CN111291087A - Information pushing method and device based on face detection - Google Patents

Information pushing method and device based on face detection Download PDF

Info

Publication number
CN111291087A
CN111291087A CN202010047101.XA CN202010047101A CN111291087A CN 111291087 A CN111291087 A CN 111291087A CN 202010047101 A CN202010047101 A CN 202010047101A CN 111291087 A CN111291087 A CN 111291087A
Authority
CN
China
Prior art keywords
information
face
user account
user
pushing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010047101.XA
Other languages
Chinese (zh)
Inventor
陈渡雯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Kaytion Information Technology Co ltd
Original Assignee
Guangzhou Kaytion Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Kaytion Information Technology Co ltd filed Critical Guangzhou Kaytion Information Technology Co ltd
Priority to CN202010047101.XA priority Critical patent/CN111291087A/en
Publication of CN111291087A publication Critical patent/CN111291087A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2457Query processing with adaptation to user needs
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Abstract

The embodiment of the application discloses an information pushing method and device based on face detection. According to the technical scheme, the corresponding user account is determined according to the face recognition result detected by the face recognition entrance guard, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check the information conveniently, and the user experience is optimized.

Description

Information pushing method and device based on face detection
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to an information pushing method and device based on face detection.
Background
With the enhancement of safety awareness of people, higher safety requirements are put forward for entrance and exit of places such as communities, office buildings and the like, and face recognition entrance guards are generally installed at entrances and exits of the places in order to distinguish and block strangers.
The face recognition entrance guard identifies and verifies the face at the entrance and the exit, and opens the entrance guard after the verification is passed so as to allow corresponding personnel to enter and exit. At present, a display screen is generally arranged on a face recognition access control, and various information such as advertisements and notifications are displayed for people through the display screen.
At present, the information on the face recognition entrance guard is generally put in fixed pictures, so that a user cannot conveniently further know more detailed contents.
Disclosure of Invention
The embodiment of the application provides an information pushing method and device based on face detection, so that detailed contents of information can be displayed for a user.
In a first aspect, an embodiment of the present application provides an information pushing method based on face detection, including:
determining a user account according to the face recognition result, and determining the type of the concerned information of the corresponding user based on the user account;
based on the type of the concerned information, searching corresponding information in an information database, and generating link information based on the information;
displaying the information and the link information;
and pushing the information to the user account in response to the pushing request.
Further, before determining the user account according to the face recognition result, the method further includes:
establishing a binding relationship between a user account and a face verification image;
collecting information viewing records of users, determining the concerned information types of the corresponding users based on the information viewing records, and establishing the association relationship between the user accounts and the concerned information types.
Further, the determining a user account according to the face recognition result and determining the type of the information of interest of the corresponding user based on the user account includes:
acquiring a face recognition result obtained by face recognition entrance guard shooting;
retrieving a face verification image matched with the face recognition result;
determining the user account corresponding to the face recognition result according to the binding relationship between the face verification image and the user account;
and determining the type of the concerned information of the corresponding user according to the incidence relation between the user account and the type of the concerned information.
Further, the information comprises an information picture and an information link address, and the link information comprises an information two-dimensional code;
the retrieving the corresponding information in the information database based on the attention information type and generating the link information based on the information includes:
based on the attention information type, searching matched information in an information database, and acquiring an information picture and an information link address in the information;
and generating a two-dimensional code based on the information link address, and determining the two-dimensional code as the information two-dimensional code.
Further, the displaying the information and the link information includes:
displaying the information and the link information, and displaying a push button;
the pushing the information to the user account in response to the pushing request comprises:
receiving a push request, wherein the push request is generated in response to a triggering operation of the push button;
and pushing the information to the user account based on the information corresponding to the pushing request and the user account.
Further, the retrieving corresponding information in an information database based on the type of the information of interest and generating link information based on the information includes:
determining facial state features of the user according to the face recognition result;
and searching corresponding information in an information database based on the attention information type and the facial state characteristics, and generating link information based on the information.
Further, after the displaying the information and the link information, the method further includes:
determining push authorization information of the user account;
and pushing the information to the user terminal bound with the user account based on the pushing authorization information.
Further, the determining the user account according to the face recognition result includes:
acquiring a first face recognition result obtained by face recognition entrance guard shooting;
judging the face size of each face according to the first face recognition result;
determining a first target face according to the face size, and acquiring first target face feature information of the first target face;
retrieving a face verification image matched with the first target face based on the first target face feature information;
and determining the user account corresponding to the first face recognition result according to the binding relationship between the face verification image and the user account.
Further, the pushing the information to the user account in response to the pushing request includes:
responding to the pushing request to obtain a second face recognition result obtained by face recognition entrance guard shooting;
judging the face orientation of each face according to the second face recognition result;
determining a second target face according to the face orientation, and acquiring second target face feature information of the second target face;
retrieving a face verification image matched with the second target face based on the second target face feature information;
determining the user account corresponding to the second face recognition result according to the binding relationship between the face verification image and the user account;
and pushing the information to the user account.
In a second aspect, an embodiment of the present application provides an information pushing apparatus based on face detection, including an information type determining module, an information determining module, a display module, and a pushing module, where:
the information type determining module is used for determining a user account according to a face recognition result and determining the type of the concerned information of the corresponding user based on the user account;
the information determining module is used for searching corresponding information in an information database based on the attention information type and generating link information based on the information;
