
在一种可选的实施例中，所述基于通知信息确定输出信息，包括：当输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为视觉模态或者听觉模态，且在所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息确定所述输出信息；其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为听觉 模态时，将所述通知信息进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述基于所述通知信息的关键信息确定输出信息，包括：当所述输出模态为听觉模态时，将所述关键信息进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，所述基于所述通知信息的关键信息确定输出信息，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：根据所述分类信息和所述传感器采集的数据，确定所述输出设备；从所述输出设备对应模态中确定出所述输出模态。
在一种可选的实施例中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：根据所述分类信息和所述传感器采集的数据，确定所述输出模态；从所述输出模态对应的设备中确定出所述输出设备。
本申请实施例提供了一种信息输出通道选择方法，所述方法应用于电子设备中，包括：
接收信息和输出模态；当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；
当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定所述输出信息，包括：当所输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定所述输出信息，包括：当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定所述输出信息，包括：当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息确定所述输出信息；其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为听觉模态时，将所述通知信息或进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述基于所述通知信息的关键信息确定输出信息，包括：当所述输出模态为听觉模态时，将所述关键信息进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述基于所述通知信息确定输出信息，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，所述基于所述通知信息的关键信息确定输出信息，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
本申请实施例还提供一种信息输出通道选择的装置，所述装置设置于电子设备中，包括：
获取模块，配置成获取通知信息和传感器采集的数据；分类模块，配置成基于所述通知信息，确定所述通知信息对应的分类信息；确定模块，配置成根据所述分类信息和所述传感器采集的数据确定输出设备；其中，所述输出通道包括输出设备和所述输出设备对应的输出模态
在一种可选的实施例中，分类模块，配置成：基于所述通知信息的语义分析结果，确定所述通知信息对应的分类信息。
在一种可选的实施例中，所述分类信息包括以下一项或多项：隐私性信息、紧急性信息和重要性信息。
在一种可选的实施例中，确定模块，配置成：基于所述传感器采集的数据，确定可选输出通道的信道质量信息；根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道。
在一种可选的实施例中，所述信道质量信息包括以下一项或多项：可用性信息、干扰性信息、信道容量信息、隐私性信息和自适应能力信息。
在一种可选的实施例中，确定模块基于所述传感器采集的数据，确定可选输出通道的信道质量 信息中，包括：基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；基于所述可选输出通道的可用性信息和所述可选输出通道的信道容量信息，重新确定所述可选输出通道的信道容量信息；将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
在一种可选的实施例中，确定模块基于所述传感器采集的数据，确定可选输出通道的信道质量信息中，包括：基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、预设的所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
在一种可选的实施例中，确定模块根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道中，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为第一数量个时，基于选取出的输出通道的信道质量信息，从选取出的输出通道中选取第二数量个输出通道，将选取出的第二数量个输出通道确定为所述输出通道，所述第二数量大于1且小于所述第一数量。
在一种可选的实施例中，确定模块根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道中，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，基于选取出的输出通道的信道质量信息，对选取出的输出通道进行评估处理，得到选取出的输出通道的评估值；将选取出的输出通道中评估值的最大值对应的输出通道确定为所述输出通道。
在一种可选的实施例中，确定模块根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道中，包括：当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，确定出选取出的输出通道中每个输出通道的信道质量信息中隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级高于等于预设优先级的个数；将所述个数的最大值对应的输出通道确定为所述输出通道。
在一种可选的实施例中，所述第一预设条件是指所述分类信息的等级达到预设等级。
在一种可选的实施例中，确定模块从所述可选输出通道中选取出满足第二预设条件的输出通道中，包括：基于所述可选输出通道的信道质量信息，从所述可选输出通道中选取出满足所述第二预设条件的输出通道。
在一种可选的实施例中，确定模块根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道中，包括：当所述分类信息中的隐私性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中隐私性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中隐私性信息中最高的优先级；将选取出的输出通道确定为所述输出通道。
在一种可选的实施例中，确定模块根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道中，包括：当所述分类信息中的重要性信息为第一优先级或者紧急性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中重要性信息中最高的优先级，且为所述分类信息中紧急性信息中最高的优先级；将选取出的输出通道确定为所述输出通道。
在一种可选的实施例中，确定模块，配置成：对所述传感器采集的数据进行场景分析处理，得到所述传感器的场景信息；将所述分类信息、所述传感器的场景信息和可选输出通道输入至预设神经网络模型中进行多输出通道选取，得到所述输出通道。
在一种可选的实施例中，当所述电子设备为多设备的网络架构中的主设备，所述装置还配置成：将所述通知信息和所述输出模态，发送至所述输出设备
在一种可选的实施例中，当所述输出设备为所述主设备，所述装置还配置成：基于所述输出模态输出所述通知信息。在一种可选的实施例中，所述输出设备包括多个设备的网络架构中的主设备。
在一种可选的实施例中，当所述电子设备为多个设备的网络架构中的服务器或主设备，所述装置还配置成：基于所述通知信息确定输出信息；将所述输出信息和所述输出模态，发送至所述输出设备。
在一种可选的实施例中，当所述输出设备为所述主设备，所述装置还配置成：基于所述输出模 态输出所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当所述输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当所述输出模态为视觉模态或者听觉模态，且在所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息确定所述输出信息；其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当所述输出模态为听觉模态时，将所述通知信息进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息的关键信息确定输出信息中，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，确定模块，配置成：根据所述分类信息和所述传感器采集的数据，确定所述输出设备；从所述输出设备对应模态中确定出所述输出模态。
在一种可选的实施例中，确定模块，配置成：根据所述分类信息和所述传感器采集的数据，确定所述输出模态；从所述输出模态对应的设备中确定出所述输出设备。
本申请实施例提供一种信息的输出装置，所述装置设置于输出设备中，包括：
接收模块，配置成接收信息和输出模态；第一输出模块，配置成当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；第二输出模块，配置成当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
在一种可选的实施例中，第二输出模块基于所述通知信息确定所述输出信息中，包括：当所输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
在一种可选的实施例中，第二输出模块基于所述通知信息确定所述输出信息中，包括：当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
在一种可选的实施例中，第二输出模块基于所述通知信息确定所述输出信息中，包括：当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息的关键信息确定所述输出信息；其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
在一种可选的实施例中，第二输出模块基于所述通知信息确定所述输出信息中，包括：当所述输出模态为听觉模态时，将所述通知信息或进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息的关键信息确定所述输出信息中，包括：当所述输出模态为听觉模态时，将所述关键信息进行语音转换，将转换后的语音数据确定为所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息确定输出信息中，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
在一种可选的实施例中，所述装置基于所述通知信息的关键信息确定输出信息中，包括：当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
本申请实施例提供一种电子设备，包括：处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述 一个或多个实施例所述的信息输出通道选择方法。
本申请实施例提供一种输出设备，包括：处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述一个或多个实施例所述的信息输出通道选择方法。
本申请实施例提供一种计算机存储介质，存储有可执行指令，当所述可执行指令被一个或多个处理器执行的时候，所述处理器执行如上述一个或多个实施例所述的信息输出通道选择方法，或者，执行如上述一个或多个实施例所述的信息的输出方法。
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
本申请实施例提供了一种信息输出通道选择方法，该方法可以应用于单个设备中，也可以应用于多个设备构成的网络架构中，这里，本申请实施例对此不作具体限定。
其中，针对单个设备来说，单个设备执行信息输出通道选择方法，并在确定出输出通道和输出设备对应的输出模态之后，执行下述信息的输出方法。
针对多个设备构成的网络架构来说，执行信息输出通道选择方法的设备可以为网络架构中的任意一个设备，也可以为网络架构中的主设备，还可以为该网络架构中与任意一个设备相连接的服务器，这里，本申请实施例对此不作具体限定。
图1为本申请实施例提供的一种可选的信息输出通道选择方法的流程示意图，如图1所示，该信息输出通道选择方法可以包括：
S101：获取通知信息和传感器采集的数据；
S102：基于通知信息，确定通知信息对应的分类信息；
S103：根据分类信息和传感器采集的数据确定输出通道。
目前，针对输出通道，从人体感知角度来说，主要可以通过视觉、听觉、触觉与智能终端设备发生交互，其中，智能车载可提供视觉、听觉通道，智能手机、手表、手环可提供视觉、听觉、触觉(振动)通道，智能电视可提供视觉、听觉通道，智能耳机可提供听觉通道，未来可能产生更多的新型设备，提供类似的通道服务。
