WO2019179409A1 - 一种多维视觉导购系统和方法 - Google Patents

一种多维视觉导购系统和方法 Download PDF

Info

Publication number
WO2019179409A1
WO2019179409A1 PCT/CN2019/078624 CN2019078624W WO2019179409A1 WO 2019179409 A1 WO2019179409 A1 WO 2019179409A1 CN 2019078624 W CN2019078624 W CN 2019078624W WO 2019179409 A1 WO2019179409 A1 WO 2019179409A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
shopping guide
signal
voice
intelligent
Prior art date
Application number
PCT/CN2019/078624
Other languages
English (en)
French (fr)
Inventor
李新福
Original Assignee
广东康云多维视觉智能科技有限公司
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 广东康云多维视觉智能科技有限公司 filed Critical 广东康云多维视觉智能科技有限公司
Publication of WO2019179409A1 publication Critical patent/WO2019179409A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0281Customer communication at a business location, e.g. providing product or service information, consulting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16Constructional details or arrangements
    • G06F1/1601Constructional details related to the housing of computer displays, e.g. of CRT monitors, of flat displays
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0269Targeted advertisements based on user profile or attribute
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/01Indexing scheme relating to G06F3/01
    • G06F2203/011Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/01Indexing scheme relating to G06F3/01
    • G06F2203/012Walk-in-place systems for allowing a user to walk in a virtual environment while constraining him to a given position in the physical environment

