CN111539219B

CN111539219B - Method, equipment and system for disambiguation of natural language content titles

Info

Publication number: CN111539219B
Application number: CN202010325483.8A
Authority: CN
Inventors: 袁志伟; 戴帅湘
Original assignee: Individual
Current assignee: Wu Chenxi
Priority date: 2017-05-19
Filing date: 2017-05-19
Publication date: 2024-04-26
Anticipated expiration: 2037-05-19
Also published as: CN107193810B; CN107193810A; CN111539204A; CN111539219A; CN111539217B; CN111539201A; CN111539218A; CN111538812A; CN111539203A; CN111539202A; CN111538811A; CN111539216A; CN111539217A; CN111539214A; CN111539215A

Abstract

The invention aims to provide a method, equipment and a system for disambiguating natural language content titles. Specifically, by determining the actual meaning item information corresponding to the content title after the conversion of the natural language command of the user from the plurality of meaning item information according to the equipment type information of the output equipment and outputting the content corresponding to the content title according to the actual meaning item information, the real meaning of the user can be understood when the meaning of the natural language expression of the user is converted into the meaning with definite expression but the content indicated by the meaning is not definite, the accuracy of user graph identification is improved, and the user voice interaction experience is also improved.

Description

Method, equipment and system for disambiguation of natural language content titles

The application is a division, the application number of the parent application is 201710357079.7, the application date is 2017-05-19, and the invention name is 'a method, equipment and system for disambiguating natural language content titles'.

Technical Field

The present invention relates to the field of speech recognition technology, and more particularly, to a method, apparatus, and system for natural speech content title disambiguation.

Background

Interactions between the user and the device include key control, remote control, somatosensory control, touch control, and the like. With the development of NLP (natural language processing ) technology, an interaction mode, i.e., voice interaction control, is added between a user and a device.

The user interacts with the device using natural language, it is desirable that the device is able to maximize understanding of the user's intent, but humans often have words that appear with ambiguous meanings such as omitted words, referents, etc. when expressed in natural language, existing speech recognition techniques typically utilize context to determine the specific meaning of the omitted words, referents, etc. in the user's language expression. However, when the user interacts with the device using natural language, there is also a case where the meaning of the user's natural language expression is determined after being converted into text, and the text expression of the user's natural language after speech recognition is unique, including neither the omission word nor the reference word. There are cases where the text is expressed explicitly and the content to which it refers is not determined. At this time, the device receiving the natural language input of the user cannot understand the true meaning of the user, so that the accuracy of user intention recognition is reduced, and the user voice interaction experience is affected.

Disclosure of Invention

The invention provides a method applied to a natural language content title disambiguation system, the system comprises a first device, other devices at least comprising a second device, a cloud and a network, the method comprises the following steps:

The user sends a natural language command;

the first device or the second device determines whether an object of the natural language command sent by the user is self;

After the first device or the second device determines that the object of the user for sending the natural language command is self, the natural language command is sent to the cloud;

The cloud receives the natural language command and then converts the natural language command into a content title, wherein the content title is uniquely determined on a literal expression, but the represented content is not uniquely determined;

The cloud determines the content specifically represented by the content title, wherein the cloud combines the device type of the first device or the second device when determining the content specifically represented by the content title;

the cloud returns the content specifically represented by the content title to the first device or the second device after determining the content specifically represented by the content title;

And the first equipment or the second equipment receives the content of the specific representation of the determined content title returned by the cloud and outputs the content of the specific representation of the determined content title.

Optionally, the cloud receives a device type tag from the first device or the second device.

Optionally, the cloud obtains the device type tag of the first device or the second device locally.

Optionally, the first device or the second device determines whether the object to which the user sends the natural language command is itself by one or more of the following:

according to the distance between the user and the equipment;

Detecting the natural language command direction of a user according to the audio;

the user frontal orientation is detected from the image.

The present invention provides a method for natural language content title disambiguation, the method comprising performing at a device the steps of:

determining whether an object of a natural language command sent by a user is self;

after determining that the object of the natural language command sent by the user is self, receiving the natural language command input by the user;

The natural language commands are sent to the cloud,

Such that the cloud, upon receiving the natural language command, converts the natural language command into a content title that is uniquely identified in the literal representation, but whose representative content is not uniquely identified; the cloud determines the content specifically represented by the content title, and the cloud combines the equipment type of the equipment when determining the content specifically represented by the content title;

receiving content specifically represented by the determined content title returned by the cloud;

And outputting the content specifically represented by the determined content title.

The present invention provides a computer medium having stored thereon a computer program, the program being executed by a device to cause the device to:

The natural language commands are sent to the cloud,

The invention provides a device for disambiguation of natural language content titles, comprising a processor, a memory and a program stored on the memory and executable by the processor, the processor executing the program to perform the steps of:

The natural language commands are sent to the cloud,

The present invention provides an output device for natural language content title disambiguation, the output device comprising:

A module for determining whether an object to which the user transmits a natural language command is itself;

a module for receiving a natural language command input by a user after determining that an object of the natural language command transmitted by the user is the object;

a module for sending natural language commands to the cloud,

A module for receiving content specifically represented by the determined content title returned by the cloud;

and a module for outputting the content specifically represented by the determined content title.

The present invention provides an apparatus for natural language content title disambiguation, the apparatus comprising information processing means including:

a module for sending natural language commands to the cloud,

The present invention provides an apparatus for natural language content title disambiguation, the apparatus comprising:

a detection unit configured to determine whether an object to which the user transmits a natural language command is itself;

the sound pickup unit is configured to receive a natural language command input by a user after determining that an object of the natural language command sent by the user is the object;

a transmitting unit that transmits the natural language command to the cloud,

the receiving unit is configured to receive the content specifically represented by the determined content title returned by the cloud;

and an output unit configured to output the content specifically represented by the determined content title.

The invention provides a method for disambiguation of natural language content titles, which performs the following steps at the cloud:

Receiving a natural language command sent by equipment;

Converting the natural language command into a content title, wherein the content title is uniquely identified in a literal representation, but the content it represents is not uniquely identified;

determining content specifically represented by the content title, wherein the device type of the device is combined when determining the content specifically represented by the content title;

The content specifically represented by the content title is returned to the device after the content specifically represented by the content title is determined.

The present invention provides a computer medium having stored thereon a computer program, the program being executed by a cloud to cause the cloud to:

Receiving a natural language command sent by equipment;

The invention provides a cloud for disambiguation of natural language content titles, which comprises a processor, a memory and a program stored on the memory and executable by the processor, wherein the processor executes the program to realize the following steps:

Receiving a natural language command sent by equipment;

The present invention provides a cloud for natural language content title disambiguation, the cloud comprising:

A module for receiving natural language commands sent by the device;

means for converting a natural language command into a content title, wherein the content title is uniquely identified in a literal representation, but the content it represents is not uniquely identified;

A module for determining content specifically represented by the content title, wherein the device type of the device is incorporated in determining the content specifically represented by the content title;

And a module for returning the content specifically represented by the content title to the device after determining the content specifically represented by the content title.

The present invention provides a cloud for natural language content title disambiguation, the cloud including an information processing apparatus including:

A module for receiving natural language commands sent by the device;

The receiving unit is used for receiving the natural language command sent by the equipment;

A first processing unit coupled to the receiving unit, the first processing unit configured to convert the natural language command into a content title, wherein the content title is literally uniquely determined, but the content it represents is not uniquely determined;

A second processing unit coupled to the first processing unit, the second processing unit configured to determine content specifically represented by the content title, wherein the device type of the device is incorporated in determining the content specifically represented by the content title;

And a transmitting unit configured to return the content specifically represented by the content title to the device after determining the content specifically represented by the content title.

Alternatively, the first processing unit and the second processing unit may be combined into one processing unit.

The invention provides a natural language content title disambiguation system, which comprises a cloud as described, a device as described and a network.

Compared with the prior art, the embodiment of the invention determines the actual meaning item information corresponding to the content title after the natural language command of the user is converted from the plurality of meaning item information according to the equipment type information of the output equipment, and outputs the content corresponding to the content title according to the actual meaning item information, so that when the meaning of the natural language expression of the user is converted into the meaning with definite expression but the indicated content is not definite, the true meaning of the user can be understood, the accuracy of the intention recognition of the user is improved, and the voice interaction experience of the user is also improved.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:

FIG. 1 illustrates a block diagram of a system for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 2 illustrates a method flow for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 3 illustrates a first embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 4 illustrates a second embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 5 illustrates a third embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 6 shows a fourth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 7 shows a fifth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 8 shows a sixth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 9 shows a seventh embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 10 shows an eighth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 11 shows a ninth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 12 shows a tenth embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

FIG. 13 shows an eleventh embodiment for natural language content title disambiguation, in accordance with an embodiment of the present invention;

Fig. 14 shows a twelfth embodiment for natural language content title disambiguation, according to an embodiment of the present invention.

The same or similar reference numbers in the drawings refer to the same or similar parts.

Detailed Description

The invention is described in further detail below with reference to the accompanying drawings.

In the following description, since the specification is used to describe many technical details to assist in understanding the present invention, the present invention can be implemented even without the technical details, and the technical solution of the present invention is not limited to only the scenes and environments described in the specification.

Description of the problem

When a user sends a control command to a device using natural language, it is desirable that the natural language command is expressed more closely to natural language, while it is also desirable that the device be able to actually understand the intent of its control command. For example, when the user wants to play the music "cannot say secret" of Zhou Jielun, it is the existing practice to not only explicitly play the content "cannot say secret", but also explicitly play the category "music", that is, at least the template "i want to listen to … …" or "please play music … …" needs to be established, and express it in terms of the template at the time of natural language input, that is, the natural language input "i want to listen to the cannot say secret", or "please play the music cannot say secret" is required, so that the receiving device can understand the user's real intention. If the user simply inputs "please play a secret that cannot be said", the device cannot immediately determine whether the user requested music "secret that cannot be said" or movie "secret that cannot be said", some of the prior art will determine the intention of the user request based on the context information, and some will give the user the option to determine the actual intention of his request by prompting. However, these existing schemes either have the possibility of erroneously recognizing the intention of the user or have the problem that the recognition response time is excessively long and the burden of use on the user is increased.

The above problem scenario may exist in a home environment or in a vehicle-mounted environment. In addition, in an office environment, similar problem scenarios may exist. For example, when a user inputs a "first AI meeting" into the device in a conference room through natural language and a file corresponding to the "first AI meeting" includes video, audio, and text or web pages, the device cannot determine whether the user really intends to play the video "first AI meeting", play audio "first AI meeting", or play text or web pages related to the "first AI meeting". The device may determine the user's intent from the context information or may choose to determine the actual intent of its request by prompting the user. However, as such, these existing schemes have either the possibility of erroneously recognizing the intention of the user or the problem that the recognition response time is excessively long and the burden of use on the user is increased.

The above user natural language input content, scene, environment, etc. are merely for illustrative purposes and are not limited thereto. For a better understanding of the present invention, the following description of the embodiments refers to some input contents, scenes and environments, however, the understanding of the technical solution of the present invention should not be limited thereto, and all possible input contents, scenes and environments are within the protection scope of the present invention.

