Video playing method and device in booth
By identifying visitors' video and audio information, recognizing their physical characteristics and semantic content, controlling the display of relevant information on the back-end screen, and playing target video clips in split screens based on the intention recognition results, the problem of low communication efficiency between exhibitors and visitors is solved, and the efficiency of business operations is improved.
Patent Information
- Application Number
- CN202411272448.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2024-11-26
AI Technical Summary
In the exhibition hall, the low efficiency of communication between exhibitors and visitors makes it difficult for businesses to carry out their business. Existing video presentation methods are unable to effectively identify visitors' intentions and conduct targeted promotions.
By performing image and semantic recognition on the video and audio information of visitors, their physical characteristics and semantic content are identified, and the relevant information is displayed on the back-end screen. Based on the intention recognition results, the target video clip is played in the split screen to guide the staff to provide targeted explanations.
It improves communication efficiency between exhibitors and visitors, helping companies conduct business more effectively.
Smart Images

Figure CN119031183A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of information interaction, and in particular to a video playing method and device in a booth. Background Art
[0002] With the development of digital technology, many companies, as exhibitors in the exhibition hall, display digital products in their own reserved booths in the exhibition hall to attract potential customers and better conduct their business.
[0003] However, there are many exhibitors in the exhibition hall and many visitors come to visit the exhibition hall. How to attract visitors to pay attention to the exhibitors' digital products has become a difficult problem. In addition, visitors and exhibitors' staff need to communicate to clarify the intentions of both parties, which is conducive to subsequent cooperation. However, existing exhibitors display their products through videos, and exhibitors' staff provide one-to-one service to visitors. In many cases, the current visitors have no intention of cooperation, but visitors with cooperation intentions miss the opportunity to cooperate with exhibitors because they do not fully understand the exhibitors' products. Therefore, the communication efficiency between the existing exhibitors' staff and visitors is low, which greatly affects the business development of the company. Summary of the invention
[0004] In view of the problems in the prior art, the embodiments of the present invention provide a method and device for playing videos in a booth, which can at least partially solve the problems in the prior art.
[0005] In one aspect, the present invention provides a method for playing a video in a booth, comprising:
[0006] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0007] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0008] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0009] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0010] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0011] Wherein, obtaining the video image of the digital cow on the main screen of the booth includes:
[0012] In response to the self-action performed by the first staff member according to the self-portrait image displayed in the third area of the background screen, according to the pre-established mapping relationship between the preset self-action and the preset digital cow action, the digital cow action corresponding to the self-action is used as the video action in the video image;
[0013] In response to the voice information sent by the first staff member, the voice information is enhanced and the enhanced voice information is used as the video sound in the video image.
[0014] The step of identifying the intention of the text information includes:
[0015] Semantically matching the text information with a preset promotional video keyword, and if a preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is matched, determining the intention recognition result as a first intention recognition result indicating intention;
[0016] If a preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is not matched, it is determined that the intention recognition result is a second intention recognition result indicating no intention.
[0017] The step of determining the target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen includes:
[0018] If it is determined that the intention recognition result is the first intention recognition result, querying in the summary content whether there is text that is the same as a preset promotional video keyword with a semantic similarity greater than a preset threshold;
[0019] If it is determined to exist, the split screen where the currently playing promotional video clip corresponding to the same text exists is determined as the target split screen.
[0020] Wherein, the video playing method in the booth further includes:
[0021] If it is determined that it does not exist, or if it is determined that the intention recognition result is the second intention recognition result, the split-screen logo corresponding to the split-screen that has not played the promotional video clip will be broadcast through the Digital Cow.
[0022] Wherein, the video playing method in the booth further includes:
[0023] Acquiring facial expression information and brain wave information of the visitor during the playing of the promotional video;
[0024] Performing preference recognition on the facial expression information and the brain wave information, and determining the visitor's favorite video clip in the promotional video according to the preference recognition result;
[0025] Extracting keywords from the video content of the favorite video clip, and using the keywords as summary content of the promotional video clip;
[0026] Displaying promotional video clips with the summary content as video clip labels in each sub-area of the split screen for playing the promotional video;
[0027] In response to the second staff member triggering an action of explaining the target promotional video clip to the visitor, the playing of the target promotional video clip is started.