多种通道属性各不相同(如信道容量、隐私性、干扰性等)，依赖的设备也不相同。在各种场景下，不同通道的可触达性、可用性不同。例如，手机UI界面通道，通道的信道容量最高、隐私性很高，一般作为主要通道，但在强光、运动等环境下，抗干扰能力差，在运动、驾驶等场景下息屏可用性差。智能车载互联语音、智能手表振动、智能耳机语音，在隐私性、信道容量方面整体弱于手机UI界面，但在上述手机抗干扰能力不足或者可用性不足的场景下，这些设备的抗干扰能力和可用性都高于手机UI界面，可以作为辅助通道为用户提供便捷、自然、泛在的服务。
通过设备传感器信息，智能感知用户位置、身体、情绪等状态，根据用户所处情境，无需用户操作，自动智能地为其选择最佳输出通道，为用户提供便捷、自然、无割裂感的服务，即“泛在服务”，是人机交互未来发展的重要方向。
然而，针对相关技术中的人机交互时，传输通道的选择通常依赖于单一设备或者单一场景模式，而不能够针对不同类型的电子设备或者不同类型场景做到有效匹配，本申请实施例提供一种信息输出通道选择方法，获取通知信息，例如，该通知信息可以为智能手机接收到的一条短信，还可以为一个智能手机生成的一条提示信息，还可以为UI界面信息或者图形用户交互界面(Graphical User Interface，GUI)界面信息。
其中，UI界面信息为以UI Tree为架构存储的界面信息，UI Tree指的是系统中的UI元素内容类似HTML的树形层次结构，GUI界面信息为以GUI Tree为架构存储的界面信息，GUI Tree指的是系统中的GUI元素内容类似HTML的树形层次结构，例如，智能手机中第三方应用程序(Application，APP)的界面中一个UI界面信息或者一个GUI界面信息，UI界面信息或者GUI界面信息中均包括有控件的属性信息。
这里，除了获取通知信息之外，还需要获取传感器采集的数据，其中，以单个设备为例来说，传感器指的是与单个设备相关的传感器，可以是与单个设备相连接的传感器，也可以是单个设备上的传感器。
针对多个设备构成的网络架构来说，传感器为与多个设备相关的传感器，可以是与多个设备相连接的传感器，也可以是多个设备上的传感器，多个设备中的每个设备接收到与之相关的传感器采集的数据，每个设备将接收到的传感器采集的数据发送至主设备或者服务器，从而使得网络架构中的主设备或者服务器可以获取到传感器采集的数据。
其中，上述传感器可以包括位置传感器、环境传感器、运动传感器等等这几类，这里，本申请 实施例对此不作具体限定。
以传感器为每个设备上的传感器为例来说，在电子设备中，传感器可以包括压力传感器、陀螺仪传感器、气压传感器、磁传感器、加速度传感器、距离传感器、接近光传感器、指纹传感器、温度传感器、触摸传感器、环境光传感器、骨传导传感器等。
其中，压力传感器用于感受压力信号，可以将压力信号转换成电信号。在一些实施例中，压力传感器可以设置于显示屏。压力传感器的种类很多，如电阻式压力传感器，电感式压力传感器，电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器，电极之间的电容改变。根据电容的变化确定压力的强度。当有触摸操作作用于显示屏，根据压力传感器检测所述触摸操作强度。也可以根据压力传感器的检测信号计算触摸的位置。在一些实施例中，作用于相同触摸位置，但不同触摸操作强度的触摸操作，可以对应不同的操作指令。例如：当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时，执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时，执行新建短消息的指令。
陀螺仪传感器可以用于确定电子设备的运动姿态。在一些实施例中，可以通过陀螺仪传感器确定电子设备围绕三个轴(即X、Y和Z轴)的角速度。陀螺仪传感器可以用于拍摄防抖。示例性的，当按下快门，陀螺仪传感器检测电子设备抖动的角度，根据角度计算出镜头模组需要补偿的距离，让镜头通过反向运动抵消电子设备的抖动，实现防抖。陀螺仪传感器还可以用于导航，体感游戏场景。
加速度传感器可检测电子设备在各个方向上(一般为三轴)加速度的大小。当电子设备静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。
环境光传感器用于感知环境光亮度。环境光传感器还可以与接近光传感器配合，检测电子设备是否在口袋里，以防误触。
指纹传感器用于采集指纹。可以利用采集的指纹特性实现指纹解锁。
温度传感器用于检测温度。
触摸传感器，也称“触控面板”。触摸传感器可以设置于显示屏，由触摸传感器与显示屏组成触摸屏，也称“触控屏”。触摸传感器用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作。在另一些实施例中，触摸传感器也可以设置于电子设备的表面，与显示屏所处的位置不同。
这里，在获取到通知信息和传感器采集的数据之后，对通知信息进行分类，从而可以得到通知信息对应的分类信息，其中，该分类信息包括以下一项或多项：隐私性信息、紧急性信息和重要性信息；其中，这里，可以利用预设的分类规则对通知信息进行分类，从而可以得到通知信息对应的分类信息，还可以利用神经网络模型进行分类，从而得到通知信息对应的分类信息，这里，本申请实施例对此不作具体限定。
如此，这里通过采用分类的方式得到分类信息，可以知晓通知信息对应的隐私性信息、紧急性信息和重要性信息中的至少一项，从而利用通知信息对应的分类信息和传感器采集的数据来确定输出通道，其中，输出通道包括输出设备和输出设备对应的输出模态，也就是说，根据分类信息和传感器采集的数据能够确定输出设备和输出设备对应的输出模态。
其中，为了实现根据分类信息和传感器采集的数据确定出输出通道，这里，可以采用预设的确定规则的方式来确定输出通道，也可以采用神经网络模型的方式来确定输出通道，本申请实施例对此不作具体限定。
需要说明的是，上述输出通道可以用于信息的输出；其中，上述输出设备可以包括：智能手机、智能电视、智能耳机、智能手表、智能手环、扫地机器人等等；上述输出设备对应的输出模态可以包括：视觉模态、听觉模态和触觉模态。
另外，上述隐私性信息、紧急性信息、重要性信息可以用优先级表示，在实际应用中可以使用低、中和高来表示不同等级的优先级。
为了得到通知信息对应的分类信息，在一种可选的实施例中，S102可以包括：
基于通知信息的语义分析结果，确定通知信息对应的分类信息。
可以理解地，可以对通知信息进行语义分析，并对语义分析结果进行多标签分类，从而可以得到通知信息对应的分类信息，这里，可以根据通知信息的具体形式来对通知信息进行处理从而得到通知信息对应的分类信息，例如，通知信息为一张图片时，需要对通知信息进行图像识别处理得到文本内容，在对文本内容依次进行语义分析和多标签分类，从而可以得到通知信息对应的分类信息。
另外，当通知信息为UI界面信息时，可以通过对UI界面信息中各控件的属性信息进行处理，从而得到通知信息对应的分类信息，对UI界面信息中各控件的属性信息进行处理，可以采用下述神经网络模型的方式实现：
将各控件的属性信息输入至预设的第一神经网络模型中进行数值化编码，得到各控件的数值化向量；
将各控件的数值化向量输入至预设的第二神经网络模型中进行语义分析，得到各控件的语义向量；
将各控件的语义向量输入至预设的第三神经网络模型中进行信息提取融合，得到第一UI的语义向量；
将第一UI的语义向量输入至预设的第四神经网络模型中进行多标签分类，得到UI界面信息对应的分类信息。
这里，UI界面信息的各控件的属性信息可以包括：文本位置，控件位置(在UI中的位置)，交互属性和控件在UI Tree(UI Tree为UI界面信息的存储结构)中的位置信息，其中，控件在UI Tree中的位置信息可以为控件在UI Tree中前序、中序、后序遍历的对应索引等。
需要说明的是，上述预设的第一神经网络模型、预设的第二神经网络模型、预设的第三神经网络模型和预设的第四神经网络模型可以为四个独立的神经网络模型，也可以为一个神经网络模型的四个子神经网络模型，这里，本申请实施例对此不作具体限定。
如此，通过上述神经网络模型的处理，可以得到UI界面信息对应的隐私性信息、紧急性信息和重要性信息中的一种或多种。
为了确定出输出通道，在一种可选的实施例中，S103可以包括：
基于传感器采集的数据，确定可选输出通道的信道质量信息；
根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道。
其中，可选输出通道指的是传感器对应的电子设备对应的输出通道，可选输出通道包括可选输出设备和可选输出设备对应的输出模态，例如，针对单个设备来说，上述传感器为单个设备相关的传感器，那么上述传感器对应的电子设备即为单个设备，可选输出通道即为单个设备对应的输出通道；针对多个设备来说，上述传感器为多个设备相关的传感器，那么上述传感器对应的电子设备即为多个设备，可选输出通道即为多个设备对应的输出通道。
通常地，在输出通道选择中，一般存在多个可选输出通道，那么，为了选取出最佳的输出通道，这里，基于传感器采集的数据对可选输出通道进行信道质量的评估处理，从而可以得到可选输出通道的信道质量信息；其中，针对多个设备的网络架构来说，基于每个设备相关的传感器采集的数据，对每个设备对应的每个可选输出通道进行信道质量评估处理，从而可以得到每个可选输出通道的信道质量信息；针对单个设备来说，基于传感器采集的数据，对单个设备对应的每个可选输出通道进行信道质量评估处理，从而可以得到每个可选输出通道的信道质量信息。
那么，在知晓可选输出通道的信道质量信息之后，再结合分类信息，从可选输出通道中确定输出通道，即输出设备和输出设备对应的输出模态，其中，信道质量信息包括以下一项或多项：可用性信息、干扰性信息、信道容量信息、隐私性信息和自适应能力信息；这样，在选取输出设备和输出设备对应的输出模态时，结合通知信息对应的分类信息和可选输出通道的信道质量信息，使得选取出的输出设备和输出设备对应的输出模态，与通知信息对应的分类信息和当前场景能够有效匹配。
其中，上述可用性信息用于反映通道的可用程度，通常用优先级来表示，优先级越高，通道的可用程度越高，优先级越低，通道的可用程度越低；上述干扰性信息用于反映通道的是否可抗干扰以及可抗干扰能力的等级，例如可以包括：不可抗干扰，可抗干扰，可抗干扰能力等级，信道容量信息用于反映通道可传输的信息的容量，可以用数值表示，也可以分为不同等级，等级越高，可传输的信息的容量越大，等级越低，可传输的信息的容量越小；隐私性信息用于反映通道的隐私性等级，等级越高，说明通道的隐私性越强，等级越低，说明通道的隐私性越弱；自适应能力信息用于反映通道的自适应能力，可以包括：是否具有UI自适应能力，是否具有简洁的自然语音播报能力，是否具有信息压缩能力，是否具有振动模式的自适应能力等等；需要说明的是，本申请实施例不限于此。
为了得到可选输出通道的信道质量信息，在一种可选的实施例中，基于传感器采集的数据，确定可选输出通道的信道质量信息，包括：
基于传感器采集的数据，得到可选输出通道的可用性信息和可选输出通道的干扰性信息；
将可选输出通道的可用性信息、可选输出通道的干扰性信息、预设的可选输出通道的信道容量 信息、预设的可选通道的隐私性信息和预设的可选输出通道的自适应能力信息中的至少一项，确定为可选输出通道的信道质量信息。
可以理解地，这里基于传感器采集的数据，采用传感器状态检测机制，对可选输出通道进行状态检测，从而可以得到可选输出通道的可用性信息和可选输出通道的干扰性信息。
由于每个可选输出通道的信道容量信息、可选输出通道的隐私性信息和可选输出通道的自适应能力信息都是预先存储好的，所以，在得到可选输出通道的可用性信息和干扰性信息之后，将可选输出通道的可用性信息、可选输出通道的干扰性信息、可选输出通道的信道容量信息、可选输出通道的隐私性信息和可选输出通道高的自适应能力信息至少一项确定为可选输出通道的信道质量信息。如此，可选输出通道的信道质量信息可以用于确定输出设备和输出设备对应的输出模态。
为了提高可选输出通道的信道质量信息的准确性，在一种可选的实施例中，基于传感器采集的数据，确定可选输出通道的信道质量信息，包括：
基于传感器采集的数据，得到可选输出通道的可用性信息和可选输出通道的干扰性信息；
基于可选输出通道的可用性信息和可选输出通道的信道容量信息，重新确定可选输出通道的信道容量信息；
将可选输出通道的可用性信息、可选输出通道的干扰性信息、可选输出通道的信道容量信息、预设的可选输出通道的隐私性信息和预设的可选输出通道的自适应能力信息中的至少一项，确定为可选输出通道的信道质量信息。
可以理解地，这里基于传感器采集的数据，采用传感器状态检测机制，对可选输出通道进行状态检测，从而可以得到可选输出通道的可用性信息和可选输出通道的干扰性信息，由于可选输出通道的可用性信息对可选输出通道的信道容量信息具有一定的影响，所以这里，基于可选输出通道的可用性信息对可选输出通道的信道容量信息进行修正，可以采用预设的修正规则进行修正，从而可以重新确定出可选输出通道的信道容量信息。
举例来说，可用性信息用优先级表示时，若可用性信息为第一优先级时，修正系数为1，重新确定出的可选输出通道的信道容量信息为预设的可选输出通道的信道容量信息，若可用性信息为第二优先级时，修正系数为0.8，将预设的可选输出通道的信道容量信息的数值乘以0.8，以重新得到可选输出通道的信道容量信息，若可用性信息为第三优先级时，修正系数为0.5，将预设的可选输出通道的信道容量信息的数值乘以0.5，以重新得到可选输出通道的信道容量信息，其中，第一优先级大于第二优先级，第二优先级大于第三优先级。
由于每个可选输出通道的隐私性信息和可选输出通道的自适应能力信息都是预先存储好的，所以，在得到可选输出通道的可用性信息、干扰性信息和信道容量信息之后，将可选输出通道的可用性信息、可选输出通道的干扰性信息、可选输出通道的信道容量信息、可选输出通道的隐私性信息和可选输出通道高的自适应能力信息至少一项确定为可选输出通道的信道质量信息。如此，可选输出通道的信道质量信息可以用于确定输出设备和输出设备对应的输出模态。
知晓通知信息对应的分类信息和可选输出通道的信道质量信息后，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；
当选取出的输出通道的数目为一个时，将选取出的输出通道确定为输出通道。