General overview

When a user sends a command using natural language, the natural language command is converted into a content title having a plurality of actual meaning items of information by a speech recognition technique, that is, the content title is uniquely determined in a text expression, but the content represented by the content title is not uniquely determined, particularly different contents having the same title, particularly contents having different output forms, and at this time, the device type can be incorporated in determining the content to which the content title particularly points. The device is an output device, which is used for outputting content corresponding to a content title, wherein the content corresponding to the content title is adapted to the actual meaning item information corresponding to the content title, that is, the output device is used for outputting the content specifically pointed by the content title. In some embodiments, the output device is also a device that receives user natural language commands; in some embodiments, the output device is a different device than the device that receives the user natural language command. In some embodiments, the output device may be a device having only output capabilities. In some embodiments, the output device may be a device that may have the capability to acquire content corresponding to the content title based on the actual meaning item information corresponding to the content title, in addition to the output capability.

In some embodiments, when the output device has a sound pickup function, the output device may simultaneously function as a device that receives a user natural language command; when the output device does not have the sound pickup function, the output device is different from the device for receiving the natural language command of the user, and at this time, the output device can be controlled by other control devices with the sound pickup function; in some embodiments, when the output device has a sound pickup function, or a part of the output devices have a sound pickup function, the output device may also be a different device from the device that receives the user natural language command, and in this case, the output device may be controlled by another control device having a sound pickup function; in some embodiments, when a part of the output devices have a sound pickup function, the output device having the sound pickup function and the device receiving the user natural language command are the same device, and the output device not having the sound pickup function and the device receiving the user natural language command are different devices, and the output device not having the sound pickup function may be controlled by other control devices having the sound pickup function.

In some embodiments, if the device type of the output device is an audio playback device, preferentially determining that the content to which the content title points is audio content associated with the content title; if the device type of the output device is a video playing device, the content pointed by the content title is preferentially determined to be video content related to the content title.

In some embodiments, if the output device includes an audio playback device and a video playback device, and the device type of the output device is a video playback device, preferentially determining that the content to which the content title points is video content related to the content title; if only the video playing device exists, the user is prompted to select to play the audio content or the video content pointed by the content title, or the content pointed by the content title is preferentially determined to be the video content related to the content title, and the user is prompted to determine that the content is the video content related to the content title, and optionally, the user is prompted to switch to the audio content related to the content title or not.

In some embodiments, the control device stores the output device and its device type, and the user can set the output device and its device type information through the input means of the control device. In some embodiments, the user may activate the output devices by controlling the input means of the device, may activate all of the output devices, or may activate a portion of the output devices. The setting and starting processes can be input through characters such as a keyboard, a touch screen and the like, and can also be input through natural language commands received by a sound pickup device. The pick-up device of the control device receives the natural voice input command of the user and completes the process of the content specifically pointed by the content title.

For example, a user's natural language input of "a secret that cannot be said" is converted into the word "a secret that cannot be said" after the speech-converted word processing, which is uniquely determined here for the speech-converted word processing, whereas "a secret that cannot be said" may represent music "a secret that cannot be said" and may represent a movie "a secret that cannot be said", at which time, if the output device is sound, it is preferentially determined that the true intention of the user's natural language input of "a secret that cannot be said" is music "; if the output device is a television, then the real intent to prioritize the user natural language input "cannot say secret" is the movie "cannot say secret"; alternatively, if the environment in which the user is located is where both sound and television are present and the output device is television, then the real intent to preferentially determine that the user natural language input "cannot say secret" is the movie "cannot say secret"; if the environment in which the user is located is where only a television is present and the output device is a television, then the true intent of the user's natural language input "cannot say secret" is to preferentially determine that the movie "cannot say secret" and to prompt the user to determine that it is the movie "cannot say secret", optionally prompting the user whether to switch to the music "cannot say secret".

In the interaction process, the sound equipment and the television have the sound pickup function, so that the sound equipment and the television are output equipment and can be used as equipment for receiving natural language commands of users; alternatively, the control device may also receive a user natural language command, where the control device stores a television in which the environment in which the user is located includes sound of an output audio file and an output video file, the user inputs a natural language through the control device and the control device completes the foregoing process of recognizing the actual intention of the user, and transmits the determined content to the output device. In this process, a user may input devices and device types included in the user environment via text or natural language, which may be used to activate all or a portion of the devices included in the user environment.

The above examples may be used in a home environment, in a vehicle-mounted environment, or any environment where similar devices exist.

For example, the user's natural language input "first AI meeting", which is converted into the word "first AI meeting" after speech conversion word processing, is uniquely determined here for speech conversion word processing, however "first AI meeting" may represent video "first AI meeting", and may also represent audio "first AI meeting" or "first AI meeting" related words or web pages, at which time, if the output device is connected to sound, the real intention of the user's natural language input "first AI meeting" is preferentially determined to be audio "first AI meeting"; if the output device is a projector or television with sound connected, then the real intention of preferentially determining that the user natural language input "first AI meeting" is video "first AI meeting"; if the output device is a projector with no sound connected, the real intention of preferentially determining that the user natural language input of the first AI meeting is related words or web pages of the first AI meeting; optionally, if the environment in which the user is located has both sound and projector, and the output device is a projector, then first determining whether the projector is connected to the sound, if not, then preferentially determining that the real intention of the user's natural language input "first AI meeting" is "first AI meeting" related text or web page; if the connection is made, the real intention of the user natural language input 'first AI meeting' is preferentially determined to be video 'first AI meeting', optionally the user is prompted to determine that the user is video 'first AI meeting', optionally whether the user is prompted to switch to audio 'first AI meeting', or 'first AI meeting' related words or web pages.

In the above interaction process, both the sound and the television have a sound pickup function, but the projector does not have a sound pickup function. Therefore, the sound equipment and the television are output equipment and can also be used as equipment for receiving the natural language commands of the user, the projector is output equipment, but not used as equipment for receiving the natural language commands of the user, and the projector can receive the natural language commands of the user through the control device, complete the process of identifying the real intention of the user by the control device and control the output content to be sent to the projector; optionally, since the environment where the user is located includes a projector without a pickup function, all natural language commands are received by the control device, and the control device completes the process of recognizing the real intention of the user, and controls the output content to be sent to the output device; in some embodiments, the control device is further configured to determine an output capability the device has.

Device type information

The device type information may be represented by any identifier that can distinguish between different device types, and in particular embodiments, the identifier may be the type of the output file or a device type tag. The identification of the device type can be done automatically or can be set manually by the user. Information such as device self attributes, user attributes, context, etc. can be incorporated in the device type distinguishing identification process. In the process of distinguishing and identifying the device types, disambiguation of the device types can be completed through interaction, and meanwhile, the disambiguation effect can be continuously improved through an enhanced learning model through user behavior in the interaction process.

Content title

The content corresponding to the content title may be the content stored locally in the internal memory, may be the content stored in the external memory, or may be the content obtained through internet searching.

System architecture

As shown in fig. 1, the system 100 includes at least a first device 110, and in some embodiments, a network device 130 and a network 140; in some embodiments, the first device 110 may independently accomplish the present invention; in some embodiments, first device 110 cooperates with network device 130 connection via network 140 to accomplish the present invention; in some embodiments, the system 100 further comprises at least one second device 120, the first device 110 being coupled to the second device 120 via a network 140 to perform the present invention; in some embodiments, the first device 110 and the second device 120 cooperate with the network device 130 through the network 140 connection to complete the present invention; in some embodiments, the system 100 further includes a smart device 150, the smart device 150 controlling the system 100 through the network 140 to accomplish the present invention.

Here, the first device 110 may be any electronic product capable of outputting one or more combinations of media contents such as video, audio, pictures, text, and the like. In some embodiments, the first device 110 includes, by way of non-limiting example, a television, a stereo, a projector, a car stereo, a car display, a smart rear view mirror, and the like. In some embodiments, the output content includes, by way of non-limiting example, speaker output audio and video in conjunction with a display, display output text and pictures, and the like. In some embodiments, the first device 110 has sound pickup capability. In some embodiments, the first device 110 optionally has voice conversion text capabilities. In some embodiments, the first device 110 optionally includes a processor, a memory, and a program stored on the memory that is executable on the processor, the processor executing the program to perform the corresponding functions and/or methods of the present invention; in some embodiments, the first device 110 optionally includes or is coupled to a computer readable medium, such as Random Access Memory (RAM) and/or cache memory, wherein the computer readable medium stores a program for execution by a processor for performing the corresponding functions and/or methods of the present invention. The first device 110 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. In some embodiments, the first device 110 optionally includes or is connected to a computer readable medium for storing other information, optionally including user requested content; in some embodiments, the first device 110 optionally includes several modules, which may be program modules, configured to perform the functions of the embodiments of the present invention; in some embodiments, the first device 110 comprises a controller comprising a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, is capable of carrying out the respective functions and/or methods of the present invention; in some embodiments, the first device 110 optionally includes a wireless or wired network connection unit; in some embodiments, first device 110 may implement NLP functionality, identifying natural language input of a user; in some embodiments, the first device 110 may implement a network search function; in some embodiments, the first device 110 may include an operating system; the first device 110 may install an Application (APP) for performing the corresponding functions of the present invention; the first device 110 may be activated by means of a button, a remote control, a wake-up word or smart device 150, etc.

The second device 120 may be any electronic product capable of outputting one or more combinations of video, audio, pictures, text, etc., but having a different type of media output than the first device 110. In some embodiments, the second device 120 includes, by way of non-limiting example, a television, stereo, projector, car stereo, car display, smart rear view mirror, and the like. In some embodiments, the output content includes, by way of non-limiting example, speaker output audio and video in conjunction with a display, display output text and pictures, and the like. In some embodiments, the second device 120 has sound pickup capability. In some embodiments, the second device 120 optionally has voice conversion text capabilities. In some embodiments, the second device 120 optionally includes a processor, a memory, and a program stored on the memory that is executable on the processor to perform the program to implement the corresponding functions and/or methods of the present invention; in some embodiments, the second device 120 optionally includes or is coupled to a computer readable medium, such as Random Access Memory (RAM) and/or cache memory, wherein the computer readable medium stores a program for execution by a processor for performing the corresponding functions and/or methods of the present invention. The second device 120 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. In some embodiments, the second device 120 optionally includes or is connected to a computer readable medium for storing other information, optionally including user requested content. In some embodiments, the second device 120 optionally includes several modules, which may be program modules, configured to perform the functions and/or methods corresponding to the embodiments of the present invention. In some embodiments, the second device 120 comprises a controller comprising a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, is capable of carrying out the respective functions of the invention. In some embodiments, the second device 120 optionally includes a wireless or wired network connection unit; in some embodiments, the second device 120 may implement NLP functionality, identifying natural language input of the user; the second device 120 may implement a network search function; in some embodiments, the second device 120 may include an operating system; the second device 120 may install an application APP for performing the corresponding functions of the present invention; the second device 120 may be activated by means of a button, a remote control, a wake-up word or smart device 150, etc.

