WO2021056467A1 - 信息查询方法及显示装置 - Google Patents

信息查询方法及显示装置 Download PDF

Info

Publication number
WO2021056467A1
WO2021056467A1 PCT/CN2019/108720 CN2019108720W WO2021056467A1 WO 2021056467 A1 WO2021056467 A1 WO 2021056467A1 CN 2019108720 W CN2019108720 W CN 2019108720W WO 2021056467 A1 WO2021056467 A1 WO 2021056467A1
Authority
WO
WIPO (PCT)
Prior art keywords
work
query
audio
information
target
Prior art date
Application number
PCT/CN2019/108720
Other languages
English (en)
French (fr)
Inventor
徐楚
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to PCT/CN2019/108720 priority Critical patent/WO2021056467A1/zh
Priority to US17/046,321 priority patent/US11782976B2/en
Priority to CN201980001847.2A priority patent/CN110799973B/zh
Publication of WO2021056467A1 publication Critical patent/WO2021056467A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/635Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/432Query formulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/438Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/638Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/686Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings

Definitions

  • the present disclosure relates to the field of display technology, and in particular to an information query method and display device.
  • Each display device can display images.
  • the electronic drawing screen can display a variety of works. Moreover, because the display effect of the electronic drawing screen is more realistic and the displayed works can be replaced, it has been loved by people.
  • the embodiments of the present disclosure provide an information query method and display device, and the technical solution is as follows:
  • an information query method for a display device, and the method includes:
  • the query result is obtained according to the query intention and reference information, wherein the reference information includes: the type of the query intention, and whether the work information query instruction includes the detection result of the at least one target entity, the The query result includes: at least one of images, audio, and text;
  • the at least one target entity includes: a first target entity containing author information of the work, and/or a second target entity containing name information of the work.
  • the at least one target entity includes the second target entity, and the method further includes:
  • the work information query instruction includes the second target entity, detecting whether the current work displayed by the display device is the same as the target work indicated by the second target entity;
  • the reference information further includes: a detection result of whether the current work and the target work are the same.
  • the multiple types of intents include: a first type, the first type of intent includes an intent related to a work introduction, and before the query result is obtained according to the query intent and reference information, the method further include:
  • the work to be profiled is determined according to whether the work information query instruction contains the detection result of the at least one target entity; wherein, when the work information query instruction is at least When the second target entity is included, the work to be introduced is the target work indicated by the second target entity; when the work information query instruction does not include the second target entity and includes the first target entity, the The work to be profiled is any work of the author indicated by the first target entity;
  • the reference information further includes: a detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the obtaining the query result according to the query intention and reference information includes:
  • the type of the query intention is the first type
  • the audio library includes the introduction audio
  • the work information query instruction includes at least a second target entity
  • the current work is the same as the target work
  • the introduction audio in the audio library is acquired, and the query result includes: the introduction audio;
  • the type of the query intention is the first type
  • the audio library includes the introduction audio
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work , Acquiring the image of the target work and the introduction audio in the audio library, and the query result includes: the image of the target work and the introduction audio;
  • the audio library includes the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the audio is acquired
  • the query result includes: the introduction audio.
  • the obtaining the query result according to the query intention and reference information includes:
  • the type of the query intention is the first type
  • the work information query instruction includes at least a second target entity, and the current work and the target work If the same, the introduction text of the work to be introduced and the audio of the introduction text are obtained, and the query result includes: the introduction text of the work to be introduced and the audio of the introduction text;
  • the work information query instruction includes at least a second target entity, and the current work and the target work If they are different, the image of the work to be introduced, the introduction text of the work to be introduced, and the audio of the introduction text are obtained.
  • the query result includes: the image of the work to be introduced and the introduction of the work to be introduced Text, and the audio of the introduction text;
  • the audio library does not include the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the query result includes: the brief introduction text of the work to be briefed, and the audio of the brief introduction text.
  • the multiple types of intents include: a second type, and the second type of intent includes: an intent related to any information in an information group, and the information group includes: information about the author and information about the work
  • the obtaining of the query result according to the query intention and reference information includes:
  • the type of the query intent is the second type
  • the work information query instruction includes at least a second target entity, and the current work is the same as the target work
  • the text of any information is obtained
  • the audio of the text of the any information the query result includes: the text of the any information, and the audio of the text of the any information
  • the type of the query intention is the second type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work, then the image of the target work is acquired,
  • the text of the any information, and the audio of the text of the any information, the query result includes: the image of the target work, the text of the any information, and the audio of the text of the any information ;
  • the type of the query intent is the second type
  • the work information query instruction includes the first target entity and does not include the second target entity, the text of any one of the information and the one The audio of the text of the information
  • the query result includes: the text of any of the information, and the audio of the text of the any of the information.
  • the multiple types of intents include: a third type, and the intents of the third type include: intents related to the on-demand work, and obtaining the query result according to the query intent and reference information includes:
  • the type of the query intent is the third type
  • the work information query instruction includes at least a second target entity, and the current work is the same as the target work
  • acquiring is used to prompt the current work Is the audio of the target work
  • the query result includes: the audio for prompting that the current work is the target work
  • the type of the query intention is the third type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work
  • the image of the target work is acquired
  • the audio used to indicate the target work the query result includes: an image of the target work, and the audio used to indicate the target work.
  • the obtaining the query result according to the query intention and reference information further includes:
  • the type of the query intention is the third type
  • the work information query instruction does not include the second target entity and includes the first target entity, then it is determined that the author of the current work and the first target entity of the query intention are determined. Whether the target authors indicated by a target entity are the same;
  • the query result includes: the audio indicating that the current work is the only work of the target author
  • the author of the current work is the same as the target author, and the current work is not the only work of the target author, obtain the image of the first work and the audio used to indicate the first work ,
  • the first work is any work other than the current work among the works of the target author, and the query result includes: an image of the first work, and an image indicating the first work Audio
  • the query result includes: an image of the second work, and audio used to indicate the second work.
  • the obtaining the query result according to the query intention and reference information further includes:
  • the type of the query intention is the third type
  • the work information query instruction does not include the first target entity and the second target entity
  • an image of the third work is obtained and used to indicate The audio of the third work
  • the query result includes: an image of the third work, and the audio used to indicate the third work
  • the third work is any work of other authors except the author of the current work; when the current work is not the only work of the author At the time, the third work is any work other than the current work among the works of the author of the current work.
  • the query command for obtaining work information includes:
  • the work information query instruction in the form of voice is obtained.
  • the works include: works.
  • a display device including: a processor, a display screen, and a speaker;
  • the processor is used for:
  • the query result is obtained according to the query intention and reference information, wherein the reference information includes: the type of the query intention, and whether the work information query instruction includes the detection result of the at least one target entity, the The query result includes: at least one of images, audio, and text;
  • the at least one target entity includes: a first target entity containing author information of the work, and/or a second target entity containing name information of the work.
  • the at least one target entity includes the second target entity
  • the processor is configured to: when the work information query instruction includes the second target entity, detect the current work displayed by the display device Whether it is the same as the target work indicated by the second target entity;
  • the reference information further includes: a detection result of whether the current work and the target work are the same.
  • the multiple intent types include: a first type, the first type of intent includes an intent related to a work introduction, and the processor is configured to:
  • the work to be profiled is determined according to whether the work information query instruction contains the detection result of the at least one target entity; wherein, when the work information query instruction is at least When the second target entity is included, the work to be introduced is the target work indicated by the second target entity; when the work information query instruction does not include the second target entity and includes the first target entity, the The work to be profiled is any work of the author indicated by the first target entity;
  • the reference information further includes: a detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the processor is configured to: when the type of the query intent is the first type, if the audio library includes the introduction audio, the work information query instruction includes at least a second target entity, and If the current work is the same as the target work, the introduction audio in the audio library is acquired, and the query result includes: the introduction audio;
  • the type of the query intention is the first type
  • the audio library includes the introduction audio
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work , Acquiring the image of the target work and the introduction audio in the audio library, and the query result includes: the image of the target work and the introduction audio;
  • the audio library includes the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the audio is acquired
  • the query result includes: the introduction audio.
  • the processor is configured to: when the type of the query intent is the first type, if the audio library does not include the introduction audio, the work information query instruction includes at least a second target entity, And the current work is the same as the target work, the introduction text of the work to be introduced and the audio of the introduction text are obtained, and the query result includes: the introduction text of the work to be introduced and the introduction Text audio
  • the work information query instruction includes at least a second target entity, and the current work and the target work If they are different, the image of the work to be introduced, the introduction text of the work to be introduced, and the audio of the introduction text are obtained.
  • the query result includes: the image of the work to be introduced and the introduction of the work to be introduced Text, and the audio of the introduction text;
  • the audio library does not include the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the query result includes: the brief introduction text of the work to be briefed, and the audio of the brief introduction text.
  • the multiple types of intents include: a second type, and the second type of intent includes: an intent related to any information in an information group, and the information group includes: information about the author and information about the work
  • the processor is used to: when the type of the query intention is the second type, if the work information query instruction includes at least a second target entity, and the current work and the If the target works are the same, the text of any information and the audio of the text of any information are obtained.
  • the query result includes: the text of any information and the audio of the text of any information ;
  • the type of the query intention is the second type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work, then the image of the target work is acquired,
  • the text of the any information, and the audio of the text of the any information, the query result includes: the image of the target work, the text of the any information, and the audio of the text of the any information ;
  • the type of the query intent is the second type
  • the work information query instruction includes the first target entity and does not include the second target entity, the text of any one of the information and the one The audio of the text of the information
  • the query result includes: the text of any of the information, and the audio of the text of the any of the information.
  • the multiple intent types include: a third type, and the third type of intent includes: an intent related to an on-demand work, and the processor is configured to: when the type of the query intent is the third In case of type, if the work information query instruction includes at least a second target entity, and the current work is the same as the target work, the audio prompting that the current work is the target work is obtained, and the query result Including: the audio for prompting that the current work is the target work;
  • the type of the query intention is the third type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work
  • the image of the target work is acquired
  • the audio used to indicate the target work the query result includes: an image of the target work, and the audio used to indicate the target work.
  • the processor is configured to: when the type of the query intention is the third type, if the work information query instruction does not include a second target entity and includes a first target entity, determine the current Whether the author of the work is the same as the target author indicated by the first target entity of the query intention;
  • the query result includes: the audio indicating that the current work is the only work of the target author
  • the author of the current work is the same as the target author, and the current work is not the only work of the target author, obtain the image of the first work and the audio used to indicate the first work ,
  • the first work is any work other than the current work among the works of the target author, and the query result includes: an image of the first work, and an image indicating the first work Audio
  • the query result includes: an image of the second work, and audio used to indicate the second work.
  • the processor is configured to: when the type of the query intent is the third type, if the work information query instruction does not include the first target entity and the second target entity, obtain An image of a third work, and audio used to indicate the third work, the query result includes: an image of the third work, and the audio used to indicate the third work;
  • the third work is any work of other authors except the author of the current work; when the current work is not the only work of the author At the time, the third work is any work other than the current work among the works of the author of the current work.
  • the processor is configured to: obtain the work information query instruction in voice form by means of voice collection.
  • the works include: paintings.
  • the display device further includes a microphone
  • the processor is configured to:
  • a display device in another aspect, includes:
  • Instruction acquisition module used to acquire work information query instructions
  • the intention recognition module is used to recognize the intention of the work information query instruction to obtain the query intention
  • the type determination module is used to determine the type of query intent in the multiple types of intent
  • An entity detection module configured to detect whether the work information query instruction includes at least one target entity
  • the result obtaining module is configured to obtain the query result according to the query intention and reference information, wherein the reference information includes: the type of the query intention and whether the work information query instruction contains the detection result of at least one target entity ,
  • the query result includes: at least one of image, audio, and text;
  • the information display module is used to display the query result.
  • the at least one target entity includes: a first target entity containing author information of the work, and/or a second target entity containing name information of the work.
