Shopping recommendation method and device based on smart TV, smart TV and medium

By identifying and building an attention database, smart TV realizes automatic recommendation of products that are of interest to users, solves the problem of smart TV not being able to recognize and recommend, and improves the intelligence of shopping recommendations and advertising monetization capabilities.

CN116017000BActive Publication Date: 2024-11-26SHENZHEN SKYWORTH RGB ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211714023.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-27
Publication Date
2024-11-26
Estimated Expiration
2042-12-27

AI Technical Summary

Technical Problem

Smart TV cannot automatically identify and recommend products that users are interested in. Users need to take the initiative to take screenshots and search, and they cannot buy them again after the advertisement is played, resulting in the loss of shopping opportunities and the inability to meet user needs.

Method used

By identifying whether the current screen is an advertisement, receiving user feedback data, building an attention database, including product information and user information in the advertisement, and presenting product information sorted at attention when the shopping function column appears, realizing intelligent shopping recommendations.

Benefits of technology

It improves the intelligence of shopping recommendations, recommends products based on user attention, and different users see different recommendations when viewing the same shopping function column, which enhances advertising monetization capabilities and improves users' purchasing opportunities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116017000B_ABST
    Figure CN116017000B_ABST
Patent Text Reader

Abstract

This application discloses a shopping recommendation method, device, smart TV, and computer-readable storage medium based on a smart TV. The method includes: identifying whether the currently displayed screen is an advertisement; after determining that the currently displayed screen is an advertisement, receiving user feedback data on the advertisement; constructing an attention database based on the feedback data, wherein the attention database includes at least one product information in the advertisement and user information corresponding to the user; and after detecting that the currently displayed screen is a shopping function section, presenting product information from the user's attention database to make shopping recommendations. This application improves the intelligence of smart TV shopping recommendations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data recognition technology, and in particular to a shopping recommendation method and device based on a smart TV, a smart TV, and a computer-readable storage medium. Background Art

[0002] Smart TVs offer not only video playback but also shopping services. Traditional smart TVs display a multi-functional interface before entering a video channel, featuring a shopping section that allows users to search for and purchase products. Currently, however, users can only take screenshots of videos, identify and search for products, and then purchase them. However, these purchases require user-initiated participation; once the product image fades, the user loses the opportunity to purchase the product. Currently, smart TVs lack shopping recommendations, failing to meet users' needs for purchasing desired products. Summary of the Invention

[0003] The main purpose of this application is to provide a shopping recommendation method and device based on smart TV, a smart TV and a computer-readable storage medium, aiming to solve the technical problem of how to realize the intelligence of smart TV shopping recommendations.

[0004] To achieve the above objectives, the present application provides a shopping recommendation method based on a smart TV, the shopping recommendation method based on a smart TV comprising the following steps:

[0005] Identify whether the currently displayed image is an advertisement;

[0006] After determining that the currently presented image is an advertisement, receiving user feedback data on the advertisement;

[0007] Building an attention database based on the feedback data, wherein the attention database includes at least one product information in the advertisement and user information corresponding to the user;

[0008] After detecting that the currently presented screen is a shopping function column, the product information in the attention database is presented to make shopping recommendations.

[0009] Optionally, the step of identifying whether the currently presented image is an advertisement comprises the following steps:

[0010] Get the category label provided by the currently playing channel;

[0011] If the classification mark is a preset target classification mark, it is determined that the currently playing picture is an advertisement.

[0012] Optionally, the step of identifying whether the currently presented image is an advertisement further comprises the following steps:

[0013] Obtaining a currently playing video segment and identifying the video segment;

[0014] If the video clip is an advertisement, it is determined that the currently played picture is an advertisement.

[0015] Optionally, the feedback data includes positive feedback data and negative feedback data. After determining that the currently presented image is an advertisement, after receiving the user's feedback data on the advertisement, the method further includes the following steps:

[0016] Determining the type of the feedback data;

[0017] If it is positive feedback data, assigning first weight information to the advertisement;

[0018] If it is negative feedback data, assigning the advertisement second weight information;

[0019] The first weight information and the second weight information are weighted and counted to obtain the user's attention to the advertisement.

[0020] Optionally, constructing an attention database according to the feedback data includes the following steps:

[0021] Acquire the user's attention to the advertisement obtained from the feedback data, and user information corresponding to the user, wherein the user information includes at least facial feature information;

[0022] An attention degree database corresponding to the user information is constructed according to the attention degree.