the display module is used for displaying the information and the link information;
and the pushing module is used for responding to a pushing request to push the information to the user account.
In a third aspect, an embodiment of the present application provides a computer device, including: a memory and one or more processors;
the memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the information push method based on face detection according to the first aspect.
In a fourth aspect, the present application provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are used to perform the information pushing method based on face detection according to the first aspect.
According to the embodiment of the application, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check the information conveniently, and the user experience is optimized.
Drawings
Fig. 1 is a flowchart of an information pushing method based on face detection according to an embodiment of the present application;
fig. 2 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application;
fig. 3 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application;
fig. 4 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application;
fig. 5 is a schematic diagram of an information pushing apparatus based on face detection according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Fig. 1 is a flowchart illustrating an information push method based on face detection according to an embodiment of the present disclosure, where the information push method based on face detection according to the embodiment of the present disclosure may be implemented by an information push apparatus based on face detection, and the information push apparatus based on face detection may be implemented in a hardware and/or software manner and integrated in a computer device.
The following description will be given by taking the information pushing method based on face detection executed by the information pushing device based on face detection as an example. Referring to fig. 1, the information push method based on face detection includes:
s101: and determining a user account according to the face recognition result, and determining the type of the concerned information of the corresponding user based on the user account.
Illustratively, a face recognition result is obtained by detecting a face by a face recognition access control, a camera for shooting the face is arranged on the face recognition access control, and when the face is detected by the camera, the face is subjected to feature analysis and extraction, so that a face recognition result is obtained. Furthermore, after the face is detected and a face recognition result is generated, the face recognition access control sends the face recognition result to an information pushing device based on the face detection.
And after the face recognition result is received, matching the face verification image with the face recognition result in a face image library, and after the matching is successful, unlocking the entrance guard by the face recognition entrance guard so that the user can enter and exit the face recognition entrance guard. The face verification image and the user account have a binding relationship, namely, a user uploads a personal face image as the face verification image when establishing the user account, the face verification image and the user account are bound, and the face verification image is stored in a face image library.
Further, the type of information of interest should be understood as the type of information of interest to the user, such as food, clothing, digital, cosmetics, etc. The type of the information concerned by the user can be used for collecting information browsing conditions of user equipment (such as a mobile phone, a computer and the like) related to a user account, for example, collecting information browsing conditions of the user equipment on a wechat public number, a wechat applet and a webpage, and judging the type of the information concerned by the user according to information type distribution conditions corresponding to the information browsing conditions.
Optionally, the type of the information of interest of each user may be determined according to a preset time interval or a time period for browsing the collected information, and the determined type of the information of interest is bound with the user account. Or determining the collected information browsing condition after determining the user account according to the face recognition result, and binding the determined attention information type with the user account. Furthermore, the type of the information concerned by the user can be set by the user, and the set type of the information concerned by the user is bound with the user account.
After a user account corresponding to a face recognition result uploaded by a face recognition entrance guard is determined, the type of the information concerned by the user is determined according to the binding relationship between the user account and the type of the information concerned.
S102: and searching corresponding information in an information database based on the attention information type, and generating link information based on the information.
Illustratively, after the type of the information of interest of the user is determined, the information corresponding to the type of the information of interest is searched in the information database. The information can record the information type of the information by setting a label, and when the information is searched, the label corresponding to the information type to be searched is determined according to the concerned information type, so that the corresponding information is determined. Or classifying and establishing folders in the information database according to the information types, storing the information in the folders of the corresponding types, and determining the corresponding information according to the folder corresponding to the concerned information type.
The number of the information messages may be one or more, if the number of the information messages is one, one information message may be randomly confirmed from the corresponding tag or the folder, or one information message may be confirmed according to a predetermined policy (e.g., determined according to time), and if the number of the information messages is multiple, a plurality of information messages may be randomly confirmed from the corresponding tag or the folder, or a plurality of information messages may be confirmed according to a predetermined policy (e.g., determined according to time).
Further, after the information is determined, link information for accessing the detailed information address is generated according to the detailed information address corresponding to the information, and the detailed information address can be accessed according to the link information. In other embodiments, the link information corresponding to each information may be pre-stored or generated in the information database, and the corresponding link information may be determined directly according to the information. The website corresponding to the detailed information address records detailed content related to the information, and the link information may be a website, a two-dimensional code, or other information that can be used to log in the detailed information address.
S103: and displaying the information and the link information.
Illustratively, after the information and the link information are determined, a display screen on the face recognition entrance guard is controlled to display the information and the link information.
In other embodiments, if a plurality of determined information messages are provided, the corresponding information messages and the corresponding link messages can be sequentially displayed according to a set time interval.
S104: and pushing the information to the user account in response to the pushing request.
The push request can be triggered by a push button displayed on the face recognition access control. Furthermore, after the push button is triggered, the face recognition access control generates a push request pointing to the currently displayed information and the user account corresponding to the current user in response to the operation triggered by the push button, and sends the push request to the information push device based on the face detection, and the information push device based on the face detection responds to the push request to push the corresponding information and/or the detailed information of the information to the corresponding user account.