[0028] Wherein, the video playing method in the booth further includes:
[0029] Detecting the smoothness of the video image of the digital cow on the main screen of the booth, and if it is determined that the smoothness is lower than a preset smoothness, lowering the image quality of display elements other than the digital cow on the main screen;
[0030] If it is determined that the fluency is still lower than the preset fluency, preset digital cow models with lower model accuracy than the currently displayed digital cow are called in sequence until the fluency is no lower than the preset fluency.
[0031] In one aspect, the present invention provides a video playback device in a booth, comprising:
[0032] An acquisition unit, for responding to a visitor's initial participation action performed according to the video image of the digital cow on the main screen of the booth, and acquiring the video and sound attribute information shot by the visitor;
[0033] a recognition unit, configured to perform image recognition on the captured video to obtain appearance feature information of the visitor, perform semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and control the background screen to display the appearance feature information and the corresponding text information in the first area;
[0034] a determination unit, configured to perform intention recognition on the text information, determine a target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and control the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0035] a sending unit, configured to respond to the visitor's in-depth participation action performed according to the guidance information, and to send a presentation reminder message carrying the appearance feature information to the second staff member, so that the second staff member can explain the promotional video clip to the visitor at the location of the target split screen;
[0036] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0037] In another aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus, wherein:
[0038] The processor and the memory communicate with each other via the bus;
[0039] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the following method:
[0040] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0041] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0042] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0043] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0044] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0045] An embodiment of the present invention provides a non-transitory computer-readable storage medium, including:
[0046] The non-transitory computer-readable storage medium stores computer instructions, which cause the computer to execute the following method:
[0047] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0048] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0049] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0050] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0051] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0052] The video playback method and device in the booth provided by the embodiment of the present invention respond to the initial participation action performed by the visitor based on the video image of the digital cow in the main screen of the booth, obtain the captured video and sound attribute information of the visitor; perform image recognition on the captured video to obtain the appearance feature information of the visitor, perform semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and control the background screen to display the appearance feature information and the corresponding text information in the first area; perform intention recognition on the text information, determine the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and control the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; in response to the in-depth participation action performed by the visitor based on the guidance information, send a lecture reminder message carrying the appearance feature information to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen, which can improve the communication efficiency between the exhibitor's staff and visitors and is conducive to the business development of the exhibitor enterprise. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0054] Figure 1 It is a flowchart of a method for playing videos in a booth provided by an embodiment of the present invention.
[0055] Figure 2 It is a schematic diagram for explaining a backstage screen in a booth provided by an embodiment of the present invention.
[0056] Figure 3 It is a schematic diagram for explaining the split screen in a booth provided by an embodiment of the present invention.
[0057] Figure 4 It is a structural schematic diagram of a video playback device in a booth provided by an embodiment of the present invention.
[0058] Figure 5 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0059] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily.
[0060] Figure 1 FIG. 1 is a flow chart of a method for playing a video in a booth provided by an embodiment of the present invention. Figure 1 As shown, the video playing method in the booth provided by the embodiment of the present invention includes:
[0061] Step S1: In response to a visitor's initial participation action performed based on the video image of Digital Cow on the main screen of the booth, the video and sound attribute information shot by the visitor is obtained.
[0062] Step S2: performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and corresponding text information in the first area.
[0063] Step S3: Perform intention recognition on the text information, determine the target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently being played corresponding to each split screen, and control the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area.
[0064] Step S4: in response to the visitor's in-depth participation action performed according to the guidance information, sending a presentation reminder message carrying the appearance feature information to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0065] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0066] In the above step S1, the device responds to the initial participation action performed by the visitor based on the video image of the digital cow in the main screen of the booth, and obtains the video and sound attribute information of the visitor. The device can be a computer device that executes the method, for example, it can include a server, specifically an exhibitor enterprise server. It should be noted that the acquisition and analysis of data involved in the embodiments of the present invention are authorized by the user. The embodiments of the present invention involve three types of display screens, in which the main screen and split screen are placed in the booth, and the background screen can be placed in the exhibitor's office, without specific limitation.
[0067] There can be only one main screen and one background screen, and there can be multiple sub-screens, which can be determined based on the number of visitors who visit the products at the same time. The first staff member controls the digital bull in the main screen and disseminates information to the visitors in the exhibition hall through the digital bull to attract as many visitors as possible to visit the company's booth.
[0068] The second staff member controls each sub-area in the split screen to play promotional video clips, so as to explain to visitors through the promotional video clips and promote cooperation between visitors and enterprises as much as possible.
