JP7130771B2 - Attention information processing method and device, storage medium, and electronic device - Google Patents

Description

<Cross reference to related applications>
This application is filed based on a Chinese patent application with application number 201810374723.6 and filed on April 24, 2018, and claims priority from the Chinese patent application. The entire contents of the application are incorporated herein by reference.
TECHNICAL FIELD The present invention relates to the technical field of information statistics, and more particularly to a method and apparatus for processing attention information, a storage medium, and an electronic device.

With the development of technology, each company uses various methods to promote their services, and a more common method of promoting services is to recommend information to users through some multimedia platforms. is. These information may be in image form, audio form, video form, etc., advertisements being one example.

With the explosive increase in recommendation information, the recommendation information lacks accuracy. Blindly displaying information that users don't like not only wastes multimedia resources, but also reduces users' commitment to multimedia resources. It can be seen that the degree of user's attention to certain recommended information has important reference value for subsequent accurate recommendations.

To solve the above technical problems, embodiments of the present invention provide attention information processing methods and devices, storage media, and electronic devices.

The attention information processing method provided by an embodiment of the present invention includes:
exhibiting the first content data;
obtaining feature information of at least one display object, and determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
and performing attention information statistics for the first content data based on attention information between the at least one exhibit and the first content data.

In an embodiment of the invention, the method comprises:
a step of recommending second content data waiting to be exhibited based on the statistical attention information;
The method further includes displaying the second content data.

In an embodiment of the present invention, characteristic information of at least one display object is obtained, and attention information between the at least one display object and the first content data is obtained based on the characteristic information of the at least one display object. The step of determining
obtaining line-of-sight direction information of at least one display object, and determining attention information between the at least one display object and the first content data based on the line-of-sight direction information of the at least one display object; include.

In an embodiment of the present invention, the attention information includes instruction information for instructing whether or not the exhibition object will pay attention to the first content data.

determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
Determining whether the line of sight of the at least one display object has entered a first display area based on the line-of-sight direction information of the at least one display object, and displaying the first content data in the first display area is the display area in the device,
In the case of the display target whose line of sight has entered the first display area, the instruction information corresponding to the display target is used to indicate that the display target has paid attention to the first content data,
In the case of the display object whose line of sight did not enter the first display area, the instruction information corresponding to the display object is used to indicate that the display object did not pay attention to the first content data.

In an embodiment of the present invention, the attention information further includes a degree of attention to the first content data to be exhibited.

determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
For an exhibition object whose line of sight has entered the first display area, a target position where the line of sight of the exhibition object is projected onto the first display area is determined based on the line-of-sight direction information of the display object, and the target position is determined. The method further includes determining a degree of attention to the first content data to be displayed based on a positional relationship with respect to the first display area.

In an embodiment of the present invention, the attention information further includes attention time for the first content data to be displayed.

determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
For an exhibition object whose line of sight entered the first display area, the time when the line of sight of the exhibition object entered the first display area is statistically calculated, and based on the statistical time, the first content data of the exhibition object is displayed. The step of determining attention time is further included.

In an embodiment of the present invention, the step of obtaining viewing direction information of the at least one display object comprises:
obtaining eye angle information and head pose information for at least one exhibit;
and calculating gaze direction information of the at least one exhibit based on eye angle information and head pose information of the at least one exhibit.

In an embodiment of the present invention, the step of obtaining eye angle information and head pose information of the at least one exhibit subject comprises:
obtaining at least one image of the exhibit;
processing the image of the at least one exhibit using a first neural network to obtain eyeball angle information of the at least one exhibit;
and processing the image of the at least one exhibit using a second neural network to obtain head pose information of the at least one exhibit.

In an embodiment of the present invention, the step of performing attention information statistics for said first content data based on attention information between said at least one display object and said first content data comprises:
Number of people who pay attention to the first content data, number of people corresponding to different degrees of attention, and different A step of statisticizing attention information of at least one of the number of people corresponding to the attention time is included.

In an embodiment of the present invention, the feature information of the at least one display object is obtained, and based on the feature information of the at least one display object, attention between the at least one display object and the first content data is obtained. The step of confirming the information is
Obtaining geographical position information of at least one display object, and determining attention information between the at least one display object and the first content data based on the geographical position information of the at least one display object. Including steps.

In an embodiment of the present invention, the attention information includes instruction information for instructing whether or not the exhibition object will pay attention to the first content data.

determining attention information between the at least one display object and the first content data based on the geographical location information of the at least one display object;
Determining whether the position of the at least one exhibit falls within the first area range determined based on the position of the display device, based on the geographic location information of the at least one exhibit. including
When the position of the at least one display object is within the range of the first area, the indication information corresponding to the display object is to indicate that the display object has paid attention to the first content data. used,
If the position of the at least one display object does not fall within the range of the first area, the instruction information corresponding to the display object indicates that the display object did not pay attention to the first content data. including being used to

In an embodiment of the present invention, the attention information further includes attention time for the first content data to be displayed.

determining attention information between the at least one display object and the first content data based on the geographical location information of the at least one display object;
Statisticalize the time when the position of the at least one display object of the display object entered the first area range for the display object whose position of the at least one display object entered the first area range, and the statistical time determining an attention time for the first content data to be displayed, based on .

In an embodiment of the present invention, the step of performing attention information statistics for said first content data based on attention information between said at least one display object and said first content data comprises:
Among the number of people who pay attention to the first content data and the number of people corresponding to different attention times for the first content data, based on the attention information between the at least one exhibition object and the first content data statistically at least one of the information of interest.

In an embodiment of the present invention, the feature information of the at least one display object is obtained, and based on the feature information of the at least one display object, attention between the at least one display object and the first content data is obtained. The step of confirming the information is
obtaining interactive information between the at least one display object and the first content data, and based on the interactive information between the at least one display object and the first content data, the at least one display object and the first content data.

In an embodiment of the present invention, the step of performing attention information statistics for said first content data based on attention information between said at least one display object and said first content data comprises:
Based on the attention information between the at least one display object and the first content data, the step of statistically calculating the attention information of the number of people corresponding to different interactive frequencies with respect to the first content data.

An apparatus for processing attention information provided by an embodiment of the present invention comprises:
a display unit for displaying the first content data;
an acquisition unit for acquiring characteristic information of at least one display object;
a determination unit for determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
a statistics unit for performing attention information statistics on the first content data based on the attention information between the at least one display object and the first content data.

In an embodiment of the invention, the device comprises:
further comprising a recommendation unit for recommending the second content data waiting for display based on the statistical attention information;
The display unit displays the second content data.

In an embodiment of the present invention, the obtaining unit further obtains viewing direction information of the at least one display object.