In other embodiments, the push button may also be set in a face recognition access control in a physical button manner, and the push request may be triggered by pressing the push button.
According to the method, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check conveniently, and the user experience is optimized.
In another embodiment, the face recognition result includes a recognition result of a human face or a head-worn article, such as, for example, a recognition that a user wears glasses or a hat. Accordingly, the determined type of the user's attention information may be the type of the worn object, such as glasses or a hat. Optionally, the identification of the user wearing the article further includes identifying characteristics of the article, such as a style, a brand, and the like, in addition to identifying the type of the article, and determining the corresponding article style and the article brand as the information type concerned by the user. Therefore, content identification and information recommendation can be carried out in a diversified mode, and information recommendation efficiency and conversion rate are remarkably improved.
In one embodiment, pushing the information to the user account in response to the push request comprises: and responding to the pushing request, and pushing the information to the user account of the pre-bound user equipment. The pre-bound user device may be a smartphone used by a user, and the user account of the user device may be an operating system account (such as an apple system account) or a user registration account. Preferably, the pushing the information to the user account of the pre-bound user equipment includes: the method comprises the steps of obtaining app applications installed by user equipment, determining apps capable of being used for displaying information (if the information is football boot information, corresponding push display can be push display of apps such as Tianmao apps and Jingdong apps), displaying the information through the apps capable of displaying the information, specifically, obtaining app interfaces of the information to be displayed in advance, calling access rights to display the information through the apps, or sending the information to a server of the apps, and displaying the information through the apps after the information is sent to the apps through the server. Optionally, in another embodiment, in addition to displaying the information, the item corresponding to the information may be directly added to the shopping cart of the app, so as to facilitate the operation processing of the user and reduce the operation steps of the user.
Fig. 2 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application, where the information pushing method based on face detection is an embodiment of the information pushing method based on face detection. Referring to fig. 2, the information push method based on face detection includes:
s201: and establishing a binding relationship between the user account and the face verification image.
For example, the establishment of the user account may be performed on network platforms such as a wechat, a QQ, a microblog, and the like, and the embodiment takes the wechat as an example for description. Furthermore, a user account is registered on a pre-established WeChat applet or a WeChat public number, a personal face image of the user is uploaded in a mode of photographing or picture library selection to serve as a face verification image, the face verification image and the user account are bound, and the face verification image and the user account are stored in a face image library.
S202: collecting information viewing records of users, determining the concerned information types of the corresponding users based on the information viewing records, and establishing the association relationship between the user accounts and the concerned information types.
Illustratively, after a user establishes a user account, information viewing records under the user account are collected, and a binding relationship between the information viewing records and the corresponding user account is established. Specifically, when a user performs information viewing operation by using the wechat applet and the wechat public number, a corresponding information viewing record is generated, and meanwhile, browsing records of terminal equipment (such as a mobile phone, a tablet computer and the like) logging in a user account on a webpage, a shopping website and the like are collected and stored as the information viewing record. Furthermore, the WeChat applet and the WeChat public number can push various kinds of consultation, and when the user clicks to check, the WeChat applet and the WeChat public number collect the browsing times, the browsing duration and the corresponding information types of each user and generate corresponding information checking records.
Furthermore, the type of the information concerned by the user can be determined according to the information type corresponding to the latest record in the consultation record, the information type which is recently viewed by the user is determined according to the timestamp corresponding to the information viewing record, and the information type is determined as the type of the information concerned by the user. The method can also set the weight for different information types according to the information viewing record corresponding to the user account, the setting of the weight can be determined according to the browsing duration, the browsing times, the browsing platform and the like, the weighting processing is carried out on various information types, and finally the corresponding attention information type is determined.
Furthermore, after the type of the concerned information corresponding to the user is determined, an association relationship between the user account and the type of the concerned information is established, and the type of the concerned information corresponding to the user account can be determined based on the association relationship.
S203: and acquiring a face recognition result obtained by face recognition entrance guard shooting.
Specifically, be provided with the camera that is used for shooing the people's face on face identification entrance guard, simultaneously, but be provided with touch operation's display screen on the face identification entrance guard, can show the shooting picture and the face scanning guide picture of camera on the display screen to the guide user carries out face identification scanning. When the camera detects the face, the feature analysis and extraction are carried out on the face, so that a face recognition result is obtained. After the face is detected and a face recognition result is generated, the face recognition entrance guard sends the face recognition result to an information pushing device based on face detection.
S204: and retrieving the face verification image matched with the face recognition result.
Specifically, after receiving the face recognition result, matching the face recognition result with a face verification image in a face image library, and determining the face verification image matched with the face recognition result.
Optionally, after the matching is successful, the face recognition entrance guard unlocks the entrance guard so that the user can enter and exit the face recognition entrance guard. In other embodiments, a face image library can be set in the face recognition entrance guard, and matching of face verification images is performed locally after a face recognition result is generated, so that the speed of entrance guard unlocking is increased.
S205: and determining the user account corresponding to the face recognition result according to the binding relationship between the face verification image and the user account.
Specifically, after the face verification image corresponding to the face recognition result is matched, the user account bound with the face verification image is determined according to the binding relationship between the face verification image and the user account.
S206: and determining the type of the concerned information of the corresponding user according to the incidence relation between the user account and the type of the concerned information.
Specifically, after a user account corresponding to a user for unlocking the face recognition access control is determined, the type of the attention information of the corresponding user is determined according to the incidence relation between the user account and the type of the attention information. The type of the information of interest of each user can be determined according to a preset time interval or a time period for browsing the collected information, and the determined type of the information of interest is bound with the user account. Or determining the collected information browsing condition after determining the user account according to the face recognition result, and binding the determined attention information type with the user account. Furthermore, the type of the information concerned by the user can be set by the user, and the set type of the information concerned by the user is bound with the user account.