[0069] The background screen is used to display the visitor's appearance feature information and corresponding text information to the first staff member, which is conducive to the first staff member to organize language based on the visitor's appearance feature information and corresponding text information, and spread it through Digital Cow, so as to have preliminary communication with the visitor at the first time.
[0070] It is also used to display the target split-screen logo and the appearance feature information of the corresponding visitor to the first staff member, which is beneficial for the first staff member to organize the guidance information according to the target split-screen logo and the appearance feature information of the corresponding visitor, and transmit the guidance information to the visitor through Digital Cow, guiding the visitor to the corresponding target split-screen for in-depth communication.
[0071] The digital cow is a virtual image that simulates a physical cow by modeling it based on the physical cow.
[0072] The initial participation action may be an action of the visitor approaching the main screen, an action of viewing the main screen at a close distance, an action of touching the digital cow on the main screen, etc., without specific limitation.
[0073] The main screen may be provided with a camera, a microphone and a speaker, wherein:
[0074] The camera is used to shoot visitors who perform preliminary participation actions, obtain the shot video, and then send the shot video to the server in real time.
[0075] The microphone is used to collect the voice attribute information of the visitor who performs the initial participation action. The voice attribute information may include the speech content, timbre, pitch, etc., and then send the voice attribute information to the server in real time.
[0076] The loudspeaker is used by the first staff to disseminate information to visitors through the digital cow.
[0077] The backstage screen may be equipped with a camera, a microphone and a speaker, including:
[0078] The camera is used to take a selfie of the first staff member to obtain a selfie image. The first staff member adjusts according to the selfie image and makes his own actions, such as waving to say hello, nodding and smiling, etc.
[0079] The microphone is used to collect the sound made by the first staff member, send the sound to the server, output the sound through the digital cow, and spread it to the visitors.
[0080] The loudspeaker is used to output the sound made by the visitor, which helps the first staff to communicate with the visitor.
[0081] The backstage screen can be equipped with a camera and a head-mounted display with an integrated brain wave detector, where:
[0082] The camera is used to collect the facial expression information of the visitors and send the facial expression information to the server.
[0083] The head display integrated with the brain wave detector is worn by visitors so that they can watch three-dimensional promotional video images. In addition, the brain wave detector can also collect the visitor's brain wave signals in real time while the visitor is watching the three-dimensional promotional video images, and send the brain wave signals to the server, so that the server can combine the brain wave signals with facial expression information to identify the visitor's favorite video clips.
[0084] It should be noted that the recorded video and sound attribute information need to be matched to the same visitor.
[0085] If multiple visitors speak to the Digital Cow at the same time, it is difficult for the server to distinguish which visitor said what to the Digital Cow, and it is difficult for the first staff member to connect with the subsequent words, which affects communication with the visitors.
[0086] Therefore, shooting a video may also include shooting the lip movements of the visitor, identifying the semantic content represented by the lip movements, and then matching the semantic content with the corresponding sound attribute information, so as to obtain the visitor corresponding to the shot video and the sound attribute information.
[0087] Obtain the video image of the digital cow on the main screen of the booth, including:
[0088] In response to the self-action made by the first staff member according to the self-portrait image displayed in the third area of the background screen, according to the pre-established mapping relationship between the preset self-action and the preset digital cow action, the digital cow action corresponding to the self-action is used as the video action in the video image; the first staff member may be a full-time staff member who helps the enterprise with publicity and promotion. Figure 2 As shown, what is displayed in the third area of the backstage screen is the selfie image of the first staff member taken by the backstage screen camera.
[0089] The above mapping relationships are embodied by the digital cow model, and the modeling process of the digital cow model is not described in the embodiment of the present invention. For example, the first staff member nods, and the corresponding digital cow action is that the digital cow nods.
[0090] In response to the voice information sent by the first staff member, the voice information is enhanced and the enhanced voice information is used as the video sound in the video image. The enhanced voice information may include adding animation sound effects so that the enhanced voice information is closer to the sound of the cow in the animation.
[0091] In the above step S2, the device performs image recognition on the captured video to obtain the appearance feature information of the visitor, performs semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controls the background screen to display the appearance feature information and the corresponding text information in the first area. The appearance feature information may include whether the visitor wears glasses, clothing style and color, etc.
[0092] Existing mature technologies can be used to perform image recognition on captured videos.
[0093] Existing mature technologies can be used to perform semantic recognition on sound attribute information.