[0023] Optionally, after the step of constructing the attention database corresponding to the user information according to the attention, the following steps are further included:

[0024] Acquire product information in the advertisement, and add the product information to the attention database, wherein the attention database also includes the attention corresponding to the product information;

[0025] The attention levels corresponding to the product information are matched in an attention level database, and the product information is pre-ordered according to the attention levels.

[0026] Optionally, after detecting that the currently presented screen is a shopping function column, presenting the product information in the attention database to make shopping recommendations includes the following steps:

[0027] After detecting that the current interface is a shopping function column, obtaining current user information, and matching the target attention database corresponding to the user information in the attention database;

[0028] The commodity information in the target attention database is presented to make shopping recommendations.

[0029] In addition, to achieve the above-mentioned purpose, the present application further provides a shopping recommendation device based on a smart TV, wherein the shopping recommendation device based on a smart TV comprises:

[0030] Advertisement identification module, used to identify whether the currently presented image is an advertisement;

[0031] A data receiving module, configured to receive user feedback data on the advertisement after determining that the currently presented image is an advertisement;

[0032] An attention database construction module is used to construct an attention database based on the feedback data, wherein the attention database includes at least one commodity information in the advertisement and user information corresponding to the user;

[0033] The shopping recommendation module is used to present the product information in the attention database to make shopping recommendations after detecting that the currently presented screen is a shopping function column.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a smart TV, which includes: a memory, a processor, and a smart TV-based shopping recommendation program stored on the memory and runnable on the processor, and the smart TV-based shopping recommendation program is configured to implement the steps of the smart TV-based shopping recommendation method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which a shopping recommendation program based on a smart TV is stored. When the shopping recommendation program based on a smart TV is executed by a processor, the steps of the shopping recommendation method based on a smart TV as described above are implemented.

[0036] This application identifies whether the currently presented screen is an advertisement when playing a video on a smart TV. Only after determining that the currently presented screen is an advertisement, does it start to receive user feedback data on the advertisement, and then build an attention database based on the feedback data, wherein the attention database includes at least one product information in the advertisement and user information corresponding to the user; after building the attention database corresponding to the user, after detecting that the currently presented screen is a shopping function column, the product information in the attention database is presented to make shopping recommendations, so that different people can see different shopping recommendations when watching the shopping function column, thereby improving the intelligence of the shopping recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1It is a schematic diagram of the structure of a smart TV in the hardware operating environment involved in the embodiment of the present application;

[0038] Figure 2 This is a flowchart of the first embodiment of the shopping recommendation method based on smart TV of this application;

[0039] Figure 3 This is a flowchart of the second embodiment of the shopping recommendation method based on smart TV of this application;

[0040] Figure 4 This is a flowchart of an application scenario of an embodiment of the shopping recommendation method based on smart TV of the present application;

[0041] Figure 5 This is a structural diagram of the smart TV-based shopping recommendation device of this application.

[0042] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0044] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a smart TV in the hardware operating environment involved in the embodiment of the present application.

[0045] like Figure 1 As shown, the smart TV may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0046] Those skilled in the art will understand that Figure 1The structure shown in the figure does not constitute a limitation to the smart TV, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0047] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a shopping recommendation program based on a smart TV.

[0048] exist Figure 1 In the smart TV shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the smart TV of the present application can be set in the smart TV, and the smart TV calls the smart TV-based shopping recommendation program stored in the memory 1005 through the processor 1001, and executes the smart TV-based shopping recommendation method provided in the embodiment of the present application.

[0049] The embodiment of the present application provides a shopping recommendation method based on smart TV, referring to Figure 2 , Figure 2 This is a flowchart of the first embodiment of a shopping recommendation method based on smart TV in this application.

[0050] In this embodiment, the smart TV-based shopping recommendation method includes:

[0051] Step S10, identifying whether the currently presented image is an advertisement;

[0052] With the continuous development of technology, advertising is mainly pushed by displaying advertising pictures and text or dynamic images and videos on electronic advertising screens and LCD advertising screens. However, this technology also requires large-scale deployment and cannot respond to customers' preferences in a timely manner, thus losing the best opportunity for advertising monetization. Although it is currently possible to allow users to take screenshots of videos and identify, search and purchase products, these purchases require active user participation. Once the product image passes, the user loses the opportunity to purchase the product. The advertisements on major channels only explain the product details to users. After the advertisement is played, it is difficult to find or ignore the corresponding product. In addition, there are many advertisements, and users easily forget the advertised products, resulting in poor advertising monetization capabilities. Therefore, the present application provides a method for making shopping recommendations based on the user's level of attention to the advertised products.