Definitions

  • the invention relates to the field of intelligent control, in particular to a multi-dimensional visual shopping guide system and method.
  • an object of the present invention is to provide a multi-dimensional visual shopping guide system and method with low cost, all-weather and user experience.
  • a multi-dimensional visual shopping guide system comprising:
  • An input module configured to acquire at least one input signal of a user, where the input signal includes an image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal;
  • the intelligent shopping guide module is configured to perform smart shopping guide according to the at least one input signal, where the smart shopping guide includes a user's eye tracking, a user's voice recognition, an AI smart voice presentation, and a virtual model display control of the item;
  • An air display screen for displaying a virtual model of an item by means of air imaging.
  • a display cabinet is disposed, and the air display screen is disposed on a composition plane of the display cabinet.
  • the display cabinet is provided with a booth for placing a real model of the article or article.
  • the display cabinet is further provided with an ambience light and a status indicator, and the input end of the ambient light and the input end of the status indicator are connected to the output end of the intelligent shopping guide module.
  • the display cabinet is further provided with a power module and a speaker, and an output end of the power module is connected to an input end of the intelligent shopping guide module, and an output end of the intelligent shopping guide module is connected to an input end of the speaker.
  • the smart shopping guide module comprises:
  • a gesture recognition unit configured to identify a gesture of the user according to the acquired gesture signal
  • a voice intercom unit configured to identify a voice instruction of the user according to the acquired voice signal
  • An image recognition unit configured to perform eye tracking and facial expression recognition according to the acquired image signal
  • a brain wave signal recognition unit configured to identify a brain wave of the user according to the acquired brain wave signal
  • a touch signal recognition unit configured to identify a touch instruction of the user according to the acquired touch signal
  • the analyzing unit is configured to perform a shopping guide intelligent analysis according to at least one of a gesture of the user, a voice instruction of the user, a result of eye tracking and facial expression recognition, a brain wave of the user, and a touch instruction of the user;
  • the AI unit is configured to perform AI intelligent control and AI intelligent voice announcement of the item on the virtual model of the item according to the result of the shopping guide intelligent analysis, wherein the AI intelligent control includes zoom control, view switching control and color change control of the virtual model of the item.
  • the smart shopping guide module further includes:
  • a selection unit for the user to select at least one of a color, a type, a size, a size, and a brand of the item
  • a two-dimensional code payment unit configured to perform payment by scanning a two-dimensional code after the user selects an item to be purchased
  • the storage unit is configured to store the gesture of the user, the voice instruction of the user, the result of the eye tracking and facial expression recognition, the brain wave of the user, the touch instruction of the user, the result of the smart analysis of the shopping guide, and the AI smart voice presentation content.
  • the smart shopping guide module is further connected with a background server, which is used for remote communication with the intelligent shopping guide module, remotely stores the virtual model of the AI intelligent voice presentation content and the item, and remotely controls the display of the air display screen through the intelligent shopping guide module.
  • a background server which is used for remote communication with the intelligent shopping guide module, remotely stores the virtual model of the AI intelligent voice presentation content and the item, and remotely controls the display of the air display screen through the intelligent shopping guide module.
  • Content and big data analysis based on data from the Smart Shopping Module is used for remote communication with the intelligent shopping guide module, remotely stores the virtual model of the AI intelligent voice presentation content and the item, and remotely controls the display of the air display screen through the intelligent shopping guide module.
  • the input module includes at least one of a camera, a touch screen, a somatosensory device, a voice collection module, and a brain wave acquisition device.
  • a multi-dimensional visual shopping method includes the following steps:
  • the input signal including an image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal;
  • the smart guide including user's eye tracking, user's voice recognition, AI smart voice announcement, and virtual model display control of the item;
  • the virtual model of the item is displayed by air imaging on the air display screen based on the results of the smart shopping guide.
  • the invention has the beneficial effects that the multi-dimensional visual shopping guide system and method of the present invention performs intelligent shopping guide according to at least one of a user's image signal, touch signal, gesture signal, voice signal and brain wave letter, and the intelligent shopping guide includes the user's Speech recognition and AI intelligent voice presentation, through the user's voice recognition and AI intelligent voice presentation, no need for shopping guides to provide users with 24-hour all-weather product explanation and object consulting services according to the needs of users, reducing the management cost of shopping guides and not Limited by the size of the customer, the service quality is high and the user experience is good; the intelligent shopping guide includes the user's eye tracking, the user's voice recognition, the AI smart voice announcement and the virtual model display control of the item, and the user's attention focus and user are identified through the intelligent shopping guide.
  • the voice command can perform corresponding AI intelligent voice announcement for the user and use the air imaging technology on the air display screen according to the user's image signal, touch signal, gesture signal, voice signal or brain wave signal while the AI voice is being explained.
  • Dynamically display the corresponding items 360 degrees without dead ends The proposed model, more intuitive, dimension, richer and more interactive, greatly increased the attractiveness to customers.
  • FIG. 1 is a block diagram showing the overall structure of a multi-dimensional visual shopping guide system according to the present invention
  • FIG. 2 is a flow chart of steps of a multi-dimensional visual shopping method according to the present invention.
  • FIG. 3 is a block diagram of an internal module of the intelligent shopping guide module of the present invention.
  • FIG. 4 is a schematic structural view of a specific embodiment of a multi-dimensional visual shopping guide system according to the present invention.
  • FIG. 5 is a flow chart of a specific embodiment of a multi-dimensional visual shopping method according to the present invention.
  • a multi-dimensional visual shopping guide system of the present invention includes:
  • An input module configured to acquire at least one input signal of a user, where the input signal includes an image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal;
  • the intelligent shopping guide module is configured to perform smart shopping guide according to the at least one input signal, where the smart shopping guide includes a user's eye tracking, a user's voice recognition, an AI smart voice presentation, and a virtual model display control of the item;
  • An air display screen for displaying a virtual model of an item by means of air imaging.
  • a display cabinet is further disposed, and the air display screen is disposed on a composition plane of the display cabinet.
  • the display cabinet is provided with a booth for placing a real model of the item or item.
  • the display cabinet is further provided with an ambient light and a status indicator, and the input end of the ambient light and the input end of the status indicator are connected to the output end of the intelligent shopping guide module.
  • the display cabinet is further provided with a power module and a speaker, and an output end of the power module is connected to an input end of the intelligent shopping guide module, and an output end of the intelligent shopping guide module is connected to an input end of the speaker. .
  • the smart shopping guide module includes:
  • a gesture recognition unit configured to identify a gesture of the user according to the acquired gesture signal
  • a voice intercom unit configured to identify a voice instruction of the user according to the acquired voice signal
  • An image recognition unit configured to perform eye tracking and facial expression recognition according to the acquired image signal
  • a brain wave signal recognition unit configured to identify a brain wave of the user according to the acquired brain wave signal
  • a touch signal recognition unit configured to identify a touch instruction of the user according to the acquired touch signal
  • the analyzing unit is configured to perform a shopping guide intelligent analysis according to at least one of a gesture of the user, a voice instruction of the user, a result of eye tracking and facial expression recognition, a brain wave of the user, and a touch instruction of the user;
  • the AI unit is configured to perform AI intelligent control and AI intelligent voice announcement of the item on the virtual model of the item according to the result of the shopping guide intelligent analysis, wherein the AI intelligent control includes zoom control, view switching control and color change control of the virtual model of the item.
  • the smart shopping guide module further includes:
  • a selection unit for the user to select at least one of a color, a type, a size, a size, and a brand of the item
  • a two-dimensional code payment unit configured to perform payment by scanning a two-dimensional code after the user selects an item to be purchased
  • the storage unit is configured to store the gesture of the user, the voice instruction of the user, the result of the eye tracking and facial expression recognition, the brain wave of the user, the touch instruction of the user, the result of the smart analysis of the shopping guide, and the AI smart voice presentation content.