[0094] like Figure 2 As shown, the appearance feature information of a visitor displayed in the first area on the backstage screen is as follows Figure 2 In "1,
[0095] XXXXXX”, the text information of the visitor displayed in the first area of the backstage screen is as follows Figure 2 middle
[0096] "YYYYY
[0097] YYYYYY
[0098] YYYY”.
[0099] For example, "1, XXXXXX" means "1, a female audience member with long hair and wearing a red down jacket";
[0100] "YYYYY
[0101] YYYYYY
[0102] YYYY" specifically means:
[0103] “Why is this digital cow so cute?
[0104] Does it have a name?
[0105] What products does your company produce?
[0106] It can be understood that the above three sentences are identified in the order of the sound attribute information of visitor 1.
[0107] The first staff member can see the above “1. Female audience with long hair and red down jacket” and “Why is this digital cow so cute? Does it have a name? What products does your company produce?” through the first area of the backstage screen. The first staff member can reply with the following information:
[0108] "The digital cow is as cute as you. It doesn't have a name yet. Why don't you call it 'Niuniu'? Our company provides milk products." The above information is output through the video image of the digital cow on the main screen, which can further attract more interested visitors to participate.
[0109] In the above step S3, the device performs intention recognition on the text information, determines the target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controls the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area. The intention recognition of the text information includes:
[0110] The text information is semantically matched with preset promotional video keywords. If a preset promotional video keyword is matched whose semantic similarity with the text information is greater than a preset semantic similarity threshold, the intention recognition result is determined to be a first intention recognition result indicating intention; the preset promotional video keywords can be set independently according to actual conditions, for example, may include milk products, pastures, breeding and logistics, etc., and the preset semantic similarity threshold can be set independently according to actual conditions.
[0111] Referring to the above example, if the semantic similarity between the text information "product" and "milk product" is greater than the preset semantic similarity threshold, it is determined that the female audience with long hair and wearing a red down jacket is interested.
[0112] If a preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is not matched, it is determined that the intention recognition result is a second intention recognition result indicating no intention.
[0113] The step of determining a target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, comprises:
[0114] If it is determined that the intention recognition result is the first intention recognition result, then it is queried in the summary content whether there is text that is the same as the preset promotional video keyword with a semantic similarity greater than a preset threshold; each split screen has a corresponding number of sub-areas, and the number of sub-areas can be zero, indicating that the visitor who has just watched the promotional video has no favorite promotional video clips, or no visitor has watched the promotional video yet, such as Figure 3 As shown in the figure, there is a split screen with three "sub-areas", which correspond to the summary content of the promotional video clips, such as "milk product packaging", "calf breeding" and "cattle disease prevention and treatment". After the second staff member finishes explaining the promotional video clip to the current visitor, the sub-areas can be cleared. Figure 3 The sub-area content shown is restored to playing the promotional video through the promotional video playing area.
[0115] If it is determined to exist, the split screen where the promotional video clip corresponding to the same text is currently being played is determined as the target split screen. Referring to the above description, "Milk Product Packaging" and "Milk Product" have the same text. If the promotional video clip corresponding to "Milk Product Packaging" is played on split screen No. 1, split screen No. 1 is determined as the target split screen. If multiple split screens are playing promotional video clips corresponding to "Milk Product Packaging", such as split screen No. 1 and split screen No. 4, a split screen can be randomly selected as the target split screen. Each target split screen identifier can be as follows: Figure 2 When the first staff member completes the target split screen identification and the appearance feature information corresponding to the visitor through the guidance information broadcast, the second area is displayed. Figure 2 The corresponding target split-screen identifier and the appearance feature information of the corresponding visitor are deleted.
[0116] The video playing method in the booth also includes:
[0117] If it is determined that it does not exist, or if it is determined that the intention recognition result is the second intention recognition result, the split screen logo corresponding to the split screen that does not play the promotional video clip is broadcast through the digital cow. If the summary content of the "sub-area" corresponding to no split screen contains the same words as "milk products";
[0118] Alternatively, if the intention recognition result of visitor 2 is no intention, and split screen No. 3 is currently playing a promotional video, then split screen No. 3 is determined as a split screen that does not play a promotional video clip. Each split screen in the booth needs to be opened to display the company's products. By default, each split screen plays a promotional video. The content directly broadcasted through Digital Bull may include:
[0119] "Please go to screen No. 3 to learn about our company's products, thank you."