[0053] In this embodiment, the smart TV can be a TV product based on Internet application technology, equipped with an open operating system and chip, an open application platform, capable of realizing two-way human-computer interaction functions, and integrating multiple functions such as audio and video, entertainment, and data to meet the diverse and personalized needs of users.

[0054] In this embodiment, to avoid unnecessary resource consumption, the following operations can be performed only when the smart TV is playing an advertisement or displaying advertisement content. That is, the following operations are performed only when the currently playing or displayed image is identified as an advertisement. Before that, it is only necessary to detect whether it is an advertisement period. It should be noted that the product in the advertisement period can be one or multiple items, and this embodiment is applicable to both.

[0055] Step S20, after determining that the currently presented image is an advertisement, receiving user feedback data on the advertisement;

[0056] In this embodiment, after determining that the currently displayed screen is an advertisement, the smart TV begins receiving user feedback data regarding the advertisement in the current screen. This feedback data can include operating instructions from the smart TV's remote control, such as changing channels, adjusting volume, turning the TV on and off, etc., or data collected by other sensors or identifiers within the smart TV, such as the distance between the user and the smart TV and whether a user is present in front of the smart TV. It should be noted that these users can be multiple or just one person at a time, and when receiving feedback data, data from all users can be received.

[0057] Step S30: constructing an attention database based on the feedback data, wherein the attention database includes at least one of the product information in the advertisement and the user information corresponding to the user;

[0058] In this embodiment, the received feedback data corresponding to each user is processed differently, that is, the feedback data of user A is distinguished from the feedback data of user B. During the distinction process, information instructions preset in the feedback data can be used to construct an attention database corresponding to each user. After the attention database is constructed, the product information in the advertisements viewed by each user is added to the respective attention database. For example, after determining that user A is watching the smart TV at this time, the feedback data corresponding to user A is received, and the attention database A corresponding to user A is constructed. The product information in the advertisements viewed by user A is added to the attention database A corresponding to user A. If user B is watching the smart TV at another time, the feedback data corresponding to user B is received, and the attention database B corresponding to user B is constructed. There will be no conflict with the attention database A of user A. Similarly, the product information corresponding to the advertisement viewed by user B is added to the attention database B.

[0059] It should be noted that the above-mentioned attention database can be stored in a place with storage function in the smart TV, or it can be stored in a server or cloud server that is connected to the smart TV, and can be called when the attention database is needed; after creating the attention database corresponding to a certain user, no additional attention database corresponding to the user will be created. For example, after user A watches the smart TV for the first time and creates the corresponding attention database A, the next time or at another time when user A watches it again, the smart TV will store the product information in the advertisement at this time in the attention database A based on the received feedback data, and will not build an additional attention database again. It is understandable that the advertising product information stored in two different time periods may be the same or different. If the product information is the same twice, you can choose to overwrite the old one with the latest product information, or you can choose not to overwrite it.

[0060] In this embodiment, the product information added to the attention database can be sorted according to the level of attention. From a quantitative perspective, the higher the attention, the higher the number. For example, if the attention level of product a is 3 and the attention level of product b is 1, then it is obvious that the attention level of product a is higher.

[0061] Step S40: After detecting that the currently presented screen is a shopping function column, the product information in the attention database is presented to make shopping recommendations.

[0062] In this embodiment, shopping recommendations can appear in the shopping section of the smart TV or on any screen at any time. However, compared to appearing in the shopping section of the smart TV, if ads appear abruptly while the user is watching a video, it will be counterproductive. Therefore, it is best to appear in the shopping section of the smart TV to improve advertising monetization. After detecting that the current screen is the shopping section, when the user is shopping or browsing products, the product information in the user's corresponding attention database is presented to provide shopping recommendations.

[0063] In this embodiment, when playing a video on a smart TV, it is identified whether the currently presented picture is an advertisement. Only after determining that the currently presented picture is an advertisement, the user's feedback data on the advertisement is received, and then an attention database is constructed based on the feedback data, wherein the attention database includes at least one product information in the advertisement and user information corresponding to the user; after constructing the attention database corresponding to the user, after detecting that the currently presented picture is a shopping function column, the product information in the attention database is presented to make shopping recommendations, so that different people can see different shopping recommendations when watching the shopping function column, thereby improving the intelligence of the shopping recommendations.