也就是说，可以预先设置选取规则从可选输出通道中选取出输出通道，这里，第一预设条件是指分类信息的等级达到预设等级，例如，分类信息的隐私性信息、紧急性信息和重要性信息均满足预设等级，或者，分类信息的隐私性信息、紧急性信息和重要性信息中至少一个或者两个满足预设等级，其中，预设等级可以为等级中的最高等级，也可以为等级中的次高等级，这里，本申请实施例对此不作具体限定。
只有当分类信息满足第一预设条件才从可选输出通道中选取出满足第二预设条件的输出通道，也就是说，只有当分类信息满足第一预设条件才选取输出通道，并且选取的方法是从可选输出通道中选取出满足第二预设条件的输出通道，针对第二预设条件，在一种可选的实施例中，从可选输出通道中选取出满足第二预设条件的输出通道，包括：
基于可选输出通道的信道质量信息，从可选输出通道中选取出满足第二预设条件的输出通道。
也就是说，以可选输出通道的信道质量信息为依据，将可选输出通道中满足第二预设条件的输出通道选取出，其中，选取出可选输出通道中信道质量信息达到预设的信道质量信息的输出通道，例如，可以选取出信道质量信息中的隐私性信息达到预设等级、可用性信息达到预设等级、干扰性信息达到可抗干扰、信道容量信息达到预设容量值、自适应能力信息中包括UI自适应能力的输出通 道；还可以从可选输出通道中选取出隐私性信息为最高优先级、且信道质量信息中的可用性信息不为最低优先级的输出通道。
另外，针对选取出的一个输出通道的情况，直接将选取出的输出通道确定为输出通道。针对选取出多个输出通道的情况，可以从选取出的输出通道中任意选取出一个输出通道或者多个输出通道，也可以采用预设的选取规则选取出一个输出通道或者多个输出通道，从而将选取出的输出通道确定为输出通道，这里，本申请实施例对此不作具体限定。
针对选取出多个输出通道的情况来说，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；
当选取出的输出通道的数目为第一数量个时，基于选取出的输出通道的信道质量信息，从选取出的输出通道中选取第二数量个输出通道，将选取出的第二数量个输出通道确定为输出通道；其中，第二数量大于1且小于第一数量。
可以理解地，经过第一预设条件和第二预设条件的筛选之后，在选取出第一数量个输出通道之后，可以基于选取出的输出通道的信道质量信息，从选取出的输出通道中选取第二数量个输出通道，选取方式可以是依据信道质量信息中的一个或多个信息，例如隐私性信息，按照优先级由高到低进行排序，针对相同优先级的情况，再基于可用性信息按照优先级由高到低进行排序，从而可以得到按照信道质量信息的排序结果，将排序结果中排在前面的第二数量个输出通道选取出来，最终将选取出的第二数量个输出通道确定为输出通道。
可见，确定出的输出通道的数目可以为一个也可以为多个，这里，本申请实施例对此不作具体限定。
为了选取出最佳的输出通道，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；
当选取出的输出通道为多个时，基于选取出的输出通道的信道质量信息，对选取出的输出通道进行评估处理，得到选取出的输出通道的评估值；
将选取出的输出通道中评估值的最大值对应的输出通道确定为输出通道。
可以理解地，可以利用加权求和算法进行评估，例如，针对每个选取出的输出通道的信道质量信息中的可用性信息、干扰性信息、隐私性信息、信道容量信息和自适应能力信息进行打分，将得分与对应的权重值进行加权求和，从而可以得到每个选取出的输出通道的评估值，进而可以将评估值的最大值对应的输出通道确定为输出通道。
当然，还可以采用其他方式来选取输出通道，例如，选取出信道容量信息中最大容量值的输出通道为输出通道，或者，选取出隐私性信息为最高优先级的输出通道为输出通道，这里，本申请实施例对此不作具体限定。
另外，为了选取出最佳的输出通道，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；
当选取出的输出通道为多个时，确定出选取出的输出通道中每个输出通道的信道质量信息中隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级高于等于预设优先级的个数；
将个数的最大值对应的输出通道确定为输出通道。
也就是说，在选取出多个输出通道时，为了确定出最终用于信息输出的输出通道，这里，可以对选取出的输出通道中的每个输出通道的信道质量信息中的隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级与预设优先级进行比较和统计，从而确定出每个输出通道的信道质量信息中这三个优先级中高于等于预设优先级的个数。
例如，当有两个选出的输出通道A和B，A的隐私性信息为第一优先级、可用性信息为第一优先级、信道容量信息为第一优先级，B的隐私性信息为第一优先级、可用性信息为第一优先级、信道容量信息为第二优先级，此时，若预设的优先级为第一优先级，且第一优先级高于第二优先级时，那么A的个数为3，B的个数为2。
在确定出每个输出通道对应的高于等于预设优先级的个数之后，将个数的最大值对应的输出通道用于信息的输出。
针对一些通知信息的隐私性要求较高的情况来说，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息中的隐私性信息为第一优先级时，从可选输出通道中选取出信道质量信息中隐私性信息为最高优先级的输出通道；
将选取出的输出通道确定为输出通道。
可以理解地，针对通知信息的隐私性信息为第一优先级时，其中，第一优先级为分类信息中隐私性信息中最高的优先级，即针对隐私性信息为最高优先级的通知信息来说，为了保证信息的隐私性，这里，直接将可选输出通道中信道质量信息中隐私性信息为最高优先级的输出通道用于信息的输出，也就是说，隐私性信息为最高优先级的信息利用隐私性信息为最高优先级的输出通道进行信息的输出。
当然，还可能存在多个隐私性信息为最高优先级的输出通道，此时可以比较可用性信息和干扰性信息，从而选取出最优的输出通道进行信息的输出。
针对一些通知信息的重要性和紧急性要求较高的情况来说，在一种可选的实施例中，根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道，包括：
当分类信息中的重要性信息为第一优先级或者紧急性信息为第一优先级时，从可选输出通道中选取出信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道；
将选取出的输出通道确定为输出通道。
可以理解地，针对通知信息的重要性信息或者紧急性信息为第一优先级时，其中，第一优先级为分类信息中重要性信息中最高的优先级，且为分类信息中紧急性信息中最高的优先级，即针对重要性信息为最高优先级的通知信息或者紧急性信息为最高优先级的通知信息来说，为了保证信息及时安全地通知用户，这里，直接将可选输出通道中信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道用于信息的输出，也就是说，重要性信息或者紧急性信息为最高优先级的信息利用可抗干扰且可用性信为最高优先级的输出通道进行信息的输出，使得信息及时安全地输出。
为了确定输出通道，除了采用上述根据分类信息和信道质量信息从可选输出通道中选取输出通道之外，还可以采用下述神经网络模型的方式来选取输出通道，在一种可选的实施例中，S103可以包括：
对传感器采集的数据进行场景分析处理，得到传感器的场景信息；
将分类信息、传感器的场景信息和可选输出通道输入至预设神经网络模型中进行多输出通道选取，得到输出通道。
可以理解地，先对传感器采集的数据进行场景分析处理，得到能够输入至预设神经网络模型的数据，这里，对传感器采集的数据进行场景分析处理，得到传感器的场景信息。
再将分类信息、传感器的场景信息和可选输出通道一起输入至预设的神经网路模型中，从而从可选输出通道选取出输出通道。
如此，利用预设神经网络模型就可以实现从可选输出通道中选取出输出通道。
进一步地，在利用预设神经网络模型选取输出通道中，需要先得到传感器的场景信息，为了得到传感器的场景信息，在一种可选的实施例中，对传感器采集的数据进行场景分析处理，得到传感器的场景信息，包括：
将传感器采集的数据输入至预设的第五神经网络模型中进行数值化编码，得到各传感器的数值化向量；
将各传感器的数值化向量输入至预设的第六神经网络模型中进行场景分析，得到各传感器的场景表示向量；
将各传感器的场景表示向量输入至预设的第七神经网络模型中进行信息提取融合，得到传感器的场景信息。
需要说明的是，上述第五神经网络模型、第六神经网络模型和第七神经网络模型可以为三个独立的神经网络模型，也可以为一个神经网络模型的三个子神经网络模型，这里，本申请实施例对此不作具体限定。
在采用上述设置好的选取规则或者预设的神经网络模型选取出输出通道之后，针对不同场景，电子设备可以对通知信息实现不同的处理方式；这里，针对单个设备的场景来说，在确定出输出通道之后，可以基于通知信息确定输出信息，具体的确定方法详见下述主设备侧、或者服务器侧、或者输出设备侧的输出信息的确定方法的内容，在确定出输出信息之后，利用输出模态输出输出信息即可。
针对多个设备的网络架构来说，电子设备可以为多个设备的网络架构的主设备或服务器。
针对执行主体为主设备，且确定出的输出设备为网络架构中除了主设备以外的设备时，在一种可选的实施例中，当电子设备为多个设备的网络架构中的主设备，上述方法还包括：
将通知信息和输出模态，发送至输出设备。
针对主设备来说，在网络架构中承担了较多的计算工作，为了减轻主设备的负荷，这里，在确定出输出设备和输出设备对应的输出模态之后，将通知信息和输出模态发送至输出设备，以使得输出设备基于通知信息确定输出信息，以使得输出设备基于输出模态输出输出信息。
为了实现输出信息，当输出设备为主设备，在一种可选的实施例中，上述方法还包括：
基于输出模态输出通知信息。
也就是说，电子设备本身确定出的输出设备为本身时，且确定出的输出通道的信道容量落入第一容量范围时，直接基于输出模态输出通知信息即可，例如，主设备确定输出设备为主设备、且输出通道的信道容量信息落入第一容量范围时，基于输出模态输出通知信息。
针对执行主体为服务器或者主设备的情况来说，且确定出的输出设备为网络架构中除了主设备以外的设备时，在一种可选的实施例中，当电子设备为多个设备的网络架构中的服务器或者主设备，上述方法还包括：
基于通知信息确定输出信息；
将输出信息和输出模态，发送至输出设备。
针对服务器或者来说，可以用于集中处理网络架构中的计算工作，为网络架构中的各设备分担计算量，所以这里，服务器在确定出输出设备和输出设备对应的输出模态之后，可以基于通知信息确定输出信息，再将输出信息和输出模态发送至输出设备，也就是说，只需要输出设备基于输出模态输出输出信息即可。
需要说明的是，上述主设备也可以承担输出信息的确定工作，从而得到输出信息，再将输出信息和输出模态发送至输出设备。
为了实现输出信息，当输出设备为主设备，在一种可选的实施例中，上述方法还包括：
基于输出模态输出输出信息。
也就是说，电子设备本身确定出的输出设备为本身时，且确定出的输出通道的信道容量落入第二容量范围时，基于通知信息确定输出信息，基于输出模态输出输出信息即可，例如，主设备确定输出设备为主设备、且输出通道的信道容量信息落入第一容量范围时，基于输出模态输出输出信息。
为了确定出输出设备，在一种可选的实施例中，输出设备包括多个设备的网络架构中的主设备。
通常地，主设备在网络架构中属于与其他设备交互频次最多的设备，一般由用户预先设定，这里将输出设备包括主设备，这样，针对不同类型的电子设备和不同类型的场景，将主设备作为信息的输出设备，有利于信息及时地输出。
为了实现服务器或者主设备基于通知信息确定输出信息，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将分类信息对应的触觉类别，确定为输出信息。
可以理解地，由于模态至少可以包括：视觉模态，听觉模态和触觉模态，针对不同模态确定输出信息的方式是不同的，其中，针对输出模态为触觉模态的情况来说，服务器中预先存储有触觉类别与分类信息之间的映射关系，以分类信息为重要性信息、触觉为振动为例来说，重要性信息的优先级越高，振动的强度越强，振动持续的时间越长，重要性信息的优先级越低，振动的强度越弱，振动持续的时间越短。
有了上述映射关系，可以将分类信息对应的触觉类别作为输出信息即可，将分类信息的优先级越高的，振动的强度越强，振动持续的时间越长，将分类信息的优先级越低的，振动的强度越弱，振动持续的时间越短。例如，通知信息为航班取消信息，经过分类之后，确定该信息的紧急性信息的优先级为最高优先级，那么，在确定使用触觉通道时，振动的强度使用最强强度，振动持续的时间使用最长时间。
除了上述触觉模态之外，针对视觉模态和听觉模态来说，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第一容量范围时，基于通知信息的关键信息确定输出信息。
另外，针对视觉模态和听觉模态来说，在一种可选的实施例中，基于通知信息确定输出信息， 包括：
当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第二容量范围时，基于通知信息确定输出信息。
可以理解地，结合输出设备和输出设备对应的输出模态所构成的输出通道的信道容量信息来判断利用通知信息还是通知信息的关键信息来确定输出信息，这里，需要预先设置有第一容量范围和第二容量范围，其中，预设的第二容量范围与预设的第一容量范围不同，且第二容量范围大于第一容量范围，如此，可以将确定输出信息的方式分为两大类，一类是输出通道的信道容量信息落入预设的第一容量范围的情况，也就是说，在利用较小信道容量的输出通道来输出信息时，需要控制输出信息的容量，所以，这里利用通知信息的关键信息来确定输出信息即可，其中，关键信息是从通知信息中提取出的信息，能够简要的反映出通知信息中的主要内容的信息。
另一类是输出通道的信道质量落入预设的第二容量范围的情况来说，在利用具有较大信道容量的输出通道来输出信息时，不需要控制输出信息的容量，所以，这里利用通知信息来确定输出信息即可。
另外，针对未落入预设的第一容量范围和第二容量范围的情况来说，可以采用上述利用通知信息的关键信息来确定输出信息，也可以采用上述利用通知信息确定输出信息，这里，本申请实施例对此不作具体限定。
针对输出模态为听觉模态时，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为听觉模态时，将通知信息进行语音转换，将转换后的语音数据确定为输出信息。