The determining unit further determines attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object.

In an embodiment of the present invention, the attention information includes instruction information used to instruct whether or not an exhibition object will pay attention to the first content data,
The determination unit is
for determining whether or not the line of sight of the at least one exhibition object has entered a first display area, which is a display area of first content data on a display device, based on the line-of-sight direction information of the at least one exhibition object; In the case of an exhibit object having a first determination subunit and whose line of sight enters the first display area, the instruction information corresponding to the exhibit object indicates that the exhibit object has paid attention to the first content data. In the case of a display object whose line of sight did not enter the first display area, the instruction information corresponding to the display object indicates that the display object did not pay attention to the first content data. used for

In an embodiment of the present invention, the attention information further includes a degree of attention to the first content data to be exhibited,
The determination unit is
For an exhibition object whose line of sight has entered the first display area, a target position where the line of sight of the exhibition object is projected onto the first display area is determined based on the line-of-sight direction information of the display object, and the target position is determined. It further comprises a second determination sub-unit for determining the degree of attention to the first content data to be exhibited based on the positional relationship with respect to the first display area.

In an embodiment of the present invention, the attention information further includes attention time for the first content data to be displayed,
The determination unit is
For an exhibition object whose line of sight entered the first display area, the time when the line of sight of the exhibition object entered the first display area is statistically calculated, and based on the statistical time, the first content data of the exhibition object is displayed. It further comprises a third determining subunit for determining attention time.

In an embodiment of the invention the acquisition unit comprises:
an acquisition subunit for acquiring eye angle information and head pose information of at least one exhibit;
a calculation subunit for calculating gaze direction information of the at least one exhibit based on eye angle information and head pose information of the at least one exhibit.

In an embodiment of the invention, said acquisition subunit further comprises:
obtaining at least one exhibitable image;
using a first neural network to process the image of the at least one exhibit to obtain eyeball angle information of the at least one exhibit;
Processing the image of the at least one exhibit using a second neural network to obtain head pose information of the at least one exhibit.

In an embodiment of the present invention, the statistical unit further focuses the first content data on the first content data based on the attention information between the at least one display object and the first content data. At least one of attention information among the number of people who are watching, the number of people corresponding to different degrees of attention, and the number of people corresponding to different attention times is statistically collected.

In an embodiment of the present invention, said obtaining unit further obtains the geographical location information of at least one display object.

The determining unit further determines attention information between the at least one exhibiting object and the first content data based on the geographic location information of the at least one exhibiting object.

In an embodiment of the present invention, the attention information includes instruction information used to instruct whether or not an exhibition object will pay attention to the first content data,
The determination unit is
for determining, based on the geographic location information of the at least one display object, whether the position of the at least one display object falls within the first area range determined based on the position of the display device; wherein if the position of the at least one display object is within the range of the first area, the indication information corresponding to the display object is that the display object is in the first When the position of the at least one display object does not fall within the range of the first area, the instruction information corresponding to the display object is used to indicate that the content data has been paid attention to. Used to indicate that the subject did not pay attention to the first content data.

In an embodiment of the present invention, the attention information further includes attention time for the first content data to be displayed,
The determination unit is
Statisticalize the time when the position of the at least one display object of the display object entered the first area range for the display object whose position of the at least one display object entered the first area range, and the statistical time further comprising a fifth determining sub-unit for determining an attention time for the first content data to be exhibited based on the;

In an embodiment of the present invention, the statistical unit further focuses the first content data on the first content data based on the attention information between the at least one display object and the first content data. At least one attention information of the number of people who are watching and the number of people corresponding to different attention times is statistically collected.

In an embodiment of the present invention, the obtaining unit further obtains interactive information between at least one exhibit and the first content data.

The determining unit further determines attention information between the at least one exhibitable object and the first content data based on interactive information between the at least one exhibitable object and the first content data. .

In an embodiment of the present invention, the statistic unit further comprises counting the number of people corresponding to different interactive frequencies for the first content data, based on attention information between the at least one display object and the first content data. Statistical attention information of.

A storage medium provided by an embodiment of the present invention stores executable instructions, and when the executable instructions are executed by a processor, the above-described attention information processing method is realized.

An electronic device provided by an embodiment of the present invention includes:
a memory configured to store executable instructions;
a processor for communicating with the memory and executing the executable instructions to implement the method of processing information of interest described above.

The technical solution of an embodiment of the present invention is to exhibit first content data, obtain characteristic information of at least one exhibit object, and obtain attention information between the at least one exhibit object and the first content data and perform attention information statistics for the first content data based on the attention information between the at least one display object and the first content data. Adopting the technical solution of the embodiment of the present invention, attention information statistics for the first content data is realized, and the statistical result is used as the basis or influence factor for allocating the subsequent multimedia resources, and according to the exhibition object's own business. Accurate recommendations for recommending matched information to exhibitors can be achieved.

1 is a network architecture diagram of an embodiment of the present invention; FIG. 1 is a first schematic flow chart of a method for processing attention information according to an embodiment of the present invention; 4 is a second schematic flow chart of a method for processing attention information according to an embodiment of the present invention; 3 is a third schematic flow chart of a method for processing attention information according to an embodiment of the present invention; 4 is a fourth schematic flow chart of a method for processing attention information according to an embodiment of the present invention; 1 is a first schematic diagram of a configuration of an attention information processing apparatus according to an embodiment of the present invention; FIG. FIG. 4 is a second schematic diagram of the configuration of the attention information processing apparatus according to the embodiment of the present invention; 1 is a schematic diagram of a configuration of an electronic device according to an embodiment of the present invention; FIG.

Various exemplary embodiments of the invention are described in detail below with reference to the accompanying drawings. Note that unless otherwise stated, the relative arrangements, numerical formulas and values of the components and steps described in these embodiments do not limit the scope of the invention.

At the same time, for ease of explanation, it should be understood that the sizes of the various parts shown in the drawings are not drawn according to actual proportionality.

The following description of at least one exemplary embodiment is merely exemplary in nature and in no way serves as a limitation on the invention and its application or use.

Techniques, methods, and equipment known to those of ordinary skill in the relevant fields may not be described in detail, but where appropriate, said techniques, methods, and equipment are considered part of the description. There is a need.

Note that in the following drawings, similar reference numbers and letters indicate similar items, so that once a particular item is defined in one drawing, it need not be further described in subsequent drawings.