  • the smart shopping guide module is further connected with a background server, and the background server is configured to remotely communicate with the smart shopping guide module, and remotely store the virtual model of the AI smart voice presentation content and the item, through the smart
  • the shopping guide module remotely controls the display content of the air display screen and performs big data analysis according to the data of the intelligent shopping guide module.
  • the input module includes at least one of a camera, a touch screen, a somatosensory device, a voice collection module, and a brain wave acquisition device.
  • a multi-dimensional visual shopping method of the present invention includes the following steps:
  • the input signal including an image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal;
  • the smart guide including user's eye tracking, user's voice recognition, AI smart voice announcement, and virtual model display control of the item;
  • the virtual model of the item is displayed by air imaging on the air display screen based on the results of the smart shopping guide.
  • the embodiment provides a multi-dimensional visual shopping guide system, which mainly includes an input module, an intelligent shopping guide module, a power module, a background server, and an air display screen disposed on one side of the display cabinet.
  • the display cabinet is composed of a plurality of planes and/or curved surfaces.
  • the display cabinet may be a rectangular parallelepiped composed of six planes.
  • the display case may be a variant of a rectangular parallelepiped, such as in a cuboid, with one face formed by a curved surface.
  • the display case can be in the shape of other polyhedrons.
  • the space enclosed by the plurality of faces of the display cabinet may be a closed space or an open space, such as a cuboid with an open top.
  • a display stand for the real model of the item or item is placed in the display case.
  • the air display screen is disposed on a composition plane of the display cabinet, and the air display screen may be a transparent liquid crystal touch screen or the like.
  • the air display screen may be a flat screen or a curved screen.
  • the air display screen is configured to display a virtual model of at least one item, which is a virtual two-dimensional or three-dimensional model of a product for sale (such as a car, etc.), that is, a model generated by an image processing software in a computer.
  • the air display screen can also be used to display two-dimensional images or text.
  • the display cabinet has a plurality of faces that are air display screens that can display a virtual model of the item in different directions.
  • a portion of the air display screen may display information other than a virtual model, such as a two-dimensional image, a textual introduction, a product LOGO, and the like.
  • the air display screen has two working modes: one is a standby working mode, and the air display screen can display a dynamic advertisement or a game video waiting machine screen; the other is a shopping guide mode, and the air display screen can be Provide users with intelligent shopping guide services.
  • the air display screen can also provide corresponding software buttons on the display interface for the user to select, such as a work mode/standby mode switch button, a two-dimensional code pay button, a color switch button, a view switch button, and the like.
  • the input module is configured to acquire at least one input signal of the user to facilitate interaction with the user.
  • the input module of this embodiment may include a camera, a touch screen, a somatosensory device, a voice collection module, and a brain wave acquisition device.
  • a camera that captures images of users mainly potential customers who need to purchase goods.
  • the camera can adopt an RGB-D camera capable of simultaneously acquiring two-dimensional face image information and depth information to obtain a more accurate user image.
  • a somatosensory device for capturing a user's gesture signal (such as a signal for capturing an item for viewing angle switching, etc.).
  • the somatosensory device may be a Kinect somatosensory sensor.
  • a voice collection module is used to collect voice signals of users.
  • the user's voice signal may be a voice command signal of a user such as "opening the door”, “turning on the interior air conditioner", "changing the body color to black”.
  • the voice collection module may be a voice collection device such as a pickup or a microphone.
  • the brain wave collecting device is used for collecting the brain wave signal of the user, so as to recognize the user's thought or thought.
  • the brain wave acquisition device can be implemented by using a TGAM module or other brain wave sensors.
  • a touch screen is used for a user to input a touch instruction by means of a touch.
  • the touch screen can be attached to the air display screen or combined with the air display screen.
  • the intelligent shopping guide module is configured to receive an image signal, a gesture signal, a voice signal, a touch signal, and a brain wave signal of the user, and perform according to at least one of a user image signal, a gesture signal, a voice signal, a touch signal, and a brain wave signal.
  • the intelligent shopping guide includes the user's eye tracking, the user's facial expression recognition, the user's voice instruction recognition, the user's brain wave, the touch command recognition, the AI smart voice presentation, and the virtual model display control of the item.
  • the intelligent shopping guide module is the core of the whole system, and can provide users with multi-dimensional, multi-view and interactive intelligent shopping guide services.
  • the user's eye tracking is mainly to identify the focus of the user's attention (when seeing the part of interest, the user's eyeball will be different from the case where the attention part is not seen, such as the time of eyeball staying), so as to facilitate the air display screen.
  • Directly switching the virtual model of the item to the focus of the user's attention (such as identifying the user's attention to the car's body, then directly switching to the virtual model of the car body);
  • the user's facial expression recognition mainly to identify the user's current mood (such as happy, not Happy, etc.), the recognition of both is based on the image captured by the camera.
  • the user's voice command recognition is mainly for recognizing the voice commands contained in the user's voice signal, so as to perform corresponding operations on the virtual model displayed on the air display screen, such as color switching.
  • the touch signal is used to identify the user's touch command, so as to perform corresponding operations on the virtual model displayed on the air display screen, such as color switching.
  • Brain wave recognition mainly recognizes the user's thoughts or ideas, so as to perform corresponding operations on the virtual model displayed on the air display screen, such as color switching.
  • AI intelligent voice announcement means that the AI model obtained by machine learning training serves as the role of the existing shopping guide, and provides detailed introduction and explanation of the corresponding items according to the user's instructions or the needs of the user.
  • the AI model can provide customers with corresponding presentation services 24 hours a day, similar to chat robots but smarter, greatly reducing the number of shopping guides.
  • the virtual model display control of the item mainly includes zoom control of the virtual model of the item, view switching control, color change control, and the like.
  • the data of the virtual model of the item may be stored in a smart shopping guide module.
  • the data of the virtual model of the item may be downloaded to the smart shopping guide module via the Internet, WIFI or USB interface in real time or non-real time.
  • the smart shopping guide module can transmit data through the wired or wireless manner between the input module and the air display screen, including but not limited to HDMI, VGA, USB, WIFI, Bluetooth, and infrared signals.
  • the intelligent shopping guide module is provided with a display driving module for driving the air display screen, and is powered by the power module.
  • the smart shopping guide module can be software, hardware, firmware, and combinations thereof.
  • the smart shopping guide module can be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a smart watch, a computer, an industrial computer, and the like.
  • the specific component units in the intelligent shopping guide module mainly include a gesture recognition unit, a voice intercom unit, an image recognition unit, an electroencephalogram signal recognition unit, a touch signal recognition unit, an analysis unit, and an AI unit.
  • a gesture recognition unit configured to identify a gesture of the user according to the acquired gesture signal
  • a voice intercom unit configured to identify a voice instruction of the user according to the acquired voice signal
  • an image recognition unit configured to perform an eye according to the acquired image signal
  • the tracking and facial expression recognition unit is configured to identify a brain wave of the user according to the acquired brain wave signal
  • the touch signal recognition unit is configured to identify the touch instruction of the user according to the acquired touch signal.
  • the analyzing unit is configured to perform a shopping guide intelligent analysis according to at least one of a gesture of the user, a voice instruction of the user, a result of eye tracking and facial expression recognition, a brain wave of the user, and a touch instruction of the user.
  • the intelligent analysis of the shopping guide includes the user's eye movements, facial expressions, voice commands, touch commands, meanings represented by the somatosensory gestures (such as gestures that require color switching), ideas or ideas, and AI voice explanations. content.
  • the AI unit is configured to perform AI intelligent control and AI intelligent voice presentation of the item on the virtual model of the item according to the result of the shopping guide intelligent analysis.
  • the AI smart voice announcement of the item is based on the detailed content (such as history, sales volume, performance, features, and after-sales service) pre-stored in the smart shopping guide module or obtained from the Internet, and the user can touch, gesture, and voice. Choose or get what you need to know.
  • the AI intelligent control includes zoom control, viewing angle switching control, and color shift control of the virtual model of the item. For example, the AI smart control can enlarge or reduce the virtual model according to input signals such as a user's gesture or voice.