针对输出模态为听觉模态时，在一种可选的实施例中，基于通知信息的关键信息确定输出信息，包括：
当输出模态为听觉模态时，将关键信息进行语音转换，将转换后的语音数据确定为输出信息。
也就是说，针对输出模态为听觉模态，当确定基于通知信息确定输出信息时，将通知信息进行语音转换，将转换后的语音数据确定为输出信息，当确定基于关键信息确定输出信息时，将关键信息进行语音转换，将转换后的语音数据确定为输出信息。
另外，针对输出模态为视觉模态的情况，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为视觉模态时，基于输出通道对应的输出设备，对通知信息进行UI自适应，得到输出信息。
针对输出模态为视觉模态的情况，在一种可选的实施例中，基于通知信息的关键信息确定输出信息，包括：
当输出模态为视觉模态时，基于输出通道对应的输出设备，对关键信息进行UI自适应，得到输出信息。
也就是说，针对输出模态为视觉模态，当确定基于通知信息确定输出信息时，基于输出通道对应的输出设备对通知信息进行UI自适应，从而可以得到输出信息，当确定基于关键信息确定输出信息时，基于输出通道对应的输出设备对通知信息进行UI自适应，从而可以得到输出信息。
其中，上述UI自适应的全称为UI元素的相对自适应，是指两个UI元素之间保持一种相对的位置不要变化，例如，UI元素A永远处于UI元素B右边的50像素处位置。再比如，一个UI背景框，不论屏幕尺寸怎么变化，框的左边缘永远距离屏幕左边100像素，框的右边缘永远距离屏幕右边100像素。
另外，以通知信息为UI界面信息为例来说，在一种可选的实施例中，UI界面的关键信息可以包括：任务主题的控件的属性信息和关键信息的控件的属性信息，可以采用下述方式得到输出信息：
将任务主题的控件的属性信息和关键信息的控件的属性信息分别输入至预设的第一神经网络模型中进行数值化编码，得到任务主题的控件的数值化向量和关键信息的控件的数值化向量；
将任务主题的控件的数值化向量和关键信息的控件的数值化向量分别输入至预设的第二神经网络模型中进行语义分析，得到任务主题的控件的语义向量和关键信息的控件的语义向量；
将任务主题的控件的语义向量和关键信息的控件的语义向量分别输入至预设的第三神经网络模型中进行信息提取融合，得到第二UI的语义向量；
利用文本生成算法和文本摘要生成算法，对第二UI的语义向量进行处理，得到UI的文本描述。
还是以通知信息为UI界面信息为例来说，在一种可选的实施例中，UI界面可以包括：可见控件的属性信息，可以采用下述方式得到UI的文本描述：
将可见控件的属性信息输入至预设的第一神经网络模型中进行数据化编码，得到可见控件的数 值化向量；
将可见控件的数值化向量输入至预设的第二神经网络模型中进行语义分析，得到可见控件的语义向量；
将可见控件的语义向量输入至预设的第三神经网络模型中进行信息提取融合，得到第三UI的语义向量；
利用文本生成算法和文本摘要生成算法，对第三UI的语义向量进行处理，得到UI的文本描述。
针对视觉模态或者听觉模态，为了确定出输出信息，在一种可选的实施例中，基于UI的文本描述，确定输出信息，包括：
当输出模态为视觉模态时，将UI的文本描述确定为输出信息；
当输出模态为听觉模态时，对UI的文本描述进行语音转换，将转换后的语音数据确定为输出信息。
可以理解地，首先判断输出模态为视觉模态还是听觉模态，若为视觉模态，也就是说输出通道能够输出UI的文本描述，所以直接将UI的文本描述确定为输出信息；若为听觉模态，也就是说输出通道不能够直接输出UI的文本描述，所以将UI的文本描述可以利用文本转语音(Text To Speech，TTS)算法进行语音转换，并将转换后的语音数据确定为输出信息，从而使得输出设备能够将输出信息成功输出。
需要说明的是，为了确定出输出通道，在一种可选的实施例中，根据分类信息和传感器采集的数据确定输出通道，包括：
根据分类信息和传感器采集的数据，确定输出设备；
从输出设备对应模态中确定出输出模态。
可以理解地，在确定输出通道时，可以是根据分类信息和传感器采集的数据先确定输出设备，再从输出设备对应的模态中再确定输出模态，从而确定出输出通道；例如，传感器采集的数据可以获取到每个可选设备的状态(可以作为可用性信息)，该状态包括开启状态和关闭状态，这样，根据分类信息和可选设备的状态就可以确定出输出设备；传感器采集的数据可以获取到每个可选设备与用户之间的距离(可以作为可用性信息)，这样，可以根据分类信息和可选设备与用户之间的距离来确定输出设备；传感器采集的数据可以获取到用户的状态(可以作为可用性信息)时，其中，该状态可以为不可听、不可视和不可触，这样，根据分类信息和用户的状态可以确定出输出设备。
在选取出输出设备之后，为了从输出设备对应的模态中选取出输出模态，这里，可以还是可以结合分类信息和传感器采集的数据来选取输出模态，例如，传感器采集的数据可以获取到所处环境状态(可以作为干扰性信息)，该状态包括光线和噪音等等，这样，可以根据分类信息和环境状态来选取输出模态；传感器采集的数据可以获取到所处的时间维度(可以作为可用性信息)，时间维度包括：早、中和晚，这样，可以根据分类信息和时间维度来选取输出模态；传感器采集的数据可以获取到用户所处的场合(可以作为隐私性信息)，该场合可以包括公开场合或者隐私场合，可以根据分类信息和用户所处的场合来选取输出模态；传感器采集的数据可以获取到用户的状态，该状态可以包括运动状态和静止状态(可以作为干扰性信息)，可以根据分类信息和用户的状态来选取输出模态；如此，便可以确定出输出设备和输出设备对应的输出模态。
为了确定出输出通道，在一种可选的实施例中，根据分类信息和传感器采集的数据确定输出通道，包括：
根据分类信息和传感器采集的数据，确定输出模态；
从输出模态对应的设备中确定出输出设备。
可以理解地，在确定输出通道时，可以是根据分类信息和传感器采集的数据先确定输出模态，再从输出模态对应的设备中再确定输出设备，从而确定出输出通道；例如，传感器采集的数据可以获取到所处环境状态，该状态包括光线和噪音等等，这样，可以根据分类信息和环境状态来选取输出模态；传感器采集的数据可以获取到所处的时间维度，时间维度包括：早、中和晚，这样，可以根据分类信息和时间维度来选取输出模态；传感器采集的数据可以获取到用户所处的场合，该场合可以包括公开场合或者隐私场合，可以根据分类信息和用户所处的场合来选取输出模态；传感器采集的数据可以获取到用户的状态，该状态可以包括运动状态和静止状态，可以根据分类信息和用户的状态来选取输出模态。
在选取出输出模态之后，为了从输出模态对应的设备中选取出输出设备，这里，可以还是可以结合分类信息和传感器采集的数据来选取输出设备，例如，传感器采集的数据可以获取到每个可选设备的状态，该状态包括开启状态和关闭状态，这样，根据分类信息和可选设备的状态来选取输出 设备；传感器采集的数据可以获取到每个可选设备与用户之间的距离，这样，可以根据分类信息和可选设备与用户之间的距离来选取输出设备；传感器采集的数据可以获取到用户的状态时，其中，该状态可以为不可听、不可视和不可触，这样，根据分类信息和用户的状态可以选取输出设备。如此，便可以确定出输出设备和输出设备对应的输出模态。
另外，针对多个设备的网络架构下由主设备或者服务器执行信息输出通道选择方法之后，为了使得输出设备输出信息，本申请实施例提供一种信息的输出方法，该方法应用于输出设备中，其中，该输出设备可以为单个设备场景中的单个设备，也可以为多个设备的网络架构中的任意一个设备，图2为本申请实施例提供的一种可选的信息输出方法的流程示意图，如图2所示，该信息的输出方法可以包括：
S201：接收信息和输出模态；
S202：当接收到的信息为输出信息时，基于输出模态输出输出信息；
S203：当接收到的信息为通知信息时，基于通知信息确定输出信息，基于输出模态输出输出信息。
需要说明的是，上述接收到的信息可以为通知信息，也可以为输出信息，其中，通知信息为信息输出通道选择方法中的通知信息，该输出信息为基于通知信息确定的输出信息，或者基于通知信息的关键信息确定的输出信息。
这里，输出设备在接收到信息和输出模态之后，需要分为两种情况，一种情况是服务器或者主设备在执行完成信息输出通道选择方法之后，确定输出信息，那么，此时输出设备接收到的信息为输出信息，可以直接基于输出模态输出的信息即可。
另一种情况是主设备在执行完成信息输出通道选择方法之后，直接将通知信息和输出模态发送至输出设备，那么，输出设备接收到的信息为通知信息，输出设备需要进一步对通知信息进行处理以得到输出信息，再基于输出模态输出输出信息。
针对另一种情况，为了针对输出模态为触觉模态的情况下确定出输出信息，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将分类信息对应的触觉类别，确定为输出信息。
这里，输出设备侧针对输出模态为触觉模态的情况下基于通知信息确定输出信息的方法，与服务器侧或者主设备侧针对输出模态为触觉模态的情况下基于通知信息确定输出信息的方法相同，这里，不再赘述。
为了针对输出模态为视觉模态或者听觉模态的情况下确定输出信息，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第一容量范围时，基于通知信息的关键信息确定输出信息。
在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第二容量范围时，基于通知信息确定输出信息；
其中，预设的第二容量范围与预设的第一容量范围不同，且第二容量范围大于第一容量范围。
这里，输出设备侧针对输出模态为视觉模态或者听觉模态的情况下基于通知信息确定输出信息的方法，与服务器侧或者主设备侧针对输出模态为视觉模态或者听觉模态的情况下基于通知信息确定输出信息的方法相同，这里，不再赘述。
针对输出模态为视觉模态的情况下，在一种可选的实施例中，基于通知信息确定输出信息，包括：
当输出模态为听觉模态时，将通知信息或通知信息的关键信息进行语音转换，将转换后的语音数据确定为输出信息。
在一种可选的实施例中，基于通知信息的关键信息确定输出信息，包括：
当输出模态为听觉模态时，将关键信息进行语音转换，将转换后的语音数据确定为输出信息。
这里，输出设备侧针对输出模态为听觉模态的情况下将通知信息或通知信息的关键信息进行语音转换，将转换后的语音数据确定为输出信息的方法，与服务器侧或者主设备侧针对输出模态为听觉模态的情况下将通知信息或通知信息的关键信息进行语音转换，将转换后的语音数据确定为输出信息的方法相同，这里，不再赘述。
针对输出模态为听觉模态的情况下，在一种可选的实施例中，基于通知信息确定输出信息，包 括：
当输出模态为视觉模态时，基于输出通道对应的输出设备，对通知信息进行UI自适应，得到输出信息。
在一种可选的实施例中，基于通知信息的关键信息确定输出信息，包括：
当输出模态为视觉模态时，基于输出通道对应的输出设备，对关键信息进行UI自适应，得到输出信息。
这里，输出设备侧针对输出模态为视觉模态的情况下基于输出通道对应的输出设备，对通知信息或通知信息的关键信息进行UI自适应，得到输出信息的方法，与服务器侧或者主设备侧针对输出模态为视觉模态的情况下基于输出通道对应的输出设备，对通知信息或通知信息的关键信息进行UI自适应，得到输出信息的方法相同，这里，不再赘述。
需要说明的是，本申请实施例提供的信息输出通道选择方法和信息的输出方法可以应用于会议场景、车内场景、沐浴场景和运动场景中，这里，本申请实施例不限于此。
举例来说，针对会议场景来说，用户的智能手机收到一个信息，多个设备构成的网络架构中包括：智能手机、智能手表、智能耳机和智能眼镜，获取用户的智能手机、智能手表、智能耳机和智能眼镜的传感器采集的数据，利用上述信息输出通道选择方法，对上述接收到的信息进行分类处理，得到分类信息中重要性信息为最高优先级、隐私性信息为最高优先级、紧急性信息为最高优先级，通过分类信息和传感器采集的数据，可以从智能手机、智能手表、智能耳机和智能眼镜所包括的所有输出通道(相当于上述可选输出通道)选取出输出通道(集)(相当于上述输出通道)，例如，得到的输出通道(集)为：智能手机-卡片、智能眼镜-卡片、智能手表-振动；针对选择智能手机-卡片和智能眼镜-卡片这两个通道时，可以基于输出通道的信道容量信息，例如，针对智能手机-卡片来说，信道容量信息落入预设的第二容量范围时，基于输出设备对接收到的信息进行UI自适应，从而确定出输出信息，将输出信息显示在智能手机上；针对智能眼镜-卡片来说，信道容量信息落入预设的第一容量范围时，基于接收到的信息的关键信息进行UI自适应，从而确定出输出信息，最终将输出信息显示在智能眼镜上，例如，关键信息为发信人，标题信息；针对选择智能手表-振动这一通道时，可以基于接收到的信息对应的分类信息，从分类信息与振动强度的映射关系中，确定出接收到的信息的振动强度，最终智能手表以接收到的信息的振动强度进行振动。
由此可以看出，针对不同的分类信息的通知信息所采用的输出通道是不同的，并且输出通道的不同使得输出信息也会有所不同，可见，本申请实施例提出的信息输出选择方法能够针对不同类型的电子设备和不同场景下的电子设备做到有效适配。
需要说明的是，本申请实施例针对设备的选择，模态的选择和信息的选择不限于上述所涉及的场景，还可以包括其他场景，以图3为例进行扩展说明，图3为本申请实施例提供的一种可选的多个设备构成的网络架构的实例的结构示意图，如图3所示，该网络结构包括：服务器、智能电视、智能眼镜、智能手表、智能手机和智能耳机，其中，服务器分别与智能电视、智能眼镜、智能手表、智能手机和智能耳机相连接，该网络架构中的可选输出通道可以包括：智能手机-卡片、智能手表-卡片、智能车机-卡片、智能电视-卡片，这些属于视觉通道，智能耳机-语音、智能手机-语音、智能车机-语音、智能手表-语音、智能电视-语音，这些属于听觉通道，智能手表-振动和智能手机-振动，这些属于触觉通道。
基于该网络架构，当智能手机接收到一条短信时，服务器获取该短信(相当于上述通知信息)，智能电视、智能眼镜、智能手表、智能手机和智能耳机中每个设备的传感器采集数据，服务器获取每个设备的传感器采集的数据，从而得到传感器采集的数据，在获取到通知信息和传感器采集的数据之后，对通知信息进行处理，得到通知信息对应的分类信息，其中，包括通知信息对应的重要性信息、紧急性信息和隐私性信息，在根据通知信息和传感器采集的数据确定输出通道中，第一种是根据分类信息和传感器采集的数据所得到的可选输出通道的信道质量信息，采用选取规则，确定输出通道；第二种是根据分类信息、传感器采集的数据所得到的传感器的场景信息和可选输出通道，采用预设的神经网络模型，确定输出通道。