Embodiments of the present invention may be applied to electronic equipment, such as computer systems/servers, capable of operating in numerous other general purpose or special purpose computing system environments or configurations. Examples of well-known computing systems, environments, and/or configurations suitable for use with electronic devices such as computer systems/servers include personal computer systems, server computer systems, thin clients, thick clients, handhelds or laptops. top, microprocessor-based systems, set-top boxes, programmable consumer electronic products, networked personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems. These include, but are not limited to:

Electronic devices such as computer systems/servers may be described in the general context of computer system-executable instructions (such as program modules) being executed by a computer system. Generally, program modules include routines, programs, programs of interest, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. A computer system/server can be implemented in a distributed cloud computing environment. In distributed cloud computing environments, tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in storage media in local or remote computing systems including storage devices.

FIG. 1 is a schematic diagram of all hardware entities for interactive execution of information in an embodiment of the present invention. FIG. 1 includes servers 11 . . . 1n and display devices 21-24. Display devices 21-24 perform information interaction with a server over a wired or wireless network. Display devices are realized through mobile phones, desktops, PCs, all-in-ones, VR devices, AR devices, and so on. In one example, servers 11...1n interact with a first type of terminal (e.g., terminals where advertisers are located, or targets for which advertising material and content promotions are provided, etc.) over a network, After submitting an advertisement delivered by a type of terminal (such as a terminal where an advertiser is located or a target for providing advertising material and content promotion), the corresponding advertisement is stored in the server cluster. By adding an administrator, a series of processes such as checking advertisements delivered by the first type of terminals (such as terminals where advertisers are located, or targets for providing advertising materials and content promotions, etc.) can be executed. For terminals of the first type (terminals where advertisers are located, or targets for which advertising materials and content promotions are provided, etc.), terminals in which the display devices 21 to 24 are present are terminals of the second type (for example, It is sometimes referred to as the terminal where the normal display object is located, or the object of advertisement display or exposure). Advertisements can be added to all applications installed on the display device or to specified applications (game applications, video applications, navigation applications, etc.) to display more recommendations for display.

The example of FIG. 1 above is merely an example of a system architecture for implementing embodiments of the present invention, and embodiments of the present invention are not limited to the system architecture described in FIG. 1 above. Various embodiments of the present invention are proposed based on the system architecture.

FIG. 2 is a first schematic flow chart of a method for processing attention information according to an embodiment of the present invention. As shown in FIG. 2, the attention information processing method includes the following steps.

At step 201, the first content data is displayed.

In embodiments of the present invention, the first content data can be any kind of recommendation information. The recommended information can be, but is not limited to, still images, dynamic images, short videos, long videos, interactive games, and the like. In one example, the first content data can be advertisements.

In embodiments of the present invention, the display device may be a general display screen, an all-in-one machine, a projector, a virtual reality (VR) device, an augmented reality (AR) device, or the like.

In step 202, obtain feature information of at least one display object, and determine attention information between the at least one display object and the first content data based on the feature information of the at least one display object; .

Here, the exhibited object can be a user, a robot, or other smart devices.

In an embodiment of the present invention, the feature information includes at least one of viewing direction information of the display object, geographical position information of the display object, and interactive information between the display object and the first content data.

Taking the line-of-sight direction information of the display target as an example, the line-of-sight of the display target can indicate whether the display target pays attention to the first content data. When the object to be exhibited pays attention to the first content data, it is possible to further determine the degree of attention and attention time for the first content data to be exhibited. These pieces of attention information can estimate the effect of presenting the first content data to the exhibition target.

Here, since the attention information can be accurately expressed by the viewing direction information of the exhibition object, the attention information determined by the viewing direction information of the exhibition object is more consistent with the original intention of the exhibition object. More accurate information recommendation can be achieved by using the attention information as a reference for subsequent recommended information.

Taking the geographic location information of the display object as an example, the geographic location information of the display object can indicate whether the display object is near the display device. It can also indicate whether or not the content data has been noticed. When an object to be exhibited pays attention to the first content data, it is possible to further determine the degree of attention and attention time for the first content data to be exhibited, and the attention information determined based on the geographical position information is also sent to the object to be exhibited. can also be used to gauge the effect of presenting the first content data of

Here, the geographic location information of the display object can be obtained by camera or navigation positioning system, so it can be realized very conveniently and quickly, and the cost is low. By referring to the attention information determined by the geographical location information for the subsequent recommended information, it is possible to match most of the recommended items to be exhibited and improve the effect of presenting the recommended information.

Taking the interactive information between the display object and the first content data as an example, the interaction with the display object of the first content data (for example, browse operation, download operation, praise operation, attention operation, click operation, etc.) can also be displayed. It can indicate whether or not the target pays attention to the first content data. When the display object focuses on the first content data, the interactive frequency (the number of interactive operations triggered within a unit time) for the first content data of the display object can be further determined, and based on these interactive information The decided attention information can also be used to estimate the effect of presenting the first content data to the exhibition target.

Here, the interactive information to be displayed can be directly obtained by the display device or the remote control device, and does not require a separate device, so it can be realized very conveniently and quickly, and the cost is low. be done. The attention information determined by the interactive information can accurately display the attention information. By using such attention information as a reference for subsequent recommendation information, more accurate information recommendation can be realized. As a result, it is possible to greatly improve the effect of presenting the recommended information in accordance with the purpose of the exhibition.

Here, different feature information can be used to estimate attention information between the display object and the first content data from different dimensions. In one example, attention information between at least one display object and the first content data can be determined based on one type of feature information. In another example, attention information between at least one exhibitable object and the first content data can be determined based on two or three types of characteristic information.

At step 203, performing statistics of attention information for the first content data based on the attention information between the at least one display object and the first content data.

For example, based on the attention information between the at least one exhibition object and the first content data, the number of people who pay attention to the first content data, the number of people corresponding to different degrees of attention, and different At least one of attention information of the number of people corresponding to the attention time and the number of people corresponding to different interactive frequencies is collected.

Optionally, the method further comprises recommending second content data to be displayed based on the statistical attention information, and displaying the second content data on the display device.

In one embodiment, the content data exhibited on the display device may be randomly recommended by a server or cloud, or may be personalized based on specific reference information. . In one example, if no reference information was obtained by the server or cloud, randomly recommend information to the exhibit. In another example, if reference information is obtained by a server or cloud, recommend personalized information for the exhibit based on the reference information. Here, the reference information can be obtained by performing statistics on the attention information of each content data.

Here, the reference information can be the number of people paying attention to specific information, the number of people corresponding to different attention levels, the number of people corresponding to different attention times, or the number of people corresponding to different interaction frequencies, but is limited to these. not. Content data recommendations may be implemented in conjunction with any two or more of these references.

For example, there are three candidate information, information 1, information 2, and information 3, respectively. In a certain statistical period, when 30 people pay attention to information 1, 20 people pay attention to information 2, and 3 people pay attention to information 3, information 1 is displayed as content data. to exhibit.