[0120] When a visitor likes a certain promotional video clip after watching the promotional video, the promotional video clip will be shown again, and the second staff member will explain the promotional video clip.
[0121] According to the method of the embodiment of the present invention, for a visitor who has watched the promotional video once and has a preference for at least one promotional video segment, a second staff member explains the promotional video to the visitor in combination with the at least one promotional video segment.
[0122] It should be noted that if Figure 3 As shown, when a promotional video is played in the promotional video playback area, no promotional video clip can be played in any sub-area.
[0123] When a promotional video clip is played in one of the sub-areas, other sub-areas cannot play the corresponding promotional video clip, and the promotional video playback area cannot play the promotional video either. The second staff member can manually switch and control it. For example, when the promotional video is played in the promotional video playback area, when the second staff member needs to play the promotional video clip corresponding to sub-area 2, he clicks on the screen position corresponding to sub-area 2 to start playing the promotional video clip corresponding to sub-area 2, and simultaneously stops playing the promotional video in the promotional video playback area, thereby ensuring that there will be no sound interference caused by the simultaneous playing of two videos.
[0124] Similarly, when the second staff member needs to play the promotional video clip corresponding to sub-area 3, he clicks the screen position corresponding to sub-area 3 to start playing the promotional video clip corresponding to sub-area 3, and stops playing the promotional video clip in sub-area 2.
[0125] Similarly, when playing the promotional video clip corresponding to sub-area 2, when the second staff member needs to play the promotional video in the promotional video playback area, he clicks on the screen position corresponding to the promotional video playback area to start playing the promotional video in the promotional video playback area, and at the same time stops playing the promotional video clip in sub-area 2.
[0126] A played status mark may be generated at the start time of the promotional video segment being played, so that the server can determine the summary content of the currently playing promotional video segment according to the played status mark.
[0127] In the above step S4, the device responds to the in-depth participation action performed by the visitor according to the guidance information, and sends a presentation reminder message carrying the appearance feature information to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the target split screen; the second staff member can specifically be a professional with professional knowledge of the company's products.
[0128] Referring to the above description, the guidance information may be specifically "Please ask the female audience with long hair and wearing a red down jacket to go to split screen No. 1 to watch the explanation of 'Milk Product Packaging'". Since 'Milk Product Packaging' is being explained by the second staff member to the previous visitor, the female audience with long hair and wearing a red down jacket and the previous visitor listen to the explanation of the same second staff member together, allowing the second staff member to serve multiple visitors at the same time.
[0129] The second staff member can receive presentation reminder messages through his mobile phone. When he sees a female audience member with long hair and wearing a red down jacket approaching, he will know that she is a potential customer guided by the first staff member.
[0130] The guiding information is sent by the first staff member browsing the target split screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow. Please refer to the above description and do not repeat it.
[0131] The video playing method in the booth also includes:
[0132] The facial expression information and brain wave information of the visitor are obtained during the playing of the promotional video; the obtaining process can refer to the above description, and the facial expression information and brain wave information of the visitor are changing at each playing moment of the promotional video.
[0133] The preference recognition is performed on the facial expression information and the brain wave information, and the visitor's favorite video clip in the promotional video is determined according to the preference recognition result; by observing the preference recognition result at each playback moment of the promotional video, the playback time corresponding to the playback starting point of the preference appearance and the playback time corresponding to the playback starting point of the preference disappearance can be used as the favorite video clip in the promotional video.
[0134] Keywords are extracted from the video content of the favorite video clip, and the keywords are used as the summary content of the promotional video clip; the keywords can be identified by using existing mature video content identification methods.
[0135] In each sub-area of the split screen for playing the promotional video, a promotional video clip with the summary content as the video clip label is displayed respectively; by using the summary content as the video clip label, it is convenient for the second staff member to quickly and accurately determine the visitor's preferences.
[0136] In response to the second staff member triggering an action to explain the target promotional video clip to the visitor, the target promotional video clip is played. Figure 3 As shown, sub-areas 1 to 3 may be arranged in the order in which the promotional video clips appear during the playing of the promotional video.
[0137] If the second staff member explains the promotional video clip corresponding to sub-area 2 to the visitor, this can be achieved by clicking on the area corresponding to sub-area 2.