这样，可以通过上述信息输出通道选择方法从可选输出通道中选取出，与通知信息对应的分类信息和传感器采集的数据所反映的当前场景最为匹配的最优输出通道(集)。
采用上述信息输出通道选择方法时，若接收到的比较重要的信息，为了及时准确地通知用户，当用户戴着智能耳机，且其他设备均距离用户的距离较远时，可以通过智能耳机-语音这一输出通道输出；接收到比较紧急的信息，为了及时地通知用户，当用户戴着智能眼镜，且其他设备均处于关闭状态时，通过智能眼镜-卡片这一输出通道输出；接收到不便公开的信息，为了保证隐私性，当用 户戴着智能手表，且智能手表和智能手机处于开启状态，智能电视、智能耳机和智能眼镜处于关闭状态，可以通过智能手机-卡片、智能手表-卡片这一输出通道输出。
如此，针对不同类型的电子设备和不同类型的场景下使得信息与输出通道得到有效匹配。
下面举实例来对上述一个或多个实施例中的信息输出通道选择方法和信息的输出方法进行描述。
本实例以通知信息为UI界面信息，且多个设备构成的网络架构(例如图3)为例，图4为本申请实施例提供的一种可选的信息输出通道选择方法和信息的输出方法的实例的流程示意图，如图4所示，服务器获取多个设备中的一个UI界面的UI界面信息(相当于图4中的卡片信息)，其中，图5为本申请实施例提供的一种可选的UI卡片设计架构示意图，如图5所示，展示卡片的成套信息包括：必选项和可选项，其中，该成套信息梯度呈现，根据优先级分为必要信息(对应必选项)和可选信息(对应可选项)，必选项包括泛在图标+建议，应用图标+名称，辅助信息和核心信息，可选项包括：图像展示和按钮入口；需要说明的是，小卡承载所有必要信息，大卡承载更多辅助信息，提供清晰的模板，便于进行信息提取呈现。
图6为本申请实施例提供的一种可选的UI界面的实例的示意图，如图6所示，为一个航班信息的UI界面，UI界面上包括：XX旅行，航班助手，航班号，X月X日，预计于07:15在深圳宝安T3起飞，预计09:35在上海浦东T1达到的航班，准点率为90％，值机柜台为E01-E18，等级口为F28，其中，UI界面还包括控件：航班助手、查看订单和预定酒店。
其中，针对UI界面信息(相当于卡片信息)，首先需要获取卡片信息(以UI Tree结构存在)，UI Tree中的每一个节点表示UI中的一个表示元素或操作控件(Control/Widget/Element)，其给出了该元素的相关属性，UI Tree的元素属性信息包括：文本描述、交互属性(是否可点击、是否可输入文字、是否可滑动等)、元素位置等。
其中，在搭载安卓(Android)平台的设备中，从系统中获取卡片信息的方法主要有两种：第一种是通过Android系统的Accessibility Service相关接口来获取图像界面元素；第二种是通过UI交互软件，直接获得界面元素；其中，通过Android Accessibility Service相关接口来获取UI界面信息时，需要界面截图来辅助获取控件的相关图像信息。通过UI交互软件，一般可直接获取卡片信息。
在图4中，服务器在获取到卡片信息之后，首先，需要对卡片信息进行分类，即对泛在卡片信息字段进行分类，分类信息可以包括以下至少一项：隐私性信息，紧急性信息和重要性信息；其中，分类信息一般用优先级表示，隐私性信息可以反映出卡片信息的内容涉及用户隐私的程度，紧急性信息可以反映出卡片信息的内容需要及时输出的紧迫程度，重要性信息可以反映出卡片信息的内容中包含的信息量的重要程度。
其中，分类信息中的隐私性信息、紧急性信息、重要性信息，可通过为卡片信息构建多模态神经网络1进行多标签分类推理实现，具体过程参考下方流程：
SA01：提取卡片信息中用户可见的各个控件的属性信息；
其中，各个控件的属性信息包括但不限于文本描述、控件位置、交互属性、控件在UI Tree中的位置信息(如控件在UI Tree中前序、中序、后序遍历的对应索引等)；
SA02：对各个控件的属性信息依次输入第一神经网络模型进行数值化编码，得到对各个控件的数值化向量；
SA03：将各个控件的数值化向量依次输入第二神经网络模型，得到各个控件的语义向量；
SA04：将各个控件的语义向量依次输入第三神经网络模型进行信息提取和融合，得到第一UI的语义向量；
SA05：将第一UI的语义向量输入第四神经网络模型进行多标签分类，提取卡片信息的隐私性信息、重要性信息、紧急性信息。
SA06：从卡片信息中按照UI元素规范提取出关键控件的信息文本列表，若关键控件的信息文本列表所包含文本过长，将上述第一UI的语义向量输入一个神经网络模型进行关键信息的抽取，得到关键信息；
SA07：从卡片信息中提取出用户可见可交互的响应控件的属性信息，即响应信息。
其中，在对卡片信息进行分类时，如图4所示，还对卡片信息进行控件元素的提取和数据挖掘，从而可以得到卡片信息的关键信息和辅助信息，其中，该关键信息包括任务主题，任务主题为卡片信息对应的任务名称，例如，航班信息的UI界面，任务主题即为航班信息，任务主题可以通过卡片信息中的指定控件元素获取；关键信息除了采用上述方法之外，还可以指定控件元素列表组成；辅助信息可以为响应信息，包括对UI界面所呈现信息可支持的响应方式，响应信息通过卡片信息的可 交互控件元素获取；其中，可交互的控件可以包括可点击和/或可输入的控件。
上述SA02提到的网络模型，可以是任意网络类型，不局限于特定的模型；上述SA03中提到的网络模型可以是任意网络模型，不局限于特定的模型；上述SA04中提到的神经网络模型可以是任意能接受序列输入的模型，如RNN[1,2,3]、Transformer[4]、Bert[5]等，不局限于特定的模型；上述SA03-SA06中提到的网络模型可以是一个单独的模型，也可以是同一个模型中不同的网络模块；SA05中提到的多标签分类采用的网络模型是一种多个输出标签，每个标签都带有类别信息的网络模型。
本实例中，在获取到分类信息之后，为了进行通道选择，需要获取传感器采集的数据，针对不同类型的电子设备或者不同类型场景下传输通道的选择，如图4所示，针对泛在服务中的传感器涉及运动传感器、位置传感器、环境传感器、其他传感器。其中，运动传感器，用于监测设备运动，如倾斜、晃动、旋转或摆动等运动，运动传感器包括加速度传感器、陀螺仪/角速度传感器、重力传感器、线性加速度传感器、旋转矢量传感器等；位置传感器，用于确定设备在世界参照系中的物理位置，位置传感器包括地磁传感器、方向传感器、距离/接近传感器等；环境传感器，用于监测设备所处环境的各种属性，环境传感器包括光/红外传感器、气压、温度等；还有其他类型的传感器，如智能手表、智能手环中的光学心率传感器、光学血氧传感器，智能耳机中的骨振动传感器等等。
本实例中，可通过多个设备的传感器感知实现对多通道信道质量的评估，从而得到通道的信道质量信息，具体地，可通过各设备的传感器状态检测机制，实现各设备所涉及的所有可选输出通道的信道质量信息。
针对每个输出通道来说，每个输出通道的信道质量信息是不同的，在不同类型的电子设备和不同类型的场景下，信道质量信息汇总如下面表1所示：
表1
如图4和表1所示，在可选输出通道中，智能手机-卡片、智能手表-卡片、智能车机-卡片、智能电视-卡片属于视觉通道，智能耳机-语音、智能手机-语音、智能车机-语音、智能手表-语音、智能电视-语音属于听觉通道，智能手表-振动和智能手机-振动属于触觉通道，视觉通道、听觉通道和触觉通道的信道容量信息大体上依次下降。本实例在保证隐私性和可触达条件下，将按照信道容量信息选择最佳通道。触觉通道信息容量最弱，一般用作相应设备信息到达的提示，不担当主要信息传 输通道。
本实例中，输出通道的可用性信息、干扰性信息和信道容量信息等是基于各个设备的传感器采集的数据采用状态检测机制对各个设备对应的输出通道进行评估。
如图4所示，在获取到分类信息和可选输出通道的信道质量信息之后，可以采用泛在交互交规进行通道选择。针对泛在交互规则，本实例提出基于卡片信息对应的分类信息和信道质量信息，智能感知的通道自动选择方案；具体地，可人工编制泛在交互规则，进行通道的选择，此种方式灵活多变，可适应较多场景，具体交互过程参考下方流程：
SB01：计算卡片信息对应的隐私性信息、紧急性信息和重要性信息；
SB02：基于计算出的隐私性信息、紧急性信息和重要性信息，利用交互规则，确定是否进行通道传输；
SB03：根据卡片信息对应的隐私性信息，排除隐私性信息达不到的通道；
SB04：根据信道质量的要求，排除可用性信息、干扰性信息任一为差的通道；
SB05：如剩余多个通道，保留信道质量信息和隐私性信息最佳的通道，得到信息输出的最优通道(集)。
此外，还可以将卡片信息对应的分类信息和传感器采集的输出所得到的场景信息组合起来，与可选输出通道输入给多模态交互模型，进行通道的选择，此种方式，交互设计智能化，可避免人工预设考虑不全面，具体过程参考下方流程：
SC01：提取卡片信息中用户可见的各个控件的相关属性信息；
其中，属性信息包括但不限于文本描述、控件位置、交互属性、控件在UI Tree中的位置信息(如控件在UI Tree中前序、中序、后序遍历的对应索引等)；
SC02：对各个控件的属性信息依次输入第一神经网络模型进行数值化编码，得到对各个控件的数值化向量；
SC03：将各个控件的数值化向量依次输入第二神经网络模型得到对各个控件的语义向量；
SC04：将各个控件的语义向量依次输入第三神经网络模型进行信息提取融合，得到第二UI的语义向量；
SC05：依次提取多设备传感器采集到的数据；
SC06：对各个传感器采集到的数据依次输入第五神经网络模型进行数值化编码，得到对各个传感器的数值化向量；
SC07：将各个传感器的数值化向量依次输入第六神经网络模型得到对各个传感器的场景表示向量；
SC08：将各个传感器的场景表示向量依次输入第七神经网络模型进行信息提取融合，得到传感器状态的场景表示向量；
SC09：将第二UI的语义向量(相当于上述通知信息)和传感器状态场景表示向量(相当于上述传感器的场景信息)，输入预设的神经网络模型(相当于上述多模态交互模型)进行多分类，得到最优通道(集)。
上述SC03和SC06中提到的网络模型可以是任意网络模型，不局限于特定的模型；SC04和SC08中提到的神经网络模型可以是任意能接受序列输入的模型，如RNN[1,2,3]、Transformer[4]、Bert[5]等，不局限于特定的模型；上述SC03-SC09中提到的网络模型可以是一个单独的模型，也可以是同一个模型中不同的网络模块。
参考表1，可选输出通道的信道质量信息展现形式各不相同。因此，如图4所示，本实例将在通道选择完成后，进行通道适配设计，例如，将通知信息的信息量与信道容量自适应。
其中，从人体感知角度可以将可选输出通道分为视觉、听觉、触觉，在图4中可以针对不同到模态对信息进行输出：
在触觉上，将卡片信息映射到振动模式上，振动模式的映射可以根据分类信息的紧急性信息、重要性信息、隐私性信息进行适配。
视觉上，具有较大显示空间的通道可展示全部信息，较小显示空间的通道可展示压缩信息，即关键信息；然后在各设备做UI自适应，具体来说，在视觉上，进行UI自适应，对于信道容量信息大小落入预设的第一容量范围的通道，基于选取的最优通道(集)对卡片信息的关键信息进行UI自适应后进行输出，对于信道容量信息落入预设的第二容量范围的通道，选取卡片信息进行UI自适应后进行输出。
听觉上，对容量大的通道，输出全部信息，对容量小的设备，选取压缩信息，即关键信息进行 传输；从通过多模态神经网络2得到UI的文本描述，此外，还要将卡片信息转化成通顺的文本，再将其通过TTS转换为简洁、自然、准确的语音输出给用户，可以方便用户在视觉不便的时候能够通过语音实现UI信息的获取。更进一步地，能够基于语音实现对UI的操作，实现基于全语音的UI交互。具体过程参考下方流程：
SD01：提取卡片信息中用户可见的各个控件的属性信息；
SD02：对各个控件的属性信息依次输入第一神经网络模型进行数值化编码，得到对各个控件的数值化向量；
SD03：将各个控件的数值化向量依次输入第二神经网络模型得到对各个控件的语义向量；
SD04：将各个控件的语义向量依次输入第三神经网络模型进行信息提取融合，得到第三UI的语义向量；
SD05：将第三UI的语义向量传输给文本生成/文本摘要模型进行通顺文本的生成。
SD06：通过TTS算法，将文本转换成语音输出给选定通道。
上述步骤SD02中提到的数值化编码方法不局限于特定算法；上述SD02和SD03中提到的网络模型可以是任意网络模型，不局限于特定的模型；SD04中提到的神经网络模型可以是任意能接受序列输入的模型，如RNN[1,2,3]、Transformer[4]、Bert[5]等，不局限于特定的模型；上述SD02-SD06中提到的网络模型可以是一个单独的模型，也可以是同一个模型中不同的网络模块。
如此，实现不同输出通道的不同模态下的通道模态自适应。
前述主要智能手机上卡片信息来实现，可扩展到其他使用频次最高的主要智能设备和更多形式的UI，以及无UI展示的信息传输中通道选择和多模态信息的自适应呈现。
听觉通道上，生成自然通顺的语音，除了卡片信息文本自然通顺外，还可以通过传感器和相关图像、语音技术识别用户静态信息(性别、年龄段等固有身体特征)和动态情绪(人脸表情、大哭、愤怒)和行为状态(躺沙发、开车、睡眠)，将额外的提示信息添加到文本中，影响TTS的生成风格，使其更加自然。
在上述如图4所示的信息输出通道选择和信息的输出方法中，基于多设备传感器的智能感知，自动为用户选取当前场景下的最优通道(集)，无需用户操作，为卡片信息适配出最优通道(集)，利用最优通道(集)呈现形式输出给用户，完成了一种全新泛在交互框架的设计，在手机/平板等常用主设备的输出通道被判定不可靠的情况下，可自动选取最优通道(集)进行无缝无感的信息输出，可有效提升通信可靠性，为用户提供无缝便捷的泛在服务，提升用户体验。