  • the at least one target entity includes the second target entity
  • the display device further includes:
  • the work detection module is configured to detect whether the current work displayed by the display device is the same as the target work indicated by the second target entity when the work information query instruction includes a second target entity, and the reference information further includes : The detection result of whether the current work and the target work are the same.
  • the multiple intent types include: a first type, the first type of intent includes an intent related to a work introduction, and the display device further includes:
  • the work to be profiled determination module is used to determine the work to be profiled according to the detection result of whether the work information query instruction contains at least one target entity when the type of the query intention is the first type; wherein, when the When the work information query instruction includes at least a second target entity, the work to be profiled is the target work indicated by the second target entity; when the work information query instruction does not include the second target entity and includes the first target In the case of an entity, the work to be profiled is any work of the author indicated by the first target entity;
  • the audio detection module is configured to detect whether the audio library contains the introduction audio of the work to be introduced, and the reference information also includes a detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the result obtaining module is used for:
  • the type of the query intention is the first type
  • the audio library includes the introduction audio
  • the work information query instruction includes at least a second target entity
  • the current work is the same as the target work
  • the introduction audio in the audio library is acquired, and the query result includes: the introduction audio;
  • the type of the query intention is the first type
  • the audio library includes the introduction audio
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work , Acquiring the image of the target work and the introduction audio in the audio library, and the query result includes: the image of the target work and the introduction audio;
  • the audio library includes the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the audio is acquired
  • the query result includes: the introduction audio.
  • the result obtaining module is used for:
  • the type of the query intention is the first type
  • the work information query instruction includes at least a second target entity, and the current work and the target work If the same, the introduction text of the work to be introduced and the audio of the introduction text are obtained, and the query result includes: the introduction text of the work to be introduced and the audio of the introduction text;
  • the work information query instruction includes at least a second target entity, and the current work and the target work If different, the image of the work to be profiled and the profile text of the work to be profiled, and the audio of the profile text are obtained.
  • the query results include: the image of the work to be profiled, the profile text of the work to be profiled, And the audio of the introduction text;
  • the audio library does not include the introduction audio
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the query result includes: the brief introduction text of the work to be briefed, and the audio of the brief introduction text.
  • the multiple types of intents include: a second type, and the second type of intent includes: an intent related to any information in an information group, and the information group includes: information about the author and information about the work
  • the result acquisition module is used to:
  • the type of the query intent is the second type
  • the work information query instruction includes at least a second target entity, and the current work is the same as the target work
  • the text of any information is obtained
  • the audio of the text of the any information the query result includes: the text of the any information, and the audio of the text of the any information
  • the type of the query intention is the second type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work
  • the image of the target work is acquired
  • the query result includes: the image of the target work, the text of the any information, and the audio of the text of the any information .
  • the result obtaining module is also used for:
  • the type of the query intent is the second type
  • the work information query instruction includes the first target entity and does not include the second target entity, the text of any one of the information and the one The audio of the text of the information
  • the query result includes: the text of any of the information, and the audio of the text of the any of the information.
  • the multiple types of intents include: a third type, and the third type of intent includes: an intent related to an on-demand work, and the result obtaining module is used for:
  • the type of the query intent is the third type
  • the work information query instruction includes at least a second target entity, and the current work is the same as the target work
  • acquiring is used to prompt the current work Is the audio of the target work
  • the query result includes: the audio for prompting that the current work is the target work
  • the type of the query intention is the third type
  • the work information query instruction includes at least a second target entity, and the current work is different from the target work
  • the image of the target work is acquired
  • the audio used to indicate the target work the query result includes: an image of the target work, and the audio used to indicate the target work.
  • the result obtaining module is further used for:
  • the type of the query intention is the third type
  • the work information query instruction does not include the second target entity and includes the first target entity, then it is determined that the author of the current work and the first target entity of the query intention are determined. Whether the target authors indicated by a target entity are the same;
  • the query result includes: the audio indicating that the current work is the only work of the target author
  • the author of the current work is the same as the target author, and the current work is not the only work of the target author, obtain the image of the first work and the audio used to indicate the first work ,
  • the first work is any work other than the current work among the works of the target author, and the query result includes: an image of the first work, and an image indicating the first work Audio
  • the query result includes: an image of the second work, and audio used to indicate the second work.
  • the result obtaining module is further used for:
  • the type of the query intention is the third type
  • the work information query instruction does not include the first target entity and the second target entity
  • an image of the third work is obtained and used to indicate The audio of the third work
  • the query result includes: an image of the third work, and the audio used to indicate the third work
  • the third work is any work of other authors except the author of the current work; when the current work is not the only work of the author At the time, the third work is any work other than the current work among the works of the author of the current work.
  • the instruction acquisition module includes:
  • the voice collection module is used to obtain the work information query instruction in voice form through voice collection.
  • the works include: paintings.
  • a display device in another aspect, includes: a microphone, a speaker, a display screen, and a processor, and the processor is connected to the microphone, the speaker, and the display screen;
  • the processor is configured to receive a work information query instruction through the microphone, and perform at least one of the following operations according to the work information query instruction:
  • the processor is configured to: determine the image to be displayed according to the work information query instruction, and control the display screen to display the image to be displayed when the current image displayed on the display screen is different from the image to be displayed.
  • the processor is configured to: determine the image to be displayed according to the work information query instruction, and when the current image displayed on the display screen is the same as the image to be displayed, control the speaker to play for prompting the current image The same voice as the image to be displayed.
  • FIG. 1 is a flowchart of an information query method for a display device provided by an embodiment of the present disclosure according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of another information query method for the display device provided by the embodiment of the present disclosure provided by the embodiment of the present disclosure;
  • FIG. 3 is a schematic structural diagram of a display device provided by an embodiment of the disclosure.
  • FIG. 4 is a schematic structural diagram of another display device provided by an embodiment of the disclosure.
  • FIG. 5 is a schematic structural diagram of another display device provided by an embodiment of the disclosure.
  • FIG. 1 is a flowchart of an information query method for a display device provided in an embodiment of the present disclosure provided by an embodiment of the present disclosure.
  • the display device is an electronic picture screen as an example.
  • the display device may also be, for example, a television, an air conditioner with a display function, and the like.
  • the information query method may include:
  • Step 101 Obtain a work information query instruction.
  • Step 102 Perform intention recognition on the work information query instruction to obtain the query intention.
  • Step 103 Determine the type of query intent among multiple types of intent.
  • Step 104 Detect whether the work information query instruction includes at least one target entity.
  • Step 105 Obtain the query result according to the query intention and the reference information, where the reference information includes: the type of the query intention, and whether the work information query instruction contains the detection result of at least one target entity, and the query result includes: image, audio, and text. At least one type of information.
  • Step 106 Display the query result.
  • the display device can respectively determine the type of query intention after obtaining the work information query instruction, and obtain the detection of whether the work information query instruction contains at least one target entity result.
  • the display device can also obtain and display the query result based on the type including the query intention and whether the work information query instruction includes the reference information of the detection result of at least one target entity. It can be seen that the display device provided by the embodiment of the present disclosure can implement information query based on reference information, thus enriching the functions of the display device.
  • FIG. 2 is a flowchart of another information query method for the display device provided by the embodiment of the present disclosure provided by the embodiment of the present disclosure.
  • the display device is an electronic picture screen as an example.
  • the display device may also be, for example, a television, an air conditioner with a display function, and the like.
  • the above-mentioned work is taken as an example as a painting.
  • the work may not be a painting (such as a music work, a film and television work, etc.).
  • the information query method may include:
  • Step 201 Obtain a work information query instruction.
  • the work information query instruction may be a voice collected during the user's speech on the display device.
  • the display device may be provided with a query button (or displayed with a query button), and when the user clicks the query button, the display device may collect the user's voice to obtain the work information query instruction.
  • the display device includes a processor and a microphone. In step 201, the processor can obtain the work information query instruction through the microphone.
  • Step 202 Perform intention identification on the work information query instruction to obtain the query intention.
  • an intent recognition model may be stored in the display device, and the display device may perform intent recognition on the work information query instruction through the intent recognition model.
  • the intent recognition model may be based on a traditional machine learning algorithm or a deep learning algorithm.
  • the traditional machine learning algorithm can be for example: Support Vector Machine (SVM)
  • the deep learning algorithm can be for example: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM, Long Short-Term Memory) ) Or regional convolutional neural networks (region-based Convolutional Neural Networks, RCNN), etc.
  • the display device in the embodiment of the present disclosure performs intent recognition on various work information query instructions, and the query intent that can be recognized can be as shown in Table 1.
  • the query intent recognized by the display device can be embodied by the basic intent and slots in Table 1.
  • One basic intent and one slot can reflect one query intent. Assuming that the basic intent "author's nationality" corresponding to number 1 in Table 2 recognized by the display device and the slot "author name" corresponding to number 1 is recognized by the display device, the query intent recognized by the display device is: query the nationality of the "author name” .
  • the query intent recognized by the display device is: inquire about the "work name” profile .
  • the work information query instruction collected by the display device in step 201 may be: “introduce the xxxx of xx", where "xx" represents the name of an author, and "xxxx” represents a painting of the author.
  • the query intention recognized by the display device can be composed of "inquiry about work profile” and "work name” (xxxx) corresponding to number 22 in Table 2, for example, "inquiry about xxxx profile”.
  • Table 1 shows a total of 25 different query intentions, and the query intentions that can be recognized by the display device in the embodiment of the present disclosure are not limited to these 25 query intentions.
  • the display device when the display device recognizes the intention of the work information query instruction and obtains the query intention, it can also obtain the serial number of the query intention. For example, obtain the corresponding serial number of the query intent in Table 2.
  • the intent recognition model can not only obtain the above query intent, but also obtain at least one slot.
  • the slot obtained by the display device may include "Author Name”.
  • the slot obtained by the display device may include the "title of the work”.
  • Step 203 Determine the type of query intent among multiple types of intent.
  • the display device may determine the type of the query intention among multiple types of intentions. For example, the display device may search for the intent type corresponding to the query intent in the corresponding relationship between the multiple intents and the multiple intent types, and then determine the intent type as the type of the query intent.
  • the display device may also search for the number of the query intent in the corresponding relationship between multiple intent numbers and multiple intent types in step 203. Corresponding intent type, and then determine the intent type as the type of the query intent.
  • Step 204 Detect whether the work information query instruction includes at least one target entity.
  • At least one target entity includes a first target entity and/or a second target entity.
  • at least one target entity includes the first target entity and the second target entity as an example.
  • the first target entity contains the author information of the work
  • the second target entity contains the name information of the work.
  • the work information query command is used to query a certain thing, such as querying a certain work, querying a certain author, or querying other things.
  • the entity of the work information query instruction may include things that the query intends to use for query.
  • the display device needs to analyze the work information query instruction (or the query intention of the work information query instruction) to determine whether the work information query instruction includes the first target entity, and whether the work information query instruction includes the first target entity. 2. Target entity.
  • it may only detect whether the work information query instruction includes the first target entity or the second target entity, or other entities, which is not limited in the embodiment of the present application.
  • Step 205 When the work information query instruction includes the second target entity, detect whether the current work displayed by the display device is the same as the target work indicated by the second target entity.
  • the display device may also detect the current work displayed by the display device and the second target entity. 2. Whether the target work indicated by the target entity is the same, and obtain the detection result of whether the current work and the target work are the same.
  • the reference information on which the query result is obtained in the subsequent step 208 may also include the detection result of whether the current work is the same as the target work.
  • Step 206 When the type of the query intention is the first type, determine the work to be profiled according to the detection result of whether the work information query instruction contains at least one target entity.
  • the work to be profiled is the target work indicated by the second target entity; when the work information query instruction does not include the second target entity and contains the first target entity, the work to be profiled A work is any work of the author indicated by the first target entity.
  • Step 207 Detect whether the audio library contains the introduction audio of the work to be introduced, and obtain a detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the display device may also determine the work to be introduced, and then determine the preset audio library Whether the introduction audio of the work to be introduced is included in the file to obtain the detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the reference information on which the query result is obtained in the subsequent step 208 may also include the detection result of whether the current work is the same as the target work.