For example, there are three candidate information, information 1, information 2, and information 3, respectively. In a certain statistical period, 30 people pay attention to information 1, 30 people pay attention to information 2, 30 people pay attention to information 3, and the degree of attention of information 1 is high. The number of people with attention level is 4, the number of people with attention level of information 2 is 17 people, and the number of people with attention level of information 3 is high level attention level is 12 people. In this case, information 2 is exhibited on the display device as content data.

For example, there are three candidate information, information 1, information 2, and information 3, respectively. In a certain statistical period, 30 people pay attention to information 1, 30 people pay attention to information 2, 30 people pay attention to information 3, and the attention time of information 1 is 3 minutes. If the number of people who exceeded the attention time by 3 minutes is 4, the number of people who exceeded the attention time by 3 minutes in information 2 is 17, and the number of people who exceeded the attention time by 3 minutes in information 3 is 12, the information 2 is changed to the content Data is displayed on the display device.

For example, there are three candidate information, information 1, information 2, and information 3, respectively. If the number of interactions with information 1 is 10, the number of interactions with information 2 is 13, and the number of interactions with information 3 is 0 in a certain statistical period, information 2 is treated as content data. displayed on the display device as

FIG. 3 is a second schematic flowchart of a method for processing attention information according to an embodiment of the present invention. As shown in FIG. 3, the attention information processing method includes the following steps.

At step 301, the first content data is displayed.

In embodiments of the present invention, the first content data can be any kind of recommendation information. The recommended information can be, but is not limited to, still images, dynamic images, short videos, long videos, interactive games, and the like. In one example, the first content data can be advertisements.

In the embodiments of the present invention, the display device can be a general display screen, an all-in-one device, a projector, a VR device, an AR device, and so on.

In one embodiment, the first content data exhibited on the display device may be randomly recommended by a server or cloud, or may be recommended for personalization based on specific reference information. good too. In one example, if no reference information was obtained by the server or cloud, randomly recommend information to the exhibit. In another example, if reference information is obtained by a server or cloud, recommend personalized information for the exhibit based on the reference information. Here, the reference information can be obtained by performing statistics on the attention information of each first content data.

In step 302, obtaining line-of-sight direction information of at least one display object, and determining attention information between the at least one display object and the first content data based on the line-of-sight direction information of the at least one display object. Determine.

In embodiments, gaze direction information for at least one exhibit can be obtained based on the following method.
The method comprises obtaining eye angle information and head pose information of at least one exhibit;
and calculating gaze direction information of the at least one exhibit based on eye angle information and head pose information of the at least one exhibit.

Furthermore, the step of obtaining eye angle information and head pose information of at least one exhibit subject comprises:
obtaining at least one image of the exhibit;
processing the image of the at least one exhibit using a first neural network to obtain eyeball angle information of the at least one exhibit;
and processing the image of the at least one exhibit using a second neural network to obtain head pose information of the at least one exhibit.

For example, using a camera, target images (face images, etc.) P1, P2, P3, P4 of five exhibition objects (exhibition object 1 to exhibition object 5) within the shooting range supported by the camera, and You can get P5. Each target image is input to a first neural network and a second neural network respectively. Taking P1 as an example, the first neural network is used to acquire iris angle estimation information eye1 of P1. A second neural network is used to obtain head posture estimation information head1 of P1. Then, based on the eyeball angle prediction information eye1 and the head posture prediction information head1, the line-of-sight direction information of the display object 1 can be calculated. For P2 to P5, the line-of-sight direction information of the exhibition object 2 to the exhibition object 5 can be obtained in the same manner.

In an embodiment of the present invention, attention information between at least one display object and the first content data is determined based on viewing direction information of at least one display object. Here, the attention information includes at least one of the following, respectively:
1) instruction information used for instructing whether or not the display object pays attention to the first content data;
2) degree of attention to the first content data to be exhibited, and
3) attention time for the first content data to be exhibited;

In one embodiment, the attention information includes instruction information for instructing whether or not an exhibit subject pays attention to the first content data. The step of determining attention information between at least one display target and the first content data includes: based on the line-of-sight direction information of the at least one display target, the line of sight of the at least one display target is aligned with the first content data; including the step of determining whether or not the content data has entered a first display area, which is the display area of the display device; The information is used to indicate that the display object has paid attention to the first content data, and in the case of the display object whose line of sight did not enter the first display area, the instruction information corresponding to the display object is It is used to indicate that the display target did not pay attention to the first content data.

For example, line-of-sight direction information S1, S1, S3, S4, and S5 of five exhibition objects (exhibition object 1 to exhibition object 5) are acquired. It should also be understood that the line-of-sight direction information has different representations based on different coordinate systems. When S1 and S3 enter the first display area where the first content data exist and S2, S4, and S5 do not enter the first display area where the first content data exist, the display object 1 and the display object 3 are displayed in the first display area. 1 content data, and exhibit target 2, exhibit target 4, and exhibit target 5 do not pay attention to the first content data.

In one embodiment, the attention information further includes a degree of attention of the display target to the first content data, and the at least one display target and the first display target are displayed on the basis of line-of-sight direction information of the at least one display target. The step of determining attention information between the content data and the content data includes, for an exhibition object whose line of sight enters the first display area, displaying the line of sight of the exhibition object in the first display area based on the line-of-sight direction information of the exhibition object. and determining the degree of attention to the first content data to be displayed based on the positional relationship of the target position with respect to the first display area.

For example, line-of-sight direction information S1, S2, S3, S4, and S5 of five exhibition objects (exhibition object 1 to exhibition object 5) are acquired. When S1 and S3 enter the first display area where the first content data exists, the exhibit target 1 and the exhibit target 3 are paying attention to the first content data. In the case of exhibition object 1, the degree of attention to the first content data of exhibition object 1 can be estimated from the target position T1 of the first display area projected by S1. In one example, the closer the distance from the center O of the first display area, the higher the degree of attention. Accordingly, the degree of attention F1 for the first content data of the exhibition object 1 is inversely proportional to the distance from T1 to O, and similarly, the degree of attention F3 for the first content data of the exhibition object 3 can be obtained. In one embodiment, the degree of attention can be quantified into several levels. For example, the object whose distance from the center O is in the first proximity range is the high attention level, the object whose distance from the center O is the second proximity range is the medium attention level, and the distance from the center O is the third proximity level. is the low attention level.