The network device 130 is connected to the first device 110 and/or the second device 120. Here, the network device 130 includes, but is not limited to, an implementation such as a network host, a single network server, a set of multiple network servers, or a set of computers based on cloud computing. Here, the Cloud is composed of a large number of hosts or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, a super virtual computer composed of a group of loosely coupled computer sets. In particular embodiments, network device 130 may host multiple servers. In some embodiments, the network device may be referred to as a network device node; in some embodiments, the network device node may be one node to perform the corresponding functions of the present invention, or may be a plurality of nodes to perform the corresponding functions of the present invention together, where the plurality of nodes may be arranged in a centralized manner or may be arranged in a distributed manner. In some embodiments, the network device 130 includes a processor, a memory, and a program stored on the memory that can run on the processor, the processor executing the program to perform the corresponding functions of the present invention. In some embodiments, network device 130 optionally includes or is coupled to a computer-readable medium, such as Random Access Memory (RAM) and/or cache memory, in which a program is stored for execution by a processor for performing the corresponding functions and/or methods of the present invention. Network device 130 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. In some embodiments, network device 130 optionally includes or is connected to a computer readable medium for storing other information. In some embodiments, network device 130 optionally includes several modules, which may be program modules, configured to perform the functions and/or methods associated with the various embodiments of the invention. In some embodiments, the network device 130 includes a controller including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, is capable of carrying out the corresponding functions of the invention. In some embodiments, the network device 130 may be implemented by one or more computing devices. In some embodiments, network device 130 is implemented by one or more computing units. In some embodiments, the network device 130 may be implemented by a server; in some embodiments, the network device 130 may be implemented by a distributed server; in some embodiments, the network device 130 is disposed within an environment in which the user is located; in some embodiments, the network device 130 is provided separately; in some embodiments, the network device 130 may be disposed in the first device 110 or the second device 120; in some embodiments, the network device 130 may also be disposed outside of the user's environment; in some embodiments, the network device 130 may implement a storage function, store other information, optionally user requested content; in some embodiments, network device 130 may implement NLP functionality, identifying natural language input of the user; in some embodiments, network device 130 may implement a network search function; in some embodiments, network device 130 may implement network connection functions; in some embodiments, network device 130 may include an operating system; the network device 130 may install an application APP for performing the corresponding functions of the present invention.

The network 140 may connect the first device 110 and the second device 120, or may connect the network device 130 and the first device 110 and/or the second device 120. Network 140 illustratively includes, without limitation, a local area network LAN, a wide area network WAN, an Ethernet network, the Internet, any mobile communications network, a satellite network, or any other wired/wireless network; in some embodiments, network 140 may include a combination of networks; in some embodiments, the wireless connection may also be implemented by near field communication.

The smart device 150 has a sound pickup function, and may be any electronic product that can perform man-machine interaction with a user through a keyboard, a touch pad, a touch screen, or handwriting equipment, voice, etc., such as a PC, a mobile phone, a smart phone, a PDA, a wearable device, a palm computer PPC, a smart remote controller, or a tablet computer. Particularly for environments where the first device 110, the second device 120, etc. do not have a pickup function. In some embodiments, the smart device 150 includes a processor, a memory, and a program stored on the memory that can run on the processor, the processor executing the program to implement the corresponding functions of the present invention; in some embodiments, the smart device 150 includes a computer readable medium storing a program for execution by a processor for performing the corresponding functions of the present invention; in some embodiments, the smart device 150 includes a controller, the control including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, is capable of carrying out the respective functions of the present invention; in some embodiments, the smart device 150 optionally includes several modules, which may be program modules, for performing the corresponding functions of the present invention; in some embodiments, the smart device 150 optionally includes an operating system; in some embodiments, the smart device 150 optionally includes a touch sensitive display screen or keyboard; in some embodiments, the smart device 150 optionally includes a display device; in some embodiments, the smart device 150 optionally includes a keyboard, a mouse; in some embodiments, the smart device 150 installs an application APP for performing the corresponding functions of the present invention.

It should be understood by those skilled in the art that the first device 110, the second device 120, the network device 130, and the intelligent device 150 are merely examples, and other first devices, second devices, network devices, or intelligent devices that may be present in the present invention or in the future are also included within the scope of the present invention and are incorporated herein by reference. Here, the first device, the second device, the network device, and the intelligent device each include an electronic device capable of automatically performing numerical calculation and information processing according to a preset or stored instruction, and the hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a digital processor (DSP), an embedded device, and the like.

In some embodiments, the processor may include, by way of non-limiting example, a central processing unit CPU, a graphics processing unit GPU, a CPU and GPU, a microprocessor, a digital signal processor, or any other processing unit or component known in the art; in some embodiments, the functions of the processor may be alternatively performed by hardware logic components, including, by way of non-limiting example, field programmable gate arrays FPGAs, application specific integrated circuits ASICs, application specific standard products ASSPs, system on chip SOCs, complex programmable logic devices CPLDs, and the like.

In some embodiments, a computer readable medium is used to store information. Computer-readable media can include, by way of non-limiting example, volatile and nonvolatile memory, removable and non-removable media, for storage of information by any technology; computer-readable media include, by way of non-limiting example, RAM, ROM, EEPROM, flash memory, CD-ROM, digital versatile disk DVD, optical storage, magnetic disk, magnetic tape, any other magnetic storage device, RAID storage systems, USB connected to devices by hot plug, or any other medium capable of storing information.

In some embodiments, program modules are stored in a computer readable medium and are executable by a processor; in some embodiments, the program modules may be application programs stored on a computer readable medium and executed on a processor.

Summary of the flow

As shown in fig. 2, a method for natural language content title disambiguation includes the steps of:

step 201, receiving a natural language command input by a user;

When the user interacts with the device in voice, the user is more prone to use a natural and simpler expression mode, for example, the user may directly send the natural language command "play the secret which cannot be spoken by Zhou Jielun", even directly send the natural language command "secret which cannot be spoken", "first AI meeting", etc., and then the natural language command input by the user can be collected through a sound collecting device such as a microphone, etc.

And step 203, converting the natural language command into a content title, wherein the text corresponding to the content title is provided with a plurality of sense item information.

Specifically, the natural voice command is converted into text by a voice recognition technology such as a method based on a vocal tract model and voice knowledge, a template matching method and a method using an artificial neural network, so that a corresponding content title can be obtained, wherein the text corresponding to the content title has a plurality of sense item information.

Here, the text corresponding to the content title having a plurality of sense item information means that the text corresponding to the content title is unique in terms of a text expression, but the content represented by the text is not uniquely determined, that is, has a plurality of sense items. For example, "a secret that cannot be said" may represent music "a secret that cannot be said" or a movie "a secret that cannot be said"; the "first AI meeting" may represent a "first AI meeting" video, or may represent a "first AI meeting" audio, or a "first AI meeting" related text or web page.

Step 205, determining the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

For example, assuming that a natural language command input by a user is "secret incapable of being said" and device type information of an output device is sound, it may be determined that the actual meaning item information is music "secret incapable of being said"; if the device type information of the output device is television, the actual meaning item information can be determined to be the movie 'secret which cannot be said'; if the output device includes both a television and sound, then when the output device is a television, it may be determined that the actual sense item information is the movie "cannot say secret". In another embodiment, if the output device includes only a television, the actual meaning information may be determined to be the movie "cannot say secret" and the user may be prompted to determine that the content is the movie "cannot say secret", optionally prompting the user whether to switch to the music "cannot say secret".

For another example, assuming that the natural language command input by the user is "the first AI meeting", and the device type information of the output device is a projector or a television connected with sound, it may be determined that the actual meaning item information is a video of "the first AI meeting"; if the equipment type information of the output equipment is sound equipment, determining that the actual meaning item information is 'first AI meeting' audio; if the device type information of the output device is a projector to which no sound is connected, it may be determined that the actual meaning item information is a "first AI meeting" related text, picture, or web page.

Step 207, the output device outputs the content corresponding to the content title, where the content corresponding to the content title is adapted to the actual meaning item information.

Specifically, the output device firstly acquires the content corresponding to the content title according to the actual meaning item information, and then outputs the content; or the output device directly outputs the content corresponding to the content title, wherein the content corresponding to the content title is matched with the actual meaning item information. For example, the output device may obtain and output the content corresponding to the content title by searching the internal memory or the external memory locally, may obtain and output the content corresponding to the content title by searching the network, and may receive and output the content corresponding to the content title transmitted by other devices.

For example, an output device such as a sound may search locally for a built-in memory or a connected CD, search over a network, or receive and obtain music "cannot say secret" from other devices and play; an output device such as a television may search locally for built-in memory or attached VCD, DVD, USB memory, web searches, or receive and obtain the movie "cannot say secrets" from other devices and play; an output device such as a projector may obtain the "first AI meeting" related text or web page, etc. from the other device.

The possible embodiments will be described below by way of non-limiting example, and the present invention is not limited to the cases listed below, in which the text corresponding to a content title has a plurality of meaning item information, meaning that the text corresponding to the content title is literally unique, but the content represented by it is not uniquely determined.

First embodiment

As shown in fig. 3, in a first embodiment, the system 100 includes a first device 110. A method for natural language content title disambiguation comprising the steps of:

In step 301, the first device 110 receives a natural language command entered by a user.

The user may prefer to use a more natural, simpler expression when interacting with the device, such as the user may directly send the natural language command "play Zhou Jielun's cannot say secret", or even directly send the natural language command "cannot say secret", "first AI meeting", etc.

In step 303, after receiving the natural language command, the first device 110 converts the natural language command into a content title, where a text corresponding to the content title has a plurality of meaning item information.

Specifically, the first device 100 may collect a natural language command input by a user through a sound collection device such as a microphone, etc.; then, the natural voice command is converted into text through a voice recognition technology such as a method based on a sound channel model and voice knowledge, a template matching method and a method using an artificial neural network, so that a corresponding content title can be obtained, and the conversion of the natural language command into the content title is realized, wherein a text corresponding to the content title has a plurality of meaning item information.

Here, the text corresponding to the content title having a plurality of sense item information means that the text corresponding to the content title is unique in terms of a text expression, but the content represented by the text is not uniquely determined. For example, "a secret that cannot be said" may represent music "a secret that cannot be said" or a movie "a secret that cannot be said"; the "first AI meeting" may represent a "first AI meeting" video, or may represent a "first AI meeting" audio, or a "first AI meeting" related text or web page.

In step 305, the first device 110 determines, according to the device type information of the corresponding output device, the actual sense item information corresponding to the content title from the plurality of sense item information.

For example, assuming that the natural language command input by the user is "cannot say secret", and the device type information of the output device is sound, the first device 110 may determine that the actual sense item information is music "cannot say secret"; if the device type information of the output device is television, the first device 110 may determine that the actual meaning item information is the movie "cannot say secret"; if the output device includes both television and stereo, then when the output device is television, the first device 110 may determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the output device includes only a television, the first device 110 may determine that the actual sense item information is a movie "cannot say secret" and prompt the user to determine that the content is a movie "cannot say secret", optionally prompting the user whether to switch to a music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the output device is a projector or television connected with sound, the first device 110 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the output device is sound, the first device 110 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the output device is a projector to which no sound is connected, the first device 110 may determine that the actual sense item information is a word, picture, or web page associated with "the first AI meeting".

In step 307, the first device 110 outputs the content corresponding to the content title according to the actual meaning item information.