S207: and searching matched information in an information database based on the attention information type, and acquiring an information picture and an information link address in the information.
Illustratively, after the type of the information of interest of the user is determined, information corresponding to the type of the information of interest is searched in an information database and is sent to a face recognition entrance guard for display. Specifically, the information includes an information picture and an information link address, and after the matched information is searched in the information database, the information picture and the information link address in the information are obtained.
For example, the information may record the information type of the information by setting a tag, and when retrieving the information, the tag corresponding to the information type to be retrieved is determined according to the information type of interest, so as to determine the corresponding information. Or classifying and establishing folders in the information database according to the information types, storing the information in the folders of the corresponding types, and determining the corresponding information according to the folder corresponding to the concerned information type.
The information picture is used for displaying brief information of the information, such as a cover page of an advertisement and the like, and detailed information of the information is recorded in a corresponding webpage in the information link address. In other embodiments, the information may further include multimedia information such as voice information and video information that can be played on the face recognition access control, and the multimedia information may be synchronously sent to the face recognition access control for playing according to a preset display policy.
S208: and generating a two-dimensional code based on the information link address, and determining the two-dimensional code as the information two-dimensional code.
Specifically, after the information picture and the information link address are determined, a two-dimensional code generating tool is called, a two-dimensional code is generated based on the information address, the two-dimensional code is determined to be an information two-dimensional code, and the information two-dimensional code is link information. Optionally, the information two-dimensional code may be generated synchronously when the information link address is stored in the information base, or generated based on the determined information link address after the information link address is determined according to the face recognition result, or generated in real time after the face recognition entrance guard receives the information link address.
S209: and displaying the information and the link information, and displaying a push button.
Specifically, after the information and the link information are determined, the face recognition access control display screen displays an information picture in the information, and synchronously displays an information two-dimensional code corresponding to the link information in an overlapping mode on the information picture. In other embodiments, the information picture and the information two-dimensional code can be superimposed and synthesized, that is, the information two-dimensional code is attached to the information picture, and the face recognition entrance guard directly displays the superimposed consultation picture.
Furthermore, when the information picture is displayed, a push button is synchronously displayed on the display screen, optionally, a character pattern of 'one-key push' can be displayed on the push button, and a user is guided to click.
S210: receiving a push request, the push request being generated in response to a triggering operation of the push button.
S211: and pushing the information to the user account based on the information corresponding to the pushing request and the user account.
The push request is triggered in response to the click operation of the push button, when the push button is clicked, the face recognition access control generates a push request pointing to the current user account and information, and sends the push condition to the information push device based on face detection.
Further, after receiving the push request, according to the information and the user account to which the push request is directed, the detailed information of the corresponding user consultation is sent to the user account, for example, the detailed information is sent to the corresponding user account through a wechat public number.
According to the method, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check conveniently, and the user experience is optimized. Meanwhile, information checking records of the user are collected in advance, the type of the information concerned by the user is determined according to the information checking records of the user, information which meets personal requirements better is pushed to the user, and user experience is improved.
Fig. 3 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application, where the information pushing method based on face detection is an embodiment of the information pushing method based on face detection. Referring to fig. 3, the information push method based on face detection includes:
s301: and determining a user account according to the face recognition result, and determining the type of the concerned information of the corresponding user based on the user account.
S302: and determining the facial state characteristics of the user according to the face recognition result.
The facial state features comprise expression features, fatigue degree features and other features which reflect the facial state of the user. Further, after the face recognition result uploaded by the face recognition entrance guard is obtained and successfully matched with the face verification image in the face image library, the face recognition result is analyzed to obtain the facial state characteristics of the user.
Illustratively, a facial state feature extraction model can be established based on a neural network model, the facial state feature extraction model is trained according to facial images of different figures under different expressions and fatigue degrees, namely, a facial recognition result corresponding to the facial image is taken as input, and expression features and fatigue degree features are taken as output, the facial state feature extraction model is trained until the training times and accuracy reach preset requirements, and then the training of the facial state feature extraction model is completed. When the facial state features of the user need to be acquired, the face recognition result is input into the facial state feature extraction model, and the facial state features of the user are acquired.
S303: and searching corresponding information in an information database based on the attention information type and the facial state characteristics, and generating link information based on the information.
For example, the association relationship between the facial status features and the product information of different product information in the information types is pre-established, wherein the association relationship between the product information and the facial status features can be recorded in the form of a pointer, a linked list or a table, which is not limited in this embodiment. For example, according to different using effects of different products in different facial states, the product with better using effect is corresponding to the corresponding facial state, and the association relationship between the corresponding product information and the facial state characteristics is rewarded, for example, the product information corresponding to the product capable of relieving the tension of people is associated with the facial state characteristics reflecting the tension.
Further, after the attention information type of the user account is determined, based on the current facial state feature of the user, product information related to the facial state feature in the attention information type is determined, corresponding information in an information database is searched based on the product information, and link information is generated based on the information.