[0064] Further, refer to Figure 3 Based on the first embodiment of the present application, a second embodiment of the shopping recommendation method based on a smart TV is proposed. In this embodiment, the above step S10 identifies whether the currently presented screen is a refinement of an advertisement, including the following steps:

[0065] Step S101, obtaining the classification label provided by the currently playing channel;

[0066] Step S102: If the classification mark is a preset target classification mark, it is determined that the currently playing picture is an advertisement.

[0067] In this embodiment, identifying whether the currently presented screen is an advertisement can be performed by obtaining the classification markup of the currently playing channel that classifies programs and advertisements for the smart TV to read, to determine whether the current screen is an advertisement. The classification markup can be used to distinguish different types of videos through different symbols or segment marks. For example, the channel can add marks to the video progress bar by itself, with the time period for playing programs as program marks or marks, and the time period for advertising as advertising marks or marks; or corresponding marks or marks can be inserted into the video stream for distinction. Correspondingly, if the classification markup at this time is the classification markup corresponding to advertising, that is, the target classification markup, then it can be determined that the currently playing screen is an advertisement; if the classification markup at this time is not the classification markup corresponding to advertising, that is, it is not the target classification markup, then it is determined that the currently playing screen is not an advertisement.

[0068] Exemplarily, the step of identifying whether the currently presented image is an advertisement further includes the following steps:

[0069] Step S103, obtaining the currently playing video segment and identifying the video segment;

[0070] Step S104: If the video clip is an advertisement, determine that the currently playing image is an advertisement.

[0071] In this embodiment, identifying whether the currently presented picture is an advertisement may also be that the smart TV obtains or monitors the currently played picture in real time, identifies the advertisement through a preset advertisement recognition algorithm, and after determining that there is an advertisement in the picture or what is being played is an advertisement, it can be determined that the currently played picture is an advertisement; when there is no advertisement in the picture, it is determined that the currently played picture is not an advertisement.

[0072] Exemplarily, the feedback data includes positive feedback data and negative feedback data. After determining that the currently presented image is an advertisement, after receiving the user's feedback data on the advertisement, the following steps are further included:

[0073] Step S201, determining the type of the feedback data;

[0074] Step S202: If it is positive feedback data, assign first weight information to the advertisement;

[0075] Step S203: if the feedback is negative, assigning second weight information to the advertisement;

[0076] Step S204: Perform weighted statistics on the first weight information and the second weight information to obtain the user's attention to the advertisement.

[0077] In this embodiment, after determining that the currently playing image is an advertisement, it is necessary to determine whether the user is interested in the currently playing advertisement. Therefore, the user's feedback data can be collected and sent by controlling a preset behavior recognition unit, and then the feedback data is received. The behavior recognition unit can be a remote control corresponding to the smart TV, a human body sensor and / or a face recognition device provided in or on the surface of the smart TV. It should be noted that the human body sensor can be a human body sensor manufactured by the pyroelectric effect or by other principles, and this is not limited here. The face recognition device at least includes a device for implementing the most basic face recognition, such as a camera and a memory for storing the face recognition program.

[0078] In this embodiment, the feedback data sent by the remote control may include instructions such as changing channels, adjusting volume, turning the TV on and off, etc.; the feedback data sent by the human body sensor may include data on whether the user is around the smart TV, including the distance; the feedback data sent by the face recognition device may include whether the user's face is facing the screen and user information of the user's facial features.

[0079] In this embodiment, the types of feedback data for products in advertisements can include positive feedback data and negative feedback data. Positive feedback data can include user attention to the advertisement, for example, the user's failure to operate the remote control during the commercial period, which corresponds to the remote control standby command or volume increase command; data indicating the user's presence near the smart TV during the commercial period; and feedback data indicating the user facing or approaching the screen during the commercial period. Correspondingly, negative feedback data can include user inattention to the advertisement, for example, the user's use of channel change commands, volume reduction commands, or power off commands during the commercial period; feedback data indicating the user leaving or moving away from the smart TV during the commercial period; and feedback data indicating the user not facing the screen during the commercial period. It should be noted that regardless of whether positive or negative feedback data is received, the smart TV will receive the corresponding user information.

[0080] In this embodiment, after receiving feedback data, the type of feedback data can be determined. If the feedback data is positive, a first weighting information is assigned to the current advertisement, where the first weighting information can be a quantitative score or data such as +1 or +3. If the feedback data is negative, a second weighting information is assigned to the current advertisement, where the second weighting information can be a quantitative score or data such as -1 or -3. For example, if user A's feedback data regarding the current advertisement is received, and the remote control command is to increase the volume (i.e., positive feedback data), the advertisement is assigned a +1 point. If the feedback data sent by the human body sensor indicates that user A is staying near the smart TV, the advertisement is assigned a +1 point. If the feedback data sent by the facial recognition device indicates that user A is not facing the screen, the advertisement is assigned a -1 point.

[0081] In this embodiment, after obtaining all the first weight information and second weight information of the current advertisement, weighted statistics can be performed to obtain the user's attention to the current advertisement. For example, as mentioned above, user A performs weighted statistics on the first weight information and second weight information of the current advertisement, and the final result is +1 point. At this time, +1 point is the attention of user A to the current advertisement.

[0082] In one embodiment, constructing the attention database based on the feedback data includes the following steps:

[0083] Step S301: Acquire the user's attention to the advertisement obtained from the feedback data, and user information corresponding to the user, wherein the user information at least includes facial feature information;

[0084] Step S302: construct an attention database corresponding to the user information according to the attention.

[0085] In this embodiment, after receiving feedback data, a corresponding attention database can be constructed based on it. It is understood that the attention database can be one database per person, i.e., one database per user, or one database per multiple users, i.e., information corresponding to multiple users is stored in the same database, but each person's information is differentiated and does not interfere with each other. The attention database can be stored in a storage component of the smart TV, or it can be uploaded to a cloud server or server via the Internet. Therefore, in this embodiment, user information corresponding to the user currently viewing the advertisement can be obtained first, where the user information may include the user's facial features, and then a corresponding attention database can be constructed based on the user information and the user's feedback data on the advertisement.

[0086] Exemplarily, after the step of constructing the attention database corresponding to the user information according to the attention, the following steps are further included:

[0087] Step S303: Acquire product information in the advertisement, and add the product information to the attention database, wherein the attention database also includes the attention corresponding to the product information;

[0088] Step S304: matching the attention level corresponding to the product information in an attention level database, and performing a preset sorting on the product information according to the attention level.

[0089] In this embodiment, the attention database should include at least one product information from an advertisement in addition to user information. Therefore, the product information from the currently playing advertisement can be obtained and added to the attention database. It is understandable that the product information already has corresponding user attention at this point, so the attention level obtained by weighted statistics of the advertisement attention based on the above feedback data can be directly obtained. At this point, the product information in the advertisement can be marked with the corresponding attention level and pre-sorted. The pre-sorted sorting can be from high to low or from low to high. The purpose of the sorting in this embodiment is to allow the product information in the attention database to be sorted according to attention level for subsequent operations, so no specific sorting method is specified. At this point, a list of product information is obtained, sorted by attention level.

[0090] It should be noted that the product information in the attention database includes at least one product information, and the product information added to the attention database at different time periods has corresponding attention. Therefore, each time a new product information is added, it will be re-sorted to obtain the latest product information list.

[0091] In one embodiment, after detecting that the currently presented screen is a shopping function column, presenting the product information in the attention database to make shopping recommendations includes the following steps:

[0092] Step S401, after detecting that the current interface is a shopping function column, obtaining current user information, and matching the target attention database corresponding to the user information in the attention database;

[0093] Step S402: presenting the product information in the target attention database to make shopping recommendations.

[0094] In this embodiment, after constructing an attention database corresponding to each user, upon detecting that the current interface is a shopping function section, the user information corresponding to the user currently using the smart TV can be obtained. This is then used to match the target attention database corresponding to the user information in multiple attention databases. At this point, when the user uses the shopping function section, the product information in the target attention database can be presented in descending order of attention, i.e., the first product information is the product information with the highest attention for the user, thereby making shopping recommendations. It is understandable that when a user opens the shopping function section, the face recognition device recognizes the user's face, calls the attention database corresponding to the user's face, and sorts and presents the products according to their attention level. Each user has different viewing behavior, generates different attention to different advertisements, and the sorting of the products presented is also different.

[0095] In addition, to assist in understanding the embodiments of the present application, refer to Figure 4 , and also provides a schematic diagram of the application process of an embodiment.