Specifically, the first device 110 may obtain, according to the actual meaning item information, the content corresponding to the content title by searching the internal memory or the external memory locally and outputting the content, or may obtain, by searching the network, the content corresponding to the content title and outputting the content, or may receive, by outputting, the content corresponding to the content title sent by another device. For example, the first device 110 may be, for example, a sound device, which may search locally for a built-in memory or a connected CD, search over a network, or receive and obtain music "cannot say secrets" from other devices and play; the first device 110, such as a television, may search locally for built-in memory or attached VCD, DVD, USB memory, web searching, or receive and obtain the movie "cannot say secrets" from other devices and play; the first device 110 is, for example, a projector, which may obtain the "first AI meeting" related text or web page, etc. from other devices and present the corresponding text or web page.

Optionally, a method for natural language content title disambiguation comprises the steps of:

Receiving, at the first device 110, a natural language command input by a user; converting a natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; device type information of the first device 110 is combined in determining the actual sense item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving a natural language command input by a user; converting the natural language command into a content title; device type information of the first device 110 is combined in determining the actual sense item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; converting the natural language command into a content title; device type information of the first device 110 is combined in determining the actual sense item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for incorporating device type information of the first device 110 in determining the actual sense item information; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for incorporating device type information of the first device 110 in determining the actual sense item information; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; a second processing unit configured to determine the actual sense item information, the device type information of the first device 110 being incorporated in determining the actual sense item information; and the output unit is configured to output the content corresponding to the content title according to the actual meaning item information.

Second embodiment

As shown in fig. 4, in a second embodiment, the system 100 includes a first device 110, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

In step 401, the first device 110 receives a natural language command input by a user.

In step 409, after receiving the natural language command, the first device 110 sends the natural language command to the network device 130.

Optionally, the first device 110 also sends its own device type information to the network device 130.

In step 403, the network device 130 receives the natural language command and converts the natural language command into a content title, where a text corresponding to the content title has a plurality of meaning information.

For example, "a secret that cannot be said" may represent music "a secret that cannot be said" or a movie "a secret that cannot be said"; the "first AI meeting" may represent a "first AI meeting" video, or may represent a "first AI meeting" audio, or a "first AI meeting" related text or web page.

Optionally, the network device 130 receives its device type information from the first device 110;

Optionally, the network device 130 obtains the device type information of the first device 110 locally.

In step 405, the network device 130 determines, according to the device type information of the first device 110, actual sense item information corresponding to the content title from the plurality of sense item information.

For example, assuming that the natural language command input by the user is "cannot say secret", and the device type information of the first device 110 is sound, the network device 130 may determine that the actual sense item information is music "cannot say secret"; if the device type information of the first device 110 is television, the network device 130 may determine that the actual meaning item information is the movie "cannot say secret"; if the first device 110 includes both television and stereo, then when it is television, the network device 130 may determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the first device 110 includes only a television, the network device 130 may determine that the actual sense item information is a movie "cannot say secret" and prompt the user to determine that the content is a movie "cannot say secret", optionally prompting the user whether to switch to a music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the first device 110 is a projector or a television connected with sound, the network device 130 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the first device 110 is sound, the network device 130 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the first device 110 is a projector with no sound connected, the network device 130 may determine that the actual sense item information is a "first AI meeting" related text, picture, or web page.

In step 411, the network device 130 returns the actual sense item information to the first device 110 after determining the actual sense item information.

In step 407, after receiving the actual sense item information returned by the network device 130, the first device 110 outputs the content corresponding to the content title according to the actual sense item information.

Specifically, the first device 110 may obtain, by searching the internal memory or the external memory locally, the content corresponding to the content title and output the content, or may obtain, by searching the network, the content corresponding to the content title and output the content, or may receive, by sending, by other devices, the content corresponding to the content title and output the content. For example, the first device 110 may be, for example, a sound device, which may search locally for a built-in memory or a connected CD, search over a network, or receive and obtain music "cannot say secrets" from other devices and play; the first device 110, such as a television, may search locally for built-in memory or attached VCD, DVD, USB memory, web searching, or receive and obtain the movie "cannot say secrets" from other devices and play; the first device 110, such as a projector, may obtain the "first AI meeting" related text or web pages, etc. from other devices and render the text or web pages.

Receiving, at the first device 110, a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: a unit for receiving a natural language command input by a user; a unit for transmitting a natural language command to the network device 130, causing the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combining device type information of the first device 110 when determining the actual meaning item information; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: a unit for receiving a natural language command input by a user; a unit for transmitting a natural language command to the network device 130, causing the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combining device type information of the first device 110 when determining the actual meaning item information; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: the sound pickup unit is configured to receive natural language commands input by a user; a transmitting unit configured to transmit a natural language command to the network device 130, to cause the network device 130 to convert the natural language command into a content title after receiving the natural language command, and to combine device type information of the first device 110 when determining the actual meaning item information; a receiving unit configured to receive the actual sense item information returned by the network device 130; and the output unit is configured to output the content corresponding to the content title according to the actual meaning item information.

At the network device 130, receiving the natural language command sent by the first device 110 and converting the natural language command into a content title; device type information of the first device 110 is combined in determining the actual sense item information; the actual sense item information is returned to the first device 110.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: receiving a natural language command sent by the first device 110, and converting the natural language command into a content title; device type information of the first device 110 is combined in determining the actual sense item information; the actual sense item information is returned to the first device 110.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command sent by the first device 110, and converting the natural language command into a content title; device type information of the first device 110 is combined in determining the actual sense item information; the actual sense item information is returned to the first device 110.

Optionally, the network device 130 includes: a unit for receiving a natural language command sent by the first device 110; a unit for converting the natural language command into a content title; means for incorporating device type information of the first device 110 in determining the actual sense item information; and means for returning the actual sense item information to the first device 110.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving a natural language command sent by the first device 110; a unit for converting the natural language command into a content title; means for incorporating device type information of the first device 110 in determining the actual sense item information; and means for returning the actual sense item information to the first device 110.

Optionally, the network device 130 includes: a receiving unit, configured to receive a natural language command sent by the first device 110; a first processing unit for converting natural language commands into content titles; a second processing unit, configured to determine the actual sense item information, where the device type information of the first device 110 is combined when the actual sense item information is determined; and a sending unit, configured to return the actual meaning item information to the first device 110.

Third embodiment

As shown in fig. 5, in a third embodiment, the system 100 includes a first device 110, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 501, the first device 110 receives a natural language command input by a user;

The user may prefer to use a more natural, simpler expression when interacting with the device, for example, the user may directly send a natural language command such as "play Zhou Jielun's cannot say secret", or even send a natural language command such as "cannot say secret", "first AI meeting".

Step 503, the first device 110 converts the natural language command into a content title and sends the content title to the network device 130; the text corresponding to the content title is provided with a plurality of sense item information;

Optionally, the first device 110 also sends its own device type information to the network device 130;

step 505, the network device 130 receives the content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110;

Step 511, the network device 130 returns the actual meaning item information to the first device 110;

In step 507, after receiving the actual sense item information returned by the network device 130, the first device 110 outputs the content corresponding to the content title according to the actual sense item information.

receiving, at the first device 110, a natural language command input by a user; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving a natural language command input by a user; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type of the first device 110 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for transmitting the content title to the network device 130, causing the network device 130 to combine the device type information of the first device 110 when determining the actual meaning item information after receiving the content title; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for transmitting the content title to the network device 130, causing the network device 130 to combine the device type information of the first device 110 when determining the actual meaning item information after receiving the content title; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 includes: the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; a transmitting unit configured to transmit a content title to the network device 130, so that the network device 130 combines device type information of the first device 110 when determining the actual meaning item information after receiving the content title; a receiving unit configured to receive the actual sense item information returned by the network device 130; and the output unit is configured to output the content corresponding to the content title according to the actual meaning item information.

At the network device 130: receiving a content title transmitted by the first device 110; device type information of the first device 110 is combined in determining the actual sense item information; the actual sense item information is returned to the first device 110.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: receiving a content title transmitted by the first device 110; device type information of the first device 110 is combined in determining the actual sense item information; the actual sense item information is returned to the first device 110.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: and receiving a content title sent by the first device 110, and returning the actual sense item information to the first device 110 in combination with the device type of the first device 110 when determining the actual sense item information.

Optionally, the network device 130 includes: a unit for receiving a content title transmitted by the first device 110; means for incorporating device type information of the first device 110 in determining the actual sense item information; and means for returning the actual sense item information to the first device 110.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving a content title transmitted by the first device 110; means for incorporating device type information of the first device 110 in determining the actual sense item information; and means for returning the actual sense item information to the first device 110.

Optionally, the network device 130 includes: a receiving unit, configured to receive a content title sent by the first device 110; a first processing unit, configured to determine the actual sense item information, where the device type information of the first device 110 is combined when determining the actual sense item information; and a sending unit, configured to return the actual meaning item information to the first device 110.

Fourth embodiment

As shown in fig. 6, in a fourth embodiment, the system 100 includes a first device 110, at least one second device 120, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 601, a user sends a natural language command;

In step 603, after the first device 110 or the second device 120 determines that the object that the user sends the natural language command is itself, the natural language command is converted into a content title, where a text corresponding to the content title has multiple sense item information.

Optionally, the first device 110 or the second device 120 determines whether the object to which the user sends the natural language command is itself by one or a combination of the following ways:

-determining the output device from a distance between the user and the first device and a distance between the user and the second device;

-determining the output device according to the direction in which the user issued the natural language command;

-determining the output device according to the current frontal orientation of the user.

For example, if the output device is determined according to the distance between the user and the first device and the distance between the user and the second device, and assuming that the distance between the user and the first device 110 is d1 and the distance between the user and the second device 120 is d2 and d1> d2, the second device 120, which is the device closest to the user, may be determined as the output device.

For another example, if the output device is determined according to the direction in which the user issues the natural language command. Specifically, the user natural language command direction may be detected by voice, and the device existing in the direction may be detected by an image, and the device in the natural language command direction may be determined as an output device, for example, a device closest to the user in the natural language command direction may be determined as an output device.

If the output device is determined according to the current front face of the user, for example. Specifically, the device existing in the direction of the current front face of the user is detected as the output device through the image, for example, the device closest to the user in the direction of the current front face of the user is used as the output device.

Step 605, the first device 110 or the second device 120 determines, according to its own device type information, actual sense item information corresponding to the content title from the plurality of sense item information;

For example, assuming that the natural language command input by the user is "cannot say secret", and the device type information of the first device 110 or the second device 120 is sound, it may be determined that the actual meaning item information is music "cannot say secret"; if the device type information of the first device 110 or the second device 120 is a television, determining that the actual meaning item information is a movie "cannot be said secret"; if the first device 110 or the second device 120 includes both television and stereo, then when it is television, it may be determined that the actual sense item information is the movie "cannot say secret". In another embodiment, if the first device 110 or the second device 120 only includes a television, the actual meaning item information may be determined to be a movie "cannot say secret" and the user may be prompted to determine that the content is a movie "cannot say secret", optionally prompting the user whether to switch to a music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the first device 110 or the second device 120 is a projector or a television connected with sound, it may be determined that the actual meaning item information is "first AI meeting" video; if the device type information of the first device 110 or the second device 120 is sound, it may be determined that the actual sense item information is "the first AI meeting" audio; if the device type information of the first device 110 or the second device 120 is a projector to which no sound is connected, it may be determined that the actual sense item information is a "first AI meeting" related text, picture, or web page.

