Search

CN-121979476-A - Display device, method and related apparatus

CN121979476ACN 121979476 ACN121979476 ACN 121979476ACN-121979476-A

Abstract

The embodiment of the application provides display equipment, a method and a related device, which relate to the technical field of display and comprise the steps of performing preliminary recognition on voices collected by a sound collecting device and communicated by users under a scene of multi-user discussion, acquiring the travel intention of each user when travel related information is included in a recognition result, generating travel recommendation information based on the travel intention of each user, and controlling a display screen to display the travel recommendation information. The travel requirements of the user can be recognized based on the communication voice of the user, and a travel scheme considering personalized requirements of family members can be generated through a recommendation algorithm. Finally, the multi-user collaborative decision is realized through large screen display, and the efficiency and the accuracy of travel planning are obviously improved.

Inventors

  • GU YUANJUN
  • JIN FENG
  • ZHAO WEI

Assignees

  • 深圳泰力维智能科技有限公司

Dates

Publication Date
20260505
Application Date
20260127

Claims (12)

  1. 1. A display device, the display device comprising: A display screen configured to display a screen; a sound collection device configured to collect sound; A controller coupled to the display screen, the controller configured to: under the scene of multi-person discussion, the voice collection equipment collects the voice communicated by the user for preliminary recognition; When the identification result is determined to comprise travel related information, acquiring the travel intention of each user; generating travel recommendation information based on the travel intention of each user; and controlling the display screen to display the travel recommendation information.
  2. 2. The display device of claim 1, wherein the controller is configured to: Dividing the voice into a plurality of voice fragments, wherein each voice fragment comprises the voice of only one user; clustering the voice fragments to obtain clustering fragments respectively corresponding to each user, and sequencing the clustering fragments based on time sequence to obtain target voice fragments respectively corresponding to each user; and respectively carrying out intention recognition on the target voice fragments of each user to obtain the travel intention of each user.
  3. 3. The display device of claim 2, wherein the controller is configured to: performing voice recognition on the target voice fragment to obtain a text corresponding to the target voice fragment; performing intention recognition on the text to obtain a first travel intention; Intent reasoning is carried out on the text based on the travel knowledge graph, and a second travel intent implied by the text is obtained; And fusing the first travel intention and the second travel intention to obtain the travel intention.
  4. 4. A display device according to claim 3, wherein the controller is configured to: Acquiring entities related to the text and travel; Mapping the entity to a corresponding node in the travel knowledge graph, and starting from the node, reasoning based on the historical travel information of the user to obtain the second travel intention.
  5. 5. The display device of claim 4, wherein the controller is configured to: aligning the first intent to travel with the second intent to travel; if the first travel intention and the second travel intention are matched with each other, supplementing the second travel intention based on the second travel intention to obtain the travel intention; and if the first travel intention and the second travel intention conflict, correcting the first travel intention based on the second travel intention to obtain the travel intention.
  6. 6. The display device of claim 5, wherein the controller is configured to: acquiring voiceprint characteristics of each user, and determining identity of each user based on the voiceprint characteristics; Determining the weight of the travel intention corresponding to each user according to the identity; Determining travel claims corresponding to all users respectively according to the weight and the travel intention; constructing a travel recommendation network based on travel claims respectively corresponding to all users, and determining group travel consensus vectors of all users based on the travel recommendation network; And generating the travel recommendation information based on the group travel consensus vector.
  7. 7. The display device of claim 6, wherein the controller is configured to: determining the degree of dispute in each dimension in the group travel consensus vector; generating a first recommendation option based on the corresponding dimension consensus when the dispute degree is less than or equal to a preset value; generating a plurality of second recommendation options based on the corresponding dimensional disputes when the degree of dispute is greater than the preset value; and merging the first recommendation options and the plurality of second recommendation options to obtain the travel recommendation information.
  8. 8. The display device of any one of claims 1-7, wherein the controller is configured to: acquiring the current environment state and display content; Determining a target moment for displaying the travel recommendation information based on the environment state and the display content; And controlling the display screen to display the travel recommendation information at the target moment.
  9. 9. The display device of claim 8, wherein the controller is configured to: acquiring a feedback instruction of a user on the travel recommendation information; and adjusting the travel recommendation information based on the feedback instruction.
  10. 10. A display method, comprising: under the scene of multi-person discussion, collecting the voice communicated by the user, and carrying out content recognition on the voice; When determining that the content identification result comprises travel related information, acquiring the travel intention of each user; generating travel recommendation information based on the travel intention of each user; and controlling the display screen to display the travel recommendation information.
  11. 11. A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor to implement the method of claim 10.
  12. 12. A computer program product comprising a computer program which, when executed by a controller, implements the method of claim 10.