  • Step 208 Obtain the query result according to the query intention and the reference information, where the reference information includes: the type of the query intention, whether the work information query instruction contains the detection result of at least one target entity, the detection result of whether the current work and the target work are the same, and Whether the audio library contains the detection result of the introduction audio of the work to be introduced, the query result includes: at least one of image, audio, and text.
  • Step 209 Display the query result.
  • the display device needs to display the image (for example, the processor in the display device controls the display screen in the display device to display the image); when the query result includes audio, the display device needs to display the image.
  • the audio is played (for example, the processor in the display device controls the speaker in the display device to play the audio); when the query result includes text, the display device needs to display the text (for example, the processor in the display device controls the display device).
  • the display in the display shows text).
  • the multiple intent types in step 203 may include various intent types.
  • the embodiment of the present disclosure will take at least one of the first type, the second type, and the third type as an example. The steps in the embodiment are explained.
  • the multiple intent types in step 203 may also be other intent types, which are not limited in the embodiment of the present disclosure.
  • the first type of intent includes intent related to the introduction of the work.
  • the basic intent corresponding to number 22 in Table 2 and the query intent composed of slots are the first type of intent.
  • the second type of intent includes the intent related to any information in the information group, the information group includes: the author's information, and the information other than the brief introduction in the information of the work (such as the price of the work, the collection location, etc.).
  • the basic intents corresponding to numbers 1 to 22 in Table 2 and the query intents composed of slots are all intents of the second type.
  • the third type of intent includes: intent related to on-demand works.
  • intent related to on-demand works For example, the basic intent corresponding to number 23 in Table 2 and the query intent composed of slots are both the third type of intent.
  • step 208 when the types of query intentions are the first type, the second type, and the third type.
  • the above step 208 may include:
  • the work information query instruction includes at least the second target entity, and the current work is the same as the target work, then the introduction audio of the work to be introduced in the audio library is obtained.
  • the query result at this time includes: the introduction audio.
  • the audio library can be used to store pre-recorded introduction audio of at least one work.
  • the type of the query intention is the first type, it means that the query intention is used to query the introduction of the work to be introduced. Therefore, it is necessary to check whether the audio library contains the introduction audio of the work to be introduced.
  • the query intent needs to include at least the second target entity (for example, the query intent only includes the second target entity, or the query intent includes not only the second target entity but also the first target entity). If the current work displayed by the display device is the same as the target work indicated by the second target entity (that is, the work to be profiled), the display device does not need to acquire the image of the target work.
  • the display device only needs to obtain the work to be introduced in the audio library (that is, the target The introduction audio of the work) is sufficient, without the need to obtain images and text.
  • the display device only needs to play the acquired introduction audio, without changing the currently displayed work. For example, if the query intention is "introduction work A", and the display device currently displays work A, and the audio library contains the introduction audio of work A, the display device only needs to obtain the introduction audio of the work A in the audio library in step 208 .
  • the work information query instruction contains at least the second target entity, and the current work is different from the target work, then the image of the target work and the work to be profiled in the audio library are obtained Intro audio.
  • the query result includes: the image of the target work and the introduction audio.
  • the type of query intent is the first type
  • the audio library contains the introduction audio of the work to be introduced
  • the work information query instruction includes at least the second target entity, and the current work is different from the target work, then the description is to be introduced
  • the work is not the work currently displayed by the display device. Therefore, the display device not only needs to obtain the introduction audio of the work to be introduced in the audio library, but also needs to obtain the image of the work to be introduced (that is, the target work) without obtaining the text. In this way, in step 209, the display device not only needs to play the acquired introduction audio, but also needs to replace the currently displayed work with the work to be introduced.
  • the display device needs to obtain the introduction audio of the work A in the audio library in step 208 , And work A.
  • the introduction audio of the work to be introduced in the audio library is obtained.
  • the query result includes: the introduction audio.
  • the display device can determine that any work of author B is a work to be profiled, and the query intention includes the first target entity "Author B", and the audio library contains the work to be introduced.
  • the display device only needs to obtain the audio of the introduction work from the audio library.
  • the work information query command includes at least the second target entity, and the current work is the same as the target work, then the introduction text of the work to be introduced and the introduction are obtained Text audio.
  • the query result includes: the introduction text of the work to be introduced, and the audio of the introduction text.
  • the display device needs to acquire the introduction text of the work to be introduced, and the audio of the introduction text, without acquiring an image.
  • the audio of the introduction text may also be obtained by converting the introduction text into audio after the display device obtains the introduction text, which is not limited in the embodiment of the present disclosure.
  • the display device can determine that any work of author B is a work to be introduced, and the query intent includes the first target entity "Author B", which is not included in the audio library For the introduction audio of the work to be introduced, the display device needs to obtain the introduction text of the work to be introduced and the audio of the introduction text.
  • the work information query instruction includes at least the second target entity, and the current work is different from the target work, then the work to be introduced and its introduction text are obtained, and the Audio of the introduction text.
  • the query result includes: the image of the work to be profiled, the profile text of the work to be profiled, and the audio of the profile text.
  • the display device when the type of query intention is the first type, in the fifth case, the current work displayed by the display device is not the same as the target work, and the display device not only needs to obtain the introduction text of the work to be introduced, but also As well as the audio of the introduction text, it is also necessary to obtain the image of the work to be displayed (that is, the target work). For example, if the query intent is "introduction to work A", the display device can determine that the query intent includes the second target entity "work A", if the audio library does not contain the introductory audio of the work A, and the display device does not currently display If there is work A, the display device not only needs to obtain the introduction text of work A and the audio of the introduction text, but also needs to obtain the image of work A.
  • the introduction text of the work to be introduced and the introduction text of the introduction text are obtained.
  • the query result includes: the introduction text of the work to be introduced, and the audio of the introduction text.
  • the type of query intent is the first type
  • the display device can determine that any work of author B is a work to be introduced, and the query intent includes the first target entity "Author B", which is not included in the audio library
  • the display device obtains the introduction text of the work to be introduced and the audio of the introduction text.
  • the embodiment of the present disclosure does not limit the sequence of the method steps.
  • the display device may first perform step 206 and step 207, and then perform step 204 and step 205.
  • the display device can determine which of the above six situations the current situation is based on the judgment result of the previous steps, and then acquire the information that needs to be acquired in this situation.
  • the second type of intent is used to query any information in the information group, which includes: the author’s information and the work’s information except the introduction Outside information.
  • the foregoing step 208 may include:
  • the work information query instruction includes at least the second target entity, and the current work is the same as the target work, the text of any information and the audio of the text of any information are acquired.
  • the query result includes: the text of any information and the audio of the text of any information.
  • the type of query intent is the second type
  • the work that the user wants to query is the same as the work currently displayed on the display device, and the display device only needs to obtain the query intent.
  • the text and audio of any information can be used without obtaining images. For example, if the query intention is "how much is the price of work A", the display device may determine that the work information query instruction includes the second target entity "work A”, and any piece of information that needs to be queried for the query intention is "work A" the price of”. If the display device currently displays work A, the display device needs to obtain the text and audio of the price of work A.
  • the work information query instruction includes at least the second target entity, and the current work is different from the target work, the image of the target work, the text of any information, and the audio of the text of any information are acquired.
  • the query result includes: the image of the target work, the text of any information, and the audio of the text of any information.
  • the type of query intention is the second type
  • the target work that the user wants to query is not the same as the work currently displayed on the display device, and the display device not only needs to obtain the query
  • the intention requires the text and audio of any information to be queried, and the image of the target work also needs to be obtained.
  • the display device may determine that the work information query instruction includes the second target entity "work A”, and any piece of information that needs to be queried for the query intention is "work A" the price of”. If the display device does not currently display the work A, the display device needs to obtain the image of the work A, as well as the text and audio of the price of the work A.
  • the work information query instruction includes the first target entity and does not include the second target entity, the text of any information and the audio of the text of any information are acquired.
  • the query result includes: the text of any information and the audio of the text of any information.
  • the display device can directly obtain the information of the query intent. Text and audio are sufficient, without the need to acquire images. For example, if the query intent is "What is the age of author B", the display device may determine that the work information query instruction includes the first target entity "Author B”, and any piece of information that the query intent needs to query is "Author B" Age”. The display device needs to obtain the text and audio of author B's age.
  • the embodiment of the present disclosure does not limit the sequence of the method steps.
  • the display device may perform step 204 and step 205 in sequence, and the display device does not need to perform step 206 and step 207.
  • the display device can determine which of the above three situations the current situation is based on the judgment result of the previous steps, and then acquire the information that needs to be acquired in this situation.
  • the third type of intent is used for on-demand works.
  • the foregoing step 208 may include:
  • the work information query instruction includes at least the second target entity, and the current work is the same as the target work, then audio for prompting that the current work is the target work is obtained.
  • the query result includes: the audio for prompting that the current work is the target work.
  • the query intent is used for on-demand works.
  • the work information query instruction includes a second target entity
  • the target work indicated by the second target entity is It is the current work displayed on the display device.
  • the display device can determine that the work that the current user wants to order is the current work displayed on the display device. Therefore, the display device needs to obtain audio for prompting the current work as the target work (for example: "This is the painting you are looking for", etc.) . In this case, the display device does not need to acquire images and text.
  • the work information query instruction includes at least the second target entity, and the current work is different from the target work, the image of the target work and the audio used to indicate the target work are acquired.
  • the query result includes: the image of the target work, and the audio used to indicate the target work.
  • the type of query intent is the third type
  • the query intent is used for on-demand works.
  • the work information query instruction includes a second target entity
  • the target work indicated by the second target entity is the same as the target work indicated by the second target entity.
  • the current work displayed on the display device is different.
  • the display device can determine the target work that the current user wants to order. Therefore, the display device needs to obtain the image of the target work and the audio for prompting the target work (for example, the target work is work A, and the author of work A is author B.
  • the audio can be "Recommend work A for you" or "Recommend work A of author B for you", etc.).
  • the display device does not need to obtain the text.
  • the display device needs to display the acquired image of the target work.
  • the work information query instruction does not include the second target entity and includes the first target entity, it is determined whether the author of the current work is the same as the target author indicated by the first target entity of the query intention. It can be seen that when the query intent only includes the first target entity, the query intent is used to query the works of the target author indicated by the first target entity. At this time, the display device needs to determine whether the author of the current work displayed is the same as the target author.
  • the work information query instruction does not include the second target entity and includes the first target entity
  • the author of the current work is the same as the target author
  • the current work is the only work of the target author
  • the display device needs to obtain audio indicating that the current work is the only work of the target author. For example, "The work currently displayed is the only work of the target author”.
  • the query result includes: the audio indicating that the current work is the only work of the target author.
  • the display device can obtain the image of the first work and the audio used to indicate the first work, where the first work is any work other than the current work among the works of the target author.
  • the display device may randomly select any work of the target author from a work library containing multiple (such as 300, 400, etc.) works. For example, author B has work A and work C, and the current work displayed by the display device is work A.
  • the display device can obtain the image of work C and use it to indicate Audio of work C (such as recommending work C of author B for you).
  • the query result includes: an image of the first work, and audio used to indicate the first work.
  • the display device can acquire the image of the second work and the audio used to indicate the second work, which is any work of the target author. For example, assuming that the display device currently displays work A of author B, and the first target entity included in the work information query instruction is "author D", the display device can obtain an image of any work E of author D, and use it for Indicates the audio of Work E. At this time, the query result includes: an image of the second work, and audio used to indicate the second work.
  • the work information query instruction does not include the first target entity and the second target entity
  • the image of the third work and the audio used to indicate the third work are acquired.
  • the query result includes: the image of the third work, and the audio used to indicate the third work.
  • the display device may randomly select the third work from a work library containing multiple (such as 300, 400, etc.) works. It should be noted that when the query intention does not include the first target entity nor the second target entity, it indicates that the query intention only wants to order any work. At this time, the display device can give the user priority to display the work of the author of the current work. .
  • the display device needs to obtain other works of the author and their audio; when the current work is the only work of the author, the author has no other works other than the current work Works, at this time the display device can obtain images of other authors’ works.
  • the embodiment of the present disclosure does not limit the sequence of the method steps.
  • the display device may perform step 204 and step 205 in sequence, and the display device does not need to perform step 206 and step 207.
  • the display device can determine which of the above six situations the current situation is based on the judgment result of the previous steps, and then acquire the information that needs to be acquired in this situation.
  • the above method steps are independently completed by the display device as an example.
  • part or all of the steps may be completed by the display device through other equipment.
  • the above step 202 may be completed by the display device through the intention recognition server.
  • step 203 to step 208 may be completed by the display device through the service server.