In step 607, the first device 110 or the second device 120 outputs the content corresponding to the content title according to the actual meaning item information.

Specifically, the first device 110 or the second device 120 may obtain the content corresponding to the content title by searching the internal memory or the external memory locally and output the content, or may obtain the content corresponding to the content title by searching the network and output the content, or may receive the content corresponding to the content title sent by other devices and output the content. For example, the first device 110 or the second device 120 may be, for example, a sound device, which may locally search for a built-in memory or a connected CD, web search, or receive and obtain the music "cannot say secret" from other devices and play; the first device 110 or the second device 120 is, for example, a television, which can search locally for built-in memory or attached VCD, DVD, USB memory, search over a network, or receive and obtain the movie "cannot say secret" from the other device and play it; the first device 110 or the second device 120, such as a projector, may obtain the "first AI meeting" related text or web page, etc. from the other devices and render the text or web page.

At the first device 110 or the second device 120, determining that the object to which the user sent the natural language command is itself; receiving a natural language command input by a user; converting the natural language command into a content title; combining own device type information when determining the actual meaning item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 or the second device 120 causes the first device 110 or the second device 120 to: determining that the object of the user for sending the natural language command is self; receiving a natural language command input by a user; converting the natural language command into a content title; combining own device type information when determining the actual meaning item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: determining that the object of the user for sending the natural language command is self; receiving a natural language command input by a user; converting the natural language command into a content title; combining own device type information when determining the actual meaning item information; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for incorporating device type information of itself in determining the actual sense item information; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises information processing means, wherein the information processing means comprises: means for determining that an object to which the user sends a natural language command is itself; a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for incorporating device type information of itself in determining the actual sense item information; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: a determination unit configured to determine that an object to which the user transmits the natural language command is itself; the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; a second processing unit configured to determine the actual sense item information, the device type being incorporated in itself when determining the actual sense item information; and the output unit is configured to output the content corresponding to the content title according to the actual meaning item information.

Fifth embodiment

As shown in fig. 7, in a fifth embodiment, the system 100 includes a first device 110, at least one second device 120, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 701, a user sends a natural language command;

The user may prefer to use a more natural, simpler expression when interacting with the device, for example, the user may directly send a natural language command such as "play Zhou Jielun's cannot say secret", or even send a natural language command such as "cannot say secret", "first AI meeting", etc.

Step 709, after the first device 110 or the second device 120 determines that the object to which the user sends the natural language command is itself, the natural language command is sent to the network device 130;

optionally, the first device 110 or the second device 120 also sends own device type information to the network device 130;

In step 703, after receiving the natural language command, the network device 130 converts the natural language command into a content title, where a text corresponding to the content title has a plurality of meaning information.

Step 705, the network device 130 determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110 or the device type information of the second device 120;

For example, assuming that the natural language command input by the user is "cannot say secret", and the device type information of the first device 110 or the second device 120 is sound, the network device 130 may determine that the actual meaning item information is music "cannot say secret"; if the device type information of the first device 110 or the second device 120 is a television, the network device 130 determines that the actual sense item information is the movie "cannot say secret"; if the first device 110 or the second device 120 includes both television and stereo, then when it is television, the network device 130 may determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the first device 110 or the second device 120 only includes a television, the network device 130 may determine that the actual meaning item information is a movie "cannot say secret" and prompt the user to determine that the content is a movie "cannot say secret", optionally prompting the user whether to switch to a music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the first device 110 or the second device 120 is a projector or a television connected with sound, the network device 130 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the first device 110 or the second device 120 is sound, the network device 130 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the first device 110 or the second device 120 is a projector to which no sound is connected, the network device 130 may determine that the actual meaning item information is a "first AI meeting" related text, picture, or web page.

Optionally, the network device 130 receives corresponding device type information from the first device 110 or the second device 120;

Optionally, the network device 130 obtains the device type information of the first device 110 or the device type information of the second device 120 locally.

Step 711, the network device 130 returns the actual meaning item information to the first device 110 or the second device 120;

In step 707, after receiving the actual meaning item information returned by the network device 130, the first device 110 or the second device 120 outputs the content corresponding to the content title according to the actual meaning item information.

At the first device 110 or the second device 120, determining that the object to which the user sent the natural language command is itself; receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 causes the first device 110 or the second device 120 to: determining that the object of the user for sending the natural language command is self; receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: determining that the object of the user for sending the natural language command is self; receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: a unit for receiving a natural language command input by a user; means for determining that an object to which the user sends a natural language command is itself; a unit for transmitting a natural language command to the network device 130, causing the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combining device type information of the first device 110 or device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises information processing means, wherein the information processing means comprises: means for determining that an object to which the user sends a natural language command is itself; a unit for receiving a natural language command input by a user; a unit for transmitting a natural language command to the network device 130, causing the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combining device type information of the first device 110 or device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: a determination unit configured to determine that an object to which the user transmits the natural language command is itself; the sound pickup unit is configured to receive natural language commands input by a user; a transmitting unit configured to transmit a natural language command to the network device 130, cause the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combine the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and an output unit configured to output content corresponding to the content title according to the actual meaning item information.

At the network device 130, receiving the natural language command transmitted by the first device 110 or the second device 120, converting the natural language command into a content title, and combining the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: the natural language command sent by the first device 110 or the second device 120 is received and then converted into a content title, and when the actual meaning item information is determined, the actual meaning item information is returned to the first device 110 or the second device 120 by combining the device type information of the first device 110 or the device type information of the second device 120.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: after receiving the natural language command sent by the first device 110 or the second device 120, converting the natural language command into a content title, and combining the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information; the actual sense item information is returned to the first device 110 or the second device 120.

Optionally, the network device 130 includes: means for receiving a natural language command sent by the first device 110 or the second device 120; a unit for converting the natural language command into a content title; means for combining device type information of the first device 110 or device type information of the second device 120 in determining the actual meaning item information; and means for returning the actual sense item information to the first device 110 or the second device 120.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: means for receiving a natural language command sent by the first device 110 or the second device 120; a unit for converting the natural language command into a content title; means for combining device type information of the first device 110 or device type information of the second device 120 in determining the actual meaning item information; and means for returning the actual sense item information to the first device 110 or the second device 120.

Optionally, the network device 130 includes: a receiving unit, configured to receive a natural language command sent by the first device 110 or the second device 120; a first processing unit for converting natural language commands into content titles; a second processing unit, configured to determine the actual sense item information, where the actual sense item information is combined with device type information of the first device 110 or device type information of the second device 120; and a transmitting unit, configured to return the actual meaning item information to the first device 110 or the second device 120.

Sixth embodiment

As shown in fig. 8, in a sixth embodiment, the system 100 includes a first device 110, at least one second device 120, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

Step 801, a user sends a natural language command;

Step 803, after the first device 110 or the second device 120 determines that the object to which the user sends the natural language command is itself, the natural language command is converted into a content title and sent to the network device 130;

the text corresponding to the content title has a plurality of meaning information, for example, the "secret incapable of being said" may represent music "secret incapable of being said" or may represent movie "secret incapable of being said"; the "first AI meeting" may represent a "first AI meeting" video, or may represent a "first AI meeting" audio, or a "first AI meeting" related text or web page.

Optionally, the first device 110 or the second device 120 also sends its own device type information to the network device 130;

Step 805, after the network device 130 receives the content title, determining actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110 or the device type information of the second device 120;

Optionally, the network device 130 obtains the device type information of the first device 110 or the second device 120 locally.

Step 811, the network device 130 returns the actual meaning item information to the first device 110 or the second device 120;

In step 807, after receiving the actual meaning item information returned by the network device 130, the first device 110 or the second device 120 outputs the content corresponding to the content title according to the actual meaning item information.

Receiving a natural language command input by a user after determining that an object of the natural language command transmitted by the user is itself at the first device 110 or the second device 120; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the first device 110 or the second device 120 causes the first device 110 or the second device 120 to: determining that the object of the natural language command sent by the user is the natural language command input by the user after the object is self; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: determining that the object of the natural language command sent by the user is the natural language command input by the user after the object is self; converting the natural language command into a content title and transmitting the content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information after receiving the content title; receiving the actual sense item information returned by the network device 130; and outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: means for determining that an object to which the user sends a natural language command is itself; a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for transmitting the content title to the network device 130, causing the network device 130 to combine the device type information of the first device 110 or the device type information of the second device 120 in determining the actual meaning item information after receiving the content title; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises information processing means, wherein the information processing means comprises: means for determining that an object to which the user sends a natural language command is itself; a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for transmitting the content title to the network device 130, causing the network device 130 to combine the device type information of the first device 110 or the device type information of the second device 120 in determining the actual meaning item information after receiving the content title; means for receiving the actual sense item information returned by the network device 130; and the unit is used for outputting the content corresponding to the content title according to the actual meaning item information.

Optionally, the first device 110 or the second device 120 comprises: a determination unit configured to determine that an object to which the user transmits the natural language command is itself; the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; a transmitting unit configured to transmit a content title to the network device 130, so that the network device 130 combines the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information after receiving the content title; a receiving unit configured to receive the actual sense item information returned by the network device 130; and the output unit is configured to output the content corresponding to the content title according to the actual meaning item information.

At the network device 130, the content title sent by the first device 110 or the second device 120 is received, and the actual meaning item information is returned to the first device 110 or the second device 120 in combination with the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: receiving a content title sent by the first device 110 or the second device 120, and returning the actual meaning item information to the first device 110 or the second device 120 in combination with the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a content title sent by the first device 110 or the second device 120, and returning the actual meaning item information to the first device 110 or the second device 120 in combination with the device type information of the first device 110 or the device type information of the second device 120 when determining the actual meaning item information.

Optionally, the network device 130 includes: a unit for receiving a content title transmitted by the first device 110 or the second device 120; means for combining device type information of the first device 110 or device type information of the second device 120 in determining the actual meaning item information; and means for returning the actual sense item information to the first device 110 or the second device 120.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving a content title transmitted by the first device 110 or the second device 120; means for combining device type information of the first device 110 or device type information of the second device 120 in determining the actual meaning item information; and means for returning the actual sense item information to the first device 110 or the second device 120.

Optionally, the network device 130 includes: a receiving unit for receiving a content title transmitted by the first device 110 or the second device 120; a first processing unit, configured to determine the actual sense item information, where the actual sense item information is combined with device type information of the first device 110 or device type information of the second device 120; and a sending unit, configured to return the actual meaning item information to the first device 110 or the second device 120.

Seventh embodiment

As shown in fig. 9, in a seventh embodiment, the system 100 includes a first apparatus 110, a smart device 150, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 901, a user sends a natural language command;

In step 903, after receiving the natural language command, the intelligent device 150 converts the natural language command into a content title, where the text corresponding to the content title has a plurality of meaning information.

In step 905, the intelligent device 150 determines the actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110.