本申请实施例提供了一种信息输出通道选择方法，包括：获取通知信息和传感器采集的数据，基于通知信息，确定通知信息对应的分类信息，根据分类信息和传感器采集的数据，确定输出通道，输出通道包括输出设备和输出设备对应的输出模态；也就是说，在本申请实施例中，通过获取通知信息和传感器采集的数据，并在得到通知信息对应的分类信息之后，以分类信息和传感器采集的数据为基础，确定输出通道，从而知晓输出设备和输出设备对应的输出模态，可见，不论是任何类型的电子设备的通知信息和任何类型场景下传感器采集的数据，只要获取到通知信息和传感器采集的数据，就可以确定出输出通道，即在具有通知信息和传感器采集的数据的情况下，就可以确定出与通知信息对应的分类信息和传感器所反映的当前场景下最为匹配的输出设备和输出设备对应的输出模态，与相关技术中特定设备下或者特定场景下输出通道的选取方法相比，该信息输出通道选择方法适用不同类型的电子设备和不同类型的场景，并且针对通知信息对应的分类信息，并结合传感器采集的数据，实现了针对不同类型的电子设备或者不同类型场景下传输通道的有效匹配。
基于前述实施例相同的发明构思，本申请实施例提供一种信息输出通道选择装置，图7为本申请实施例提供的一种可选的信息输出通道选择装置的结构示意图，如图7所示，该信息输出通道选择装置包括：获取模块71，配置成获取通知信息和传感器采集的数据；分类模块72，配置成基于通知信息，确定通知信息对应的分类信息；确定模块73，配置成根据分类信息和传感器采集的数据确定输出通道；其中，输出通道包括输出设备和输出设备对应的输出模态。
在一种可选的实施例中，分类模块72，配置成：基于通知信息的语义分析结果，确定通知信息对应的分类信息。
在一种可选的实施例中，分类信息包括以下一项或多项：隐私性信息、紧急性信息和重要性信息。
在一种可选的实施例中，确定模块73，配置成：基于传感器采集的数据，确定可选输出通道的信道质量信息；根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道。
在一种可选的实施例中，信道质量信息包括以下一项或多项：可用性信息、干扰性信息、信道容量信息、隐私性信息和自适应能力信息。
在一种可选的实施例中，确定模块73基于传感器采集的数据，确定可选输出通道的信道质量信息中，包括：基于传感器采集的数据，得到可选输出通道的可用性信息和可选输出通道的干扰性信息；基于可选输出通道的可用性信息和可选输出通道的信道容量信息，重新确定可选输出通道的信道容量信息；将可选输出通道的可用性信息、可选输出通道的干扰性信息、可选输出通道的信道容量信息、预设的可选通道的隐私性信息和预设的可选输出通道的自适应能力信息中的至少一项，确定为可选输出通道的信道质量信息。
在一种可选的实施例中，确定模块73基于传感器采集的数据，确定可选输出通道的信道质量信息中，包括：基于传感器采集的数据，得到可选输出通道的可用性信息和可选输出通道的干扰性信息；将可选输出通道的可用性信息、可选输出通道的干扰性信息、预设的可选输出通道的信道容量信息、预设的可选通道的隐私性信息和预设的可选输出通道的自适应能力信息中的至少一项，确定为可选输出通道的信道质量信息。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为一个时，将选取出的输出通道确定为输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为一个时，将选取出的输出通道确定为输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道的数目为多个时，基于选取出的输出通道的信道质量信息，从选取出的输出通道中选取多个输出通道，将选取出的多个输出通道确定为输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，基于选取出的输出通道的信道质量信息，对选取出的输出通道进行评估处理，得到选取出的输出通道的评估值；将选取出的输出通道中评估值的最大值对应的输出通道确定为输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息满足第一预设条件时，从可选输出通道中选取出满足第二预设条件的输出通道；当选取出的输出通道为多个时，确定出选取出的输出通道中每个输出通道的信道质量信息中隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级高于等于预设优先级的个数；将个数的最大值对应的输出通道确定为输出通道。
在一种可选的实施例中，第一预设条件是指分类信息的等级达到预设等级。
在一种可选的实施例中，确定模块73从可选输出通道中选取出满足第二预设条件的输出通道中，包括：基于可选输出通道的信道质量信息，从可选输出通道中选出满足第二预设条件的输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息中的隐私性信息为第一优先级时，从可选输出通道中选取出信道质量信息中隐私性信息为最高优先级的输出通道；其中，第一优先级为分类信息中隐私性信息中最高的优先级；将选取出的输出通道确定为输出通道。
在一种可选的实施例中，确定模块73根据分类信息和可选输出通道的信道质量信息，从可选输出通道中确定输出通道中，包括：当分类信息中的重要性信息为第一优先级或者紧急性信息为第一优先级时，从可选输出通道中选取出信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道；其中，第一优先级为分类信息中重要性信息中最高的优先级，且为分类信息中紧急性信息中最高的优先级；将选取出的输出通道确定为输出通道。
在一种可选的实施例中，确定模块73，配置成：对传感器采集的数据进行场景分析处理，得到传感器的场景信息；将分类信息、传感器的场景信息和可选输出通道输入至预设神经网络模型中进行多输出通道选取，得到输出通道。
在一种可选的实施例中，当电子设备为多个设备的网络架构中的主设备，上述装置还配置成：将通知信息和输出模态，发送至输出设备。
在一种可选的实施例中，当输出设备为主设备，上述装置还配置成：基于输出模态输出通知信息。
在一种可选的实施例中，输出设备包括多个设备的网络架构中的主设备。
在一种可选的实施例中，当电子设备为多个设备的网络架构中的服务器或者主设备，上述装置还配置成：基于通知信息确定输出信息；将输出信息和输出模态，发送至输出设备。
在一种可选的实施例中，当输出设备为主设备，上述装置还配置成：基于输出模态输出输出信息。
在一种可选的实施例中，上述装置基于通知信息确定输出信息中，包括：当输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将分类信息对应的触觉类别，确定为输出信息。
在一种可选的实施例中，上述装置基于通知信息确定输出信息中，包括：当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第一容量范围时，基于通知信息的关键信息确定输出信息。
在一种可选的实施例中，上述装置基于通知信息确定输出信息中，包括：当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第二容量范围时，基于通知信息确定输出信息；其中，预设的第二容量范围与预设的第一容量范围不同，且第二容量范围大于第一容量范围。
在一种可选的实施例中，上述装置基于通知信息确定输出信息中，包括：当输出模态为听觉模态时，将通知信息进行语音转换，将转换后的语音数据确定为输出信息。
在一种可选的实施例中，上述装置基于通知信息的关键信息确定输出信息中，包括：当输出模态为听觉模态时，将关键信息进行语音转换，将转换后的语音数据确定为输出信息。
在一种可选的实施例中，上述装置基于通知信息确定输出信息中，包括：当输出模态为视觉模态时，基于输出通道对应的输出设备，对通知信息进行UI自适应，得到输出信息。
在一种可选的实施例中，上述装置基于通知信息的关键信息确定输出信息中，包括：当输出模态为视觉模态时，基于输出通道对应的输出设备，对关键信息进行UI自适应，得到输出信息。
在一种可选的实施例中，确定模块73，配置成：根据分类信息和传感器采集的数据，确定输出设备；从输出设备对应模态中确定出输出模态。
在一种可选的实施例中，确定模块73，配置成：根据分类信息和传感器采集的数据，确定输出模态；从输出模态对应的设备中确定出输出设备。
在实际应用中，上述获取模块71、分类模块72和确定模块73可由位于信息输出通道选择装置上的处理器实现，具体为中央处理器(CPU，Central Processing Unit)、微处理器(MPU，Microprocessor Unit)、数字信号处理器(DSP，Digital Signal Processing)或现场可编程门阵列(FPGA，Field Programmable Gate Array)等实现。
本申请实施例提供一种信息的输出装置，图8为本申请实施例提供的一种可选的信息的输出装置的结构示意图，如图8所示，该信息的输出装置包括：接收模块81，配置成接收信息和输出模态；第一输出模块82，配置成当接收到的信息为输出信息时，基于输出模态输出输出信息；第二输出模块83，配置成当接收到的信息为通知信息时，基于通知信息确定输出信息，基于输出模态输出输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息确定输出信息中，包括：当输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将分类信息对应的触觉类别，确定为输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息确定输出信息中，包括：当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第一容量范围时，基于通知信息的关键信息确定输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息确定输出信息中，包括：当输出模态为视觉模态或者听觉模态，且输出通道的信道容量信息落入预设第二容量范围时，基于通知信息确定输出信息；其中，预设的第二容量范围与预设的第一容量范围不同，且第二容量范围大于第一容量范围。
在一种可选的实施例中，第二输出模块83基于通知信息确定输出信息中，包括：当输出模态为听觉模态时，将通知信息或进行语音转换，将转换后的语音数据确定为输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息的关键信息确定输出信息中，包括：
当输出模态为听觉模态时，将关键信息进行语音转换，将转换后的语音数据确定为输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息确定输出信息中，包括：当输出模态为视觉模态时，基于输出通道对应的输出设备，对通知信息进行UI自适应，得到输出信息。
在一种可选的实施例中，第二输出模块83基于通知信息的关键信息确定输出信息中，包括：当输出模态为视觉模态时，基于输出通道对应的输出设备，对关键信息进行UI自适应，得到输出信息。
在实际应用中，上述接收模块81、第一输出模块82和第二输出模块83可由位于信息的输出装置上的处理器实现，具体为CPU、MPU、DSP或FPGA等实现。
图9为本申请实施例提供的一种可选的电子设备的结构示意图，如图9所示，本申请实施例提供了一种电子设备900，包括：处理器91以及存储有所述处理器91可执行指令的存储介质92，所述存储介质92通过通信总线93依赖所述处理器91执行操作，当所述指令被所述处理器91执行时，执行上述一个或多个实施例中所述信息输出通道选择方法。
需要说明的是，实际应用时，终端中的各个组件通过通信总线93耦合在一起。可理解，通信总线93用于实现这些组件之间的连接通信。通信总线93除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图9中将各种总线都标为通信总线93。
图10为本申请实施例提供的一种可选的输出设备的结构示意图，如图10所示，本申请实施例提供了一种输出设备1000，包括：处理器101以及存储有所述处理器101可执行指令的存储介质102，所述存储介质102通过通信总线103依赖所述处理器101执行操作，当所述指令被所述处理器101执行时，执行上述一个或多个实施例中所述信息的输出方法。
需要说明的是，实际应用时，终端中的各个组件通过通信总线103耦合在一起。可理解，通信总线103用于实现这些组件之间的连接通信。通信总线103除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图10中将各种总线都标为通信总线103。
本申请实施例提供了一种计算机存储介质，存储有可执行指令，当所述可执行指令被一个或多个处理器执行的时候，所述处理器执行如上述一个或多个实施例中所述的信息输出通道选择方法，或者，执行如上述一个或多个实施例中所述的信息的输出方法。
其中，计算机可读存储介质可以是磁性随机存取存储器(ferromagnetic random access memory，FRAM)、只读存储器(Read Only Memory，ROM)、可编程只读存储器(Programmable Read-Only Memory，PROM)、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)、电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，EEPROM)、快闪存储器(Flash Memory)、磁表面存储器、光盘、或只读光盘(Compact Disc Read-Only Memory，CD-ROM)等存储器。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用硬件实施例、软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述，仅为本申请的较佳实施例而已，并非用于限定本申请的保护范围。
工业实用性
本申请实施例中信息输出通道选择方法，该方法应用于电子设备中，包括：获取通知信息和传感器采集的数据，基于通知信息，确定通知信息对应的分类信息，根据分类信息和传感器采集的数据确定输出通道，输出通道包括输出设备和输出设备对应的输出模态，与相关技术中特定设备下或者特定场景下输出通道的选取方法相比，该信息输出通道选择方法适用不同类型的电子设备和不同类型的场景，并且针对通知信息对应的分类信息，并结合传感器采集的数据，实现了针对不同类型的电子设备或者不同类型场景下传输通道的有效匹配。