[0138] The video playing method in the booth also includes:
[0139] The smoothness of the video image of the digital cow in the main screen of the booth is detected. If it is determined that the smoothness is lower than the preset smoothness, the image quality of the display elements other than the digital cow in the main screen is lowered; the preset smoothness can be set independently according to actual conditions, and the display elements other than the digital cow may include grass and sky in the pasture, etc.
[0140] The image quality of display elements other than the digital cow in the main screen can be lowered by lowering the image pixels of the grass and sky in the pasture.
[0141] If it is determined that the fluency is still lower than the preset fluency, preset digital cow models with lower model accuracy than the currently displayed digital cow are called in sequence until the fluency is not lower than the preset fluency. Multiple preset digital cow models can be established in advance according to the modeling accuracy. It is understandable that the lower the model accuracy, the lower the consumption of computer resources and network resources, and the fluency can be improved accordingly.
[0142] The video playback method in the booth provided by the embodiment of the present invention responds to the initial participation action performed by the visitor based on the video image of the digital cow in the main screen of the booth, obtains the captured video and sound attribute information of the visitor; performs image recognition on the captured video to obtain the appearance feature information of the visitor, performs semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controls the background screen to display the appearance feature information and the corresponding text information in the first area; performs intention recognition on the text information, determines the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controls the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; responds to the in-depth participation action performed by the visitor based on the guidance information, sends a lecture reminder message carrying the appearance feature information to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the target split screen, which can improve the communication efficiency between the exhibitor's staff and the visitor, and is conducive to the business development of the exhibitor enterprise.
[0143] Further, obtaining the video image of the digital cow on the main screen of the booth includes:
[0144] In response to the self-action made by the first staff member according to the selfie image displayed in the third area of the background screen, according to the pre-established mapping relationship between the preset self-action and the preset digital cow action, the digital cow action corresponding to the self-action is used as the video action in the video image; the description can be made with reference to the above embodiment and will not be repeated here.
[0145] In response to the voice information sent by the first staff member, the voice information is enhanced and the enhanced voice information is used as the video sound in the video image. The above embodiment can be referred to for description and will not be repeated.
[0146] Furthermore, the identifying the intention of the text information includes:
[0147] The text information is semantically matched with the preset promotional video keywords. If a preset promotional video keyword is matched whose semantic similarity with the text information is greater than a preset semantic similarity threshold, the intention recognition result is determined to be the first intention recognition result indicating intention; please refer to the above embodiment for description and will not repeat it here.
[0148] If no preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is matched, the intention recognition result is determined to be a second intention recognition result indicating no intention.
[0149] Further, the step of determining the target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen includes:
[0150] If it is determined that the intention recognition result is the first intention recognition result, then query in the summary content whether there is text that is the same as the preset promotional video keyword with a semantic similarity greater than a preset threshold; refer to the above embodiment for description and no further details will be given.
[0151] If it is determined that there is, the split screen where the currently played promotional video clip corresponding to the same text exists is determined as the target split screen. The above embodiment can be referred to for description, and no further description is given.
[0152] Furthermore, the video playing method in the booth also includes:
[0153] If it is determined that it does not exist, or if it is determined that the intention recognition result is the second intention recognition result, the split screen logo corresponding to the split screen that does not play the promotional video clip is broadcasted through the digital cow. The above embodiment can be referred to for description and will not be repeated.
[0154] Furthermore, the video playing method in the booth also includes:
[0155] The facial expression information and brain wave information of the visitor are obtained during the process of playing the promotional video; the description may refer to the above embodiment and will not be repeated here.
[0156] The preference recognition is performed on the facial expression information and the brain wave information, and the visitor's favorite video clip in the promotional video is determined according to the preference recognition result; the description can be made with reference to the above embodiment and will not be repeated here.
[0157] Keywords are extracted from the video content of the favorite video clip, and the keywords are used as the summary content of the promotional video clip; the description can be made with reference to the above embodiment, which will not be repeated here.
[0158] In each sub-area of the split screen for playing the promotional video, a promotional video segment with the summary content as the video segment label is displayed respectively; please refer to the above-mentioned embodiment for description and no further details will be given.
[0159] In response to the second staff member triggering the target promotion video clip to explain to the visitor, the target promotion video clip is started to be played. The above-mentioned embodiment can be referred to for description and will not be repeated here.
[0160] Furthermore, the video playing method in the booth also includes:
[0161] The smoothness of the video image of the digital cow in the main screen of the booth is detected. If it is determined that the smoothness is lower than the preset smoothness, the image quality of the display elements other than the digital cow in the main screen is lowered; please refer to the above embodiment for description and no further details will be given.
[0162] If it is determined that the fluency is still lower than the preset fluency, preset digital cow models with lower model accuracy than the currently displayed digital cow are called in sequence until the fluency is not lower than the preset fluency.
[0163] Figure 4 FIG. 1 is a schematic diagram of the structure of a video playback device in a booth provided by an embodiment of the present invention. Figure 4 As shown, the video playback device in the booth provided by the embodiment of the present invention includes an acquisition unit 401, an identification unit 402, a determination unit 403 and a sending unit 404, wherein:
[0164] The acquisition unit 401 is used to respond to the initial participation action performed by the visitor based on the video image of the digital cow on the main screen of the booth, and obtain the captured video and sound attribute information of the visitor; the recognition unit 402 is used to perform image recognition on the captured video to obtain the appearance feature information of the visitor, perform semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and control the background screen to display the appearance feature information and the corresponding text information in the first area; the determination unit 403 is used to perform intention recognition on the text information, and determine the intention of the text information according to the intention recognition result and the promotional video clips currently playing corresponding to each split screen. Summary content, determine the target split screen for playing the promotional video clip to the visitor, and control the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; the sending unit 404 is used to respond to the visitor's in-depth participation action performed according to the guidance information, and send a lecture reminder message carrying the appearance feature information to the second staff member, so that the second staff member can explain the promotional video clip to the visitor at the target split screen; wherein, the guidance information is sent by the first staff member browsing the target split screen logo and the appearance feature information corresponding to the visitor, and controlling the digital cow.
[0165] Specifically, the acquisition unit 401 in the device is used to respond to the initial participation action performed by the visitor based on the video image of the digital cow in the main screen of the booth, and obtain the captured video and sound attribute information of the visitor; the recognition unit 402 is used to perform image recognition on the captured video to obtain the appearance feature information of the visitor, perform semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and control the background screen to display the appearance feature information and the corresponding text information in the first area; the determination unit 403 is used to perform intention recognition on the text information, and determine the intention of the text information according to the intention recognition result and the promotional video currently playing corresponding to each split screen. The summary content of the video clip is used to determine the target split screen for playing the promotional video clip to the visitor, and the background screen is controlled to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; the sending unit 404 is used to respond to the visitor's in-depth participation action performed according to the guidance information, and send a lecture reminder message carrying the appearance feature information to the second staff member, so that the second staff member can explain the promotional video clip to the visitor at the target split screen; wherein the guidance information is sent by the first staff member browsing the target split screen logo and the appearance feature information corresponding to the visitor, and controlling the digital cow.
[0166] The video playback device in the booth provided by the embodiment of the present invention responds to the initial participation action performed by the visitor based on the video image of the digital cow in the main screen of the booth, obtains the captured video and sound attribute information of the visitor; performs image recognition on the captured video to obtain the appearance feature information of the visitor, performs semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controls the background screen to display the appearance feature information and the corresponding text information in the first area; performs intention recognition on the text information, determines the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controls the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; responds to the in-depth participation action performed by the visitor based on the guidance information, sends a lecture reminder message carrying the appearance feature information to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen, which can improve the communication efficiency between the exhibitor's staff and visitors and is conducive to the business development of the exhibitor enterprise.
[0167] The embodiment of the video playback device in the booth provided by the embodiment of the present invention can be specifically used to execute the processing flow of the above-mentioned method embodiments. Its functions are not described in detail here, and reference can be made to the detailed description of the above-mentioned method embodiments.