In one embodiment, the attention information further includes an attention time for the first content data of the display object, and the at least one display object and the first display object are displayed based on the line-of-sight direction information of the at least one display object. The step of determining attention information between the content data and the content data includes, for an exhibition object whose line of sight entered the first display area, statisticizing the time when the line of sight of the display object entered the first display area, and calculating the statistic time. determining an attention time for the first content data to be exhibited, based on;

For example, line-of-sight direction information S1, S2, S3, S4, and S5 of five exhibition objects (exhibition object 1 to exhibition object 5) are acquired. When S1 and S3 enter the first display area where the first content data exists, the exhibit target 1 and the exhibit target 3 are paying attention to the first content data. In the case of exhibition object 1, the attention time for the first content data of exhibition object 1 is time T1 when S1 enters the first display area. Similarly, for exhibition object 3, the attention time for the first content data is time T3 when S3 enters the first display area.

In an embodiment of the present invention, attention information between the object to be exhibited and the first content data may include one or any two or more of the above information.

In step 303, performing statistics of attention information for the first content data based on the attention information between the at least one display object and the first content data.

Following step 302, different attentional information can provide important references for subsequent information recommendations as different dimensions. Therefore, based on the attention information between the at least one exhibition object and the first content data, the number of people who pay attention to the first content data, the number of people corresponding to different degrees of attention, and the number of people who pay attention to the first content data are different. At least one of the number of people corresponding to the attention time and the number of people corresponding to different interactive frequencies should be statistically collected.

In one example, within a statistical period (for example, 3 hours), the statistics of attention information are performed for information 1, and information that the number of people who pay attention to information 1 is 20, information 1 is attention and high attention Information in which the number of people at the level is 7, information in which the number of people paying attention to the information 1 and the number of people in the medium attention level is 6, information in which the number of people at the low attention level is 7 and attention to the information 1, The number of people who pay attention to the information 1 and whose attention time is in the first time range is 2, and the number of people who are watching the information 1 and whose attention time is in the second time range is 5. At least one of the information and the information that the number of people who pay attention to the information 1 and whose attention time is in the third time range is 13 is obtained.

The different information statistically obtained as described above can be used to estimate the state of attention to the first content data to be exhibited in different dimensions. The degree to which the first content data is effectively revealed (that is, the degree to which it is effectively viewed) can be estimated with reference to one or more of the above information. Therefore, it can provide an important reference for accurate recommendation of subsequent information.

In the embodiment of the present invention, attention information can be accurately represented by the sight line information of the display object, so that the attention information determined by the sight line information of the display object is more consistent with the original intention of the display object. By using such attention information as a reference for subsequent recommended information, more accurate information recommendation can be realized.

FIG. 4 is a third schematic flowchart of a method for processing attention information according to an embodiment of the present invention. As shown in FIG. 4, the attention information processing method includes the following steps.

At step 401, the first content data is displayed.

In embodiments of the present invention, the first content data can be any kind of recommendation information. The recommended information can be, but is not limited to, still images, dynamic images, short videos, long videos, interactive games, and the like. In one example, the first content data can be advertisements.

In the embodiments of the present invention, the display device can be a general display screen, an all-in-one device, a projector, a VR device, an AR device, and so on.

In step 402, obtain geographic location information of at least one exhibitable object, and focus between the at least one exhibitable object and the first content data based on the geographic location information of the at least one exhibitable object; Confirm the information.

In embodiments, geographic location information for at least one exhibit can be obtained based on the following methods.
The method comprises acquiring at least one image of the exhibit;
A third neural network is used to process the image of the at least one exhibit to obtain geographic location information of the at least one exhibit.

In another embodiment, geographic location information for at least one exhibit can be obtained based on the following methods.
The method obtains GPS information of each exhibitable terminal through a relay node (such as a wireless access node) to determine geographic location information of at least one exhibitable.

In an embodiment of the present invention, attention information between the at least one display object and the first content data is determined based on the geographic location information of the at least one display object. Here, the attention information includes at least one of the following, respectively:
1) instruction information used for instructing whether or not the display object pays attention to the first content data; and
2) attention time for the first content data to be exhibited;

In one embodiment, the attention information includes instruction information for instructing whether or not the exhibition object will pay attention to the first content data. For this reason, the step of determining attention information between the at least one display object and the first content data based on the geographical position information of the at least one display object includes geographic location of the at least one display object. determining whether the position of the at least one display object falls within the first area range determined based on the position of the display device, based on the target position information; In the case of an object whose position is within the range of the first area, the instruction information corresponding to the object to be exhibited is used to indicate that the object to be exhibited has paid attention to the first content data, and the at least In the case of an exhibition object whose position did not fall within the range of the first area, the instruction information corresponding to the exhibition object indicates that the exhibition object did not pay attention to the first content data. used for

For example, geographical position information D1, D2, D3, D4, and D5 of five exhibition objects (exhibition object 1 to exhibition object 5) are acquired. It should be understood that geographical location information has different representations based on different coordinate systems. When D1 and D3 fall within the first area range, and D2, D4, and D5 do not fall within the first area range where the first content data exists, the exhibit target 1 and the exhibit target 3 pay attention to the first content data. , and display target 2, display target 4, and display target 5 do not pay attention to the first content data.

In one embodiment, the attention information further includes an attention time for the first content data of the exhibition object, and based on geographical location information of the at least one exhibition object, the at least one exhibition object and the first display object. The step of determining attention information between one piece of content data is performed when the position of the at least one display object of the display object is determined with respect to the display object whose position of the at least one display object is within the first area range. The step of counting the time for entering the first area range and determining the attention time for the first content data to be exhibited based on the statistical time is further included.

For example, geographical position information D1, D2, D3, D4, and D5 of five exhibition objects (exhibition object 1 to exhibition object 5) are acquired. When D1 and D3 enter the first area range, exhibition object 1 and exhibition object 3 are paying attention to the first content data. In the case of exhibition object 1, the time of the first content data is the time T1 when D1 enters the first area range. Similarly, in the case of exhibition object 3, the time at which the first content data is noticed is the time T3 when D3 enters the first area range.

In an embodiment of the present invention, attention information between the display object and the first content data may include one or any two or more of the above information.

In step 403, obtaining geographic location information of at least one exhibit object, and focusing attention between the at least one exhibit object and the first content data based on the geographic location information of the at least one exhibit object; Confirm the information.

Following step 402, different attentional information can provide important references for subsequent information recommendations as different dimensions. Therefore, based on the attention information between the at least one exhibition object and the first content data, the number of people who pay attention to the first content data and the number of people corresponding to different attention times for the first content data It is necessary to statistically focus on at least one of the information of interest.

In one example, in a statistical period (for example, 3 hours), the attention information of the information 1 is statistically analyzed. information in which the number of people within the time range is 2; information in which the number of people watching information 1 is 5 and whose attention time is within the second time range; At least one piece of information is obtained from the information that the number of people whose attention time is within the third time range is 13.