  • the smart shopping guide module may further include a selection unit for the user to select at least one of a color, a type, a size, a size, and a brand of the item to implement a personalized shopping guide service.
  • the smart shopping guide module may further include a two-dimensional code payment unit, and when the user selects an item to be purchased, the two-dimensional code payment unit can generate or present on the air display screen for payment and link to the first A two-dimensional code for a three-party payment platform (such as WeChat payment platform) for users to conduct flexible and convenient payment operations.
  • a three-party payment platform such as WeChat payment platform
  • the smart shopping guide module may further include a storage unit that stores a gesture of the user, a voice instruction of the user, a result of eye tracking and facial expression recognition, a brain wave of the user, a touch instruction of the user, and a shopping guide.
  • a storage unit that stores a gesture of the user, a voice instruction of the user, a result of eye tracking and facial expression recognition, a brain wave of the user, a touch instruction of the user, and a shopping guide.
  • the smart shopping guide module may also be connected with a background server for remotely communicating with the intelligent shopping guide module, remotely storing the virtual model of the AI smart voice presentation content and the item, and remotely controlling the air display through the intelligent shopping guide module.
  • the display content of the screen and the big data analysis (such as user behavior analysis, mood analysis, etc.) according to the data of the intelligent shopping guide module.
  • the multi-dimensional visual shopping system can also include a support structure for securing the display case.
  • the support structure may be a cabinet, a bracket or a hanger, and the like.
  • the support structure is not limited to a specific shape or structure, and the air display screen may be mounted upward or mounted on the side that is easy to display.
  • the embodiment shows a specific structure of a multi-dimensional visual shopping guide system, which includes a display cabinet 100, an air display screen 200, and a smart shopping guide module (including an analysis unit 301, a display driving module 302, and a power supply module 303).
  • the support structure 400 (the support structure in this embodiment is a cabinet), the horn 500, the status indicator light, and the ambience light 600.
  • the smart shopping guide module and the horn 500 are both mounted inside the support structure 400, and the display cabinet 100 is embedded in the support structure 400.
  • the air display screen 200 constitutes one of the faces of the display case 100.
  • the status indicator and ambient light 600 are both mounted on the upper edge of the support structure 400, and the status indicator is used to indicate the status of the air display screen (such as standby or operational status).
  • the ambient light 400 can have multiple functions, and the main function is to enhance the lighting effect of the multi-dimensional visual shopping guide system.
  • FIG. 4 it can be seen that the plurality of faces of the display case 100 constitute a display space for the merchant or the store owner to place a physical model 700 of goods or merchandise.
  • the block diagram of the module of this embodiment is shown in FIG. 1 , wherein the user operates through the air display screen, and the intelligent shopping guide module controls the air display screen 200 , the horn 500 , the status indicator light and the ambience light 600 according to the input signal of the air display screen.
  • the merchant or the store owner or the like can set the color of the status indicator or the atmosphere lamp 600 as needed, for example, set to red, blue, green, or a plurality of colors in turn, and the like.
  • the merchant or the owner can also set the sound of the speaker to play, such as setting music, voice prompts, AI smart voice presentation content or user interactive feedback sound, and the like.
  • the embodiment provides a multi-dimensional visual shopping method.
  • the present embodiment is described by taking a multi-dimensional visual shopping guide system in FIG. 1 as an example.
  • the multi-dimensional visual shopping guide system includes an input module, a smart shopping guide module, a power supply module, and an air display screen disposed on one side of the display cabinet.
  • the display cabinet is composed of a plurality of planes and/or curved surfaces, and the plurality of planes and/or curved surfaces enclose a space for displaying physical goods or models, and the air display screen is disposed on at least one side of the display cabinet .
  • the air display screen is for displaying a virtual model of at least one item.
  • the input module includes a camera, a touch screen, a somatosensory device, a voice acquisition module, and a brain wave acquisition device.
  • a camera that captures images of users (mainly potential customers who need to purchase goods).
  • a somatosensory device for capturing a user's gesture signal (such as a signal for capturing an item for viewing angle switching, etc.).
  • a voice collection module is used to collect voice signals of users.
  • the brain wave collecting device is used for collecting the brain wave signal of the user, so as to recognize the user's thought or thought.
  • a touch screen is used for a user to input a touch instruction by means of a touch.
  • the intelligent shopping guide module is configured to perform smart shopping guide according to at least one of a user's image signal, a gesture signal, a voice signal, a touch signal, and a brain wave signal, the smart guide including the user's eye tracking, the user's facial expression recognition, and the user Voice command recognition, user brainwaves, touch command recognition, AI smart voice presentation, and virtual model display control of items.
  • the method of this embodiment includes the following steps:
  • step S1 The user selects to enter the corresponding mode by touching the working mode/standby mode switching button of the air display screen: if it is selected to enter the working mode, step S2 is performed; if the standby mode is selected, the standby screen is displayed on the air display screen.
  • the standby screen can display advertisements, games or other content.
  • the air display screen displays at least one two-dimensional or three-dimensional virtual model of the item.
  • the three-dimensional virtual model of the automobile can be displayed on the air display screen (the three-dimensional virtual model here refers to the three-dimensional virtual model generated by the image software).
  • the intelligent shopping guide module collects at least one of an image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal of the user through the input module.
  • the intelligent shopping guide module performs intelligent shopping guide according to the collected at least one signal and the virtual model of the item.
  • step S4 can be further subdivided into the following steps:
  • S41 Perform eye tracking of the user and facial expression recognition of the user according to the image signal of the user to analyze the focus and mood of the user.
  • the analyzed user focus can cause the air display screen to directly switch the virtual model of the item to the focus of the user's attention (such as identifying the user's attention to the body of the car, then directly switching to the virtual model of the vehicle body); and the analyzed user mood can be Stored locally or uploaded to the backend server via the Internet, etc., as a data foundation for subsequent analysis of user behavior.
  • the virtual model of the car can be scaled according to the user's gesture signal (unlimited by the physical object, can be infinitely zoomed), the angle of view switching and the color change of the body.
  • the virtual model of the car can be scaled according to the user's touch on the corresponding button on the air display screen (unlimited by the physical object, can be infinitely zoomed), the angle of view switching and the color change of the vehicle body.
  • the virtual model of the car can be scaled according to the idea or idea represented by the user's brain wave signal (unlimited by the physical object, can be infinitely zoomed), the angle of view switching and the color change of the body.
  • S46 Provide an AI smart voice announcement service to the user according to at least one of a user's image signal, a touch signal, a gesture signal, a voice signal, and a brain wave signal.
  • the AI model can be used to explain in detail the performance, price, sales volume and history of a well-known domestic automobile to the customer in order to replace the shopping guide to act as a 24-hour all-weather shopping guide AI.
  • step numbers in the above embodiments they are only provided for convenience of explanation, and the order between the steps is not limited.
  • the order of execution of the steps in the embodiments can be adapted according to the understanding of those skilled in the art. Adjustment.
  • the present invention can be applied to intelligent shopping guides and displays for automobiles, food, backpacks, watches, mobile phones and the like.
  • the present invention has the following advantages over the prior art:
  • the user can provide 24 hours a day product explanation and object consulting service according to the user's needs, which reduces the management cost of the shopping guide and is not limited by the size of the customer. , high quality of service and good user experience.
  • the air imaging technology is used on the air display screen to dynamically display the virtual model of the corresponding object with 360 degrees without dead angle, which is more intuitive and more diverse. More interactive, greatly increasing the appeal to customers.
  • a background server is added, which can remotely control the display content of the air display screen and further analyze the data of the shopping guide module, and it is more convenient to manage and control the air display screen without being on site.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Human Computer Interaction (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Hardware Design (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本发明公开了一种多维视觉导购系统和方法,系统包括:输入模块,用于获取用户的至少一个输入信号,输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;智能导购模块,用于根据至少一个输入信号进行智能导购,智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;空气展示屏,用于通过空气成像的方式显示物品的虚拟模型。本发明为用户提供了全天候的商品讲解和咨询服务,服务质量高和用户体验好;通过智能导购识别用户关注的焦点和用户的语音指令,能为用户进行AI智能语音宣讲并为用户动态展示物品360度无死角的虚拟模型,更加直观、维度更丰富和交互性更强,可广泛应用于智能控制领域。