S304: and displaying the information and the link information.
S305: and determining the push authorization information of the user account.
Specifically, when the user establishes the user account, whether to accept the automatic pushing information or not can be set on a user account setting interface, corresponding pushing authorization information is generated based on the selection of the user, and the binding relationship between the pushing authorization information and the user account is established. It will be appreciated that the settings for accepting automatic push information may also be modified upon completion of the user account.
Further, after the information for display is determined, the pushing authorization information of the user is determined according to the binding relationship between the pushing authorization information and the user account, so that whether the user receives automatic pushing of the information is determined.
S306: and pushing the information to the user terminal bound with the user account based on the pushing authorization information.
Specifically, whether the user accepts automatic pushing of the information is determined according to the pushing authorization information of the user, if so, the information is pushed to the user terminal bound with the user account, otherwise, the information is not automatically pushed to the user.
In another embodiment, when setting whether to accept the automatic push information, the type of the accepted automatic push information or the type of the rejected automatic push information may be selected, and whether to push the information to the user terminal bound with the user account may be determined according to whether the information belongs to the type of the accepted automatic push information.
S307: and pushing the information to the user account in response to the pushing request.
According to the method, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check conveniently, and the user experience is optimized. Meanwhile, the information displayed to the user is determined by combining the facial features of the user, the requirements of the user are better met, whether the information is automatically pushed to the user is determined according to the pushing authorization information of the user, and the user experience is improved.
In one embodiment, after the facial features of the current user are determined, pushed information corresponding to the user who is the same as or close to the facial features is further determined, and the information is pushed to the user. Specifically, facial features of different users and corresponding pushed information are recorded in the database, corresponding recording is performed in the database after each information pushing, when the facial features of one user are newly determined, searching is performed in the database to determine recommended information used by the user with the same facial features, and the information is recommended to the current user.
Fig. 4 is a flowchart of another information pushing method based on face detection according to an embodiment of the present application, where the information pushing method based on face detection is an embodiment of the information pushing method based on face detection. Referring to fig. 4, the information push method based on face detection includes:
s401: the method comprises the steps of obtaining a first face recognition result obtained by face recognition entrance guard shooting, and judging the face size of each face according to the first face recognition result.
Specifically, be provided with the camera that is used for shooing the people's face on face identification entrance guard, simultaneously, but be provided with touch operation's display screen on the face identification entrance guard, can show the shooting picture and the face scanning guide picture of camera on the display screen to the guide user carries out face identification scanning. When the camera detects the face, the feature analysis extraction is carried out on the face, and therefore a first face recognition result is obtained. After the face is detected and a first face recognition result is generated, the face recognition entrance guard sends the first face recognition result to an information pushing device based on face detection.
Further, after receiving the first face recognition result, determining the number of people included in the first face recognition result, if only one number of people exists, directly determining the face as the first target face, otherwise, determining according to the size of each face.
Further, the sizes of the faces in the face recognition result are obtained, and sequencing is carried out according to the sizes of the faces. The judgment of the human face size can be determined according to the area surrounded by the human face edges in the first human face recognition result.
S402: and determining a first target face according to the face size, and acquiring first target face characteristic information of the first target face.
Specifically, the face with the largest face in the first recognition result is determined as a first target face, and first target face feature information of the first target face is obtained.
In other embodiments, the first target face may also be determined according to the face orientation in the first face recognition result, for example, the orientation of the face whose face size reaches a preset threshold is obtained, the orientation of the faces is determined based on the face orientation determination model, and the face with the largest size in the faces facing the camera or the screen is determined as the first target face.
In other embodiments, the determination of the first target face may also be performed according to the gazing duration of the face in the first face recognition result, for example, the gazing duration of the face with the face size reaching a preset threshold is obtained, and the face with the gazing duration reaching a time threshold is determined as the first target face.
S403: and retrieving a face verification image matched with the first target face based on the first target face feature information.
Illustratively, after the first target face feature information is confirmed, matching of face verification images is performed on the first target face feature information in a face image library, and a face verification image matched with the first target face feature information is determined.
S404: and determining the user account corresponding to the first face recognition result according to the binding relationship between the face verification image and the user account, and determining the type of the attention information of the corresponding user based on the user account.
The establishment of the user account can be performed on network platforms such as a wechat, a QQ, a microblog and the like, and the embodiment takes the wechat as an example for description. Furthermore, a user account is registered on a pre-established WeChat applet or a WeChat public number, a personal face image of the user is uploaded in a mode of photographing or picture library selection to serve as a face verification image, the face verification image and the user account are bound, and the face verification image and the user account are stored in a face image library.
Illustratively, after a user establishes a user account, information viewing records under the user account are collected, and a binding relationship between the information viewing records and the corresponding user account is established. Furthermore, the type of the information concerned by the user can be determined according to the information type corresponding to the latest record in the consultation record, the information type which is recently viewed by the user is determined according to the timestamp corresponding to the information viewing record, and the information type is determined as the type of the information concerned by the user.
Specifically, after the face verification image corresponding to the first target face feature information is matched, the user account bound with the face verification image is determined according to the binding relationship between the face verification image and the user account, and the type of the attention information of the corresponding user is determined based on the user account.
S405: and searching corresponding information in an information database based on the attention information type, and generating link information based on the information.
S406: and displaying the information and the link information.