[0096] When a smart TV is used on a certain occasion, it identifies the advertising period. After recognizing that the current broadcast is an advertising period, it identifies the user behavior during the advertising period to determine the user's attention to the behavior, and then identifies the products in the advertisement and marks the attention level of the products. If the user is interested in another product next time, the above operation is performed in the same way, and all products viewed by the user are added to the attention database and presented in the shopping function column in order of user attention level.

[0097] In this embodiment, user behavior is identified during advertising periods, and the user's attention to the product is immediately determined and recorded in the shopping function column. There is no need to worry about the advertised product being forgotten, which can improve the advertising monetization capability. In addition, by sorting and presenting the products according to the user's attention, users can be targeted to watch the products in order, further increasing the chances of product sales. When watching the shopping function column

[0098] Recognize the user's face and present the advertised products that the user is viewing. Different people viewing the shopping function's 5 columns will see different shopping recommendations, further improving the accuracy of recommendations.

[0099] In addition, refer to Figure 5 The present application further provides a shopping recommendation device based on a smart TV, the shopping recommendation device based on a smart TV comprising:

[0100] Advertisement identification module A10, used to identify whether the currently presented picture is an advertisement; data receiving module A20, used to receive user feedback data on the advertisement after determining that the currently presented picture is an advertisement;

[0101] The attention database construction module A30 is used to construct an attention database based on the feedback data, wherein the attention database includes at least one commodity information in the advertisement and the corresponding information of the user.

[0102] User information;

[0103] 5 Shopping recommendation module A40 is used to detect that the current screen is a shopping function column,

[0104] The commodity information in the attention database is presented to make shopping recommendations.

[0105] In one embodiment, the advertisement identification module A10 is further configured to:

[0106] Get the category label provided by the currently playing channel;

[0107] If the classification mark is the preset target classification mark, it is determined that the currently playing picture is an advertisement. In one embodiment, the above-mentioned advertisement identification module A10 is further used to:

[0108] Obtaining a currently playing video segment and identifying the video segment;

[0109] If the video clip is an advertisement, it is determined that the currently played picture is an advertisement.

[0110] In one embodiment, the data receiving module A20 is further configured to:

[0111] Determining the type of the feedback data;

[0112] 5. If it is positive feedback data, assign first weight information to the advertisement;

[0113] If it is negative feedback data, assigning the advertisement second weight information;

[0114] The first weight information and the second weight information are weighted and counted to obtain the user's attention to the advertisement.

[0115] In one embodiment, the attention database building module A30 is further configured to: 0 obtain the user's attention to the advertisement obtained based on the feedback data, and user information corresponding to the user, wherein the user information includes at least facial feature information;

[0116] An attention degree database corresponding to the user information is constructed according to the attention degree.

[0117] In one embodiment, the attention database building module A30 is further used to:

[0118] Acquire product information in the advertisement, and add the product information to the attention database, wherein the attention database also includes the attention corresponding to the product information;

[0119] The attention levels corresponding to the product information are matched in an attention level database, and the product information is pre-ordered according to the attention levels.

[0120] In one embodiment, the shopping recommendation module A40 is further configured to:

[0121] After detecting that the current interface is a shopping function column, obtaining current user information, and matching the target attention database corresponding to the user information in the attention database;

[0122] The commodity information in the target attention database is presented to make shopping recommendations.

[0123] In addition, the present application also provides a smart TV, which includes: a memory, a processor, and a smart TV-based shopping recommendation program stored on the memory and runnable on the processor, wherein the smart TV-based shopping recommendation program is configured to implement the steps of each embodiment of the smart TV-based shopping recommendation method as described above.

[0124] In addition, the present application also provides a computer-readable storage medium, which stores a shopping recommendation program based on a smart TV. When the shopping recommendation program based on a smart TV is executed by a processor, it implements the steps of each embodiment of the shopping recommendation method based on a smart TV as described above.

[0125] The specific implementation of the computer-readable storage medium of the present application is basically the same as the above-mentioned embodiments of the shopping recommendation method based on smart TV, and will not be repeated here.

[0126] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0127] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A shopping recommendation method based on smart TV, characterized in that: The shopping recommendation method based on smart TV comprises the following steps: Identify whether the currently displayed screen is an advertisement; After determining that the currently presented screen is an advertisement, receiving feedback data of the user on the advertisement collected and sent by a preset behavior recognition unit, wherein the behavior recognition unit includes a remote control corresponding to the smart TV, a human body sensor and a face recognition device arranged in or on the surface of the smart TV, and the feedback data sent by the remote control includes channel changing, volume adjustment, and power on / off instructions; the feedback data sent by the human body sensor includes data on whether the user is around the smart TV; the feedback data sent by the face recognition device includes whether the user's face is facing the screen and user information of the user's facial features; Building an attention database according to the feedback data, wherein the attention database includes at least one commodity information in the advertisement and user information corresponding to the user; After detecting that the currently presented screen is a shopping function column, presenting the commodity information in the attention database to make shopping recommendations; The feedback data includes positive feedback data and negative feedback data. After determining that the currently presented screen is an advertisement, after receiving the user's feedback data on the advertisement, the following steps are also included: Determining the type of the feedback data; If it is positive feedback data, assigning first weight information to the advertisement; If it is negative feedback data, assigning the advertisement second weight information; The first weight information and the second weight information are weighted and counted to obtain the user's attention to the advertisement.

2. The shopping recommendation method based on smart TV according to claim 1, characterized in that: The step of identifying whether the currently presented picture is an advertisement comprises the following steps: Get the category label provided by the currently playing channel; If the classification mark is a preset target classification mark, it is determined that the currently playing picture is an advertisement.

3. The shopping recommendation method based on smart TV according to claim 1, characterized in that: The step of identifying whether the currently presented picture is an advertisement further comprises the following steps: Obtaining a currently playing video segment and identifying the video segment; If the video clip is an advertisement, it is determined that the currently played picture is an advertisement.

4. The shopping recommendation method based on smart TV according to claim 1, characterized in that: The constructing of the attention database according to the feedback data comprises the following steps: Acquire the user's attention to the advertisement obtained according to the feedback data, and user information corresponding to the user, wherein the user information at least includes facial feature information; An attention degree database corresponding to the user information is constructed according to the attention degree.

5. The shopping recommendation method based on smart TV according to claim 4, characterized in that: After the step of constructing the attention degree database corresponding to the user information according to the attention degree, the following steps are also included: Acquire product information in the advertisement, and add the product information to the attention database, wherein the attention database also includes the attention corresponding to the product information; The attention level corresponding to the product information is matched in an attention level database, and the product information is preset in order according to the attention level.

6. The shopping recommendation method based on smart TV according to claim 1, characterized in that: After detecting that the currently presented screen is a shopping function column, presenting the commodity information in the attention database to make shopping recommendations includes the following steps: After detecting that the current interface is a shopping function column, obtaining current user information, and matching the target attention database corresponding to the user information in the attention database; The commodity information in the target attention database is presented to make shopping recommendations.

7. A shopping recommendation device based on smart TV, characterized in that: The smart TV-based shopping recommendation device comprises: An advertisement identification module, used to identify whether the currently presented image is an advertisement; A data receiving module is used to receive user feedback data on the advertisement collected and sent by a preset behavior recognition unit after determining that the currently presented screen is an advertisement, wherein the behavior recognition unit includes a remote control corresponding to the smart TV, a human body sensor and a face recognizer arranged in or on the surface of the smart TV, and the feedback data sent by the remote control includes channel changing, volume adjustment, and power on / off instructions; the feedback data sent by the human body sensor includes data on whether the user is around the smart TV; the feedback data sent by the face recognizer includes whether the user's face is facing the screen and user information of the user's facial features, and the feedback data includes positive feedback data and negative feedback data; the data receiving module is also used to determine the type of the feedback data; if it is positive feedback data, the advertisement is given first weight information; if it is negative feedback data, the advertisement is given second weight information; the first weight information and the second weight information are weighted and counted to obtain the user's attention to the advertisement; An attention database construction module is used to construct an attention database according to the feedback data, wherein the attention database includes at least one commodity information in the advertisement and user information corresponding to the user; The shopping recommendation module is used to present the commodity information in the attention database to make shopping recommendations after detecting that the currently presented screen is a shopping function column.

8. A smart TV, characterized in that: The smart TV comprises: a memory, a processor, and a smart TV-based shopping recommendation program stored in the memory and executable on the processor, wherein the smart TV-based shopping recommendation program is configured to implement the steps of the smart TV-based shopping recommendation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a shopping recommendation program based on a smart TV, and when the shopping recommendation program based on a smart TV is executed by a processor, the steps of the shopping recommendation method based on a smart TV as described in any one of claims 1 to 6 are implemented.