Description

一种多维视觉导购系统和方法
技术领域
本发明涉及智能控制领域,尤其是一种多维视觉导购系统和方法。
背景技术
在日新月异的信息化时代,为了满足人们快节奏上的生活需求,大、中型超市或商场等不仅要在自身经营管理、物流管理、价格控制、库存控制等方面做出努力,提高自身市场竞争力,还要从消费者的角度出发,以最高效率满足消费者的购买欲望。为此,商场内一般会有导购员为顾客提供商品讲解和物件咨询,但是,这种方式增加了导购人员的管理成本,而且在客户量特别大的情况下,导购员不能够为每一个客户进行充分的讲解,影响了服务质量和用户体验。此外,这种方式较为单一,只能通过导购人员口头讲解的方式来使客户了解商品,未能将讲解与商品的虚拟模型展示等结合起来为客户提供更加直观、维度更丰富和交互性更强的用户体验,对客户的吸引力不足。
发明内容
为解决上述技术问题,本发明的目的在于:提供一种成本低、全天候和用户体验好的多维视觉导购系统和方法。
本发明所采取的第一技术方案是:
一种多维视觉导购系统,包括:
输入模块,用于获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
智能导购模块,用于根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
空气展示屏,用于通过空气成像的方式显示物品的虚拟模型。
进一步,还包括展示柜,所述空气展示屏设置在展示柜的一个组成平面上。
进一步,所述展示柜内设有用于放置物品或物品的真实模型的展台。
进一步,所述展示柜上还设有氛围灯和状态指示灯,所述氛围灯的输入端和状态指示灯的输入端均与智能导购模块的输出端连接。
进一步,所述展示柜内还设有电源模块和喇叭,所述电源模块的输出端与智能导购模块的输入端连接,所述智能导购模块的输出端与喇叭的输入端连接。
进一步,所述智能导购模块包括:
手势识别单元,用于根据获取的手势信号识别用户的手势;
语音对讲单元,用于根据获取的语音信号识别用户的语音指令;
图像识别单元,用于根据获取的图像信号进行眼部跟踪和面部表情识别;
脑波信号识别单元,用于根据获取的脑波信号识别用户的脑波;
触摸信号识别单元,用于根据获取的触摸信号识别用户的触摸指令;
分析单元,用于根据用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波和用户的触摸指令中的至少一种进行导购智能分析;
AI单元,用于根据导购智能分析的结果对物品的虚拟模型进行AI智能控制和物品的AI智能语音宣讲,其中,AI智能控制包括物品的虚拟模型的缩放控制、视角切换控制和颜色变换控制。
进一步,所述智能导购模块还包括:
选择单元,用于用户选择物品的颜色、类型、大小、尺寸和品牌中的至少一个;
二维码支付单元,用于在用户选择好要购买的物品后通过扫描二维码进行支付;
存储单元,用于存储用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波、用户的触摸指令、导购智能分析的结果和AI智能语音宣讲内容。
进一步,所述智能导购模块还连接有后台服务器,所述后台服务器用于与智能导购模块远程通信,远程存储AI智能语音宣讲内容和物品的虚拟模型,通过智能导购模块远程控制空气展示屏的显示内容以及根据智能导购模块的数据进行大数据分析。
进一步,所述输入模块包括摄像头、触摸屏、体感装置、语音采集模块和脑波采集设备中的至少一种。
本发明所采取的第二技术方案是:
一种多维视觉导购方法,包括以下步骤:
获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
根据智能导购的结果在空气展示屏上通过空气成像的方式显示物品的虚拟模型。
本发明的有益效果是:本发明一种多维视觉导购系统和方法,根据用户的图像信号、触摸信号、手势信号、语音信号和脑波信中的至少一种进行智能导购,智能导购包括用户的语音识别和AI智能语音宣讲,通过用户的语音识别和AI智能语音宣讲无需导购人员就能根据用户的需要为用户提供24小时全天候的商品讲解和物件咨询服务,减少了导购人员的管理成本且不受客户量大小的限制,服务质量高和用户体验好;智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制,通过智能导购识别用户关注的焦点和用户的语音指令,能为用户进行相应的AI智能语音宣讲并在AI语音讲解的同时根据用户的图像信号、触摸信号、手势信号、语音信号或脑波信号在空气展示屏上利用空气成像技术为用户动态展示相应物品360度无死角的虚拟模型,更加直观、维度更丰富和交互性更强,极大地增加了对客户的吸引力。
附图说明
图1为本发明一种多维视觉导购系统的整体结构框图;
图2为本发明一种多维视觉导购方法的步骤流程图;
图3为本发明智能导购模块的内部模块框图;
图4为本发明多维视觉导购系统的一种具体实施例结构示意图;
图5为本发明多维视觉导购方法的一种具体实施例流程图。
具体实施方式
参考图1,本发明一种多维视觉导购系统,包括:
输入模块,用于获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
智能导购模块,用于根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
空气展示屏,用于通过空气成像的方式显示物品的虚拟模型。
进一步作为优选的实施方式,还包括展示柜,所述空气展示屏设置在展示柜的一个组成平面上。
进一步作为优选的实施方式,所述展示柜内设有用于放置物品或物品的真实模型的展台。
进一步作为优选的实施方式,所述展示柜上还设有氛围灯和状态指示灯,所述氛围灯的输入端和状态指示灯的输入端均与智能导购模块的输出端连接。
进一步作为优选的实施方式,所述展示柜内还设有电源模块和喇叭,所述电源模块的输出端与智能导购模块的输入端连接,所述智能导购模块的输出端与喇叭的输入端连接。
进一步作为优选的实施方式,所述智能导购模块包括:
手势识别单元,用于根据获取的手势信号识别用户的手势;
语音对讲单元,用于根据获取的语音信号识别用户的语音指令;
图像识别单元,用于根据获取的图像信号进行眼部跟踪和面部表情识别;
脑波信号识别单元,用于根据获取的脑波信号识别用户的脑波;
触摸信号识别单元,用于根据获取的触摸信号识别用户的触摸指令;
分析单元,用于根据用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波和用户的触摸指令中的至少一种进行导购智能分析;
AI单元,用于根据导购智能分析的结果对物品的虚拟模型进行AI智能控制和物品的AI智能语音宣讲,其中,AI智能控制包括物品的虚拟模型的缩放控制、视角切换控制和颜色变换控制。
进一步作为优选的实施方式,所述智能导购模块还包括:
选择单元,用于用户选择物品的颜色、类型、大小、尺寸和品牌中的至少一个;
二维码支付单元,用于在用户选择好要购买的物品后通过扫描二维码进行支付;
存储单元,用于存储用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波、用户的触摸指令、导购智能分析的结果和AI智能语音宣讲内容。
参考图1,进一步作为优选的实施方式,所述智能导购模块还连接有后台服务器,所述后台服务器用于与智能导购模块远程通信,远程存储AI智能语音宣讲内容和物品的虚拟模型,通过智能导购模块远程控制空气展示屏的显示内容以及根据智能导购模块的数据进行大数据分析。
进一步作为优选的实施方式,所述输入模块包括摄像头、触摸屏、体感装置、语音采集模块和脑波采集设备中的至少一种。
参考图2,本发明一种多维视觉导购方法,包括以下步骤:
获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
根据智能导购的结果在空气展示屏上通过空气成像的方式显示物品的虚拟模型。
下面结合说明书附图和具体实施例对本发明作进一步解释和说明。
参考图1,本实施例提供了一种多维视觉导购系统,该系统主要包括输入模块、智能导购模块、电源模块、后台服务器以及设置在展示柜一个侧面上的空气展示屏。
其中,所述展示柜由若干个平面和/或曲面组成,在一些实施例中,所述展示柜可以是长方体,由六个平面组成。在另一些实施例中,所述展示柜可以是长方体的变体,例如在长方体中,有一个面由曲面构成。或者,展示柜可以是其他多面体的形状。在一些实施例中,所述展示柜的多个面围成的空间可以是一个密闭空间,也可以是一个开放空间,如可以是一个顶部开放的长方体。展示柜内设有用于放置物品或物品的真实模型的展台。
空气展示屏设置在展示柜的一个组成平面上,空气展示屏可以是透明液晶触摸屏等。所述空气展示屏可以是平面屏或者是曲面屏。所述空气展示屏,用于显示至少一个物品的虚拟模型,所述虚拟模型,为待售商品(如汽车等)的虚拟二维或三维模型,即在计算机中通过图像处理软件生成的模型。在一些实施例中,所述空气展示屏还能用于显示二维图像或者文字。在一些实施例中,展示柜有多个面是空气展示屏,可以在不同的方向显示该物品的虚拟模型。在另一些实施例中,部分空气展示屏可以显示除了虚拟模型以外的信息,如二维图像、文字介绍、产品LOGO等等。优选地,所述空气展示屏有两种工作模式:一种是待机工作模式,此时空气展示屏可以显示动态广告或游戏视频等待机画面;另一种是导购模式,此时空气展示屏可为用户提供智能导购服务。此外,空气展示屏还可在显示界面上提供相应的软件按钮供用户进行选择,如工作模式/待机模式切换按钮、二维码支付按钮、颜色切换按钮、视角切换按钮等。
输入模块,用于获取用户的至少一个输入信号,以便于与用户进行交互。如图1所示,本实施例的输入模块可包括摄像头、触摸屏、体感装置、语音采集模块和脑波采集设备。
摄像头,用于捕捉用户(主要是需要购买商品的潜在客户)的图像。优选地,所述摄像头可采用能同时采集二维人脸图像信息和深度信息的RGB-D的摄像头,以获取更加精确的用户图像。
体感装置,用于捕捉用户的手势信号(如抓取某件商品进行视角切换的信号等)。优选地,所述体感装置可以是Kinect体感传感器。
语音采集模块,用于采集用户的语音信号。以汽车导购为例,用户的语音信号可以是“打开车门”、“打开车内空调”、“将车身颜色换成黑色”等用户的语音指令信号。优选地,语音采集模块可以是拾音器、麦克风等语音采集设备。
脑波采集设备,用于采集用户的脑波信号,以便于识别用户的意念或想法。脑波采集设备可采用TGAM模块或其他脑波传感器来实现。
触摸屏,用于用户通过触摸的方式输入触摸指令。优选地,触摸屏可以贴在空气展示屏上或与空气展示屏合二为一。