S407: and responding to the pushing request to obtain a second face recognition result obtained by face recognition entrance guard shooting, and judging the face orientation of each face according to the second face recognition result.
S408: and determining a second target face according to the face orientation, and acquiring second target face feature information of the second target face.
The push request is triggered in response to the click operation of the push button, when the push button is clicked, the face recognition access control generates a push request pointing to the current user account and information, and sends the push condition to the information push device based on face detection.
Further, after the pushing request is received, the face recognition entrance guard is controlled to shoot, so that a second face recognition result is obtained, and the face orientation in the second face recognition result is judged based on the face orientation judgment model.
For example, a face orientation determination model may be established based on a neural network model, and the face orientation determination model is trained according to face images of different people in different orientations, that is, a face recognition result corresponding to the face image is used as an input, and the face orientation is output to train the face orientation determination model until the training times and accuracy meet preset requirements, so that training of the face orientation determination model is completed. And when the face orientation of each face in the second face recognition result needs to be obtained, inputting the second face recognition result into the face orientation determination model to obtain the face orientation of each face.
Further, the face facing the camera or the screen is determined as a second target face and second target face feature information of the second target face is obtained.
S409: and retrieving a face verification image matched with the second target face based on the second target face feature information.
Specifically, when the second target face feature information is determined, the face verification image is retrieved from the face image library based on the second target face feature information, so that the face verification image matched with the second target face is determined.
S410: and determining the user account corresponding to the second face recognition result according to the binding relationship between the face verification image and the user account, and pushing the information to the user account.
Specifically, based on the binding relationship between the matched face verification image and the user account, the user account corresponding to the second face recognition result is determined, and the information is pushed to the user account, for example, the detailed information is sent to the corresponding user account through a wechat public number.
According to the method, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check conveniently, and the user experience is optimized. Meanwhile, the user needing to unlock the access control is determined according to the size of the face, so that the displayed information is more accurate, and when the user needs to obtain more detailed information about the information, the user sending the pushing request can be determined according to the specific face orientation when the pushing button is triggered, so that the pushing of the information is more accurate, and the user experience is optimized.
Fig. 5 is a schematic diagram of an information pushing apparatus based on face detection according to an embodiment of the present application. Referring to fig. 5, the information pushing apparatus based on face detection includes an information type determining module 51, an information determining module 52, a display module 53 and a pushing module 54.
The information type determining module 51 is configured to determine a user account according to a face recognition result, and determine a type of information of interest of a corresponding user based on the user account; an information determining module 52, configured to retrieve corresponding information in an information database based on the type of the information of interest, and generate link information based on the information; a display module 53, configured to display the information and the link information; the pushing module 54 is configured to push the information to the user account in response to a push request.
According to the method, the corresponding user account is determined according to the face recognition result detected by the face recognition access control, the attention information type of the user is determined according to the user account, the information needing to be displayed to the user is determined according to the attention information type of the user, the link information corresponding to the information is displayed to the user, the user can check more detailed content related to the information through the link information, the information can be sent to the user account in response to the pushing request of the user, the user can check conveniently, and the user experience is optimized.
The embodiment of the application also provides computer equipment which can be integrated with the information pushing device based on the face detection provided by the embodiment of the application. Fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application. Referring to fig. 6, the computer apparatus includes: an input device 63, an output device 64, a memory 62, and one or more processors 61; the memory 62 for storing one or more programs; when the one or more programs are executed by the one or more processors 61, the one or more processors 61 implement the information pushing method based on face detection as provided in the above embodiments. Wherein the input device 63, the output device 64, the memory 62 and the processor 61 may be connected by a bus or other means, as exemplified by the bus connection in fig. 6.
The memory 62 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the information pushing method based on face detection according to any embodiment of the present application (for example, the information type determining module 51, the information determining module 52, the display module 53, and the pushing module 54 in the information pushing apparatus based on face detection). The memory 62 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory 62 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 62 may further include memory located remotely from the processor 61, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 63 is operable to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 64 may include a display device such as a display screen.
The processor 61 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 62, so as to implement the above-mentioned information push method based on face detection.
The information pushing device and the computer equipment based on the face detection can be used for executing the information pushing method based on the face detection provided by the embodiment, and have corresponding functions and beneficial effects.
The present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the information push method based on face detection provided in the foregoing embodiments, where the information push method based on face detection includes: determining a user account according to the face recognition result, and determining the type of the concerned information of the corresponding user based on the user account; based on the type of the concerned information, searching corresponding information in an information database, and generating link information based on the information; displaying the information and the link information; and pushing the information to the user account in response to the pushing request.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application includes computer-executable instructions, and the computer-executable instructions are not limited to the information pushing method based on face detection described above, and may also perform related operations in the information pushing method based on face detection provided in any embodiments of the present application.
The information pushing apparatus, device and storage medium based on face detection provided in the above embodiments may execute the information pushing method based on face detection provided in any embodiment of the present application, and reference may be made to the information pushing method based on face detection provided in any embodiment of the present application without detailed technical details described in the above embodiments.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.