Different statistical information can estimate the state of attention to the first content data to be exhibited in different dimensions. Using one or more of the above information as a reference, the degree to which the first content data is effectively represented (i.e., the degree to which it is effectively viewed) can be estimated, and is an important reference for subsequent accurate information recommendations. can be provided.

In the embodiment of the present invention, the geographic location information of the display object can be acquired by the camera or the navigation positioning system, which is very convenient and quick to implement, and the cost is low. By referring to the attention information determined by the geographical location information for the subsequent recommended information, it is possible to match most of the recommended items to be exhibited and improve the effect of presenting the recommended information.

FIG. 5 is a third schematic flowchart of a method for processing attention information according to an embodiment of the present invention. As shown in FIG. 5, the attention information processing method includes the following steps.

At step 501, the first content data is displayed.

In embodiments of the present invention, the first content data can be any kind of recommendation information. The recommended information can be, but is not limited to, still images, dynamic images, short videos, long videos, interactive games, and the like. In one example, the first content data can be advertisements.

In the embodiments of the present invention, the display device can be a general display screen, an all-in-one device, a projector, a VR device, an AR device, and so on.

In step 502, obtaining interactive information between the at least one exhibitable object and the first content data; based on the interactive information between the at least one exhibitable object and the first content data, the at least Attention information is determined between one exhibition object and the first content data.

Interactivity (eg, viewing action, downloading action, admiring action, attention action, clicking action, etc.) to the exhibited first content data can also indicate whether the exhibited object pays attention to the first content data. The exhibition object can pay attention to the first content data, and further, the interactive frequency (the number of interactive operations triggered within a unit time) for the first content data of the exhibition object can be determined.

In one embodiment, the attention information includes interactive information between the display object and the first content data.

For example, five exhibit objects (exhibit object 1 to exhibit object 5) performed interactive operations on the first content data. In the statistical period, the number of operations performed by exhibition object 1 on the first content data is N1, the number of operations on the first content data by exhibition object 2 is N2, and the number of operations on the first content data by exhibition object 3 is N2. The number of operations performed on the first content data is N3, the number of operations performed by the exhibit target 4 on the first content data is N4, and the exhibit target 5 operates on the first content data. is N5, N1 to N5 can represent interactive information between the five exhibition objects and the first content data. Not limited to this, the interactive information can be estimated according to the time each display object operates the first content data.

At step 503, performing statistics of attention information for the first content data based on the attention information between the at least one display object and the first content data.

Following step 502, different attentional information can provide important references for subsequent information recommendations as different dimensions. Therefore, based on the attention information between the at least one exhibition object and the first content data, it is necessary to collect statistics on the attention information of the number of people corresponding to different interactive frequencies with respect to the first content data.

In one example, within a statistical period (for example, 3 hours), the attention information of the information 1 is statistically analyzed, and the frequency of interaction with the information 1 is within the first frequency range. Obtain information that the number of people whose frequency of interaction with 1 is in the second frequency range is 25 people.

In the embodiment of the present invention, the interactive information to be displayed can be directly obtained by using the display device or the remote control device, and no separate device is required, which is very convenient and quick. can be achieved and costs can be kept low. The attention information determined by the interactive information can accurately express the attention information, and such attention information can be used as a reference for subsequent recommendation information to achieve more accurate information recommendation. Therefore, it is possible to greatly improve the effect of presenting the recommended information in accordance with the purpose of the exhibition.

FIG. 6 is a first schematic diagram of the configuration of the attention information processing apparatus according to the embodiment of the present invention. As shown in FIG. 6, the attention information processing device includes:
a display unit 601 for displaying the first content data;
an obtaining unit 602 for obtaining characteristic information of at least one exhibit;
a determining unit 603 for determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
a statistics unit 604 for performing attention information statistics on the first content data based on the attention information between the at least one display object and the first content data.

Those skilled in the art should understand that the implementation functions of the units in the attention information processing apparatus shown in FIG. 6 can be understood with reference to the relevant description of the attention information processing method. The function of each unit in the attention information processing apparatus shown in FIG. 6 can be realized by a program running on a processor, or can be realized by a specific logic circuit.

FIG. 7 is a second schematic diagram of the configuration of the attention information processing apparatus according to the embodiment of the present invention. As shown in FIG. 7, the attention information processing device includes:
a display unit 601 for displaying the first content data;
an obtaining unit 602 for obtaining characteristic information of at least one exhibit;
a determining unit 603 for determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
a statistics unit 604 for performing attention information statistics on the first content data based on the attention information between the at least one display object and the first content data.

In one embodiment, the device comprises:
further comprising a recommendation unit 605 for recommending the second content data waiting for display based on the statistical attention information;
The display unit further displays the second content data on the display device.

In one embodiment, the obtaining unit 602 further obtains viewing direction information of at least one exhibit object.

The determining unit 603 further determines attention information between the at least one exhibiting object and the first content data based on the viewing direction information of the at least one exhibiting object.

In one embodiment, the attention information includes indication information used to indicate whether an exhibition object should pay attention to the first content data, and the determination unit 603 includes:
for determining whether or not the line of sight of the at least one exhibition object has entered a first display area, which is a display area of first content data on a display device, based on the line-of-sight direction information of the at least one exhibition object; In the case of the display object having the first determination subunit 6031 and the line of sight entering the first display area, the instruction information corresponding to the display object indicates that the display object has paid attention to the first content data. In the case of an exhibition object whose line of sight did not enter the first display area, the instruction information corresponding to the exhibition object indicates that the exhibition object did not pay attention to the first content data. used for

In one embodiment, the attention information further includes a degree of attention to the first content data to be displayed, and the determination unit 603 includes:
For an exhibition object whose line of sight has entered the first display area, a target position where the line of sight of the exhibition object is projected onto the first display area is determined based on the line-of-sight direction information of the display object, and the target position is determined. It further comprises the second determination sub-unit 6032 for determining the degree of attention to the first content data to be exhibited based on the positional relationship with respect to the first display area.

In one embodiment, the attention information further includes a degree of attention to the first content data to be displayed, and the determination unit 603 includes:
For an exhibition object whose line of sight entered the first display area, the time when the line of sight of the exhibition object entered the first display area is statistically calculated, and based on the statistical time, the first content data of the exhibition object is displayed. It further comprises said third determining sub-unit 6033 for determining attention time.

In one embodiment, the obtaining unit 602 includes:
an acquisition subunit 6021 for acquiring eye angle information and head pose information of at least one exhibit;
a calculation subunit 6022 for calculating gaze direction information of the at least one exhibit based on eye angle information and head pose information of the at least one exhibit.