智能导购模块,用于接收用户的图像信号、手势信号、语音信号、触摸信号和脑波信号,并根据用户的图像信号、手势信号、语音信号、触摸信号和脑波信号中的至少一种进行智能导购,所述智能导购包括用户的眼球跟踪、用户的面部表情识别、用户的语音指令识别、用户的脑波、触摸指令识别、AI智能语音宣讲和物品的虚拟模型显示控制。智能导购模块是整个系统的核心,能为用户提供多维度、多视角和交互性强的智能导购服务。其中,用户的眼球跟踪主要是识别用户关注的焦点所在(在看到关注的部分时,用户的眼球会与未看到关注部分的情况不同,如眼球停留的时间不同),以便于空气展示屏直接将物品的虚拟模型切换至用户关注的焦点(如识别到用户关注汽车的车身,则直接切换至车身的虚拟模型);用户的面部表情识别,主要是识别用户当前的心情(如开心、不开心等),这二者的识别都基于摄像头采集的图像。用户的语音指令识别,主要是为了识别用户的语音信号中所包含的语音指令,以便于对空气展示屏所显示的虚拟模型进行相应的操作,如颜色切换等。触摸信号识别,用于识别用户的触摸指令,以便于对空气展示屏所显示的虚拟模型进行相应的操作,如颜色切换等。脑波识别,主要是识别用户的意念或想法,以便于对空气展示屏所显示的虚拟模型进行相应的操作,如颜色切换等。AI智能语音宣讲,是指由机器学习训练得到的AI模型充当现有导购人员的角色,根据用户的指令或用户的需求提供相应物品的详细介绍和讲解。只要训练的精度高和维度足够丰富,该AI模型可以24小时全天候地为客户提供相应的宣讲服务,类似于聊天机器人但更智能,大大减少了导购人员的数量。物品的虚拟模型显示控制,主要包括物品的虚拟模型的缩放控制、视角切换控制、颜色变换控制等。在一些实施例中,所述物品的虚拟模型的数据可存储在智能导购模块中。在另一些实施例中,所述物品的虚拟模型的数据可以实时或者非实时地通过互联网、WIFI或USB接口等方式下载到智能导购模块中。
所述智能导购模块分别与输入模块和空气展示屏之间可以通过有线或者无线的方式传输数据,包括但不限于HDMI、VGA、USB、WIFI、蓝牙和红外信号等连接方式。所述智能导购模块内设有驱动空气展示屏的显示驱动模块,并由电源模块进行供电。所述智能导购模块可以是软件、硬件、固件及其组合。例如,智能导购模块可以是但不限于智能电话、平板电脑、笔记本电脑、智能手表、计算机、工控机等。
如图3所示,智能导购模块内的具体组成单元主要包括手势识别单元、语音对讲单元、图像识别单元、脑波信号识别单元、触摸信号识别单元、分析单元和AI单元。其中,手势识别单元,用于根据获取的手势信号识别用户的手势;语音对讲单元,用于根据获取的语音信号识别用户的语音指令;图像识别单元,用于根据获取的图像信号进行眼部跟踪和面部表情识别;脑波信号识别单元,用于根据获取的脑波信号识别用户的脑波;触摸信号识别单元,用于根据获取的触摸信号识别用户的触摸指令。分析单元,用于根据用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波和用户的触摸指令中的至少一种进行导购智能分析。分析单元进行导购智能分析的内容包括用户的眼球动作、面部表情、语音指令、触摸指令、体感手势所代表的含义(如代表需切换颜色的手势等)、意念或想法、需要进行AI语音讲解的内容。AI单元,用于根据导购智能分析的结果对物品的虚拟模型进行AI智能控制和物品的AI智能语音宣讲。其中,物品的AI智能语音宣讲是基于预先存储在智能导购模块本地或从互联网获取的物品详细内容(如历史、销量、性能、特点和售后服务等)进行的,用户可以通过触摸、手势、语音等方式选择或获取自己所需要了解的内容。而AI智能控制包括物品的虚拟模型的缩放控制、视角切换控制和颜色变换控制等。例如,AI智能控制能根据用户的手势或者语音等输入信号来放大或者缩小虚拟模型。
在一些实施例中,智能导购模块还可以包括选择单元,以供用户选择物品的颜色、类型、大小、尺寸和品牌中的至少一个来实现个性化的导购服务。
在一些实施例中,智能导购模块还可以包括二维码支付单元,当用户选好要购买的商品后,该二维码支付单元能在空气展示屏上生成或呈现用于付款并链接到第三方支付平台(如微信支付平台)的二维码,以供用户进行灵活和方便的付款操作。
在一些实施例中,智能导购模块还可以包括存储单元,所述存储单元存储用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波、用户的触摸指令、导购智能分析的结果和AI智能语音宣讲内容。
在一些实施例中,智能导购模块还可连接有后台服务器,所述后台服务器用于与智能导购模块远程通信,远程存储AI智能语音宣讲内容和物品的虚拟模型,通过智能导购模块远程控制空气展示屏的显示内容以及根据智能导购模块的数据进行大数据分析(如用户的行为分析、心情分析等)。
本领域技术人员应当清楚的是,该多维视觉导购系统还可以包含用于固定所述展示柜的支撑结构。其中,支撑结构可以是柜体、支架或者吊架等等。在本发明中支撑结构不限于具体的形状或者结构,所述空气展示屏可以朝上安装或者安装在容易展示的一侧。
参照图4,本实施例示出了一种多维视觉导购系统的具体结构,该系统包括展示柜100、空气展示屏200、智能导购模块(包括分析单元301、显示驱动模块302和电源模块303,)、支撑结构400(本实施例中支撑结构是柜体)、喇叭500、状态指示灯和氛围灯600。其中,智能导购模块和喇叭500均安装在支撑结构400内部,展示柜100嵌入在支撑结构400中。所述空气展示屏200构成展示柜100的其中一个面。而状态指示灯和氛围灯600均安装在支撑结构400的上部边缘,所述状态指示灯用于指示空气展示屏的状态(如待机或工作状态)。所述氛围灯400可以有多个,主要作用是提升多维视觉导购系统的灯光效果。如图4所示,可以看到展示柜100的多个面构成一个展示空间,供商家或店主等放置商品或者商品的实物模型700。本实施例的模块框图如图1所示,其中,用户通过空气展示屏操作,智能导购模块根据空气展示屏的输入信号控制空气展示屏200、喇叭500、状态指示灯和氛围灯600。在应用中,商家或店主等可以根据需要,设置状态指示灯或氛围灯600的颜色,例如设置为红色、蓝色、绿色或者多种颜色轮流变换等等。商家或店主等也可以设置喇叭播放的声音,例如设置音乐、语音提示、AI智能语音宣讲内容或者用户交互式的反馈声等等。
参照图5,本实施例提供了一种多维视觉导购方法。在本实施例中,以图1中的一种多维视觉导购系统为例对本实施例进行说明。所述多维视觉导购系统包括输入模块、智能导购模块、电源模块以及设置在展示柜一个侧面上的空气展示屏。其中,展示柜由若干个平面和/或曲面组成,所述若干个平面和/或曲面围成一个用于展示实物商品或者模型的空间,所述空气展示屏设置在展示柜的至少一个侧面上。所述空气展示屏用于显示至少一个物品的虚拟模型。输入模块包括摄像头、触摸屏、体感装置、语音采集模块和脑波采集设备。摄像头,用于捕捉用户(主要是需要购买商品的潜在客户)的图像。体感装置,用于捕捉用户的手势信号(如抓取某件商品进行视角切换的信号等)。语音采集模块,用于采集用户的语音信号。脑波采集设备,用于采集用户的脑波信号,以便于识别用户的意念或想法。触摸屏,用于用户通过触摸的方式输入触摸指令。智能导购模块,用于根据用户的图像信号、手势信号、语音信号、触摸信号和脑波信号中的至少一种进行智能导购,所述智能导购包括用户的眼球跟踪、用户的面部表情识别、用户的语音指令识别、用户的脑波、触摸指令识别、AI智能语音宣讲和物品的虚拟模型显示控制。
如图5所示,本实施例的方法包括以下步骤:
S1、用户通过触摸空气展示屏的工作模式/待机模式切换按钮选择进入相应的模式:若选择进入工作模式,则执行步骤S2;若选择进入待机模式,则在空气展示屏显示待机画面。其中,待机画面可以显示广告、游戏或其他内容。
S2、空气展示屏显示物品的至少一个二维或三维虚拟模型。例如在展示柜中展示汽车的实物模型时,可以在空气展示屏上显示该汽车的三维虚拟模型(此处的三维虚拟模型是指通过图像软件生成的三维虚拟模型)。
S3、智能导购模块通过输入模块采集用户的图像信号、触摸信号、手势信号、语音信号和脑波信号中的至少一种信号。
S4、智能导购模块根据采集的至少一种信号和物品的虚拟模型进行智能导购。
所述步骤S4可进一步细分为以下步骤:
S41、根据用户的图像信号进行用户的眼球跟踪和用户的面部表情识别,以分析用户的关注焦点和心情。分析出的用户关注焦点可使得空气展示屏直接将物品的虚拟模型切换至用户关注的焦点(如识别到用户关注汽车的车身,则直接切换至车身的虚拟模型);而分析出的用户心情可以存储到本地或通过互联网上传给后台服务器等,以作为后续对用户的行为进行分析的数据基础。
S42、根据用户的语音信号识别用户的语音指令,并根据用户的语音指令对物品的虚拟模型进行控制操作。以汽车导购为例,可根据“打开车内空调”语音指令打开车内的空调,根据“将车身颜色变为黑色” 语音指令将车身颜色变为黑色等。
S43、根据用户的手势信号对物品的虚拟模型进行控制操作。以汽车导购为例,可根据用户的手势信号对汽车的虚拟模型进行缩放(不受实物的限制,可无限缩放)、视角切换和车身颜色更改等。
S44、根据用户的触摸信号对物品的虚拟模型进行控制操作。以汽车导购为例,可根据用户触摸空气展示屏上相应的按钮对汽车的虚拟模型进行缩放(不受实物的限制,可无限缩放)、视角切换和车身颜色更改等。
S45、根据用户的脑波信号对物品的虚拟模型进行控制操作。以汽车导购为例,可根据用户脑波信号所代表的想法或意念对汽车的虚拟模型进行缩放(不受实物的限制,可无限缩放)、视角切换和车身颜色更改等。
S46、根据用户的图像信号、触摸信号、手势信号、语音信号和脑波信号中的至少一种为用户提供AI智能语音宣讲服务。以汽车导购为例,可根据客户的需要通过AI模型为客户详细讲解国内某款知名汽车的性能、价格、销量和历史等详细内容,以取代导购人员充当24小时全天候导购AI的角色。
对于上述实施例中的步骤编号,其仅为了便于阐述说明而设置,对步骤之间的顺序不做任何限定,实施例中的各步骤的执行顺序可根据本领域技术人员的理解来进行适应性调整。
本领域技术人员可以应当了解的是,本发明可以应用来进行汽车、食品、背包、手表、手机等商品的智能导购和展示。
综上所述,本发明相对于现有技术具有以下优点:
1)通过用户的语音识别和AI智能语音宣讲无需导购人员就能根据用户的需要为用户提供24小时全天候的商品讲解和物件咨询服务,减少了导购人员的管理成本且不受客户量大小的限制,服务质量高和用户体验好。
2)通过智能导购分析用户关注的焦点,能自动为用户切换至用户关注的焦点所在,更加智能和方便;通过智能导购分析用户的心情,为后续对用户的行为进行分析提供了数据来源。
3)根据用户的图像信号、触摸信号、手势信号、语音信号或脑波信号在空气展示屏上利用空气成像技术为用户动态展示相应物品360度无死角的虚拟模型,更加直观、维度更丰富和交互性更强,极大地增加了对客户的吸引力。
4)增设了后台服务器,能对空气展示屏的显示内容进行远程控制并对导购模块的数据进行进一步分析,无需在现场即可对空气展示屏进行管理和控制,更加方便。
以上是对本发明的较佳实施进行了具体说明,但本发明并不限于所述实施例,熟悉本领域的技术人员在不违背本发明精神的前提下还可做作出种种的等同变形或替换,这些等同的变形或替换均包含在本申请权利要求所限定的范围内。