Claims (43)

  1. 一种信息输出通道选择方法，所述方法应用于电子设备中，包括：
    获取通知信息和传感器采集的数据；
    基于所述通知信息，确定所述通知信息对应的分类信息；
    根据所述分类信息和所述传感器采集的数据确定输出通道；其中，所述输出通道包括输出设备和所述输出设备对应的输出模态。
  2. 根据权利要求1所述的方法，其中，所述基于所述通知信息，确定所述通知信息对应的分类信息，包括：
    基于所述通知信息的语义分析结果，确定所述通知信息对应的分类信息。
  3. 根据权利要求1或2所述的方法，其中，所述分类信息包括以下一项或多项：
    隐私性信息、紧急性信息和重要性信息。
  4. 根据权利要求1所述的方法，其中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：
    基于所述传感器采集的数据，确定可选输出通道的信道质量信息；
    根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道。
  5. 根据权利要求4所述的方法，其中，所述信道质量信息包括以下一项或多项：
    可用性信息、干扰性信息、信道容量信息、隐私性信息和自适应能力信息。
  6. 根据权利要求4所述的方法，其中，所述基于所述传感器采集的数据，确定所述可选输出通道的信道质量信息，包括：
    基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；
    基于所述可选输出通道的可用性信息和所述可选输出通道的信道容量信息，重新确定所述可选输出通道的信道容量信息；
    将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
  7. 根据权利要求4所述的方法，其中，所述基于所述传感器采集的数据，确定所述可选输出通道的信道质量信息，包括：
    基于所述传感器采集的数据，得到所述可选输出通道的可用性信息和所述可选输出通道的干扰性信息；
    将所述可选输出通道的可用性信息、所述可选输出通道的干扰性信息、预设的所述可选输出通道的信道容量信息、预设的所述可选通道的隐私性信息和预设的所述可选输出通道的自适应能力信息中的至少一项，确定为所述可选输出通道的信道质量信息。
  8. 根据权利要求4所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；
    当选取出的输出通道的数目为一个时，将选取出的输出通道确定为所述输出通道。
  9. 根据权利要求4所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；
    当选取出的输出通道的数目为第一数量个时，基于选取出的输出通道的信道质量信息，从选取出的输出通道中选取第二数量个输出通道，将选取出的第二数量个输出通道确定为所述输出通道，所述第二数量大于1且小于所述第一数量。
  10. 根据权利要求4所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；
    当选取出的输出通道为多个时，基于选取出的输出通道的信道质量信息，对选取出的输出通道进行评估处理，得到选取出的输出通道的评估值；
    将选取出的输出通道中评估值的最大值对应的输出通道确定为所述输出通道。
  11. 根据权利要求4所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息满足第一预设条件时，从所述可选输出通道中选取出满足第二预设条件的输出通道；
    当选取出的输出通道为多个时，确定出选取出的输出通道中每个输出通道的信道质量信息中隐私性信息的优先级、可用性信息的优先级和信道容量信息的优先级高于等于预设优先级的个数；
    将所述个数的最大值对应的输出通道确定为所述输出通道。
  12. 根据权利要求8至11任一项所述的方法，其中，所述第一预设条件是指所述分类信息的等级达到预设等级。
  13. 根据权利要求8至11任一项所述的方法，其中，所述从所述可选输出通道中选取出满足第二预设条件的输出通道，包括：
    基于所述可选输出通道的信道质量信息，从所述可选输出通道中选取出满足所述第二预设条件的输出通道。
  14. 根据权利要求5所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息中的隐私性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中隐私性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中隐私性信息中最高的优先级；
    将选取出的输出通道确定为所述输出通道。
  15. 根据权利要求5所述的方法，其中，所述根据所述分类信息和所述可选输出通道的信道质量信息，从所述可选输出通道中确定所述输出通道，包括：
    当所述分类信息中的重要性信息为第一优先级或者紧急性信息为第一优先级时，从所述可选输出通道中选取出信道质量信息中干扰性信息为可抗干扰，且信道质量信息中可用性信息为最高优先级的输出通道；其中，所述第一优先级为所述分类信息中重要性信息中最高的优先级，且为所述分类信息中紧急性信息中最高的优先级；
    将选取出的输出通道确定为所述输出通道。
  16. 根据权利要求1所述的方法，其中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：
    对所述传感器采集的数据进行场景分析处理，得到所述传感器的场景信息；
    将所述分类信息、所述传感器的场景信息和可选输出通道输入至预设神经网络模型中进行多输出通道选取，得到所述输出通道。
  17. 根据权利要求1所述的方法，其中于，当所述电子设备为多设备的网络架构中的主设备，所述方法还包括：
    将所述通知信息和所述输出模态，发送至所述输出设备。
  18. 根据权利要求17所述的方法，其中，当所述输出设备为所述主设备，所述方法还包括：
    基于所述输出模态输出所述通知信息。
  19. 根据权利要求1所述的方法，其中，所述输出设备包括多个设备的网络架构中的主设备。
  20. 根据权利要求1所述的方法，其中，当所述电子设备为多个设备的网络架构中的服务器或主设备，所述方法还包括：
    基于所述通知信息确定输出信息；
    将所述输出信息和所述输出模态，发送至所述输出设备。
  21. 根据权利要求20所述的方法，其中，当所述输出设备为所述主设备，所述方法还包括：
    基于所述输出模态输出所述输出信息。
  22. 根据权利要求20所述的方法，其中，所述基于所述通知信息确定输出信息，包括：
    当所述输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
  23. 根据权利要求20所述的方法，其中，所述基于通知信息确定输出信息，包括：
    当输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
  24. 根据权利要求20所述的方法，其中，所述基于所述通知信息确定输出信息，包括：
    当所述输出模态为视觉模态或者听觉模态，且在所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息确定所述输出信息；
    其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
  25. 根据权利要求24所述的方法，其中，所述基于所述通知信息确定输出信息，包括：
    当所述输出模态为听觉模态时，将所述通知信息进行语音转换，将转换后的语音数据确定为所述输出信息。
  26. 根据权利要求23所述的方法，其中，所述基于所述通知信息的关键信息确定输出信息，包括：
    当所述输出模态为听觉模态时，将所述关键信息进行语音转换，将转换后的语音数据确定为所述输出信息。
  27. 根据权利要求24所述的方法，其中，所述基于所述通知信息确定输出信息，包括：
    当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
  28. 根据权利要求23所述的方法，其中，所述基于所述通知信息的关键信息确定输出信息，包括：
    当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
  29. 根据权利要求1所述方法，其中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：
    根据所述分类信息和所述传感器采集的数据，确定所述输出设备；
    从所述输出设备对应模态中确定出所述输出模态。
  30. 根据权利要求1所述的方法，其中，所述根据所述分类信息和所述传感器采集的数据确定输出通道，包括：
    根据所述分类信息和所述传感器采集的数据，确定所述输出模态；
    从所述输出模态对应的设备中确定出所述输出设备。
  31. 一种信息的输出方法，所述方法应用于输出设备中，包括：
    接收信息和输出模态；
    当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；
    当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
  32. 根据权利要求31所述的方法，其中，所述基于所述通知信息确定所述输出信息，包括：
    当所输出模态为触觉模态时，基于预设的触觉类别与分类信息的映射关系，将所述分类信息对应的触觉类别，确定为所述输出信息。
  33. 根据权利要求31所述的方法，其中，所述基于所述通知信息确定所述输出信息，包括：
    当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第一容量范围时，基于所述通知信息的关键信息确定所述输出信息。
  34. 根据权利要求31所述的方法，其中，所述基于所述通知信息确定所述输出信息，包括：
    当所述输出模态为视觉模态或者听觉模态，且所述输出通道的信道容量信息落入预设第二容量范围时，基于所述通知信息确定所述输出信息；
    其中，所述第二容量范围与预设的第一容量范围不同，且所述第二容量范围大于所述第一容量范围。
  35. 根据权利要求34所述的方法，其中，所述基于所述通知信息确定所述输出信息，包括：
    当所述输出模态为听觉模态时，将所述通知信息或进行语音转换，将转换后的语音数据确定为所述输出信息。
  36. 根据权利要求33所述的方法，其中，所述基于所述通知信息的关键信息确定输出信息，包括：
    当所述输出模态为听觉模态时，将所述关键信息进行语音转换，将转换后的语音数据确定为所述输出信息。
  37. 根据权利要求34所述的方法，其中，所述基于所述通知信息所述确定输出信息，包括：
    当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述通知信息进行UI自适应，得到所述输出信息。
  38. 根据权利要求33所述的方法，其中，所述基于所述通知信息的关键信息确定输出信息，包括：
    当所述输出模态为视觉模态时，基于所述输出通道对应的输出设备，对所述关键信息进行UI自适应，得到所述输出信息。
  39. 一种信息输出通道选择装置，所述装置设置于电子设备中，包括：
    获取模块，配置成获取通知信息和传感器采集的数据；
    分类模块，配置成基于所述通知信息，确定所述通知信息对应的分类信息；
    确定模块，配置成根据所述分类信息和所述传感器采集的数据确定输出设备；其中，所述输出通道包括输出设备和所述输出设备对应的输出模态。
  40. 一种信息的输出装置，所述装置设置于输出设备中，包括：
    接收模块，配置成接收信息和输出模态；
    第一输出模块，配置成当接收到的信息为输出信息时，基于所述输出模态输出所述输出信息；
    第二输出模块，配置成当接收到的信息为通知信息时，基于所述通知信息确定所述输出信息，基于所述输出模态输出所述输出信息。
  41. 一种电子设备，包括：
    处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述的权利要求1至30任一项所述的信息输出通道选择方法。
  42. 一种输出设备，包括：
    处理器以及存储有所述处理器可执行指令的存储介质，所述存储介质通过通信总线依赖所述处理器执行操作，当所述指令被所述处理器执行时，执行上述的权利要求31至38任一项所述的信息的输出方法。
  43. 一种计算机存储介质，存储有可执行指令，当所述可执行指令被一个或多个处理器执行的时候，所述处理器执行如权利要求1至30任一项所述的信息输出通道选择方法，或者，执行上述的权利要求31至38任一项所述的信息的输出方法。
PCT/CN2023/113728 2022-11-10 2023-08-18 信息输出通道选择方法、信息的输出方法、装置及设备 WO2024098878A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211407206.7 2022-11-10
CN202211407206.7A CN118018167A (zh) 2022-11-10 2022-11-10 信息输出通道选择方法、信息的输出方法、装置及设备