For example, assuming that the natural language command input by the user is "cannot say secret" and the device type information of the first device 110 is sound, the smart device 150 may determine that the actual sense item information is music "cannot say secret"; if the device type information of the first device 110 is television, the intelligent apparatus 150 determines that the actual meaning item information is the movie "cannot say secret"; if the first device 110 includes both television and stereo, then when it is television, the intelligent means 150 can determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the first device 110 includes only a television, the intelligent apparatus 150 may determine that the actual sense item information is a movie "cannot say secret" and prompt the user to determine that the content is a movie "cannot say secret", optionally prompt the user whether to switch to a music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the first device 110 is a projector or a television connected with sound, the intelligent apparatus 150 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the first device 110 is sound, the intelligent apparatus 150 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the first device 110 is a projector with no sound connected, the intelligent apparatus 150 may determine that the actual sense item information is a word, picture or web page related to "the first AI meeting".

Step 911, the intelligent device 150 sends the actual meaning item information to the first apparatus 110;

In step 907, after receiving the actual sense item information sent by the intelligent device 150, the first apparatus 110 outputs the content corresponding to the content title according to the actual sense item information.

Optionally, step 913 (not shown) is also included before step 905: the intelligent device 150 determines the first apparatus 110 as an output apparatus.

Optionally, the output device is determined according to an operation submitted by the user based on the smart device with respect to the output device. Specifically, the smart device 150 may provide an interface for a user to select, through a touch screen or a keyboard, the first device 110 as an output device; the intelligent device 150 may provide a voice interactive interface where the user determines that the first apparatus 110 is an output apparatus through natural language instructions.

Optionally, the intelligent device 150 determines the output device by detecting a distance between the user and the device, for example, determining the first device 110 as the output device when the distance between the user and the first device 110 is closest;

Alternatively, the smart device 150 determines the output device by detecting the direction of the user natural language command, for example, the smart device 150 detects the direction of the user natural language command by voice and simultaneously detects the device existing in the direction as the first device 110 by image, and determines the first device 110 as the output device;

alternatively, the smart device 150 determines the output device by detecting the user front facing, for example, the smart device 150 determines the first device 110 as the output device by detecting, through an image, that the device present in the direction in which the user front facing is the first device 110.

Receiving, at the smart device 150, a natural language command input by a user; converting a natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; the actual sense item information is sent to the first device 110.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: receiving a natural language command input by a user; converting the natural language command into a content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; the actual sense item information is sent to the first device 110.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; converting the natural language command into a content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; the actual sense item information is sent to the first device 110.

Optionally, the smart device 150 includes: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; and means for transmitting the actual sense item information to the first device 110.

Optionally, the smart device 150 includes an information processing device, the information processing device including: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; means for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; and means for transmitting the actual sense item information to the first device 110.

Optionally, the smart device 150 includes: the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; a second processing unit configured to determine actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; and a transmitting unit configured to transmit the actual sense item information to the first device 110.

at the first device 110, after receiving the actual sense item information transmitted from the smart device 150, the content corresponding to the content title is output according to the actual sense item information,

The text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving actual sense item information sent by the intelligent device 150; outputting the content corresponding to the content title according to the actual meaning item information;

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving actual sense item information sent by the intelligent device 150; outputting the content corresponding to the content title according to the actual meaning item information;

Optionally, the first device 110 includes: a unit for receiving actual sense item information transmitted by the smart device 150; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: a unit for receiving actual sense item information transmitted by the smart device 150; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the first device 110 includes: a receiving unit configured to receive the actual sense item information transmitted by the smart device 150; an output unit configured to output content corresponding to the content title according to the actual sense item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Eighth embodiment

As shown in fig. 10, in an eighth embodiment, the system 100 includes an apparatus 110, at least one second apparatus 120, a smart device 150, and a network 140. A disambiguation method for natural language content titles comprising the steps of:

Step 1013, the smart device 150 determines an output device from the first device 110 and the second device 120;

Optionally, the output device is determined according to an operation submitted by the user based on the smart device 150 with respect to the output device. Specifically, the smart device 150 may provide an interface for a user to select, through a touch screen or a keyboard, the first device 110 as an output device; the intelligent device 150 may provide a voice interactive interface, and the user may determine that the first determining apparatus 110 is an output apparatus through natural language instructions.

Optionally, the intelligent device 150 determines the output device by detecting the distance of the user from the device, for example, determining that the first device 110 is the output device when the distance of the user from the first device 110 is closest;

Alternatively, the smart device determines the output device by detecting the user front facing, for example, the smart device 150 determines the first device 110 as the output device by detecting, through the image, that the device present in the direction in which the user front facing is the first device 110.

Step 1001, a user sends a natural language command;

In step 1003, after receiving the natural language command, the intelligent device 150 converts the natural language command into a content title, where the text corresponding to the content title has a plurality of meaning item information.

Step 1005, the intelligent device 150 determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device;

For example, assuming that the natural language command input by the user is "secret incapable of being spoken" and the device type information of the output device is sound, the intelligent apparatus 150 may determine that the actual sense item information is music "secret incapable of being spoken"; if the device type information of the output device is a television, the intelligent apparatus 150 determines that the actual meaning item information is the movie "cannot say secret"; if the output device includes both television and audio, then when it is television, the intelligent device 150 can determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the output device includes only a television, the intelligent device 150 may determine that the actual sense item information is the movie "cannot say secret" and prompt the user that the determined content is the movie "cannot say secret", optionally prompting the user whether to switch to the music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the output device is a projector or a television connected with sound, the intelligent apparatus 150 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the output device is sound, the intelligent apparatus 150 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the output device is a projector to which no sound is connected, the intelligent apparatus 150 may determine that the actual sense item information is "first AI meeting" related text, picture, or web page.

Step 1011, the intelligent device 150 sends the actual meaning item information to an output apparatus;

in step 1007, the output device outputs the content corresponding to the content title according to the actual meaning item information.

Specifically, the output device obtains and outputs the content corresponding to the content title through searching the internal memory or the external memory locally, or obtains and outputs the content corresponding to the content title through searching the network, or receives and outputs the content corresponding to the content title sent by other devices. For example, an output device such as a sound, which can locally search a built-in memory or a connected CD, web search, or receive and obtain music "cannot say secret" from other devices and play; an output device such as a television that can search locally for built-in memory or attached VCD, DVD, USB memory, web searches, or receive and obtain the movie "cannot say secrets" from other devices and play; the output device, such as a projector, may obtain the "first AI meeting" related text or web page, etc. from the other device and render the text or web page.

Optionally, the method further comprises step 1015 (not shown): the intelligent device 150 determines the device type information of the output device, for example, the output device may actively send the device type information to the intelligent device, or the intelligent device 150 performs a matching query in the device description information base based on the identification of the output device.

determining, at the intelligent device 150, a corresponding output apparatus; receiving a natural language command input by a user; converting a natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the output equipment; and sending the actual meaning item information to the output equipment.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: determining a corresponding output device; receiving a natural language command input by a user; converting a natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the output equipment; and sending the actual meaning item information to the output equipment.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: determining a corresponding output device; receiving a natural language command input by a user; converting a natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the output equipment; and sending the actual meaning item information to the output equipment.

Optionally, the smart device 150 includes: means for determining a corresponding output device; a unit for receiving a natural language command input by a user; a unit for converting a natural language command into a content title, wherein a text corresponding to the content title has a plurality of sense item information; a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the output device; and a unit for transmitting the actual sense item information to an output device.

Optionally, the smart device 150 comprises an information processing device, wherein the information processing device comprises: a unit for receiving a natural language command input by a user; a unit for converting a natural language command into a content title, wherein a text corresponding to the content title has a plurality of sense item information; a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the output device; and a unit for transmitting the actual sense item information to an output device.

Optionally, the smart device 150 includes: a determining unit configured to determine a corresponding output device; the sound pick-up unit is used for receiving natural language commands input by a user; the first processing unit is used for converting the natural language command into a content title, wherein a text corresponding to the content title is provided with a plurality of sense item information; a second processing unit, configured to determine actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of the output device; and the sending unit is used for sending the actual meaning item information to the output equipment.

At the output device, receiving the actual sense item information sent by the corresponding intelligent device 150; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of sense item information; the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving a natural language command input by a user and converting it into the content title by the smart device 150.

Optionally, a computer medium storing one or more programs, the program being executed by the output device to cause the output device to: receiving actual sense item information sent by the intelligent device 150; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the output device comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: receiving actual sense item information sent by the intelligent device 150; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the output device includes: a unit for receiving actual sense item information transmitted by the smart device 150; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the output device includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving actual sense item information transmitted by the smart device 150; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Optionally, the output device includes: a receiving unit configured to receive the actual sense item information transmitted by the smart device 150; an output unit configured to output content corresponding to a content title according to the actual sense item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after receiving and converting the natural language command input by the user into the content title by the intelligent device 150.

Ninth embodiment

As shown in fig. 11, in a ninth embodiment, the system 100 includes a first apparatus 110, an intelligent device 150, a network apparatus 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 1101, a user sends a natural language command;

Step 1109, after receiving the natural language command, the intelligent device 150 sends the natural language command to the network apparatus 130;

optionally, the intelligent device 150 also sends device type information to the network device 130;

Step 1103, after receiving the natural language command, the network device 130 converts the natural language command into a content title, where a text corresponding to the content title has a plurality of meaning item information;

Step 1105, the network device 130 determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110;

For example, assuming that the natural language command input by the user is "cannot say secret", and the device type information of the first device 110 is sound, the network device 130 may determine that the actual sense item information is music "cannot say secret"; if the device type information of the first device 110 is television, the network device 130 determines that the actual meaning item information is the movie "cannot say secret"; if the first device 110 includes both television and stereo, then when it is television, the network device 130 may determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the first device 110 includes only a television, the network device 130 may determine that the actual sense item information is a movie "cannot say secret" and prompt the user to determine that the content is a movie "cannot say secret", optionally prompting the user whether to switch to a music "cannot say secret".

Optionally, the network device 130 receives device type information of the first device 110 from the smart apparatus 150;

Step 1111, the network device 130 sends the actual sense item information to the first device 110;

In step 1107, after receiving the actual sense item information sent by the network device 130, the first device 110 outputs the content corresponding to the content title according to the actual sense item information.

Optionally, step 1113 (not shown) is also included before step 1103: the intelligent device 150 determines the first apparatus 110 as an output apparatus.

Optionally, the output device is determined according to an operation submitted by the user based on the smart device 150 with respect to the output device. Specifically, the smart device 150 may provide an interface for a user to select, through a touch screen or a keyboard, the first device 110 as an output device; the intelligent device 150 may provide a voice interactive interface where the user determines that the first apparatus 110 is an output apparatus through natural language instructions.

Receiving, at the smart device 150, a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; the natural language command is sent to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110.

Optionally, the smart device 150 includes: a unit for receiving a natural language command input by a user; and a unit for transmitting the natural language command to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110.

Optionally, the smart device 150 includes an information processing device, the information processing device including: a unit for receiving a natural language command input by a user; and a unit for transmitting the natural language command to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110.

Optionally, the smart device 150 includes: the sound pickup unit is configured to receive natural language commands input by a user; and a transmitting unit configured to transmit the natural language command to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the first device 110.

At the network device 130, after receiving the natural language command sent by the intelligent apparatus 150, the natural language command is converted into a content title, and according to the device type information of the first device 110, the actual meaning item information corresponding to the content title is determined from the plurality of meaning item information, and the actual meaning item information is sent to the first device 110.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: after receiving the natural language command sent by the intelligent device 150, the intelligent device converts the natural language command into a content title, determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110, and sends the actual sense item information to the first device 110.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: after receiving the natural language command sent by the intelligent device 150, the intelligent device converts the natural language command into a content title, determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110, and sends the actual sense item information to the first device 110.

Optionally, the network device 130 includes: a unit for natural language commands sent by the smart device 150; a unit for converting the natural language command into a content title; means for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; and means for transmitting the actual sense item information to the first device 110.

Optionally, the network device 130 includes an information processing apparatus, the information processing apparatus including: a unit for receiving natural language commands sent by the smart device 150; a unit for converting the natural language command into a content title; means for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the first device 110; and means for transmitting the actual sense item information to the first device 110.

Optionally, the network device 130 includes: a receiving unit, configured to receive a natural language command sent by the intelligent device 150; a first processing unit for converting natural language commands into content titles; the second processing unit is configured to determine, according to the device type information of the first device 110, actual sense item information corresponding to the content title from the plurality of sense item information; and a transmitting unit, configured to transmit the actual sense item information to the first device 110.

at the first device 110, receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Optionally, the first device 110 includes: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Optionally, the first device 110 includes: a receiving unit configured to receive actual sense item information transmitted by the network device 130; an output unit configured to output content corresponding to a content title according to the actual sense item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the natural language command from the smart device 150 and converts the natural language command into the content title.

Tenth embodiment

As shown in fig. 12, in a tenth embodiment, the system 100 includes a first apparatus 110, an intelligent device 150, a network apparatus 130, and a network 140. This embodiment illustrates a method for natural language content title disambiguation using an output device as the first device 110, wherein the method comprises the steps of:

step 1201, a user sends a natural language command;

In step 1203, after receiving the natural language command, the intelligent device 150 converts the natural language command into a content title and sends the content title to the network device 130, where the text corresponding to the content title has a plurality of meaning information.

Optionally, the intelligent apparatus 150 further transmits device type information of the corresponding output device to the network device 130;

step 1205, after receiving the content title, the network device 130 determines, according to the device type information of the output device, actual meaning item information corresponding to the content title from the plurality of meaning item information;

For example, assuming that the natural language command input by the user is "secret incapable of being spoken" and the device type information of the output device is sound, the network device 130 may determine that the actual sense item information is music "secret incapable of being spoken"; if the device type information of the output device is television, the network device 130 determines that the actual meaning item information is the movie "cannot say secret"; if the output device includes both television and audio, then when it is television, the network device 130 may determine that the actual sense item information is the movie "cannot say secret". In another embodiment, if the output device includes only a television, the network device 130 may determine that the actual sense item information is the movie "cannot say secret" and prompt the user that the determined content is the movie "cannot say secret", optionally prompting the user whether to switch to the music "cannot say secret".

For another example, assuming that the natural language command input by the user is "first AI meeting", and the device type information of the output device is a projector or a television connected with sound, the network device 130 may determine that the actual meaning item information is "first AI meeting" video; if the device type information of the output device is sound, the network device 130 may determine that the actual sense item information is "first AI meeting" audio; if the device type information of the output device is a projector to which sound is not connected, the network device 130 may determine that the actual sense item information is a word, picture, or web page associated with "the first AI meeting".

Optionally, the network device 130 receives device type information of the output device from the smart apparatus 150;

optionally, the network device 130 locally outputs device type information for the device;

Step 1211, the network device 130 sends the actual sense item information to an output device, such as the first device 110;

In step 1207, after receiving the actual sense item information sent by the network device 130, the first device 110 outputs the content corresponding to the content title according to the actual sense item information.

Specifically, the output device, for example, the first device 110, obtains the content corresponding to the content title by searching the internal memory or the external memory locally and outputs the content, or may obtain the content corresponding to the content title by searching the network and outputs the content, or may receive the content corresponding to the content title sent by other devices and output the content. For example, the first device 110 may be, for example, a sound device, which may search locally for a built-in memory or a connected CD, search over a network, or receive and obtain music "cannot say secrets" from other devices and play; the first device 110, such as a television, may search locally for built-in memory or attached VCD, DVD, USB memory, web searching, or receive and obtain the movie "cannot say secrets" from other devices and play; the first device 110, such as a projector, may obtain the "first AI meeting" related text or web pages, etc. from other devices and render the text or web pages.

Optionally, step 1213 (not shown) is also included before step 1203: the intelligent device 150 determines the first apparatus 110 as an output apparatus.

Receiving, at the smart device 150, a natural language command input by a user; the natural language command is converted into a content title and sent to the network device 130, so that the network device 130 receives the content title and then determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: receiving a natural language command input by a user; the natural language command is converted into a content title and sent to the network device 130, so that the network device 130 receives the content title and then determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a natural language command input by a user; the natural language command is converted into a content title and sent to the network device 130, so that the network device 130 receives the content title and then determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

Optionally, the smart device 150 includes: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; and a unit for transmitting the content title to the network device 130, wherein the network device 130 receives the content title and determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

Optionally, the smart device 150 includes an information processing device, the information processing device including: a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; and a unit for transmitting the content title to the network device 130, wherein the network device 130 receives the content title and determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device.

Optionally, the smart device 150 includes: the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; and a transmitting unit configured to transmit the content title to the network device 130, so that the network device 130 determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device after receiving the content title.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the network device 130: and receiving a content title sent by a corresponding output device (such as the first device 110), determining actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device, and sending the actual meaning item information to the output device.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: and receiving a content title transmitted by a corresponding output device (such as the first device 110), determining actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device, and transmitting the actual meaning item information to the output device.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: and receiving a content title transmitted by a corresponding output device (such as the first device 110), determining actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device, and transmitting the actual meaning item information to the output device.

Optionally, the network device 130 includes: means for receiving a content title transmitted by a corresponding output device (e.g., first device 110); the device type information unit is used for determining the actual meaning item information unit corresponding to the content title from the plurality of meaning item information according to the device type information of the output device; and a unit for transmitting the actual sense item information to the output device.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: means for receiving a content title transmitted by a corresponding output device (e.g., first device 110); a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the output device; and a unit for transmitting the actual sense item information to the output device.

Optionally, the network device 130 includes: a receiving unit, configured to receive a content title sent by a corresponding output device (such as the first device 110); a first processing unit, configured to determine actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of the output device; and the sending unit is used for sending the actual meaning item information to the output equipment.

Optionally, a method for natural language content title disambiguation comprises the steps of: at an output device (e.g., first device 110): receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the content title.

Optionally, a computer medium storing one or more programs executed by the first device 110 cause the first device 110 to: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the content title.

Optionally, the first device 110 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the content title.

Optionally, the first device 110 includes: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the content title.

Optionally, the first device 110 comprises an information processing apparatus, wherein the information processing apparatus comprises: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the content title.

Optionally, the first device 110 includes: a receiving unit configured to receive actual sense item information transmitted by the network device 130; an output unit configured to output content corresponding to the content title according to the actual sense item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the first device 110 after the network device 130 receives the content title.

Eleventh embodiment

As shown in fig. 13, in an eleventh embodiment, the system 100 includes a first device 110, at least one second device 120, a smart apparatus 150, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

Step 1313, the smart device 150 determines an output device from the first device 110 and the second device 120;

Optionally, the intelligent device 150 determines the output device by detecting a distance between the user and the first device 110 and a distance between the user and the second device 120, for example, determines the first device 110 as the output device when the distance between the user and the first device 110 is closest;

Step 1301, a user sends a natural language command;

Step 1309, after receiving the natural language command, the intelligent device 150 forwards the natural language command to the network apparatus 130;

Optionally, the intelligent device 150 also sends device type information of the output device to the network device 130;

Step 1303, after receiving the natural language command, the network device 130 converts the natural language command into a content title;

Step 1305, the network device 130 determines actual sense item information corresponding to the content title from the plurality of sense item information according to the device type information of the output device;

Step 1311, the network device 130 sends the actual sense item information to an output device;

In step 1307, after receiving the actual sense item information sent by the network device 130, the output device outputs the content corresponding to the content title according to the actual sense item information.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the intelligent device 150, determining that the output device is either device 110 or device 120; receiving a natural language command input by a user; the natural language command is transmitted to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and combines the device type of the output device when determining the actual meaning item information.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: determining that the output device is device 110 or device 120; receiving a natural language command input by a user; the natural language command is transmitted to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and combines the device type of the output device when determining the actual meaning item information.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: determining that the output device is device 110 or device 120; receiving a natural language command input by a user; the natural language command is transmitted to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and combines the device type of the output device when determining the actual meaning item information.

Optionally, the smart device 150 includes: means for determining that the output device is device 110 or device 120; a unit for receiving a natural language command input by a user; and a unit for transmitting the natural language command to the network device 130, causing the network device 130 to convert the natural language command into a content title after receiving the natural language command, and combining the device type of the output device when determining the actual meaning information.

Optionally, the smart device 150 includes an information processing device, the information processing device including: means for determining an output device from the first device 110 and the second device 120; a unit for receiving a natural language command input by a user; and a unit for sending the natural language command to the network device 130, so that the network device 130 receives the natural language command, converts the natural language command into a content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, the smart device 150 includes: a determining unit configured to determine an output device from the first device 110 and the second device 120; the sound pickup unit is configured to receive natural language commands input by a user; and a transmitting unit configured to transmit a natural language command to the network device 130, so that the network device 130 converts the natural language command into a content title after receiving the natural language command, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the network device 130, after receiving the natural language command sent by the intelligent device 150, converting the natural language command into a content title, wherein a text corresponding to the content title has a plurality of meaning item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to an output device.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: after receiving the natural language command sent by the intelligent device 150, converting the natural language command into a content title, wherein a text corresponding to the content title has a plurality of meaning item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to an output device.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: after receiving the natural language command sent by the intelligent device 150, converting the natural language command into a content title, wherein a text corresponding to the content title has a plurality of meaning item information; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to an output device.

Optionally, the network device 130 includes: a unit for receiving natural language commands sent by the smart device 150; a unit for converting a natural language command into a content title, wherein a text corresponding to the content title has a plurality of sense item information; a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of a corresponding output device; and a unit for transmitting the actual sense item information to an output device.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving natural language commands sent by the smart device 150; a unit for converting a natural language command into a content title, wherein a text corresponding to the content title has a plurality of sense item information; a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of a corresponding output device; and a unit for transmitting the actual sense item information to an output device.