Claims (10)

  1. 一种多维视觉导购系统,其特征在于:包括:
    输入模块,用于获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
    智能导购模块,用于根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
    空气展示屏,用于通过空气成像的方式显示物品的虚拟模型。
  2. 根据权利要求1所述的一种多维视觉导购系统,其特征在于:还包括展示柜,所述空气展示屏设置在展示柜的一个组成平面上。
  3. 根据权利要求2所述的一种多维视觉导购系统,其特征在于:所述展示柜内设有用于放置物品或物品的真实模型的展台。
  4. 根据权利要求3所述的一种多维视觉导购系统,其特征在于:所述展示柜上还设有氛围灯和状态指示灯,所述氛围灯的输入端和状态指示灯的输入端均与智能导购模块的输出端连接。
  5. 根据权利要求2所述的一种多维视觉导购系统,其特征在于:所述展示柜内还设有电源模块和喇叭,所述电源模块的输出端与智能导购模块的输入端连接,所述智能导购模块的输出端与喇叭的输入端连接。
  6. 根据权利要求1所述的一种多维视觉导购系统,其特征在于:所述智能导购模块包括:
    手势识别单元,用于根据获取的手势信号识别用户的手势;
    语音对讲单元,用于根据获取的语音信号识别用户的语音指令;
    图像识别单元,用于根据获取的图像信号进行眼部跟踪和面部表情识别;
    脑波信号识别单元,用于根据获取的脑波信号识别用户的脑波;
    触摸信号识别单元,用于根据获取的触摸信号识别用户的触摸指令;
    分析单元,用于根据用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波和用户的触摸指令中的至少一种进行导购智能分析;
    AI单元,用于根据导购智能分析的结果对物品的虚拟模型进行AI智能控制和物品的AI智能语音宣讲,其中,AI智能控制包括物品的虚拟模型的缩放控制、视角切换控制和颜色变换控制。
  7. 根据权利要求6所述的一种多维视觉导购系统,其特征在于:所述智能导购模块还包括:
    选择单元,用于用户选择物品的颜色、类型、大小、尺寸和品牌中的至少一个;
    二维码支付单元,用于在用户选择好要购买的物品后通过扫描二维码进行支付;
    存储单元,用于存储用户的手势、用户的语音指令、眼部跟踪和面部表情识别的结果、用户的脑波、用户的触摸指令、导购智能分析的结果和AI智能语音宣讲内容。
  8. 根据权利要求1所述的一种多维视觉导购系统,其特征在于:所述智能导购模块还连接有后台服务器,所述后台服务器用于与智能导购模块远程通信,远程存储AI智能语音宣讲内容和物品的虚拟模型,通过智能导购模块远程控制空气展示屏的显示内容以及根据智能导购模块的数据进行大数据分析。
  9. 根据权利要求1-8任一项所述的一种多维视觉导购系统,其特征在于:所述输入模块包括摄像头、触摸屏、体感装置、语音采集模块和脑波采集设备中的至少一种。
  10. 一种多维视觉导购方法,其特征在于:包括以下步骤:
    获取用户的至少一个输入信号,所述输入信号包括图像信号、触摸信号、手势信号、语音信号和脑波信号;
    根据所述至少一个输入信号进行智能导购,所述智能导购包括用户的眼球跟踪、用户的语音识别、AI智能语音宣讲和物品的虚拟模型显示控制;
    根据智能导购的结果在空气展示屏上通过空气成像的方式显示物品的虚拟模型。
PCT/CN2019/078624 2018-03-20 2019-03-19 一种多维视觉导购系统和方法 WO2019179409A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810229361.1 2018-03-20
CN201810229361.1A CN108573403A (zh) 2018-03-20 2018-03-20 一种多维视觉导购系统和方法

Publications (1)

Publication Number Publication Date
WO2019179409A1 true WO2019179409A1 (zh) 2019-09-26

Family

ID=63574472

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/078624 WO2019179409A1 (zh) 2018-03-20 2019-03-19 一种多维视觉导购系统和方法

Country Status (2)

Country Link
CN (1) CN108573403A (zh)
WO (1) WO2019179409A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113421141A (zh) * 2020-07-29 2021-09-21 阿里巴巴集团控股有限公司 基于脑机、脑神经信号的购物处理方法、装置及电子设备

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108573403A (zh) * 2018-03-20 2018-09-25 广东康云多维视觉智能科技有限公司 一种多维视觉导购系统和方法
CN110969053B (zh) * 2018-09-29 2023-12-22 深圳市神州云海智能科技有限公司 一种彩民分类的方法、装置及彩票机器人
CN109683711B (zh) * 2018-12-21 2022-12-20 广东美的白色家电技术创新中心有限公司 产品展示方法及装置
CN109685568B (zh) * 2018-12-21 2022-02-08 广东美的白色家电技术创新中心有限公司 产品展示方法及装置
CN109725725B (zh) * 2018-12-29 2022-08-12 出门问问信息科技有限公司 智能交互终端、以及智能交互终端的信息处理方法
CN109949121A (zh) * 2019-01-21 2019-06-28 广东康云科技有限公司 一种智能看车的数据处理方法及系统
CN109947239A (zh) * 2019-01-23 2019-06-28 广东康云科技有限公司 一种空气成像系统及其实现方法
CN111738788A (zh) * 2019-06-14 2020-10-02 北京京东尚科信息技术有限公司 一种物品信息展示方法、装置、系统、设备和存储介质
CN111402885A (zh) * 2020-04-22 2020-07-10 北京万向新元科技有限公司 一种基于语音和空气成像技术的交互方法及其系统
CN115484521A (zh) * 2021-05-31 2022-12-16 海信集团控股股份有限公司 一种智能音箱、虚拟形象控制方法、设备及介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202855246U (zh) * 2012-08-09 2013-04-03 陈滟滪 一种全息商场导购广告机
CN103116859A (zh) * 2013-02-06 2013-05-22 深圳华尔兹科技有限公司 3d导购机
CN104898581A (zh) * 2014-03-05 2015-09-09 青岛海尔机器人有限公司 一种全息智能中控系统
CN108573403A (zh) * 2018-03-20 2018-09-25 广东康云多维视觉智能科技有限公司 一种多维视觉导购系统和方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6189246B1 (en) * 1999-07-27 2001-02-20 Ravi Gorthala Three dimensional advertising billboard
CN105353582A (zh) * 2015-12-01 2016-02-24 浙江优创信息技术有限公司 一种全息投影的展示系统及基于该系统的操作方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202855246U (zh) * 2012-08-09 2013-04-03 陈滟滪 一种全息商场导购广告机
CN103116859A (zh) * 2013-02-06 2013-05-22 深圳华尔兹科技有限公司 3d导购机
CN104898581A (zh) * 2014-03-05 2015-09-09 青岛海尔机器人有限公司 一种全息智能中控系统
CN108573403A (zh) * 2018-03-20 2018-09-25 广东康云多维视觉智能科技有限公司 一种多维视觉导购系统和方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113421141A (zh) * 2020-07-29 2021-09-21 阿里巴巴集团控股有限公司 基于脑机、脑神经信号的购物处理方法、装置及电子设备

Also Published As

Publication number Publication date
CN108573403A (zh) 2018-09-25

Similar Documents

Publication Publication Date Title
WO2019179409A1 (zh) 一种多维视觉导购系统和方法
CN109085966B (zh) 一种基于云计算的三维展示系统及方法
WO2016175412A1 (en) Mobile terminal and controlling method thereof
CN112162671B (zh) 直播数据处理方法、装置、电子设备及存储介质
CN111405299B (zh) 基于视频流的直播交互方法及其相应的装置
EP3246802A1 (en) Mobile terminal and method for controlling the same
US20150381885A1 (en) Glass-type terminal and method for controlling the same
US20160267577A1 (en) Holographic interactive retail system
US20200305579A1 (en) Personalized makeup information recommendation method
EP2988495A1 (en) Data presentation method, terminal and system
CN106412412A (zh) 移动终端及其控制方法
WO2020151431A1 (zh) 一种智能看车的数据处理方法及系统
EP3331227A1 (en) Mobile terminal and method for controlling same
US20230085099A1 (en) Facial image generation method and apparatus, electronic device, and readable storage medium
US11694242B2 (en) Wearable terminal, information processing terminal, and product information display method
CN111178294A (zh) 状态识别方法、装置、设备及存储介质
CN109658167B (zh) 试妆镜设备及其控制方法、装置
US20110228155A1 (en) Cosmetic mirror and adjusting method for the same
WO2019045491A2 (en) ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF
TW201537228A (zh) 顯示裝置、包裝盒和包裝裝置
KR20150087793A (ko) 스마트 거울 장치와 그에 따른 시스템
WO2019179410A1 (zh) 一种基于三维模型的展示装置及其方法
JP2017156514A (ja) 電子看板システム
KR20180000603A (ko) 이동 단말기 및 그 제어방법
JP2024501558A (ja) 表示制御方法、装置、電子機器及び媒体

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: 19770455

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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 1205 DATED 18/01/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19770455

Country of ref document: EP

Kind code of ref document: A1