Claims (12)

1. An information push method based on face detection is characterized by comprising the following steps:
determining a user account according to the face recognition result, and determining the type of the concerned information of the corresponding user based on the user account;
based on the type of the concerned information, searching corresponding information in an information database, and generating link information based on the information;
displaying the information and the link information;
and pushing the information to the user account in response to the pushing request.
2. The method of claim 1, wherein before determining the user account according to the face recognition result, the method further comprises:
establishing a binding relationship between a user account and a face verification image;
collecting information viewing records of users, determining the concerned information types of the corresponding users based on the information viewing records, and establishing the association relationship between the user accounts and the concerned information types.
3. The method as claimed in claim 2, wherein the determining a user account according to the face recognition result and determining the type of the information of interest of the corresponding user based on the user account comprises:
acquiring a face recognition result obtained by face recognition entrance guard shooting;
retrieving a face verification image matched with the face recognition result;
determining the user account corresponding to the face recognition result according to the binding relationship between the face verification image and the user account;
and determining the type of the concerned information of the corresponding user according to the incidence relation between the user account and the type of the concerned information.
4. The information pushing method based on face detection as claimed in claim 1, wherein the information includes an information picture and an information link address, and the link information includes an information two-dimensional code;
the retrieving the corresponding information in the information database based on the attention information type and generating the link information based on the information includes:
based on the attention information type, searching matched information in an information database, and acquiring an information picture and an information link address in the information;
and generating a two-dimensional code based on the information link address, and determining the two-dimensional code as the information two-dimensional code.
5. The information pushing method based on face detection as claimed in claim 1, wherein the displaying the information and the link information includes:
displaying the information and the link information, and displaying a push button;
the pushing the information to the user account in response to the pushing request comprises:
receiving a push request, wherein the push request is generated in response to a triggering operation of the push button;
and pushing the information to the user account based on the information corresponding to the pushing request and the user account.
6. The information pushing method based on face detection as claimed in claim 1, wherein the retrieving corresponding information in an information database based on the attention information type and generating link information based on the information comprises:
determining facial state features of the user according to the face recognition result;
and searching corresponding information in an information database based on the attention information type and the facial state characteristics, and generating link information based on the information.
7. The information pushing method based on face detection as claimed in claim 1, further comprising, after the displaying the information and the link information:
determining push authorization information of the user account;
and pushing the information to the user terminal bound with the user account based on the pushing authorization information.
8. The information pushing method based on face detection according to any one of claims 1-7, wherein the determining the user account according to the face recognition result comprises:
acquiring a first face recognition result obtained by face recognition entrance guard shooting;
judging the face size of each face according to the first face recognition result;
determining a first target face according to the face size, and acquiring first target face feature information of the first target face;
retrieving a face verification image matched with the first target face based on the first target face feature information;
and determining the user account corresponding to the first face recognition result according to the binding relationship between the face verification image and the user account.
9. The method for pushing information based on face detection according to any one of claims 1-7, wherein the pushing the information to the user account in response to the pushing request includes:
responding to the pushing request to obtain a second face recognition result obtained by face recognition entrance guard shooting;
judging the face orientation of each face according to the second face recognition result;
determining a second target face according to the face orientation, and acquiring second target face feature information of the second target face;
retrieving a face verification image matched with the second target face based on the second target face feature information;
determining the user account corresponding to the second face recognition result according to the binding relationship between the face verification image and the user account;
and pushing the information to the user account.
10. The utility model provides an information pusher based on face detection which characterized in that, includes information type determination module, information determination module, display module and propelling movement module, wherein:
the information type determining module is used for determining a user account according to a face recognition result and determining the type of the concerned information of the corresponding user based on the user account;
the information determining module is used for searching corresponding information in an information database based on the attention information type and generating link information based on the information;
the display module is used for displaying the information and the link information;
and the pushing module is used for responding to a pushing request to push the information to the user account.
11. A computer device, comprising: a memory and one or more processors;
the memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the information push method based on face detection according to any one of claims 1 to 9.
12. A storage medium containing computer-executable instructions, wherein the computer-executable instructions are used for executing the information pushing method based on human face detection according to any one of claims 1 to 9 when executed by a computer processor.
CN202010047101.XA 2020-01-16 2020-01-16 Information pushing method and device based on face detection Pending CN111291087A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010047101.XA CN111291087A (en) 2020-01-16 2020-01-16 Information pushing method and device based on face detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010047101.XA CN111291087A (en) 2020-01-16 2020-01-16 Information pushing method and device based on face detection