In one embodiment, the acquisition subunit 6021 further acquires at least one image of the exhibit,
using a first neural network to process the image of the at least one exhibit to obtain eyeball angle information of the at least one exhibit;
Processing the image of the at least one exhibit using a second neural network to obtain head pose information of the at least one exhibit.

In one embodiment, the statistics unit 604 further focuses the first content data relative to the first content data based on the attention information between the at least one display object and the first content data. At least one of the number of people, the number of people corresponding to different degrees of attention, and the number of people corresponding to different attention times is statistically collected.

In one embodiment, the obtaining unit 602 further obtains geographic location information of at least one exhibit.

The determining unit 603 further determines attention information between the at least one exhibiting object and the first content data based on the geographic location information of the at least one exhibiting object.

In one embodiment, the attention information includes indication information used to indicate whether an exhibition object should pay attention to the first content data, and the determination unit 603 includes:
for determining, based on the geographic location information of the at least one display object, whether the position of the at least one display object falls within the first area range determined based on the position of the display device; and a fourth determination sub-unit 6034 of, when the position of the at least one display object is within the first area range, the indication information corresponding to the display object is that the display object is in the first 1 content data, and in the case of the display object whose position did not fall within the first area range, the instruction information corresponding to the display object is It is used to indicate that the display target did not pay attention to the first content data.

In one embodiment, the attention information further includes a degree of attention to the first content data to be displayed, and the determination unit 603 includes:
Statisticalize the time when the position of the at least one display object of the display object entered the first area range for the display object whose position of the at least one display object entered the first area range, and the statistical time further comprising a fifth determining sub-unit 6035 for determining an attention time for the first content data to be displayed based on;

In one embodiment, the statistics unit 604 further focuses the first content data relative to the first content data based on the attention information between the at least one display object and the first content data. At least one attention information of the number of people and the number of people corresponding to different attention times is statistically collected.

In one embodiment, the obtaining unit 602 further obtains interactive information between at least one exhibit and the first content data.

The determining unit 603 further determines attention information between the at least one display object and the first content data based on interactive information between the at least one display object and the first content data. do.

In one embodiment, the statistical unit 604 further calculates the number of people corresponding to different interactive frequencies for the first content data based on attention information between the at least one exhibit and the first content data. Statistics of attention information.

Those skilled in the art should understand that the implementation functions of the units in the attention information processing apparatus shown in FIG. 7 can be understood with reference to the relevant description of the attention information processing method. The function of each unit in the attention information processing apparatus shown in FIG. 7 can be implemented by a program running on a processor, or by a specific logic circuit.

Embodiments of the present invention further provide an electronic device. For example, the electronic device may be a mobile terminal, personal computer (PC), tablet computer, server, and the like. FIG. 8 is a schematic diagram of the structure of one application example of an electronic device in an embodiment of the present invention. Referring now to FIG. 8, FIG. 8 shows a schematic diagram of the structure of an electronic device 1500 for implementing the display device or server of an embodiment of the present invention. As shown in FIG. 8, electronic device 1500 includes one or more processors and communication components. The one or more processors may be, for example, one or more central processing units (CPUs) 1501 and/or one or more graphics processing units (GPUs) 1513 . The processor performs various appropriate operations and processes in response to executable instructions in read only memory (ROM) 1502 or executable instructions loaded from storage 1508 into random access memory (RAM) 1503. can do. Communication unit 1512 can include, but is not limited to, a network card. The network card may include, but is not limited to, an IB (Infiniband) network card. The processor communicates with read-only memory 1502 and/or random-access memory 1503 to execute executable instructions, and is coupled via bus 1504 to communication portion 1512 to communicate with other target devices via communication portion 1512. be able to. Thereby completing the operations corresponding to any method provided by the embodiments of the present invention.

Furthermore, the RAM 1503 can store various programs and data necessary for operating the device. CPU 1501 , ROM 1502 and RAM 1503 are interconnected via bus 1504 . In the case of RAM 1503, ROM 1502 is an optional module. RAM 1503 stores executable instructions or writes executable instructions to ROM 1502 when executed. The executable instructions cause processor 1501 to perform operations corresponding to the communication methods described above. Input/output (I/O) interface 1505 is also connected to bus 1504 . The communication unit 1512 may be integrated and configured, or may have multiple sub-modules (eg, multiple IB network cards) and be linked via a bus.

An input unit 1506 including a keyboard, mouse, etc., an output unit 1507 including a cathode ray tube (CRT), a liquid crystal display (LDC), etc. and speakers, etc., a storage unit 1508 including a hard disk, etc., and a network interface card such as a LAN card and a modem. A communication unit 1509 including a component is connected to the I/O interface 1505 . A communication unit 1509 executes communication processing via a network such as the Internet. Drivers 1510 are also connected to I/O interfaces 1505 as needed. A removable medium 1511 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory is attached to the driver 1510 as required. As a result, the read computer program is attached to storage unit 1508 as needed.

It should be noted that the architecture shown in FIG. 8 is an optional implementation, and in the specific execution process, the number and type of components in FIG. can be increased or replaced. For the setting of different functional components, implementation forms such as separable setting and integrable setting can be adopted, for example, the GPU and the CPU can be set to be separable, or the GPU can be set to be integrated into the CPU, and communication can be performed. The unit may be set to be separable, or may be set to be integrated into the CPU or GPU. All of these switchable embodiments fall within the protection scope of the present invention.

In particular, according to embodiments of the present disclosure, the processes described with reference to the flowcharts above may be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product including a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the method illustrated in the flowcharts, the program code may include instructions corresponding to performing steps of methods provided by embodiments of the present invention. In such embodiments, the computer program is downloaded and installed from a network via communication portion 1509 and/or installed from removable media 1511 . When this computer program is run by the central processing unit (CPU) 1501, it performs the above-described functions defined in the method of the present invention.

The technical solution of attention information processing of the embodiments of the present invention can be applied to driver monitoring, advertisement analysis, human-computer interaction, security monitoring, medical diagnosis, psychological research and other fields. For example, when applied to driver monitoring, the attention information processing method or apparatus of the embodiment of the present invention determines the gaze direction of the driver, whether or not the focus is appropriate, and whether the focus is appropriate and the driving behavior. By determining whether or not they match, the driver's attention is called when the driver is distracted, and safe driving is supported. In addition, when applied to human-computer interaction, the method and apparatus for processing attention information according to the embodiments of the present invention acquire the realization direction, and determine the falling point of the line of sight of the display object from the direction of the line of sight and the position of the human eye. can be issued to perform human-computer interaction such as eye-keying and eye-gaze operation. In addition, when applied to a security camera, the attention information processing method and apparatus of the present embodiment are used to acquire the actual direction, determine the attention direction from the person's line of sight direction, and predict the subsequent action. can be

The embodiments herein are described progressively, each focusing on its differences from other embodiments, and each referring to the same or similar parts between the various embodiments. be able to. The embodiments of the apparatus and system basically correspond to the embodiments of the method, so the description is relatively simple, and the relevant points should be referred to some of the embodiments of the method.