[0168] Figure 5 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 5 As shown, the electronic device includes: a processor (processor) 501, a memory (memory) 502 and a bus 503;
[0169] The processor 501 and the memory 502 communicate with each other via a bus 503;
[0170] The processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above method embodiments, for example, including:
[0171] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0172] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0173] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0174] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0175] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0176] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided by the above method embodiments, for example, including:
[0177] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0178] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0179] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0180] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0181] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0182] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables the computer to execute the methods provided by the above method embodiments, for example, including:
[0183] In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor;
[0184] Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area;
[0185] Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area;
[0186] In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen;
[0187] The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
[0188] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0189] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0190] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0192] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0193] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A video playing method in a booth, characterized in that: include: In response to a visitor's initial participation action performed based on the video image of the digital cow on the main screen of the booth, obtaining the video and sound attribute information of the visitor; Performing image recognition on the captured video to obtain appearance feature information of the visitor, performing semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and controlling the background screen to display the appearance feature information and the corresponding text information in the first area; Performing intention recognition on the text information, determining the target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and controlling the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; In response to the visitor's in-depth participation action performed according to the guidance information, a presentation reminder message carrying the appearance feature information is sent to the second staff member, so that the second staff member explains the promotional video clip to the visitor at the location of the target split screen; The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
2. The video playing method in a booth according to claim 1, characterized in that: Obtain the video image of the digital cow on the main screen of the booth, including: In response to the self-action performed by the first staff member according to the self-portrait image displayed in the third area of the background screen, according to the pre-established mapping relationship between the preset self-action and the preset digital cow action, the digital cow action corresponding to the self-action is used as the video action in the video image; In response to the voice information sent by the first staff member, the voice information is enhanced and the enhanced voice information is used as the video sound in the video image.
3. The video playing method in a booth according to claim 1, characterized in that: The performing intention recognition on the text information includes: Semantically matching the text information with a preset promotional video keyword, and if a preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is matched, determining the intention recognition result as a first intention recognition result indicating intention; If a preset promotional video keyword whose semantic similarity with the text information is greater than a preset semantic similarity threshold is not matched, it is determined that the intention recognition result is a second intention recognition result indicating no intention.
4. The video playing method in a booth according to claim 3, characterized in that: The step of determining a target split screen for playing the promotional video clip to the visitor based on the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, comprises: If it is determined that the intention recognition result is the first intention recognition result, querying in the summary content whether there is text that is the same as a preset promotional video keyword with a semantic similarity greater than a preset threshold; If it is determined to exist, the split screen where the currently playing promotional video clip corresponding to the same text exists is determined as the target split screen.
5. The video playing method in a booth according to claim 4, characterized in that: The video playing method in the booth also includes: If it is determined that it does not exist, or if it is determined that the intention recognition result is the second intention recognition result, the split-screen logo corresponding to the split-screen that has not played the promotional video clip will be broadcast through the Digital Cow.
6. The video playing method in a booth according to any one of claims 1 to 5, characterized in that: The video playing method in the booth also includes: Acquiring facial expression information and brain wave information of the visitor during the playing of the promotional video; Performing preference recognition on the facial expression information and the brain wave information, and determining the visitor's favorite video clip in the promotional video according to the preference recognition result; Extracting keywords from the video content of the favorite video clip, and using the keywords as summary content of the promotional video clip; Displaying promotional video clips with the summary content as video clip labels in each sub-area of the split screen for playing the promotional video; In response to the second staff member triggering an action of explaining the target promotional video clip to the visitor, the playing of the target promotional video clip is started.
7. The video playing method in a booth according to any one of claims 1 to 5, characterized in that: The video playing method in the booth also includes: Detecting the smoothness of the video image of the digital cow on the main screen of the booth, and if it is determined that the smoothness is lower than a preset smoothness, lowering the image quality of display elements other than the digital cow on the main screen; If it is determined that the fluency is still lower than the preset fluency, preset digital cow models with lower model accuracy than the currently displayed digital cow are called in sequence until the fluency is no lower than the preset fluency.
8. A video playback device in a booth, characterized in that: include: An acquisition unit, for responding to a visitor's initial participation action performed according to the video image of the digital cow on the main screen of the booth, and acquiring the video and sound attribute information shot by the visitor; a recognition unit, configured to perform image recognition on the captured video to obtain appearance feature information of the visitor, perform semantic recognition on the sound attribute information to obtain text information expressing the semantic content of the visitor, and control the background screen to display the appearance feature information and the corresponding text information in the first area; a determination unit, configured to perform intention recognition on the text information, determine a target split screen for playing the promotional video clip to the visitor according to the intention recognition result and the summary content of the promotional video clip currently played corresponding to each split screen, and control the background screen to display the target split screen logo and the appearance feature information corresponding to the visitor in the second area; a sending unit, configured to respond to the visitor's in-depth participation action performed according to the guidance information, and to send a presentation reminder message carrying the appearance feature information to the second staff member, so that the second staff member can explain the promotional video clip to the visitor at the location of the target split screen; The guiding information is sent by the first staff member browsing the target split-screen logo and the appearance feature information corresponding to the visitor by controlling the digital cow.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