Optionally, the network device 130 includes: a receiving unit, configured to receive a natural language command sent by the intelligent device 150; a first processing unit for converting natural language commands into content titles; a second processing unit, configured to determine actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of a corresponding output device; and a transmitting unit configured to transmit the actual sense item information to an output device.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the output device, receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Optionally, a computer medium storing one or more programs, the program being executed by the output device to cause the output device to: receiving the actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Optionally, the output device comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Optionally, the output device includes: means for receiving the actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Optionally, the output device includes an information processing apparatus, wherein the information processing apparatus includes: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Optionally, the output device includes: a receiving unit configured to receive actual sense item information transmitted by the network device 130; an output unit configured to output content corresponding to the content title according to the actual sense item information; the text corresponding to the content title has a plurality of sense item information, and the actual sense item information is determined from the plurality of sense item information according to the device type information of the output device after the network device 130 receives the natural language command sent by the intelligent device 150 and converts the natural language command into the content title.

Twelfth embodiment

As shown in fig. 14, in a twelfth embodiment, the system 100 includes a first device 110, at least one second device 120, an intelligent apparatus 150, a network device 130, and a network 140. A method for natural language content title disambiguation comprising the steps of:

step 1413, the intelligent device 150 determines an output device from the first device 110 and the second device 120;

Optionally, the smart device 150 determines the output device by detecting a distance between the user and the first device 110 and a distance between the user and the second device 120, for example, determining the first device 110 as the output device when the user is closest to the first device 110;

Step 1401, a user sends a natural language command;

Step 1403, after receiving the natural language command, the intelligent device 150 converts the natural language command into a content title and sends the content title to the network device 130, where a text corresponding to the content title has a plurality of meaning item information;

Step 1405, the network device 130 receives the content title, and determines actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device;

Step 1411, the network device 130 sends the actual sense item information to an output device;

In step 1407, after receiving the actual sense item information sent by the network device 130, the output device outputs the content corresponding to the content title according to the actual sense item information.

Optionally, a method for natural language content title disambiguation comprises the steps of: determining, at the smart device 150, an output device from the first device 110 and the second device 120; after receiving the natural language command, converting the natural language command into a content title and sending the content title to the network device 130, so that after the network device 130 receives the content title, determining the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, a computer medium storing one or more programs executed by the smart device 150 cause the smart device 150 to: determining an output device from the first device 110 and the second device 120; after receiving the natural language command, converting the natural language command into a content title and sending the content title to the network device 130, so that after the network device 130 receives the content title, determining the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, the smart device 150 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: determining an output device from the first device 110 and the second device 120; after receiving the natural language command, converting the natural language command into a content title and sending the content title to the network device 130, so that after the network device 130 receives the content title, determining the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, the smart device 150 includes: means for determining that the output device is device 110 or device 120; a unit for receiving a natural language command input by a user; means for determining an output device from the first device 110 and the second device 120; and a unit for transmitting the content title to the network device 130, so that the network device 130 receives the content title, and then determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, the smart device 150 comprises an information processing device, wherein the information processing device comprises: means for determining an output device from the first device 110 and the second device 120; a unit for receiving a natural language command input by a user; a unit for converting the natural language command into a content title; and a unit for transmitting the content title to the network device 130, so that the network device 130 receives the content title, and then determines the actual meaning item information corresponding to the content title from the plurality of meaning item information according to the device type information of the output device.

Optionally, the smart device 150 includes: a determining unit configured to determine an output device from the first device 110 and the second device 120; the sound pickup unit is configured to receive natural language commands input by a user; a first processing unit configured to convert the natural language command into a content title; and a transmitting unit configured to transmit the content title to the network device 130, so that after the network device 130 receives the content title, the actual meaning item information corresponding to the content title is determined from the plurality of meaning item information according to the device type information of the output device.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the network device 130, receiving a content title sent by the intelligent apparatus 150; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to the output equipment.

Optionally, a computer medium storing one or more programs executed by the network device 130 causes the network device 130 to: receiving a content title transmitted by the smart device 150; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to the output equipment.

Optionally, the network device 130 includes at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs including instructions for: receiving a content title transmitted by the smart device 150; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment; and sending the actual meaning item information to the output equipment.

Optionally, the network device 130 includes: a unit for receiving a content title transmitted from the smart device 150; a unit for determining actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of a corresponding output device; and a unit for transmitting the actual sense item information to the output device.

Optionally, the network device 130 includes an information processing apparatus, wherein the information processing apparatus includes: a unit for receiving a content title transmitted from the smart device 150; the device type information unit is used for determining the actual meaning item information unit corresponding to the content title from the plurality of meaning item information according to the device type information of the corresponding output device; and a unit for transmitting the actual sense item information to the output device.

Optionally, the network device 130 includes: a receiving unit for receiving a content title transmitted from the smart device 150; a first processing unit configured to determine actual sense item information corresponding to the content title from the plurality of sense item information according to device type information of a corresponding output device; and a transmitting unit configured to transmit the actual sense item information to the output device.

Optionally, a method for natural language content title disambiguation comprises the steps of: at the output device, receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

Optionally, a computer medium storing one or more programs, the program being executed by the output device to cause the output device to: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

Optionally, the output device comprises at least one processor and a memory storing one or more programs for execution by the at least one processor, the programs comprising instructions for: receiving actual sense item information sent by the network device 130; outputting the content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

Optionally, the output device includes: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

Optionally, the output device includes an information processing apparatus, wherein the information processing apparatus includes: means for receiving actual sense item information transmitted by the network device 130; a unit for outputting content corresponding to the content title according to the actual meaning item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

Optionally, the output device includes: a receiving unit configured to receive actual sense item information transmitted by the network device 130; an output unit configured to output content corresponding to the content title according to the actual sense item information; the text corresponding to the content title is provided with a plurality of item information, and the actual item information is determined from the plurality of item information according to the equipment type information of the output equipment after the network equipment receives the content title from the intelligent device.

It should be noted that the present invention may be implemented in software and/or a combination of software and hardware, e.g., using Application Specific Integrated Circuits (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to perform the steps or functions described above. Likewise, the software programs of the present invention (including associated data structures) may be stored on a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. In addition, some steps or functions of the present invention may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

Furthermore, portions of the present invention may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present invention by way of operation of the computer. Program instructions for invoking the inventive methods may be stored in fixed or removable recording media and/or transmitted via a data stream in a broadcast or other signal bearing medium and/or stored within a working memory of a computer device operating according to the program instructions. An embodiment according to the invention comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to operate a method and/or a solution according to the embodiments of the invention as described above.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the apparatus claims can also be implemented by means of one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.

Claims

1. A method for application to a natural language content title disambiguation system, the system comprising a first device, other devices including at least a second device, a cloud, and a network, the method comprising the steps of:

The user sends a natural language command;

The cloud receives the natural language command and then converts the natural language command into a content title, wherein the content title is uniquely determined on a literal expression, but the represented content is not uniquely determined; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information;

The cloud determines the content specifically represented by the content title, wherein the cloud combines the device type of the first device or the second device when determining the content specifically represented by the content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment;

The device type information of the corresponding output device includes the following:

The equipment type information of the output equipment is audio playing equipment and/or video playing equipment;

2. The method of claim 1, the cloud receiving a device type tag from the first device or the second device.

3. The method of claim 1, the cloud locally obtains a device type tag for the first device or the second device.

4. A method as claimed in any one of claims 1 to 3, wherein the first device or the second device determines whether the object to which the user sent the natural language command is itself by one or a combination of:

according to the distance between the user and the equipment;

the user frontal orientation is detected from the image.

5. A method for natural language content title disambiguation, the method comprising performing at a device the steps of: determining whether an object of a natural language command sent by a user is self;

After determining that the object of the natural language command sent by the user is self, receiving the natural language command input by the user; the natural language commands are sent to the cloud,

Such that the cloud, upon receiving the natural language command, converts the natural language command into a content title that is uniquely identified in the literal representation, but whose representative content is not uniquely identified; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information;

The cloud determines the content specifically represented by the content title, and the cloud combines the equipment type of the equipment when determining the content specifically represented by the content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment;

6. A computer medium having stored thereon a computer program, the execution of which by a device causes the device to: determining whether an object of a natural language command sent by a user is self;

Such that the cloud, upon receiving the natural language command, converts the natural language command into a content title that is uniquely identified in the literal representation, but whose representative content is not uniquely identified; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information; the cloud determines the content specifically represented by the content title, and the cloud combines the equipment type of the equipment when determining the content specifically represented by the content title;

Determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment;

Receiving content specifically represented by the determined content title returned by the cloud; and outputting the content specifically represented by the determined content title.

7. An apparatus for natural language content title disambiguation, the apparatus comprising a processor, a memory, and a program stored on the memory and executable by the processor, the processor executing the program to perform the steps of:

Such that the cloud, upon receiving the natural language command, converts the natural language command into a content title that is uniquely identified in the literal representation, but whose representative content is not uniquely identified; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information; the cloud determines the content specifically represented by the content title, and the cloud combines the equipment type of the equipment when determining the content specifically represented by the content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment;

8. An output device for natural language content title disambiguation, the output device comprising: a module for determining whether an object to which the user transmits a natural language command is itself;

a module for sending natural language commands to the cloud,

9. An apparatus for natural language content title disambiguation, the apparatus comprising information processing means, the information processing means comprising:

a module for sending natural language commands to the cloud,

a module for receiving content specifically represented by the determined content title returned by the cloud; and a module for outputting the content specifically represented by the determined content title.

10. An apparatus for natural language content title disambiguation, the apparatus comprising:

a transmitting unit that transmits the natural language command to the cloud,

the receiving unit is configured to receive the content specifically represented by the determined content title returned by the cloud; and an output unit configured to output the content specifically represented by the determined content title.

11. A method for natural language content title disambiguation, the method performing at the cloud the steps of: receiving a natural language command sent by equipment;

Converting the natural language command into a content title, wherein the content title is uniquely identified in a literal representation, but the content it represents is not uniquely identified; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information;

12. A computer medium having stored thereon a computer program, the program being executed by a cloud to cause the cloud to:

Receiving a natural language command sent by equipment;

13. A cloud for natural language content title disambiguation, the cloud comprising a processor, a memory, and a program stored on the memory and executable by the processor, the processor executing the program to effect the steps of:

Receiving a natural language command sent by equipment;

Determining content specifically represented by the content title, wherein the device type of the device is combined when determining the content specifically represented by the content title; determining actual sense item information corresponding to the content title from the plurality of sense item information according to the equipment type information of the corresponding output equipment;

14. A cloud for natural language content title disambiguation, the cloud comprising:

A module for receiving natural language commands sent by the device;

means for converting a natural language command into a content title, wherein the content title is uniquely identified in a literal representation, but the content it represents is not uniquely identified; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information;

15. A cloud for natural language content title disambiguation, the cloud comprising an information processing apparatus comprising:

A module for receiving natural language commands sent by the device;

16. A cloud for natural language content title disambiguation, the cloud comprising:

a first processing unit coupled to the receiving unit, the first processing unit configured to convert the natural language command into a content title, wherein the content title is literally uniquely determined, but the content it represents is not uniquely determined; the natural language command is converted into a content title through a voice recognition technology, and the content title is provided with a plurality of actual meaning item information;

17. The cloud of claim 16, the first processing unit and the second processing unit being combinable into one processing unit.

18. A natural language content title disambiguation system comprising a cloud according to any of claims 7-10, a device according to any of claims 13-17, and a network.