The methods, devices and systems of the present invention can be implemented in many ways. For example, the methods, apparatus, and systems of the present invention can be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware. The order of the steps of the above methods is for illustrative purposes, and the steps of the methods described herein are not limited to the order specifically described above, unless specifically described above. Furthermore, in some embodiments, the present invention may also be implemented as programs recorded on a recording medium, these programs containing machine-readable instructions for implementing methods according to the present invention. The invention thus also covers a recording medium storing a program for carrying out the method according to the invention.

The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those skilled in the art. The selection and description of the embodiments better explain the principles and practical application of the invention, and are intended to enable those skilled in the art to understand the invention in various ways with various modifications suitable for particular applications. Design an embodiment.

Claims (13)

A method of processing attention information, comprising:
exhibiting the first content data;
obtaining feature information of at least one display object, and determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
performing attention information statistics for the first content data based on attention information between the at least one exhibitable object and the first content data;
The step of obtaining characteristic information of the at least one display object and determining attention information between the at least one display object and the first content data based on the characteristic information of the at least one display object,
obtaining line-of-sight direction information of the at least one display object, and determining attention information between the at least one display object and the first content data based on the line-of-sight direction information of the at least one display object; including
the attention information includes instruction information for instructing whether or not the exhibition object pays attention to the first content data;
determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
Determining whether the line of sight of the at least one display object enters a first display area based on the line-of-sight direction information of the at least one display object, wherein the first display area is a display area in a display device for content data;
the attention information further includes a degree of attention to the first content data to be exhibited;
determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
For an exhibition object whose line of sight has entered the first display area, a target position where the line of sight of the exhibition object is projected onto the first display area is determined based on the line-of-sight direction information of the display object, and the target position is determined. further comprising the step of determining the degree of attention to the first content data to be displayed based on the positional relationship with respect to the first display area;
A method of processing attention information, comprising : the closer the distance from the center of the first display area to the target position, the higher the degree of attention. a step of recommending second content data waiting to be exhibited based on the statistical attention information;
The attention information processing method according to claim 1, further comprising: exhibiting the second content data. the attention information further includes attention time for the first content data to be exhibited;
determining attention information between the at least one display object and the first content data based on the viewing direction information of the at least one display object;
For an exhibition object whose line of sight entered the first display area, the time when the line of sight of the exhibition object entered the first display area is statistically calculated, and based on the statistical time, the first content data of the exhibition object is displayed. 2. The method of processing attention information of claim 1 , further comprising determining an attention time. The step of obtaining gaze direction information of the at least one display object,
obtaining eye angle information and head pose information for at least one exhibit;
calculating gaze direction information of the at least one exhibit based on eye angle information and head pose information of the at least one exhibit. How to process attention information. The step of obtaining eyeball angle information and head posture information of the at least one exhibit subject,
obtaining at least one image of the exhibit;
processing the image of the at least one exhibit using a first neural network to obtain eyeball angle information of the at least one exhibit;
and processing the image of the at least one exhibit using a second neural network to obtain head pose information of the at least one exhibit. How to handle featured information in . The step of obtaining characteristic information of the at least one display object and determining attention information between the at least one display object and the first content data based on the characteristic information of the at least one display object,
Obtaining geographical position information of at least one display object, and determining attention information between the at least one display object and the first content data based on the geographical position information of the at least one display object. The attention information processing method according to claim 1, comprising: The attention information includes instruction information for instructing whether or not the display target is to pay attention to the first content data,
determining attention information between the at least one display object and the first content data based on the geographical location information of the at least one display object;
determining, based on the geographic location information of the at least one exhibitable object, whether the position of the at least one exhibitable object falls within a first area range determined based on the position of the display device; 7. The attention information processing method according to claim 6 , wherein: the attention information further includes attention time for the first content data to be exhibited;
determining attention information between the at least one display object and the first content data based on the geographical location information of the at least one display object;
Statisticalize the time when the position of the at least one display object of the display object entered the first area range for the display object whose position of the at least one display object entered the first area range, and the statistical time 8. The attention information processing method according to claim 7 , further comprising: determining an attention time for the first content data to be exhibited based on. The step of obtaining characteristic information of the at least one display object and determining attention information between the at least one display object and the first content data based on the characteristic information of the at least one display object,
obtaining interactive information between the at least one display object and the first content data, and based on the interactive information between the at least one display object and the first content data, the at least one display object 2. The attention information processing method according to claim 1, further comprising determining attention information between the first content data and the first content data. performing attention information statistics for the first content data based on the attention information between the at least one display object and the first content data;
Number of people who pay attention to the first content data, number of people corresponding to different degrees of attention, and different 10. The attention information processing method according to any one of claims 1 and 3 to 9 , further comprising a step of statisticizing attention information of at least one of the number of people corresponding to the attention time. There is a processing device for attention information,
a display unit for displaying the first content data;
an acquisition unit for acquiring characteristic information of at least one display object;
a determination unit for determining attention information between the at least one display object and the first content data based on the feature information of the at least one display object;
a statistics unit for performing attention information statistics on the first content data based on the attention information between the at least one display object and the first content data ;
The obtaining unit further obtains the line-of-sight direction information of the at least one display object, and the determination unit further determines the at least one display object and the determining attention information with the first content data;
The attention information includes instruction information for instructing whether or not the display object pays attention to the first content data, and the determination unit determines the at least Determining whether or not the line of sight of one display object has entered a first display area, wherein the first display area is a display area of a display device for the first content data;
Further including the degree of attention of the display object to the first content data, the determination unit determines the display object whose line of sight enters the first display area based on the line-of-sight direction information of the display object. determining a target position projected on the first display area of the line of sight, and determining the degree of attention to the first content data of the display object based on the positional relationship of the target position with respect to the first display area; ,
The degree of attention is higher as the distance from the center of the first display area to the target position is shorter.
A device characterized by: a storage medium,
A storage medium, characterized in that it stores executable instructions which, when executed by a processor, implement the method of any one of claims 1 to 10 . an electronic device,
a memory for storing executable instructions;
and a processor for implementing the method steps of any one of claims 1 to 10 by executing the executable instructions in communication with the memory.

Images