Publications (1)

Publication Number Publication Date
WO2024098878A1 true WO2024098878A1 (zh) 2024-05-16

Family

ID=90954946

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/113728 WO2024098878A1 (zh) 2022-11-10 2023-08-18 信息输出通道选择方法、信息的输出方法、装置及设备

Country Status (2)

Country Link
CN (1) CN118018167A (zh)
WO (1) WO2024098878A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160018655A1 (en) * 2013-03-29 2016-01-21 Sony Corporation Information processing device, notification state control method, and program
CN105745906A (zh) * 2014-08-29 2016-07-06 华为技术有限公司 消息处理方法、系统及相关设备
CN108700982A (zh) * 2016-02-08 2018-10-23 索尼公司 信息处理设备、信息处理方法以及程序
CN111708439A (zh) * 2013-09-03 2020-09-25 三星电子株式会社 提供通知的方法及其电子设备
CN112051743A (zh) * 2019-06-06 2020-12-08 北京三星通信技术研究有限公司 设备控制方法、冲突处理方法、相应的装置及电子设备
US20220050518A1 (en) * 2020-05-07 2022-02-17 Google Llc Notification Delivery Based on Context Awareness

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160018655A1 (en) * 2013-03-29 2016-01-21 Sony Corporation Information processing device, notification state control method, and program
CN111708439A (zh) * 2013-09-03 2020-09-25 三星电子株式会社 提供通知的方法及其电子设备
CN105745906A (zh) * 2014-08-29 2016-07-06 华为技术有限公司 消息处理方法、系统及相关设备
CN108700982A (zh) * 2016-02-08 2018-10-23 索尼公司 信息处理设备、信息处理方法以及程序
CN112051743A (zh) * 2019-06-06 2020-12-08 北京三星通信技术研究有限公司 设备控制方法、冲突处理方法、相应的装置及电子设备
US20220050518A1 (en) * 2020-05-07 2022-02-17 Google Llc Notification Delivery Based on Context Awareness

Also Published As

Publication number Publication date
CN118018167A (zh) 2024-05-10

Similar Documents

Publication Publication Date Title
CN106598215B (zh) 虚拟现实系统的实现方法及虚拟现实装置
EP2980758B1 (en) Method and device for providing image
US20230146384A1 (en) Initiating sensory prompts indicative of changes outside a field of view
KR101574884B1 (ko) 표정 추정 장치, 제어 방법, 제어 프로그램, 및 기록 매체
CN110598576A (zh) 一种手语交互方法、装置及计算机介质
KR102448382B1 (ko) 텍스트와 연관된 이미지를 제공하는 전자 장치 및 그 동작 방법
CN108351750A (zh) 用于处理与触摸输入相关联的强度信息的设备、方法、以及图形用户界面
KR20180055708A (ko) 이미지를 처리하는 전자 장치 및 방법
KR20190074011A (ko) 음성 인식 장치 및 방법
CN111753498B (zh) 文本处理方法、装置、设备及存储介质
CN111814475A (zh) 用户画像构建方法、装置、存储介质和电子设备
JP6114773B2 (ja) 情報処理装置及び方法
WO2024098878A1 (zh) 信息输出通道选择方法、信息的输出方法、装置及设备
US11443738B2 (en) Electronic device processing user utterance and control method thereof
EP3972241A1 (en) Information processing device, information processing method, and program
CN113486260B (zh) 互动信息的生成方法、装置、计算机设备及存储介质
CN116958851A (zh) 视频时效模型的训练方法、装置、设备及存储介质
CN116977884A (zh) 视频切分模型的训练方法、视频切分方法及装置
CN115309299A (zh) 桌面卡片的显示方法、装置、终端、存储介质及程序产品
CN114035686A (zh) 融合触觉的多模态微动效广告情境构建方法
Leong et al. Obstacle Detection and Distance Estimation for Visually Impaired People
CN115424309A (zh) 人脸关键点的生成方法、装置、终端设备及可读存储介质
CN113468932A (zh) 一种智能镜及化妆教学方法
CN113469023B (zh) 确定警觉度的方法、装置、设备和存储介质
EP4325355A1 (en) Dynamic effect calculating method and apparatus

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: 23887573

Country of ref document: EP

Kind code of ref document: A1