  • the display device executes step 203 and step 208 through the intention recognition server, when the service server obtains the query result, it can directly obtain the query result locally on the service server, or obtain the query result on another server. The embodiment does not limit this.
  • the above-mentioned work information query instruction may be an instruction in the form of voice.
  • the display device may send the work information query instruction to the semantic understanding server.
  • the semantic understanding server first converts the work information query instruction in voice form into a work information query instruction in text form, and then sends the work information query instruction in text form to the display device.
  • the display device may send the work information query instruction in text form to the service server, and the service server may first send the work information query instruction to the intention recognition server.
  • the intention recognition server After receiving the work information query instruction, the intention recognition server performs intention recognition on the work information query instruction to obtain the query intention.
  • the intention recognition server sends the query intention to the business server, and the business server executes the above steps 203 to 208 based on the query intention to obtain the query result.
  • the service server sends the query result to the display device, and the display device displays the query result.
  • the service server may search for images and audio in a database stored in the data server, and the database may include: the above-mentioned audio library, the above-mentioned work library, and so on.
  • the service server can also query images, audio and text in other locations. After the service server finds the text, it can also generate the audio of the text through the semantic understanding server.
  • the service server directly sends the query result to the display device as an example.
  • the service server may also send the query result information to the display device. After the display device receives the query result information, it can be based on the information. Get query results.
  • the service server may send a link of the image to the display device, and after receiving the link of the image, the display device may obtain the image based on the link.
  • the service server may send a text to the display device, and after the display device receives the text, it may generate the audio of the text through the semantic understanding server.
  • the above query intention can also be a control intention used to control the display device to display the previous or next painting, such as the query intention composed of the basic intentions and slots corresponding to numbers 24 and 25 in Table 2.
  • the display device may not need to execute the above steps 203 to 209, but directly execute the action for the execution of the control intention.
  • the query intent is a query intent composed of basic intent and slots corresponding to number 24
  • the display device can directly display the previous painting; when the query intent is a query intent composed of basic intent and slots corresponding to number 25, The display device can directly display the next painting.
  • the display device can respectively determine the type of query intention after obtaining the work information query instruction, and obtain the detection of whether the work information query instruction contains at least one target entity result.
  • the display device can also obtain and display the query result based on the type including the query intention and whether the work information query instruction includes the reference information of the detection result of at least one target entity. It can be seen that the display device provided by the embodiment of the present disclosure can implement information query based on reference information, thus enriching the functions of the display device.
  • the display device is an electronic drawing screen as an example.
  • the display device may also be a television, or a display device with a display function. Air conditioning, etc.
  • the display device 30 may include:
  • the instruction acquisition module 301 is used to acquire work information query instructions
  • the intention recognition module 302 is used for recognizing the intention of the work information query instruction to obtain the query intention;
  • the type determination module 303 is used to determine the type of query intent among multiple types of intent
  • the entity detection module 304 is configured to detect whether the work information query instruction includes at least one target entity
  • the result obtaining module 305 is configured to obtain the query result according to the query intention and reference information, where the reference information includes: the type of the query intention, and whether the work information query instruction contains the detection result of at least one target entity, and the query result includes: image, At least one of audio and text;
  • the information display module 306 is used to display query results.
  • the type determination module can determine the type of query intention after the instruction acquisition module obtains the work information query instruction, and the entity detection module can obtain whether the work information query instruction contains at least one The detection result of a target entity.
  • the result obtaining module can obtain and display the query result based on the type including the query intention and whether the work information query instruction includes the reference information of the detection result of at least one target entity. It can be seen that the display device provided by the embodiment of the present disclosure can realize information query based on reference information, thus enriching the functions of the display device.
  • the at least one target entity includes: a first target entity containing author information of the work, and/or a second target entity containing name information of the work.
  • FIG. 4 is a schematic structural diagram of another display device provided by an embodiment of the present disclosure. As shown in FIG. 4, based on FIG. 3, the display device 30 may further include:
  • the work detection module 307 is used to detect whether the current work displayed by the display device is the same as the target work indicated by the second target entity when the work information query instruction includes the second target entity.
  • the reference information also includes: whether the current work is the target work The same test result.
  • the multiple types of intents include: a first type, and the first type of intent includes an intent related to a work introduction.
  • the display device 30 further includes:
  • the work to be profiled determination module 308 is used to determine the work to be profiled according to the detection result of whether the work information query instruction contains at least one target entity when the type of query intention is the first type; wherein, when the work information query instruction contains at least the first type For the second target entity, the work to be profiled is the target work indicated by the second target entity; when the work information query instruction does not include the second target entity and contains the first target entity, the work to be profiled is the author indicated by the first target entity Any of the works;
  • the audio detection module 309 is used to detect whether the audio library contains the introduction audio of the work to be introduced, and the reference information also includes the detection result of whether the audio library contains the introduction audio of the work to be introduced.
  • the result obtaining module 306 is used to:
  • the type of query intent is the first type
  • the audio library contains introduction audio
  • the work information query instruction includes at least a second target entity, and the current work is the same as the target work
  • the introduction audio in the audio library is obtained, and the query result Including: the introduction audio
  • the type of query intention is the first type
  • the audio library contains introduction audio
  • the work information query instruction contains at least the second target entity
  • the current work is different from the target work
  • the image of the target work and the introduction audio in the audio library are obtained ,
  • the query result includes: the image of the target work and the introduction audio;
  • the type of query intent is the first type
  • the audio library contains introduction audio
  • the work information query instruction does not include the second target entity and contains the first target entity
  • the introduction audio in the audio library is obtained, and the query result includes: The introduction audio.
  • the result obtaining module 306 is used to:
  • the type of query intent is the first type
  • the work information query instruction includes at least the second target entity, and the current work is the same as the target work
  • the introduction text of the work to be introduced and the introduction text are obtained
  • the search result includes: the introduction text of the work to be introduced, and the audio of the introduction text;
  • the type of query intent is the first type
  • the work information query instruction includes at least the second target entity, and the current work is different from the target work, then the image of the work to be introduced and the information of the work to be introduced are obtained.
  • Introduction text, and audio of the introduction text, the query result includes: the image of the work to be introduced, the introduction text of the work to be introduced, and the audio of the introduction text;
  • the type of query intent is the first type
  • the audio library does not contain introduction audio
  • the work information query command does not include the second target entity and contains the first target entity
  • the introduction text of the work to be introduced and the audio of the introduction text are obtained .
  • the query result includes: the brief introduction text of the work to be briefed, and the audio of the brief introduction text.
  • multiple types of intents include: the second type, the second type of intent includes: any information related to the intent in the information group, the information group includes: the author's information, and the information of the work except for the introduction.
  • the result obtaining module 306 is used to:
  • the type of query intent is the second type
  • the work information query instruction contains at least the second target entity, and the current work is the same as the target work
  • the text of any information and the audio of the text of any information are obtained.
  • the query result includes: the text of any information, and the audio of the text of any information;
  • the type of query intention is the second type
  • the work information query instruction contains at least the second target entity, and the current work is different from the target work
  • the image of the target work, the text of any information, and the text of any information are obtained
  • the search result includes: the image of the target work, the text of the any information, and the audio of the text of the any information.
  • the result obtaining module 306 is used to:
  • the type of the query intention is the second type
  • the work information query instruction includes the first target entity and does not include the second target entity
  • the text of any information and the audio of the text of any information are obtained, and the query result Including: the text of any information, and the audio of the text of any information.
  • multiple types of intentions include: a third type, and the third type of intentions include: intentions related to the on-demand work, and the result obtaining module 306 is used for:
  • the type of query intention is the third type
  • the work information query instruction includes at least the second target entity, and the current work is the same as the target work
  • the audio prompting that the current work is the target work is obtained, and the query results include: The audio for prompting that the current work is the target work;
  • the type of query intention is the third type
  • the work information query instruction contains at least a second target entity, and the current work is different from the target work
  • the image of the target work and the audio used to indicate the target work are obtained.
  • the result includes: the image of the target work, and the audio used to indicate the target work.
  • the result obtaining module 306 is used to:
  • the type of the query intent is the third type, if the work information query instruction does not include the second target entity and includes the first target entity, it is determined whether the author of the current work is the same as the target author indicated by the first target entity of the query intention ;
  • the author of the current work is the same as the target author, and the current work is the only work of the target author, then obtain the audio indicating that the current work is the only work of the target author, and the query result includes: The work is the audio of the only work of the said target author;
  • the query result includes: an image of the first work and audio used to indicate the first work;
  • the image of the second work and the audio used to indicate the second work are obtained.
  • the second work is any work of the target author, and the query result includes: the second work The image of and the audio used to indicate the second work.
  • the result obtaining module 306 is used to:
  • the type of query intention is the third type
  • the work information query instruction does not include the first target entity and the second target entity
  • the image of the third work and the audio used to indicate the third work are obtained, and the query result Including: the image of the third work, and the audio used to indicate the third work;
  • the third work is any work of other authors except the author of the current work; when the current work is not the only work of the author, the third work is the current work Any of the works of the author except the current one.
  • the instruction acquisition module 301 may include: a voice collection module, configured to acquire the work information query instruction in a voice form by means of voice collection.
  • FIG. 5 is a schematic structural diagram of another display device provided by an embodiment of the disclosure.
  • the display device 50 may include a processor 501, a display screen 502, and a speaker 503.
  • the processor 501 may be used to: obtain a work information query instruction; perform intent recognition on a work information query instruction to obtain a query intention; determine the type of query intent among multiple types of intents; and detect whether the work information query instruction contains at least one target Entity; the query result is obtained according to the query intent and reference information, where the reference information includes: the type of query intent, and whether the work information query instruction contains the detection results of at least one target entity, the query results include: images, audio, and text At least one type of information; when the query result includes the image, control the display screen to display the image in the query result; when the query result includes the text, control the display screen to display the query The text in the result; when the query result includes the audio, the speaker is controlled to play the audio in the query result.
  • the processor 501 may include the instruction acquisition module 301, the intention recognition module 302, the type determination module 303, the entity detection module 304, and the instruction acquisition module 301 in the display device shown in FIG. 3 and FIG. Result obtaining module 305;
  • the processor 501 may also include the work detection module 307, the work to be profiled determination module 308, and the audio detection module 309 in FIG.
  • the display screen 502 and the speaker 503 in FIG. 5 can form the information display module 306 in FIG. 3 and FIG. 4.
  • the display device shown in FIG. 5 may further include a microphone 504, and the processor 501 is configured to obtain the work information query instruction in voice form through the microphone 504.
  • the display device may be: liquid crystal display device, electronic paper, organic light emitting diode display device, mobile phone, tablet computer, television, monitor, notebook computer, digital photo frame, navigator, etc. Products or parts that display features.
  • the aforementioned processor 501 is connected to the microphone 504, the speaker 503, and the display screen 502; the processor 501 is configured to receive the work information query instruction through the microphone 504, and perform at least one of the following operations according to the work information query instruction: control the speaker 503 plays a voice that is related to the content to be queried by the work information query instruction; controls the display screen 502 to display at least one of an image and text, and the image and the text are both related to the content that the work information query instruction is used to query.
  • the processor 501 is configured to: determine the image to be displayed according to the work information query instruction, and control the display screen 502 to display the image to be displayed when the current image displayed on the display screen 502 is different from the image to be displayed.
  • the speaker 503 is controlled to play a voice prompting that the current image is the same as the image to be displayed.
  • At least one refers to one or more, and “multiple” refers to two or more.
  • At least one of the following” or similar expressions refers to any combination of these items, including any combination of single items or plural items.
  • at least one of a, b, or c can mean: a, b, c, a+b, a+c, b+c, and a+b+c, where a, b, c can be A single item can also be multiple.
  • the method embodiment provided in the embodiment of the present invention can be cross-referenced with the corresponding device embodiment, which is not limited in the embodiment of the present invention.
  • the order of the steps in the method embodiments provided by the embodiments of the present invention can be adjusted appropriately, and the steps can be increased or decreased accordingly according to the situation. Any person skilled in the art can easily think of changes within the technical scope disclosed in the present invention. The methods should all be covered within the protection scope of the present invention, so they will not be repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Library & Information Science (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种信息查询方法及显示装置,方法包括:获取作品信息查询指令(101);对作品信息查询指令进行意图识别,得到查询意图(102);确定多种意图类型中查询意图的类型(103);检测作品信息查询指令是否包含至少一种目标实体(104),根据查询意图和参考信息获取查询结果,其中,参考信息包括:查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果,查询结果包括:图像、音频和文本中的至少一种信息(105)。

Description

信息查询方法及显示装置 技术领域
本公开涉及显示显示技术领域,特别涉及一种信息查询方法及显示装置。
背景技术
随着显示技术的发展,出现了各种各样的显示装置。比如,电脑、电视机、电子书和电子画屏等。
每种显示装置均能够显示图像。比如,电子画屏能够显示各种各样的作品。并且,由于电子画屏的显示效果较为逼真,且能够对显示的作品进行更换,因此得到了人们的喜爱。
发明内容
本公开实施例提供了一种信息查询方法及显示装置,所述技术方案如下:
一方面,提供了一种信息查询方法,用于显示装置,所述方法包括:
获取作品作品信息查询指令;
对所述作品作品信息查询指令进行意图识别,得到查询意图;
确定多种意图类型中所述查询意图的类型;
检测所述作品作品信息查询指令是否包含至少一种目标实体;
根据所述查询意图和参考信息获取查询结果,其中,所述参考信息包括:所述查询意图的类型,以及所述作品作品信息查询指令是否包含所述至少一种目标实体的检测结果,所述查询结果包括:图像、音频和文本中的至少一种信息;
展示所述查询结果。
可选地,所述至少一种目标实体包括:包含作品的作者信息的第一目标实体,和/或,包含作品的名称信息的第二目标实体。
可选地,所述至少一种目标实体包括所述第二目标实体,所述方法还包括:
在所述作品信息查询指令包含所述第二目标实体时,检测所述显示装置显示的当前作品与所述第二目标实体所指示的目标作品是否相同;
所述参考信息还包括:所述当前作品与所述目标作品是否相同的检测结果。
可选地,所述多种意图类型包括:第一类型,所述第一类型的意图包括作品简介相关的意图,在所述根据所述查询意图和参考信息获取查询结果之前,所述方法还包括:
当所述查询意图的类型为所述第一类型时,根据所述作品作品信息查询指令是否包含所述至少一种目标实体的检测结果确定待简介作品;其中,当所述作品信息查询指令至少包含第二目标实体时,所述待简介作品为所述第二目标实体所指示的所述目标作品;当所述作品信息查询指令不包含第二目标实体且包含第一目标实体时,所述待简介作品为所述第一目标实体所指示的作者的任一作品;
检测音频库是否包含所述待简介作品的简介音频,所述参考信息还包括:所述音频库是否包含所述待简介作品的简介音频的检测结果。
可选地,所述根据所述查询意图和参考信息获取查询结果,包括:
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像和所述音频库中的所述简介音频,所述查询结果包括:所述目标作品的图像和所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频。
可选地,所述根据所述查询意图和参考信息获取查询结果,包括:
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述 目标作品不同,则获取所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频。
可选地,所述多种意图类型包括:第二类型,所述第二类型的意图包括:信息组中的任一信息相关的意图,所述信息组包括:作者的信息,以及作品的信息中除简介之外的信息,所述根据所述查询意图和参考信息获取查询结果,包括:
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频;
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频;
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
可选地,所述多种意图类型包括:第三类型,且所述第三类型的意图包括:点播作品相关的意图,所述根据所述查询意图和参考信息获取查询结果,包括:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取用于提示所述当前作品为所述目标作品的音频,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频;
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少 包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,以及用于指示所述目标作品的音频,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
可选地,所述根据所述查询意图和参考信息获取查询结果,还包括:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断所述当前作品的作者与所述查询意图的第一目标实体所指示的目标作者是否相同;
若所述当前作品的作者与所述目标作者相同,且所述当前作品为所述目标作者的唯一作品,则获取用于指示所述当前作品为所述目标作者的唯一作品的音频,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频;
若所述当前作品的作者与所述目标作者相同,且所述当前作品不为所述目标作者的唯一作品,则获取所述第一作品的图像,以及用于指示所述第一作品的音频,所述第一作品为所述目标作者的作品中除所述当前作品之外的任一作品,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频;
若所述当前作品的作者与所述目标作者不同,则获取第二作品的图像,以及用于指示所述第二作品的音频,所述第二作品为所述目标作者的任一作品,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
可选地,所述根据所述查询意图和参考信息获取查询结果,还包括:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含所述第一目标实体和所述第二目标实体,则获取第三作品的图像,以及用于指示所述第三作品的音频,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频;
其中,当所述当前作品为其作者的唯一作品时,所述第三作品为除所述当前作品的作者之外的其他作者的任一作品;当所述当前作品不为其作者的唯一作品时,所述第三作品为所述当前作品的作者的作品中除所述当前作品之外的任一作品。
可选地,所述获取作品作品信息查询指令,包括:
通过语音采集的方式,获取语音形式的所述作品作品信息查询指令。
可选地,所述作品包括:作品。
另一方面,提供了一种显示装置,所述显示装置包括:处理器、显示屏和扬声器;
所述处理器用于:
获取作品作品信息查询指令;
对所述作品作品信息查询指令进行意图识别,得到查询意图;
确定多种意图类型中所述查询意图的类型;
检测所述作品作品信息查询指令是否包含至少一种目标实体;
根据所述查询意图和参考信息获取查询结果,其中,所述参考信息包括:所述查询意图的类型,以及所述作品作品信息查询指令是否包含所述至少一种目标实体的检测结果,所述查询结果包括:图像、音频和文本中的至少一种信息;
在所述查询结果包括所述图像时,控制所述显示屏显示所述查询结果中的图像;
在所述查询结果包括所述文本时,控制所述显示屏显示所述查询结果中的文本;
在所述查询结果包括所述音频时,控制所述扬声器播放所述查询结果中的音频。
可选地,所述至少一种目标实体包括:包含作品的作者信息的第一目标实体,和/或,包含作品的名称信息的第二目标实体。
可选地,所述至少一种目标实体包括所述第二目标实体,所述处理器用于:在所述作品信息查询指令包含所述第二目标实体时,检测所述显示装置显示的当前作品与所述第二目标实体所指示的目标作品是否相同;
所述参考信息还包括:所述当前作品与所述目标作品是否相同的检测结果。
可选地,所述多种意图类型包括:第一类型,所述第一类型的意图包括作品简介相关的意图,所述处理器用于:
当所述查询意图的类型为所述第一类型时,根据所述作品作品信息查询指令是否包含所述至少一种目标实体的检测结果确定待简介作品;其中,当所述作品信息查询指令至少包含第二目标实体时,所述待简介作品为所述第二目标实体所指示的所述目标作品;当所述作品信息查询指令不包含第二目标实体且包含第一目标实体时,所述待简介作品为所述第一目标实体所指示的作者的任一作品;
检测音频库是否包含所述待简介作品的简介音频,所述参考信息还包括:所述音频库是否包含所述待简介作品的简介音频的检测结果。
可选地,所述处理器用于:当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像和所述音频库中的所述简介音频,所述查询结果包括:所述目标作品的图像和所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频。
可选地,所述处理器用于:当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频。
可选地,所述多种意图类型包括:第二类型,所述第二类型的意图包括:信息组中的任一信息相关的意图,所述信息组包括:作者的信息,以及作品的信息中除简介之外的信息,所述处理器用于:当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品 与所述目标作品相同,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频;
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频;
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
可选地,所述多种意图类型包括:第三类型,且所述第三类型的意图包括:点播作品相关的意图,所述处理器用于:当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取用于提示所述当前作品为所述目标作品的音频,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频;
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,以及用于指示所述目标作品的音频,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
可选地,所述处理器用于:当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断所述当前作品的作者与所述查询意图的第一目标实体所指示的目标作者是否相同;
若所述当前作品的作者与所述目标作者相同,且所述当前作品为所述目标作者的唯一作品,则获取用于指示所述当前作品为所述目标作者的唯一作品的音频,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频;
若所述当前作品的作者与所述目标作者相同,且所述当前作品不为所述目标作者的唯一作品,则获取所述第一作品的图像,以及用于指示所述第一作品的音频,所述第一作品为所述目标作者的作品中除所述当前作品之外的任一作 品,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频;
若所述当前作品的作者与所述目标作者不同,则获取第二作品的图像,以及用于指示所述第二作品的音频,所述第二作品为所述目标作者的任一作品,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
可选地,所述处理器用于:当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含所述第一目标实体和所述第二目标实体,则获取第三作品的图像,以及用于指示所述第三作品的音频,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频;
其中,当所述当前作品为其作者的唯一作品时,所述第三作品为除所述当前作品的作者之外的其他作者的任一作品;当所述当前作品不为其作者的唯一作品时,所述第三作品为所述当前作品的作者的作品中除所述当前作品之外的任一作品。
可选地,所述处理器用于:通过语音采集的方式,获取语音形式的所述作品作品信息查询指令。
可选地,所述作品包括:画作。
可选地,所述显示装置还包括:麦克风,所述处理器用于:
通过所述麦克风,获取语音形式的所述作品作品信息查询指令。
又一方面,提供了一种显示装置,所述显示装置包括:
指令获取模块,用于获取作品信息查询指令;
意图识别模块,用于对所述作品信息查询指令进行意图识别,得到查询意图;
类型确定模块,用于确定多种意图类型中所述查询意图的类型;
实体检测模块,用于检测所述作品信息查询指令是否包含至少一种目标实体;
结果获取模块,用于根据所述查询意图和参考信息获取查询结果,其中,所述参考信息包括:所述查询意图的类型,以及所述作品信息查询指令是否包含至少一种目标实体的检测结果,所述查询结果包括:图像、音频和文本中的至少一种信息;
信息展示模块,用于展示所述查询结果。
可选地,所述至少一种目标实体包括:包含作品的作者信息的第一目标实 体,和/或,包含作品的名称信息的第二目标实体。
可选地,所述至少一种目标实体包括所述第二目标实体,所述显示装置还包括:
作品检测模块,用于在所述作品信息查询指令包含第二目标实体时,检测所述显示装置显示的当前作品与所述第二目标实体所指示的目标作品是否相同,所述参考信息还包括:所述当前作品与目标作品是否相同的检测结果。
可选地,所述多种意图类型包括:第一类型,所述第一类型的意图包括作品简介相关的意图,所述显示装置还包括:
待简介作品确定模块,用于当所述查询意图的类型为所述第一类型时,根据所述作品信息查询指令是否包含至少一种目标实体的检测结果确定待简介作品;其中,当所述作品信息查询指令至少包含第二目标实体时,所述待简介作品为所述第二目标实体所指示的所述目标作品;当所述作品信息查询指令不包含第二目标实体且包含第一目标实体时,所述待简介作品为所述第一目标实体所指示的作者的任一作品;
音频检测模块,用于检测音频库是否包含所述待简介作品的简介音频,所述参考信息还包括所述音频库是否包含待简介作品的简介音频的检测结果。
可选地,所述结果获取模块用于:
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像和所述音频库中的所述简介音频,所述查询结果包括:所述目标作品的图像和所述简介音频;
当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频。
可选地,所述结果获取模块用于:
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述 目标作品相同,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述待简介作品的图像及待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频;
当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频。
可选地,所述多种意图类型包括:第二类型,所述第二类型的意图包括:信息组中的任一信息相关的意图,所述信息组包括:作者的信息,以及作品的信息中除简介之外的信息,所述结果获取模块用于:
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频;
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频。
所述结果获取模块还用于:
当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
可选地,所述多种意图类型包括:第三类型,所述第三类型的意图包括:点播作品相关的意图,所述结果获取模块用于:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少 包含第二目标实体,且所述当前作品与所述目标作品相同,则获取用于提示所述当前作品为所述目标作品的音频,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频;
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,以及用于指示所述目标作品的音频,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
可选地,所述结果获取模块还用于:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断所述当前作品的作者与所述查询意图的第一目标实体所指示的目标作者是否相同;
若所述当前作品的作者与所述目标作者相同,且所述当前作品为所述目标作者的唯一作品,则获取用于指示所述当前作品为所述目标作者的唯一作品的音频,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频;
若所述当前作品的作者与所述目标作者相同,且所述当前作品不为所述目标作者的唯一作品,则获取所述第一作品的图像,以及用于指示所述第一作品的音频,所述第一作品为所述目标作者的作品中除所述当前作品之外的任一作品,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频;
若所述当前作品的作者与所述目标作者不同,则获取第二作品的图像,以及用于指示所述第二作品的音频,所述第二作品为所述目标作者的任一作品,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
可选地,所述结果获取模块还用于:
当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含所述第一目标实体和所述第二目标实体,则获取第三作品的图像,以及用于指示所述第三作品的音频,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频;
其中,当所述当前作品为其作者的唯一作品时,所述第三作品为除所述当前作品的作者之外的其他作者的任一作品;当所述当前作品不为其作者的唯一作品时,所述第三作品为所述当前作品的作者的作品中除所述当前作品之外的 任一作品。
可选地,所述指令获取模块包括:
语音采集模块,用于通过语音采集的方式,获取语音形式的所述作品信息查询指令。
可选地,所述作品包括:画作。
再一方面,提供了一种显示装置,所述显示装置包括:麦克风、扬声器、显示屏和处理器,所述处理器与所述麦克风、所述扬声器和所述显示屏均连接;
所述处理器用于通过所述麦克风接收作品信息查询指令,并根据所述作品信息查询指令执行以下操作中的至少一个:
控制所述扬声器播放语音,所述语音与所述作品信息查询指令用于查询的内容相关;
控制所述显示屏显示图像和文本中的至少一个,所述图像和所述文本均与所述作品信息查询指令用于查询的内容相关。
可选地,所述处理器用于:根据所述作品信息查询指令确定待显示图像,在所述显示屏显示的当前图像与待显示图像不同时,控制所述显示屏显示所述待显示图像。
可选地,所述处理器用于:根据所述作品信息查询指令确定待显示图像,在所述显示屏显示的当前图像与待显示图像相同时,控制所述扬声器播放用于提示所述当前图像与所述待显示图像相同的语音。
附图说明
图1为本公开实施例提供的一种用于本公开实施例提供的显示装置的信息查询方法的流程图;
图2为本公开实施例提供的另一种用于本公开实施例提供的显示装置的信息查询方法的流程图;
图3为本公开实施例提供的一种显示装置的结构示意图;
图4为本公开实施例提供的另一种显示装置的结构示意图;
图5为本公开实施例提供的又一种显示装置的结构示意图。
具体实施方式
为使本公开的原理、技术方案和优点更加清楚,下面将结合附图对本公开 实施方式作进一步地详细描述。
虽然随着显示技术的发展,出现了各种各样的显示装置,但是目前显示装置的功能仍然较为单一。本公开实施例提供了一种显示装置,该显示装置的功能较为丰富。
示例地,图1为本公开实施例提供的一种用于本公开实施例提供的显示装置的信息查询方法的流程图。本公开实施例中以该显示装置为电子画屏为例,可选地,该显示装置也可以为诸如电视机、具有显示功能的空调等。如图1所示,该信息查询方法可以包括:
步骤101、获取作品信息查询指令。
步骤102、对作品信息查询指令进行意图识别,得到查询意图。
步骤103、确定多种意图类型中查询意图的类型。
步骤104、检测作品信息查询指令是否包含至少一种目标实体。
步骤105、根据查询意图和参考信息获取查询结果,其中,参考信息包括:查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果,查询结果包括:图像、音频和文本中的至少一种信息。
步骤106、展示查询结果。
综上所述,本公开实施例提供的信息查询方法中,显示装置能够在获取到作品信息查询指令后,分别确定查询意图的类型,以及得到作品信息查询指令是否包含至少一种目标实体的检测结果。并且,显示装置还能够基于包括该查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果的参考信息,获取并展示查询结果。可以看出,本公开实施例提供的显示装置能够基于参考信息实现信息的查询,因此丰富了显示装置的功能。
示例地,图2为本公开实施例提供的另一种用于本公开实施例提供的显示装置的信息查询方法的流程图。本公开实施例中以该显示装置为电子画屏为例,可选地,该显示装置也可以为诸如电视机、具有显示功能的空调等。另外,本申请实施例中以上述作品为画作为例,可选地,该作品也可以不为画作(如音乐作品,影视作品等)。如图2所示,该信息查询方法可以包括:
步骤201、获取作品信息查询指令。
该作品信息查询指令可以是在显示装置在用户讲话的过程中,采集到的语音。
可选地,显示装置上可以设置有查询按钮(或者显示有查询按钮),当用户点击该查询按钮时,显示装置可以采集用户的语音,以获取到作品信息查询指令。显示装置包括处理器和麦克风,步骤201中处理器可以通过麦克风获取该作品信息查询指令。
步骤202、对作品信息查询指令进行意图识别,得到查询意图。
显示装置在获取到作品信息查询指令后,需要对该作品信息查询指令进行意图识别。示例地,显示装置中可以存储有意图识别模型,显示装置可以通过该意图识别模型对该作品信息查询指令进行意图识别。
可选地,该意图识别模型可以为基于传统机器学习算法或深度学习算法等。该传统机器学习算法可以例如:支持向量机(Support Vector Machine,SVM),该深度学习算法可以例如:卷积神经网络(Convolutional Neural Networks,CNN)、长短期记忆网络(LSTM,Long Short-Term Memory)或区域卷积神经网络(region-based Convolutional Neural Networks,RCNN)等。
示例地,本公开实施例中显示装置对各种各样的作品信息查询指令进行意图识别,所能够识别得到的查询意图可以如表1所示。需要说明的是,显示装置识别到的查询意图可以通过表1中的基础意图和槽位来体现,一个基础意图和一个槽位能够体现一个查询意图。假设显示装置识别到的表2中编号1对应的基础意图“作者国籍”,以及编号1对应的槽位“作者名”,则显示装置识别到的查询意图为:查询该“作者名”的国籍。假设显示装置识别到表2中编号22对应的基础意图“询问作品简介”,以及编号22对应的槽位“作品名”,则显示装置识别到的查询意图为:询问该“作品名”的简介。示例地,步骤201中显示装置采集到的作品信息查询指令可以为:“介绍一下xx的xxxx”,其中,“xx”表示一个作者名,“xxxx”表示该作者的一个画作。此时,显示装置识别到的查询意图可以由表2中编号22对应的“询问作品简介”和“作品名”(xxxx)组成,比如可以是“询问xxxx的简介”。
需要说明的是,表1中共体现出25中不同的查询意图,本公开实施例中显示装置能够识别得到的查询意图并不限于这25种查询意图。
可选地,显示装置在对作品信息查询指令进行意图识别,得到查询意图时,还可以获取该查询意图的编号。比如,获取该查询意图在表2中对应的编号。
可选地,显示装置在对作品信息查询指令进行意图识别时,该意图识别模型不仅可以得到上述查询意图,还可以得到至少一种槽位。比如,假设显示装 置识别到的查询意图为表2中编号为1的查询意图“作者国籍”,则该显示装置得到的槽位可以包括“作者名”。假设显示装置识别到的查询意图为表2中编号为22的查询意图“询问作品简介”,则该显示装置得到的槽位可以包括“作品名”。
表1
编号 基础意图 槽位
1 作者国籍 作者名
2 作者出生地 作者名
3 询问作者名字 作者名
4 询问作者成名作 作者名
5 作者代表作 作者名
6 作者流派、风格 作者名
7 作者成就 作者名
8 询问作者简介 作者名
9 作者最贵的画 作者名
10 相似的作者有哪些 作者名
11 询问作品名字 作品名
12 画作的流派风格 作品名
13 画作类别、绘画方式创作方式 作品名
14 画的创作地点 作品名
15 创作时间 作品名
16 画作内容、色调 作品名
17 收藏地点 作品名
18 创作灵感 作品名
19 价格 作品名
20 作品地位 作品名
21 作品亮点 作品名
22 询问作品简介 作品名
23 点播 作品名和作者名(或作者名,或无)
24 上一幅
25 下一幅
步骤203、确定多种意图类型中查询意图的类型。
可选地,显示装置在确定查询意图后,可以在多种意图类型中确定该查询意图的类型。示例地,显示装置可以在多个意图与多种意图类型的对应关系中,查找该查询意图对应的意图类型,进而将该意图类型确定为该查询意图的类型。
可选地,若步骤202中显示装置获取了识别到的查询意图的编号,则显示装置在步骤203中也可以在多个意图编号与多种意图类型的对应关系中,查找该查询意图的编号对应的意图类型,进而将该意图类型确定为该查询意图的类型。
步骤204、检测作品信息查询指令是否包含至少一种目标实体。
示例地,至少一种目标实体包含第一目标实体和/或第二目标实体,本申请实施例中以至少一种目标实体包含第一目标实体和第二目标实体为例。其中,第一目标实体包含作品的作者信息,第二目标实体包含作品的名称信息。
需要说明的是,作品信息查询指令用于对某一事物进行查询,如对某一作品进行查询,或对某一作者进行查询,或对其他事物进行查询。作品信息查询指令的实体可以包括该查询意图用于查询的事物。在步骤204中,显示装置需要对作品信息查询指令(或者该作品信息查询指令的查询意图)进行分析,以确定该作品信息查询指令是否包含第一目标实体,以及该作品信息查询指令是否包含第二目标实体。
可选地,也可以是仅检测作品信息查询指令是否包含第一目标实体或第二目标实体,或者其他实体,本申请实施例对此不作限定。
步骤205、在作品信息查询指令包含第二目标实体时,检测显示装置显示的当前作品与第二目标实体所指示的目标作品是否相同。
可选地,在步骤204中得到的作品信息查询指令是否包含至少一种目标实体的检测结果表明上述作品信息查询指令包含第二目标实体时,显示装置还可以检测显示装置显示的当前作品与第二目标实体所指示的目标作品是否相同,得到当前作品与目标作品是否相同的检测结果。此时,后续步骤208中获取查询结果所基于的参考信息还可以包括:当前作品与目标作品是否相同的检测结果。
步骤206、当查询意图的类型为第一类型时,根据作品信息查询指令是否包含至少一种目标实体的检测结果确定待简介作品。
其中,当作品信息查询指令至少包含第二目标实体时,待简介作品为第二目标实体所指示的目标作品;当作品信息查询指令不包含第二目标实体且包含第一目标实体时,待简介作品为第一目标实体所指示的作者的任一作品。
步骤207、检测音频库是否包含待简介作品的简介音频,得到音频库是否包含待简介作品的简介音频的检测结果。
可选地,在步骤203中确定出的查询意图的类型为第一类型(第一类型的意图包括作品简介相关的意图)时,显示装置还可以确定待简介作品,再判断预设的音频库中是否包含该待简介作品的简介音频,以得到音频库是否包含待简介作品的简介音频的检测结果。此时,后续步骤208中获取查询结果所基于的参考信息还可以包括:当前作品与目标作品是否相同的检测结果。
步骤208、根据查询意图和参考信息获取查询结果,其中,参考信息包括:查询意图的类型、作品信息查询指令是否包含至少一种目标实体的检测结果、当前作品与目标作品是否相同的检测结果和音频库是否包含待简介作品的简介音频的检测结果,查询结果包括:图像、音频和文本中的至少一种信息。
步骤209、展示查询结果。
示例地,当查询结果包括图像时,显示装置需要对该图像进行显示(如显示装置中的处理器控制显示装置中的显示屏显示图像);当该查询结果包括音频时,该显示装置需要对该音频进行播放(如显示装置中的处理器控制显示装置中的扬声器播放该音频);当该查询结果包括文本时,显示装置需要对该文本进行显示(如显示装置中的处理器控制显示装置中的显示屏显示文本)。
需要说明的是,步骤203中的多种意图类型可以包括各种各样的意图类型,本公开实施例将以第一类型、第二类型和第三类型中的至少一种为例,对上述实施例中的步骤进行讲解。可选地,步骤203中的多种意图类型也可以是其他种的意图类型,本公开实施例对此不作限定。
示例地,第一类型的意图包括作品简介相关的意图。例如:表2中编号22对应的基础意图和槽位组成的查询意图为该第一类型的意图。
第二类型的意图包括:信息组中的任一信息相关的意图,该信息组包括:作者的信息,以及作品的信息中除简介之外的信息(比如作品的价格、收藏地点等)。例如,表2中编号1至22对应的基础意图和槽位组成的查询意图均为该第二类型的意图。
第三类型的意图包括:点播作品相关的意图。例如,表2中编号23对应的基础意图和槽位组成的查询意图均为该第三类型的意图。
以下分别对查询意图的类型分别为第一类型、第二类型和第三类型时,步骤208的过程进行讲解。
第一方面,当参考信息中查询意图的类型为第一类型时,上述步骤208可 以包括:
在第一种情况中,若音频库包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取音频库中的待简介作品的简介音频。此时查询结果包括:该简介音频。
需要说明的是,该音频库可以用于存储预先录制的至少一个作品的简介音频。当查询意图的类型为第一类型时,说明此时查询意图用于查询待简介作品的简介,所以,需要检测音频库中是否包含待简介作品的简介音频。并且,此时查询意图至少需要包含第二目标实体(比如查询意图只包含第二目标实体,或者查询意图不仅包含第二目标实体且包含第一目标实体)。若显示装置显示的当前作品与第二目标实体所指示的目标作品(也即待简介作品)相同,则显示装置也无需获取该目标作品的图像。所以,在音频库包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同时,显示装置只需要获取音频库中的该待简介作品(也即目标作品)的简介音频即可,而无需获取图像和文本。这样一来,在步骤209中,显示装置只需要播放获取到的简介音频,而无需对当前显示的作品进行更换。比如,若查询意图为“简介作品A”,且显示装置当前显示有作品A,音频库中包含作品A的简介音频,则显示装置在步骤208中仅需获取音频库中该作品A的简介音频。
在第二种情况中,若音频库包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取目标作品的图像和音频库中待简介作品的简介音频。此时,该查询结果包括:所述目标作品的图像和所述简介音频。
需要说明的是,在查询意图的类型为第一类型时,若音频库包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则说明待简介作品并非显示装置当前显示的作品,所以此时显示装置不仅需要获取音频库中待简介作品的简介音频,并且需要获取该待简介作品(也即目标作品)的图像,而无需获取文本。这样一来,在步骤209中,显示装置不仅需要播放获取到的简介音频,还需要将当前显示的作品更换为待简介作品。比如,若查询意图为“简介作品A”,且显示装置当前未显示有作品A,音频库中包含作品A的简介音频,则显示装置在步骤208中需要获取音频库中该作品A的简介音频,以及作品A。
在第三种情况中,若音频库包含待简介作品的简介音频,作品信息查询指 令不包含第二目标实体且包含第一目标实体,则获取音频库中待简介作品的简介音频。此时,查询结果包括:所述简介音频。
需要说明的是,在查询意图的类型为第一类型时,在该第三种情况中,仅需获取音频库中待简介作品的简介音频即可,无需获取图像和文本。比如,若查询意图为“简介一下作者B的作品”,则显示装置可以确定作者B的任一作品为待简介作品,并且查询意图包括第一目标实体“作者B”,音频库中包含该待简介作品的简介音频,则显示装置仅需从音频库中获取待简介作品的音频即可。
在第四种情况中,若音频库不包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取待简介作品的简介文本,以及该简介文本的音频。此时,查询结果包括:待简介作品的简介文本,以及该简介文本的音频。
需要说明的是,在查询意图的类型为第一类型时,若音频库不包含待简介作品的简介音频,则说明预先录制的作品的简介音频并不包括该待简介作品的简介音频。因此,在该第四种情况中,显示装置需要获取待简介作品的简介文本,以及该简介文本的音频,而无需获取图像。示例地,该简介文本的音频也可以是显示装置在获取到该简介文本后,对将简介文本转化为音频后得到的,本公开实施例对此不作限定。比如,若查询意图为“简介一下作者B的作品”,则显示装置可以确定作者B的任一作品为待简介作品,并且查询意图包括第一目标实体“作者B”,音频库中不包含该待简介作品的简介音频,则显示装置需获取待简介作品的简介文本,以及该简介文本的音频即可。
在第五种情况中,若音频库不包含待简介作品的简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取待简介作品及其简介文本,以及该简介文本的音频。此时,查询结果包括:待简介作品的图像,待简介作品的简介文本,以及该简介文本的音频。
需要说明的是,在查询意图的类型为第一类型时,在该第五种情况下,显示装置显示的当前作品与目标作品并不相同,则显示装置不仅需要获取待简介作品的简介文本,以及该简介文本的音频,还需要获取该待显示作品(也即目标作品)的图像。比如,若查询意图为“简介一下作品A”,则显示装置可以确定查询意图包括第二目标实体“作品A”,若音频库中不包含该作品A的简介音频,且显示装置当前并未显示有作品A,则显示装置不仅需要获取作品A 的简介文本,以及该简介文本的音频,并且需要获取作品A的图像。
在第六种情况中,若音频库不包含待简介作品的简介音频,作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取待简介作品的简介文本,以及该简介文本的音频。此时,查询结果包括:待简介作品的简介文本,以及该简介文本的音频。
需要说明的是,在查询意图的类型为第一类型时,在该第六种情况中,仅需获取待简介作品的简介文本,以及该简介文本的音频即可,无需获取图像。比如,若查询意图为“简介一下作者B的作品”,则显示装置可以确定作者B的任一作品为待简介作品,并且查询意图包括第一目标实体“作者B”,音频库中不包含该待简介作品的简介音频,则显示装置获取待简介作品的简介文本,以及该简介文本的音频。
可选地,本公开实施例不对方法步骤的前后顺序进行限定。示例地,显示装置在步骤203中确定查询意图的类型为第一类型时,显示装置可以首先执行步骤206和步骤207,之后再执行步骤204和步骤205。在执行完步骤205之后,显示装置可以根据前面步骤的判断结果,确定当前情况为上述六种情况中的哪种情况,再获取这种情况中需要获取到的信息。
第二方面,当参考信息中查询意图的类型为第二类型时,第二类型的意图用于查询信息组中的任一信息,该信息组包括:作者的信息,以及作品的信息中除简介之外的信息。此时,上述步骤208可以包括:
在第一种情况中,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取该任一信息的文本,以及该任一信息的文本的音频。查询结果包括:该任一信息的文本,以及该任一信息的文本的音频。
需要说明的是,在查询意图的类型为第二类型时,在该第一种情况中,用户想要查询的作品与显示装置当前显示的作品相同,则显示装置只需要获取该查询意图需要查询的该任一信息的文本以及音频即可,而无需获取图像。比如,若查询意图为“作品A的价格是多少”,则显示装置可以确定该作品信息查询指令包含第二目标实体“作品A”,且该查询意图需要查询的该任一信息为“作品A的价格”。若显示装置当前显示有作品A,则显示装置需要获取作品A的价格的文本和音频。
在第二种情况中,若作品信息查询指令至少包含第二目标实体,且当前作 品与目标作品不同,则获取目标作品的图像,该任一信息的文本,以及任一信息的文本的音频。此时,查询结果包括:目标作品的图像,该任一信息的文本,以及所述任一信息的文本的音频。
需要说明的是,在查询意图的类型为第二类型时,在该第二种情况中,用户想要查询的目标作品与显示装置当前显示的作品并不相同,则显示装置不仅需要获取该查询意图需要查询的该任一信息的文本以及音频,还需要获取该目标作品的图像。比如,若查询意图为“作品A的价格是多少”,则显示装置可以确定该作品信息查询指令包含第二目标实体“作品A”,且该查询意图需要查询的该任一信息为“作品A的价格”。若显示装置当前并未显示有作品A,则显示装置需要获取作品A的图像,以及作品A的价格的文本和音频。
在第三种情况中,若作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取任一信息的文本,以及任一信息的文本的音频。此时,查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
需要说明的是,在查询意图的类型为第二类型时,在该第三种情况中,用户需要查询的信息为作者的信息,此时显示装置可以直接获取该查询意图想要查询的信息的文本和音频即可,而无需获取图像。比如,若查询意图为“作者B的年龄是多少”,则显示装置可以确定该作品信息查询指令包含第一目标实体“作者B”,且该查询意图需要查询的该任一信息为“作者B的年龄”。显示装置需要获取作者B的年龄的文本和音频。
可选地,本公开实施例不对方法步骤的前后顺序进行限定。示例地,显示装置在步骤203中确定查询意图的类型为第二类型时,显示装置可以依次执行步骤204和步骤205,并且,显示装置无需执行步骤206和步骤207。在执行完步骤205之后,显示装置可以根据前面步骤的判断结果,确定当前情况为上述三种情况中的哪种情况,再获取这种情况中需要获取到的信息。
第三方面,第三类型的意图用于点播作品。当参考信息中查询意图的类型为第三类型时,上述步骤208可以包括:
在第一种情况中,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取用于提示当前作品为目标作品的音频。此时,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频。
需要说明的是,当查询意图的类型为第三类型时,该查询意图用于点播作 品,此时,若作品信息查询指令包含第二目标实体,且该第二目标实体所指示的目标作品便是显示装置显示的当前作品。则显示装置可以确定当前用户想要点播的作品为显示装置显示的当前作品,因此显示装置需要获取用于提示当前作品为目标作品的音频(比如:“这就是您要找的画呀”等)。在这种情况下,显示装置无需获取图像和文本。
在第二种情况中,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取目标作品的图像,以及用于指示目标作品的音频。此时,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
需要说明的是,当查询意图的类型为第三类型时,该查询意图用于点播作品,此时,若作品信息查询指令包含第二目标实体,且该第二目标实体所指示的目标作品与显示装置显示的当前作品不同。则显示装置可以确定当前用户想要点播的目标作品,因此显示装置需要获取目标作品的图像,以及用于提示目标作品的音频(比如:目标作品为作品A,作品A的作者为作者B,该音频可以为“为您推荐作品A”或“为您推荐作者B的作品A”等)。在这种情况下,显示装置无需获取文本。并且,在步骤209中,显示装置需要显示获取到的目标作品的图像。
若作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断当前作品的作者与查询意图的第一目标实体所指示的目标作者是否相同。可以看出,在查询意图仅包含第一目标实体时,该查询意图用于查询第一目标实体所指示的目标作者的作品。此时,显示装置需要判断显示的当前作品的作者是否与目标作者相同。
在第三种情况中,若作品信息查询指令不包含第二目标实体且包含第一目标实体,当前作品的作者与目标作者相同,且当前作品为目标作者的唯一作品,则表明显示装置显示的当前作品是查询意图想要查询的目标作者的唯一作品,因此显示装置需要获取用于指示当前作品为目标作者的唯一作品的音频。比如,“现在显示的作品为目标作者的唯一作品”。此时,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频。
在第四种情况中,若作品信息查询指令不包含第二目标实体且包含第一目标实体,当前作品的作者与目标作者相同,且当前作品不为目标作者的唯一作品,则表明该目标作者还有除当前作品之外的其他作品。因此,显示装置可以 获取第一作品的图像,以及用于指示第一作品的音频,其中,第一作品为目标作者的作品中除当前作品之外的任一作品。可选地,显示装置可以在包含多幅(如300幅、400幅等)作品的作品库中随机挑选目标作者的该任一作品。比如,作者B具有作品A和作品C,且显示装置显示的当前作品为作品A,若查询意图仅包含第一目标实体“作者B”,则显示装置可以获取作品C的图像,以及用于指示作品C的音频(如为您推荐作者B的作品C)。此时,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频。
在第五种情况中,若作品信息查询指令不包含第二目标实体且包含第一目标实体,当前作品的作者与目标作者不同,则表明查询意图用于查询并非当前作品的作者的作品。此时,显示装置可以获取第二作品的图像,以及用于指示第二作品的音频,第二作品为目标作者的任一作品。示例地,假设显示装置当前显示有作者B的作品A,且作品信息查询指令包含的第一目标实体为“作者D”,则显示装置可以获取作者D的任一作品E的图像,以及用于指示作品E的音频。此时,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
在第六种情况中,若作品信息查询指令不包含第一目标实体和第二目标实体,则获取第三作品的图像,以及用于指示第三作品的音频。此时,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频。
其中,当当前作品为其作者的唯一作品时,第三作品为除当前作品的作者之外的其他作者的任一作品;当当前作品不为其作者的唯一作品时,第三作品为当前作品的作者的作品中除当前作品之外的任一作品。可选地,显示装置可以在包含多幅(如300幅、400幅等)作品的作品库中随机挑选该第三作品。需要说明的是,当查询意图并不包含第一目标实体也不包含第二目标实体时,表明查询意图只是想要点播任一作品,此时显示装置可以优先为用户显示当前作品的作者的作品。所以,在当前作品不为其作者的唯一作品时,显示装置便需要获取该作者的其他作品及其音频;在当前作品为其作者的唯一作品时,该作者并没有除当前作品之外的其他作品,此时显示装置可以获取其他作者的作品的图像。
可选地,本公开实施例不对方法步骤的前后顺序进行限定。示例地,显示装置在步骤203中确定查询意图的类型为第三类型时,显示装置可以依次执行步骤204和步骤205,并且,显示装置无需执行步骤206和步骤207。在执行完 步骤205之后,显示装置可以根据前面步骤的判断结果,确定当前情况为上述六种情况中的哪种情况,再获取这种情况中需要获取到的信息。
需要说明的是,本公开实施例中以上述方法步骤由显示装置独立完成为例,可选地,也可以是由部分步骤或全部步骤为显示装置通过其他设备完成的。示例地,上述步骤202可以是显示装置通过意图识别服务器完成的。又示例的,步骤203至步骤208可以是显示装置通过业务服务器完成的。可选地,在显示装置通过意图识别服务器执行步骤203和步骤208时,业务服务器在获取查询结果时,可以直接在业务服务器本地获取查询结果,也可以是在其他服务器上获取查询结果,本公开实施例对此不作限定。
示例地,上述作品信息查询指令可以为语音形式的指令,显示装置在获取到作品信息查询指令后,可以将作品信息查询指令发送至语义理解服务器。语义理解服务器先将该语音形式的作品信息查询指令,转换为文本形式的作品信息查询指令后,将该文本形式的作品信息查询指令发送至显示装置。之后,显示装置可以将文本形式的作品信息查询指令发送至业务服务器,业务服务器可以首先将作品信息查询指令发送至意图识别服务器。意图识别服务器在接收到该作品信息查询指令后,对该作品信息查询指令进行意图识别,得到查询意图。之后,意图识别服务器将查询意图发送至业务服务器,由业务服务器基于该查询意图执行上述步骤203至步骤208,得到查询结果。之后,再由业务服务器将该查询结果发送给显示装置,进而显示装置显示该查询结果。
可选地,业务服务器在获取查询结果时,可以在数据服务器中存储的数据库中查找图像和音频,该数据库可以包括:上述音频库和上述作品库等。当然,该业务服务器也可以在其他位置查询图像、音频和文本。业务服务器在查询到文本后,还可以通过语义理解服务器生成该文本的音频。
上述实施例中以业务服务器直接向显示装置发送查询结果为例,可选地,业务服务器也可以向显示装置发送查询结果的信息,显示装置在接收到该查询结果的信息后,可以基于该信息获取查询结果。比如,业务服务器可以向显示装置发送图像的链接,显示装置在接收到该图像的链接后,可以基于该链接获取图像。又比如,业务服务器可以向显示装置发送文本,显示装置在接收到该文本后,可以通过语义理解服务器生成该文本的音频。
可选地,上述查询意图还可以为用于控制显示装置显示上一幅或下一幅画 作的控制意图,比如表2中编号24和25对应的基础意图和槽位组成的查询意图。在查询意图为控制意图时,显示装置可以无需执行上述步骤203至步骤209,而是直接执行该控制意图用于执行的动作。比如,在查询意图为编号24对应的基础意图和槽位组成的查询意图时,显示装置可以直接显示上一幅画作;在查询意图为编号25对应的基础意图和槽位组成的查询意图时,显示装置可以直接显示下一幅画作。
综上所述,本公开实施例提供的信息查询方法中,显示装置能够在获取到作品信息查询指令后,分别确定查询意图的类型,以及得到作品信息查询指令是否包含至少一种目标实体的检测结果。并且,显示装置还能够基于包括该查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果的参考信息,获取并展示查询结果。可以看出,本公开实施例提供的显示装置能够基于参考信息实现信息的查询,因此丰富了显示装置的功能。
图3为本公开实施例提供的一种显示装置的结构示意图,本公开实施例中以该显示装置为电子画屏为例,可选地,该显示装置也可以为诸如电视机、具有显示功能的空调等。如图3所示,该显示装置30可以包括:
指令获取模块301,用于获取作品信息查询指令;
意图识别模块302,用于对作品信息查询指令进行意图识别,得到查询意图;
类型确定模块303,用于确定多种意图类型中查询意图的类型;
实体检测模块304,用于检测所述作品信息查询指令是否包含至少一种目标实体;
结果获取模块305,用于根据查询意图和参考信息获取查询结果,其中,参考信息包括:查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果,查询结果包括:图像、音频和文本中的至少一种信息;
信息展示模块306,用于展示查询结果。
综上所述,本公开实施例提供的显示装置中,类型确定模块能够在指令获取模块获取到作品信息查询指令后,确定查询意图的类型,实体检测模块能够得到作品信息查询指令是否包含至少一种目标实体的检测结果。并且,结果获取模块能够基于包括该查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果的参考信息,获取并展示查询结果。可以看出,本公开实施例提供的显示装置能够基于参考信息实现信息的查询,因此丰富了显示 装置的功能。
可选地,所述至少一种目标实体包括:包含作品的作者信息的第一目标实体,和/或,包含作品的名称信息的第二目标实体。
可选地,图4为本公开实施例提供的另一种显示装置的结构示意图,如图4所示,在图3的基础上,该显示装置30还可以包括:
作品检测模块307,用于在作品信息查询指令包含第二目标实体时,检测显示装置显示的当前作品与第二目标实体所指示的目标作品是否相同,参考信息还包括:当前作品与目标作品是否相同的检测结果。
可选地,多种意图类型包括:第一类型,所述第一类型的意图包括作品简介相关的意图,如图4所示,显示装置30还包括:
待简介作品确定模块308,用于当查询意图的类型为第一类型时,根据作品信息查询指令是否包含至少一种目标实体的检测结果确定待简介作品;其中,当作品信息查询指令至少包含第二目标实体时,待简介作品为第二目标实体所指示的目标作品;当作品信息查询指令不包含第二目标实体且包含第一目标实体时,待简介作品为第一目标实体所指示的作者的任一作品;
音频检测模块309,用于检测音频库是否包含待简介作品的简介音频,参考信息还包括音频库是否包含待简介作品的简介音频的检测结果。
可选地,结果获取模块306用于:
当查询意图的类型为第一类型时,若音频库包含简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取音频库中的简介音频,所述查询结果包括:所述简介音频;
当查询意图的类型为第一类型时,若音频库包含简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取目标作品的图像和音频库中的简介音频,所述查询结果包括:所述目标作品的图像和所述简介音频;
当查询意图的类型为第一类型时,若音频库包含简介音频,作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取音频库中的简介音频,所述查询结果包括:所述简介音频。
可选地,结果获取模块306用于:
当查询意图的类型为第一类型时,若音频库不包含简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取待简介作 品的简介文本,以及简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频;
当查询意图的类型为第一类型时,若音频库不包含简介音频,作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取待简介作品的图像及待简介作品的简介文本,以及简介文本的音频,所述查询结果包括:所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频;
当查询意图的类型为第一类型时,若音频库不包含简介音频,作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取待简介作品的简介文本,以及简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频。
可选地,多种意图类型包括:第二类型,所述第二类型的意图包括:信息组中的任一信息相关的意图,信息组包括:作者的信息,以及作品的信息中除简介之外的信息,可选地,结果获取模块306用于:
当查询意图的类型为第二类型时,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取任一信息的文本,以及任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频;
当查询意图的类型为第二类型时,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取目标作品的图像,任一信息的文本,以及任一信息的文本的音频,所述查询结果包括:所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频。
可选地,结果获取模块306用于:
当查询意图的类型为第二类型时,若作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取任一信息的文本,以及任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
可选地,多种意图类型包括:第三类型,且所述第三类型的意图包括:点播作品相关的意图,结果获取模块306用于:
当查询意图的类型为第三类型时,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品相同,则获取用于提示当前作品为目标作品的音频,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频;
当查询意图的类型为第三类型时,若作品信息查询指令至少包含第二目标实体,且当前作品与目标作品不同,则获取目标作品的图像,以及用于指示目标作品的音频,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
可选地,结果获取模块306用于:
当查询意图的类型为第三类型时,若作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断当前作品的作者与查询意图的第一目标实体所指示的目标作者是否相同;
若当前作品的作者与目标作者相同,且当前作品为目标作者的唯一作品,则获取用于指示当前作品为目标作者的唯一作品的音频,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频;
若当前作品的作者与目标作者相同,且当前作品不为目标作者的唯一作品,则获取第一作品的图像,以及用于指示第一作品的音频,第一作品为目标作者的作品中除当前作品之外的任一作品,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频;
若当前作品的作者与目标作者不同,则获取第二作品的图像,以及用于指示第二作品的音频,第二作品为目标作者的任一作品,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
可选地,结果获取模块306用于:
当查询意图的类型为第三类型时,若作品信息查询指令不包含第一目标实体和第二目标实体,则获取第三作品的图像,以及用于指示第三作品的音频,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频;
其中,当当前作品为其作者的唯一作品时,第三作品为除当前作品的作者之外的其他作者的任一作品;当当前作品不为其作者的唯一作品时,第三作品为当前作品的作者的作品中除当前作品之外的任一作品。
可选地,指令获取模块301可以包括:语音采集模块,用于通过语音采集的方式,获取语音形式的所述作品信息查询指令。
图5为本公开实施例提供的又一种显示装置的结构示意图,如图5所示,该显示装置50可以包括:处理器501、显示屏502和扬声器503。
处理器501可以用于:获取作品信息查询指令;对作品信息查询指令进行意图识别,得到查询意图;确定多种意图类型中查询意图的类型;检测所述作品信息查询指令是否包含至少一种目标实体;根据查询意图和参考信息获取查询结果,其中,参考信息包括:查询意图的类型,以及作品信息查询指令是否包含至少一种目标实体的检测结果,查询结果包括:图像、音频和文本中的至少一种信息;在所述查询结果包括所述图像时,控制所述显示屏显示所述查询结果中的图像;在所述查询结果包括所述文本时,控制所述显示屏显示所述查询结果中的文本;在所述查询结果包括所述音频时,控制所述扬声器播放所述查询结果中的音频。
可以看出,图5所示的显示装置中,处理器501可以包括图3和图4所示的显示装置中的指令获取模块301、意图识别模块302、类型确定模块303、实体检测模块304以及结果获取模块305;可选地,处理器501也可以包括图4中的作品检测模块307、待简介作品确定模块308以及音频检测模块309。图5中的显示屏502和扬声器503可以组成图3和图4中的信息展示模块306。
可选地,图5所示的显示装置还可以包括麦克风504,处理器501用于:通过所述麦克风504,获取语音形式的所述作品信息查询指令。
需要说明的是,本公开实施例提供的显示装置可以为:液晶显示装置、电子纸、有机发光二极管显示装置、手机、平板电脑、电视机、显示器、笔记本电脑、数码相框、导航仪等任何具有显示功能的产品或部件。
示例地,上述处理器501与麦克风504、扬声器503和显示屏502均连接;处理器501用于通过麦克风504接收作品信息查询指令,并根据作品信息查询指令执行以下操作中的至少一个:控制扬声器503播放语音,该语音与作品信息查询指令用于查询的内容相关;控制显示屏502显示图像和文本中的至少一个,该图像和该文本均与作品信息查询指令用于查询的内容相关。
可选地,处理器501用于:根据该作品信息查询指令确定待显示图像,在显示屏502显示的当前图像与待显示图像不同时,控制显示屏502显示待显示图像。在显示屏502显示的当前图像与待显示图像相同时,控制扬声器503播放用于提示当前图像与待显示图像相同的语音。
本申请中,“至少一个”指的是一个或多个,“多个”指的是两个或两个以上。“以下至少一项”或其类似表达,指的是这些项中的任意组合,包括单项或复数项的任意组合。例如,a,b或c中的至少一项,可以表示:a,b,c, a+b,a+c,b+c,以及a+b+c,其中,a、b、c可以是单项也可以是多项。
需要说明的是,本发明实施例提供的方法实施例能够与相应的装置实施例相互参考,本发明实施例对此不做限定。本发明实施例提供的方法实施例步骤的先后顺序能够进行适当调整,步骤也能够根据情况进行相应增减,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到变化的方法,都应涵盖在本发明的保护范围之内,因此不再赘述。
以上所述仅为本公开的可选实施例,并不用以限制本公开,凡在本公开的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本公开的保护范围之内。

Claims (17)

  1. 一种作品信息查询方法,其特征在于,用于显示装置,所述方法包括:
    获取作品信息查询指令;
    对所述作品信息查询指令进行意图识别,得到查询意图;
    确定多种意图类型中所述查询意图的类型;
    检测所述作品信息查询指令是否包含至少一种目标实体;
    根据所述查询意图和参考信息获取查询结果,其特征在于,所述参考信息包括:所述查询意图的类型,以及所述作品信息查询指令是否包含所述至少一种目标实体的检测结果,所述查询结果包括:图像、音频和文本中的至少一种信息;
    展示所述查询结果。
  2. 根据权利要求1所述的方法,其特征在于,所述至少一种目标实体包括:包含作品的作者信息的第一目标实体,和/或,包含作品的名称信息的第二目标实体。
  3. 根据权利要求2所述的方法,其特征在于,所述至少一种目标实体包括所述第二目标实体,所述方法还包括:
    在所述作品信息查询指令包含所述第二目标实体时,检测所述显示装置显示的当前作品与所述第二目标实体所指示的目标作品是否相同;
    所述参考信息还包括:所述当前作品与所述目标作品是否相同的检测结果。
  4. 根据权利要求3所述的方法,其特征在于,所述多种意图类型包括:第一类型,所述第一类型的意图包括作品简介相关的意图,在所述根据所述查询意图和参考信息获取查询结果之前,所述方法还包括:
    当所述查询意图的类型为所述第一类型时,根据所述作品信息查询指令是否包含所述至少一种目标实体的检测结果确定待简介作品;其特征在于,当所述作品信息查询指令至少包含第二目标实体时,所述待简介作品为所述第二目标实体所指示的所述目标作品;当所述作品信息查询指令不包含第二目标实体 且包含第一目标实体时,所述待简介作品为所述第一目标实体所指示的作者的任一作品;
    检测音频库是否包含所述待简介作品的简介音频,所述参考信息还包括:所述音频库是否包含所述待简介作品的简介音频的检测结果。
  5. 根据权利要求4所述的方法,其特征在于,所述根据所述查询意图和参考信息获取查询结果,包括:
    当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频;
    当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像和所述音频库中的所述简介音频,所述查询结果包括:所述目标作品的图像和所述简介音频;
    当所述查询意图的类型为所述第一类型时,若所述音频库包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述音频库中的所述简介音频,所述查询结果包括:所述简介音频。
  6. 根据权利要求4或5所述的方法,其特征在于,所述根据所述查询意图和参考信息获取查询结果,包括:
    当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频;
    当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的图像,所述待简介作品的简介文本,以及所述简介文本的音频;
    当所述查询意图的类型为所述第一类型时,若所述音频库不包含所述简介音频,所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则获取所述待简介作品的简介文本,以及所述简介文本的音频,所述查询结果包括:所述待简介作品的简介文本,以及所述简介文本的音频。
  7. 根据权利要求3至6任一所述的方法,其特征在于,所述多种意图类型包括:第二类型,所述第二类型的意图包括:信息组中的任一信息相关的意图,所述信息组包括:作者的信息,以及作品的信息中除简介之外的信息,所述根据所述查询意图和参考信息获取查询结果,包括:
    当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频;
    当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述目标作品的图像,所述任一信息的文本,以及所述任一信息的文本的音频;
    当所述查询意图的类型为所述第二类型时,若所述作品信息查询指令包含第一目标实体且不包含第二目标实体,则获取所述任一信息的文本,以及所述任一信息的文本的音频,所述查询结果包括:所述任一信息的文本,以及所述任一信息的文本的音频。
  8. 根据权利要求3至7任一所述的方法,其特征在于,所述多种意图类型包括:第三类型,且所述第三类型的意图包括:点播作品相关的意图,所述根据所述查询意图和参考信息获取查询结果,包括:
    当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品相同,则获取用于提示所述当前作品为所述目标作品的音频,所述查询结果包括:所述用于提示所述当前作品为所述目标作品的音频;
    当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令至少包含第二目标实体,且所述当前作品与所述目标作品不同,则获取所述目标作品的图像,以及用于指示所述目标作品的音频,所述查询结果包括:所述目标作品的图像,以及所述用于指示所述目标作品的音频。
  9. 根据权利要求8所述的方法,其特征在于,所述根据所述查询意图和参考信息获取查询结果,还包括:
    当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含第二目标实体且包含第一目标实体,则判断所述当前作品的作者与所述查询意图的第一目标实体所指示的目标作者是否相同;
    若所述当前作品的作者与所述目标作者相同,且所述当前作品为所述目标作者的唯一作品,则获取用于指示所述当前作品为所述目标作者的唯一作品的音频,所述查询结果包括:所述用于指示所述当前作品为所述目标作者的唯一作品的音频;
    若所述当前作品的作者与所述目标作者相同,且所述当前作品不为所述目标作者的唯一作品,则获取第一作品的图像,以及用于指示所述第一作品的音频,所述第一作品为所述目标作者的作品中除所述当前作品之外的任一作品,所述查询结果包括:所述第一作品的图像,以及用于指示所述第一作品的音频;
    若所述当前作品的作者与所述目标作者不同,则获取第二作品的图像,以及用于指示所述第二作品的音频,所述第二作品为所述目标作者的任一作品,所述查询结果包括:所述第二作品的图像,以及用于指示所述第二作品的音频。
  10. 根据权利要求8或9所述的方法,其特征在于,所述根据所述查询意图和参考信息获取查询结果,还包括:
    当所述查询意图的类型为所述第三类型时,若所述作品信息查询指令不包含所述第一目标实体和所述第二目标实体,则获取第三作品的图像,以及用于指示所述第三作品的音频,所述查询结果包括:所述第三作品的图像,以及所述用于指示所述第三作品的音频;
    其特征在于,当所述当前作品为其作者的唯一作品时,所述第三作品为除所述当前作品的作者之外的其他作者的任一作品;当所述当前作品不为其作者 的唯一作品时,所述第三作品为所述当前作品的作者的作品中除所述当前作品之外的任一作品。
  11. 根据权利要求1至10任一所述的方法,其特征在于,所述获取作品信息查询指令,包括:
    通过语音采集的方式,获取语音形式的所述作品信息查询指令。
  12. 根据权利要求1至11任一所述的方法,其特征在于,所述作品包括:画作。
  13. 一种显示装置,其特征在于,所述显示装置包括:处理器、显示屏和扬声器;
    所述处理器用于:
    获取作品信息查询指令;
    对所述作品信息查询指令进行意图识别,得到查询意图;
    确定多种意图类型中所述查询意图的类型;
    检测所述作品信息查询指令是否包含至少一种目标实体;
    根据所述查询意图和参考信息获取查询结果,其特征在于,所述参考信息包括:所述查询意图的类型,以及所述作品信息查询指令是否包含所述至少一种目标实体的检测结果,所述查询结果包括:图像、音频和文本中的至少一种信息;
    在所述查询结果包括所述图像时,控制所述显示屏显示所述查询结果中的图像;
    在所述查询结果包括所述文本时,控制所述显示屏显示所述查询结果中的文本;
    在所述查询结果包括所述音频时,控制所述扬声器播放所述查询结果中的音频。
  14. 根据权利要求13所述的显示装置,其特征在于,所述显示装置还包括:麦克风,所述处理器用于:
    通过所述麦克风,获取语音形式的所述作品信息查询指令。
  15. 一种显示装置,其特征在于,所述显示装置包括:麦克风、扬声器、显示屏和处理器,所述处理器与所述麦克风、所述扬声器和所述显示屏均连接;
    所述处理器用于通过所述麦克风接收作品信息查询指令,并根据所述作品信息查询指令执行以下操作中的至少一个:
    控制所述扬声器播放语音,所述语音与所述作品信息查询指令用于查询的内容相关;
    控制所述显示屏显示图像和文本中的至少一个,所述图像和所述文本均与所述作品信息查询指令用于查询的内容相关。
  16. 根据权利要求15所述的显示装置,其特征在于,所述处理器用于:根据所述作品信息查询指令确定待显示图像,在所述显示屏显示的当前图像与待显示图像不同时,控制所述显示屏显示所述待显示图像。
  17. 根据权利要求15或16所述的显示装置,其特征在于,所述处理器用于:根据所述作品信息查询指令确定待显示图像,在所述显示屏显示的当前图像与待显示图像相同时,控制所述扬声器播放用于提示所述当前图像与所述待显示图像相同的语音。
PCT/CN2019/108720 2019-09-27 2019-09-27 信息查询方法及显示装置 WO2021056467A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/CN2019/108720 WO2021056467A1 (zh) 2019-09-27 2019-09-27 信息查询方法及显示装置
US17/046,321 US11782976B2 (en) 2019-09-27 2019-09-27 Method for querying information and display device
CN201980001847.2A CN110799973B (zh) 2019-09-27 2019-09-27 信息查询方法及显示装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/108720 WO2021056467A1 (zh) 2019-09-27 2019-09-27 信息查询方法及显示装置

Publications (1)

Publication Number Publication Date
WO2021056467A1 true WO2021056467A1 (zh) 2021-04-01

Family

ID=69448492

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/108720 WO2021056467A1 (zh) 2019-09-27 2019-09-27 信息查询方法及显示装置

Country Status (3)

Country Link
US (1) US11782976B2 (zh)
CN (1) CN110799973B (zh)
WO (1) WO2021056467A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130282702A1 (en) * 2012-04-18 2013-10-24 Yahoo! Inc. Method and system for search assistance
CN108170859A (zh) * 2018-01-22 2018-06-15 北京百度网讯科技有限公司 语音查询的方法、装置、存储介质及终端设备
CN109547840A (zh) * 2018-12-03 2019-03-29 深圳创维数字技术有限公司 影视作品搜索引导方法、电视及计算机可读存储介质
CN109783736A (zh) * 2019-01-18 2019-05-21 广东小天才科技有限公司 一种意图推测方法及系统

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7310600B1 (en) * 1999-10-28 2007-12-18 Canon Kabushiki Kaisha Language recognition using a similarity measure
US10120909B2 (en) * 2014-08-22 2018-11-06 Facebook, Inc. Generating cards in response to user actions on online social networks
US20160085800A1 (en) * 2014-09-23 2016-03-24 United Video Properties, Inc. Systems and methods for identifying an intent of a user query
US10776700B2 (en) * 2015-09-10 2020-09-15 Senseforth, Inc. Method and system for automatic resolution of user queries
US10489393B1 (en) * 2016-03-30 2019-11-26 Amazon Technologies, Inc. Quasi-semantic question answering
US11182840B2 (en) 2016-11-18 2021-11-23 Walmart Apollo, Llc Systems and methods for mapping a predicted entity to a product based on an online query
US20180276553A1 (en) * 2017-03-22 2018-09-27 Cisco Technology, Inc. System for querying models
US20180322155A1 (en) * 2017-05-05 2018-11-08 Microsoft Technology Licensing, Llc Search system for temporally relevant social data
US11016964B1 (en) * 2017-09-12 2021-05-25 Amazon Technologies, Inc. Intent determinations for content search
US10832219B2 (en) * 2017-12-22 2020-11-10 Microsoft Technology Licensing, Llc Using feedback to create and modify candidate streams
RU2711104C2 (ru) * 2017-12-27 2020-01-15 Общество С Ограниченной Ответственностью "Яндекс" Способ и компьютерное устройство для определения намерения, связанного с запросом для создания зависящего от намерения ответа
CN108683937B (zh) * 2018-03-09 2020-01-21 百度在线网络技术(北京)有限公司 智能电视的语音交互反馈方法、系统及计算机可读介质
CN108804532B (zh) 2018-05-03 2020-06-26 腾讯科技(深圳)有限公司 一种查询意图的挖掘和查询意图的识别方法、装置
CN110008413B (zh) 2019-03-14 2023-11-10 海信集团有限公司 一种交通出行问题查询方法和装置
US11636102B2 (en) * 2019-09-05 2023-04-25 Verizon Patent And Licensing Inc. Natural language-based content system with corrective feedback and training

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130282702A1 (en) * 2012-04-18 2013-10-24 Yahoo! Inc. Method and system for search assistance
CN108170859A (zh) * 2018-01-22 2018-06-15 北京百度网讯科技有限公司 语音查询的方法、装置、存储介质及终端设备
CN109547840A (zh) * 2018-12-03 2019-03-29 深圳创维数字技术有限公司 影视作品搜索引导方法、电视及计算机可读存储介质
CN109783736A (zh) * 2019-01-18 2019-05-21 广东小天才科技有限公司 一种意图推测方法及系统

Also Published As

Publication number Publication date
CN110799973A (zh) 2020-02-14
CN110799973B (zh) 2024-04-19
US11782976B2 (en) 2023-10-10
US20230121168A1 (en) 2023-04-20

Similar Documents

Publication Publication Date Title
US11580120B2 (en) Methods and apparatus for determining a mood profile associated with media data
US11657084B2 (en) Correlating image annotations with foreground features
WO2018072071A1 (zh) 知识图谱构建系统及方法
US20170199943A1 (en) User interface for multivariate searching
US20140325408A1 (en) Apparatus and method for providing musical content based on graphical user inputs
US11157542B2 (en) Systems, methods and computer program products for associating media content having different modalities
WO2018034028A1 (ja) 情報処理装置、情報処理方法、およびプログラム
US20140172431A1 (en) Music playing system and music playing method based on speech emotion recognition
TWI499289B (zh) 媒體內容推薦方法及媒體播放系統
US9652534B1 (en) Video-based search engine
WO2019034026A1 (zh) 基于情绪识别的艺术品推荐方法、装置、介质和电子设备
US20210165624A1 (en) Content prioritization for a display array
WO2021196610A1 (zh) 一种设备推荐方法、装置、电子设备及可读存储介质
US9189984B2 (en) Apparatus and methods for arranging media items in a physical space based on personal profiles
US20130276039A1 (en) Characteristic karaoke vod system and operating process thereof
US20200234045A1 (en) Visual Menu
CN108476336A (zh) 识别内容频道的听众的查看特性
TW202207049A (zh) 搜索方法、電子裝置及非暫時性電腦可讀記錄媒體
JP2019036191A (ja) 判定装置、判定方法及び判定プログラム
US20150189166A1 (en) Method, device and system for improving the quality of photographs
US20160026613A1 (en) Processing image to identify object for insertion into document
WO2021056467A1 (zh) 信息查询方法及显示装置
WO2017071212A1 (zh) 常用联系人的推荐处理方法及装置
US9451321B2 (en) Content management with biometric feature recognition
CN111753107A (zh) 资源展示方法、装置、设备及存储介质

Legal Events

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

Ref document number: 19947003

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19947003

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19947003

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 28.09.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19947003

Country of ref document: EP

Kind code of ref document: A1