Description

Display device, method and related apparatus Technical Field The present application relates to the field of display, and in particular, to a display device, a method and a related apparatus. Background When planning a tour, a user usually inputs keywords through a mobile phone, and the system can match and recommend a tour plan based on the keywords and display a recommendation result through the mobile phone. When the recommendation result is required to be checked by multiple persons, the mobile phone needs to be rotated or forwarded through social software, so that the efficiency of the collaborative discussion of the multiple persons is low, and the experience of the user is poor. Disclosure of Invention The embodiment of the application provides a display device, a display method and a related device, which are used for achieving the effect of improving efficiency and accuracy of travel recommendation. In a first aspect, an embodiment of the present application provides a display apparatus, including: A display screen configured to display a screen; a sound collection device configured to collect sound; A controller coupled to the display screen, the controller configured to: under the scene of multi-person discussion, the voice collection equipment collects the voice communicated by the user for preliminary recognition; When the identification result is determined to comprise travel related information, acquiring the travel intention of each user; generating travel recommendation information based on the travel intention of each user; and controlling the display screen to display the travel recommendation information. In some embodiments, the controller is configured to: Dividing the voice into a plurality of voice fragments, wherein each voice fragment comprises the voice of only one user; Clustering the voice fragments to obtain clustering fragments respectively corresponding to each user, and sequencing the clustering fragments based on time sequence to obtain target voice fragments respectively corresponding to each user. And respectively carrying out intention recognition on the target voice fragments of each user to obtain the travel intention of each user. In some embodiments, the controller is configured to: performing voice recognition on the target voice fragment to obtain a text corresponding to the target voice fragment; performing intention recognition on the text to obtain a first travel intention; Intent reasoning is carried out on the text based on the travel knowledge graph, and a second travel intent implied by the text is obtained; And fusing the first travel intention and the second travel intention to obtain the travel intention. In some embodiments, the controller is configured to: Acquiring entities related to the text and travel; Mapping the entity to a corresponding node in the travel knowledge graph, and starting from the node, reasoning based on the historical travel information of the user to obtain the second travel intention. In some embodiments, the controller is configured to: aligning the first intent to travel with the second intent to travel; if the first travel intention and the second travel intention are matched with each other, supplementing the second travel intention based on the second travel intention to obtain the travel intention; And if the first travel intention and the second travel intention conflict, correcting the first travel intention based on the second travel intention to obtain the travel intention. In some embodiments, the controller is configured to: acquiring voiceprint characteristics of each user, and determining identity of each user based on the voiceprint characteristics; Determining the weight of the travel intention corresponding to each user according to the identity; Determining travel claims corresponding to all users respectively according to the weight, the travel intention and the identity; constructing a travel recommendation network based on travel claims respectively corresponding to all users, and determining group travel consensus vectors of all users based on the travel recommendation network; And generating the travel recommendation information based on the group travel consensus vector. In some embodiments, the controller is configured to: determining the degree of dispute in each dimension in the group travel consensus vector; generating a first recommendation option based on the corresponding dimension consensus when the dispute degree is less than or equal to a preset value; generating a plurality of second recommendation options based on the corresponding dimensional disputes when the degree of dispute is greater than the preset value; and merging the first recommendation options and the plurality of second recommendation options to obtain the travel recommendation information. In some embodiments, the controller is configured to: acquiring the current environment state and display content; Determining a target moment