Publications (1)

Publication Number Publication Date
CN111291087A true CN111291087A (en) 2020-06-16

Family

ID=71026652

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010047101.XA Pending CN111291087A (en) 2020-01-16 2020-01-16 Information pushing method and device based on face detection

Country Status (1)

Country Link
CN (1) CN111291087A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111738777A (en) * 2020-07-17 2020-10-02 杭州脸脸会网络技术有限公司 Coupon pushing method and device, storage medium and intelligent terminal
CN112699159A (en) * 2020-11-13 2021-04-23 杭州海康威视系统技术有限公司 Data display method, device and equipment
CN114415908A (en) * 2022-03-14 2022-04-29 深圳市海清视讯科技有限公司 Display method, display device, electronic equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112209A (en) * 2013-04-16 2014-10-22 苏州和积信息科技有限公司 Audience statistical method of display terminal, and audience statistical system of display terminal
CN104573619A (en) * 2014-07-25 2015-04-29 北京智膜科技有限公司 Method and system for analyzing big data of intelligent advertisements based on face identification
CN108234591A (en) * 2017-09-21 2018-06-29 深圳市商汤科技有限公司 The content-data of identity-based verification device recommends method, apparatus and storage medium
CN108492431A (en) * 2018-05-30 2018-09-04 中海云智慧(北京)物联网科技有限公司 A kind of intelligent access control system
CN108597081A (en) * 2018-04-25 2018-09-28 国家计算机网络与信息安全管理中心 A kind of content displaying method and device based on Internet of Things
CN108595651A (en) * 2018-04-27 2018-09-28 深圳码隆科技有限公司 Customized information display methods, device and user terminal based on recognition of face
CN109064618A (en) * 2018-11-01 2018-12-21 重庆赛赢赛特科技有限公司 Intelligent entrance guard terminal and system
CN110661882A (en) * 2019-10-17 2020-01-07 北京睿家科技有限公司 Information pushing method and pushing equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112209A (en) * 2013-04-16 2014-10-22 苏州和积信息科技有限公司 Audience statistical method of display terminal, and audience statistical system of display terminal
CN104573619A (en) * 2014-07-25 2015-04-29 北京智膜科技有限公司 Method and system for analyzing big data of intelligent advertisements based on face identification
CN108234591A (en) * 2017-09-21 2018-06-29 深圳市商汤科技有限公司 The content-data of identity-based verification device recommends method, apparatus and storage medium
CN108597081A (en) * 2018-04-25 2018-09-28 国家计算机网络与信息安全管理中心 A kind of content displaying method and device based on Internet of Things
CN108595651A (en) * 2018-04-27 2018-09-28 深圳码隆科技有限公司 Customized information display methods, device and user terminal based on recognition of face
CN108492431A (en) * 2018-05-30 2018-09-04 中海云智慧(北京)物联网科技有限公司 A kind of intelligent access control system
CN109064618A (en) * 2018-11-01 2018-12-21 重庆赛赢赛特科技有限公司 Intelligent entrance guard terminal and system
CN110661882A (en) * 2019-10-17 2020-01-07 北京睿家科技有限公司 Information pushing method and pushing equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨露菁: "《人工智能启蒙 第3册》", 中国铁道出版社有限公司, pages: 249 - 252 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111738777A (en) * 2020-07-17 2020-10-02 杭州脸脸会网络技术有限公司 Coupon pushing method and device, storage medium and intelligent terminal
CN112699159A (en) * 2020-11-13 2021-04-23 杭州海康威视系统技术有限公司 Data display method, device and equipment
CN114415908A (en) * 2022-03-14 2022-04-29 深圳市海清视讯科技有限公司 Display method, display device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
AU2018321357B2 (en) Preserving privacy in surveillance
US10706448B2 (en) Service monitoring system and service monitoring method
CN109816441B (en) Policy pushing method, system and related device
US20180270253A1 (en) Method and system for identifying a human or machine
US20180088969A1 (en) Method and device for presenting instructional content
US11520824B2 (en) Method for displaying information, electronic device and system
CN112104899A (en) Information recommendation method and device in live broadcast, electronic equipment and storage medium
CN111291087A (en) Information pushing method and device based on face detection
CN105874451A (en) Methods, systems, and media for presenting supplemental information corresponding to on-demand media content
WO2008084053A1 (en) Adjusting a consumer experience based on a 3d captured image stream of a consumer response
CN111556366A (en) Multimedia resource display method, device, terminal, server and system
CN107341187A (en) Search processing method, device, equipment and computer-readable storage medium
CN111723237B (en) Media content access control method
CN111949702B (en) Abnormal transaction data identification method, device and equipment
WO2022134836A1 (en) Article value evaluation method and apparatus, and computer device and storage medium
WO2014126735A1 (en) Real time object scanning using a mobile phone and cloud-based visual search engine
CN111026967A (en) Method, device, equipment and medium for obtaining user interest tag
CN109598120A (en) Security postures intelligent analysis method, device and the storage medium of mobile terminal
US20170034092A1 (en) Method and device for processing short message
CN115544475A (en) Business service method and device
CN109213397B (en) Data processing method and device and user side
KR100985949B1 (en) System and method for providing product information service by mobile network system
TW201418997A (en) System and method for posting messages by audio signals
CN112000266B (en) Page display method and device, electronic equipment and storage medium
CN113010017B (en) Multimedia information interactive display method, system and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination