Information Processing Method, Apparatus, Device, and Storage Medium

Abstract

An embodiment of the present application provides an information processing method, apparatus, device, and storage medium. By acquiring an image to be processed, the image to be processed includes a human face facing a target object, processing the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face and the confidence value of the line-of-sight angle information, and finally determining the attention analysis result of the user to whom the human face belongs to the target object according to the face angle information and the confidence value of the face angle information, the line-of-sight angle information and the confidence value of the line-of-sight angle information. In this technical solution, the attention of pedestrians to the advertising screen is jointly determined based on face angle detection and eye line-of-sight angle detection, which improves the accuracy of face detection and solves the problem of detection errors that may be caused by inconsistent gaze direction and face orientation.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular, to an information processing method, apparatus, device, and storage medium. Background Art

[0002] With the continuous deepening of social informatization, advertising has become one of the mainstream forms of modern cultural dissemination and commercial promotion. The effective placement of advertisements can, to a certain extent, increase social attention and promote the conversion rate of products. Usually, whether an advertisement is effectively placed can be measured by whether the advertisement is noticed.

[0003] In the prior art, the main method for determining whether an advertisement is noticed is as follows: Based on the product sales volume after the advertisement is placed and a small-scale manual survey, the attention degree of the already placed advertisement is determined.

[0004] However, in the process of implementing the present invention, the inventor found that the above method for determining the attention degree of advertisements has the following problems: Since only some users can be surveyed, there is a certain degree of contingency, low scientificity and rigor, resulting in a low accuracy of the determined attention degree of advertisements. Summary of the Invention

[0005] Embodiments of the present application provide an information processing method, apparatus, device, and storage medium to solve the problem of low accuracy of the determined attention degree in the prior art.

[0006] In a first aspect, embodiments of the present application provide an information processing method, including:

[0007] Obtain an image to be processed, where the image to be processed includes a human face facing a target object;

[0008] Process the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face and the confidence value of the line-of-sight angle information;

[0009] Determine the attention analysis result of the user to whom the human face belongs to the target object according to the face angle information and the confidence value of the face angle information, the line-of-sight angle information and the confidence value of the line-of-sight angle information.

[0010] In a possible design of the first aspect, the processing the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face and the confidence value of the line-of-sight angle information includes:

[0011] Perform face detection on the image to be processed, and calculate the face angle information of the human face and the confidence value of the face angle information;

[0012] Perform eye detection on the image to be processed to determine the eye map information in the face;

[0013] Based on the eye map information, perform gaze tracking detection on the user to whom the face belongs to determine the gaze angle information of the eyes in the face and the confidence value of the gaze angle information.

[0014] Optionally, the performing eye detection on the image to be processed to determine the eye map information in the face includes:

[0015] Perform eye detection on the image to be processed to determine the eye key point information in the face;

[0016] Expand the eye region corresponding to the eye key point information to obtain a target eye region;

[0017] Perform human eye image segmentation on the target eye region to obtain the eye map information in the face.

[0018] In another possible design of the first aspect, the determining the attention analysis result of the user to whom the face belongs to the target object according to the face angle information and the confidence value of the face angle information, the gaze angle information and the confidence value of the gaze angle information includes:

[0019] Based on a preset face angle threshold range, the face angle information and the confidence value of the face angle information, determine a first attention result based on the face and the first attention score corresponding to the first attention result;

[0020] Based on a preset gaze angle threshold range, the gaze angle information and the confidence value of the gaze angle information, determine a second attention result of the gaze of the eyes in the face and the second attention score of the second attention result;

[0021] According to the first attention result, the first attention score, the second attention result and the second attention score, determine the attention analysis result of the user to whom the face belongs to the target object.

[0022] Optionally, the determining the attention analysis result of the user to whom the face belongs to the target object according to the first attention result, the first attention score, the second attention result and the second attention score includes:

[0023] According to the values of the first attention result and the second attention result, determine at least one target attention result with a value of true, and a true value of the attention result indicates attention;

[0024] Determine the attention analysis result of the user to whom the face belongs to the target object according to the number of the target attention results, the attention score of each target attention result, and a preset attention score threshold.

[0025] In another possible design of the first aspect, the face angle information includes: face yaw angle information and face pitch angle information;

[0026] The line-of-sight angle information of the eyes in the face includes: the left-eye line-of-sight yaw angle information and the left-eye line-of-sight pitch angle information corresponding to the left eye in the face, and / or, the right-eye line-of-sight yaw angle information and the right-eye line-of-sight pitch angle information corresponding to the right eye in the face.

[0027] In yet another possible design of the first aspect, the confidence values of the face angle information and the confidence values of the line-of-sight angle information are both confidence values after normalization processing.

[0028] In a second aspect, an information processing device provided by an embodiment of the present application includes: an acquisition module, a processing module, and a determination module;

[0029] The acquisition module is configured to acquire an image to be processed, where the image to be processed includes a face facing a target object;

[0030] The processing module is configured to process the image to be processed, and determine the face angle information of the face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the face, and the confidence value of the line-of-sight angle information;

[0031] The determination module is configured to determine the attention analysis result of the user to whom the face belongs to the target object according to the face angle information and the confidence value of the face angle information, the line-of-sight angle information, and the confidence value of the line-of-sight angle information.

[0032] In a possible design of the second aspect, the processing module is specifically configured to:

[0033] Perform face detection on the image to be processed, and calculate the face angle information of the face and the confidence value of the face angle information;

[0034] Perform eye detection on the image to be processed, and determine the eye map information in the face;

[0035] Based on the eye map information, perform line-of-sight tracking detection on the user to whom the face belongs, and determine the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information.

[0036] Optionally, the processing module is configured to perform eye detection on the image to be processed to determine the eye map information in the face, specifically:

[0037] The processing module is specifically configured to:

[0038] Perform eye detection on the image to be processed, and determine the eye key point information in the face;

[0039] Expand the eye region corresponding to the eye key point information to obtain a target eye region;

[0040] Perform human eye image segmentation on the target eye region to obtain the eye image information in the face.

[0041] In another possible design of the second aspect, the determination module is specifically configured to:

[0042] Based on a preset face angle threshold range, the face angle information, and the confidence value of the face angle information, determine a first attention result based on the face and a first attention score corresponding to the first attention result;

[0043] Based on a preset line-of-sight angle threshold range, the line-of-sight angle information, and the confidence value of the line-of-sight angle information, determine a second attention result of the eye line of sight in the face and a second attention score corresponding to the second attention result;

[0044] According to the first attention result, the first attention score, the second attention result, and the second attention score, determine an attention analysis result of the user to whom the face belongs with respect to the target object.

[0045] Optionally, the determination module is configured to determine an attention analysis result of the user to whom the face belongs with respect to the target object according to the first attention result, the first attention score, the second attention result, and the second attention score, specifically:

[0046] The determination module is specifically configured to:

[0047] According to the values of the first attention result and the second attention result, determine at least one target attention result with a true value, and a true value of the attention result indicates attention;

[0048] According to the number of target attention results, the attention score of each target attention result, and a preset attention score threshold, determine an attention analysis result of the user to whom the face belongs with respect to the target object.

[0049] In still another possible design of the second aspect, the face angle information includes: face yaw angle information and face pitch angle information;

[0050] The line-of-sight angle information of the eyes in the human face includes: the left-eye line-of-sight yaw angle information and the left-eye line-of-sight pitch angle information corresponding to the left eye in the human face, and / or the right-eye line-of-sight yaw angle information and the right-eye line-of-sight pitch angle information corresponding to the right eye in the human face.

[0051] In yet another possible design of the second aspect, the confidence values of the human face angle information and the confidence values of the line-of-sight angle information are both confidence values after being normalized.

[0052] In a third aspect, an embodiment of the present application further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method as described in the first aspect and each possible design above.

[0053] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium. A computer instruction is stored in the computer-readable storage medium. When the computer instruction runs on a computer, the computer is caused to execute the method as described in the first aspect and each possible design.

[0054] The information processing method, device, equipment, and storage medium provided by the embodiments of the present application obtain a to-be-processed image, which includes a human face facing a target object, process the to-be-processed image, determine the human face angle information and the confidence value of the human face angle information, the line-of-sight angle information of the eyes in the human face, and the confidence value of the line-of-sight angle information, and finally determine the attention analysis result of the user to whom the human face belongs to the target object according to the human face angle information and the confidence value of the human face angle information, the line-of-sight angle information, and the confidence value of the line-of-sight angle information. In this technical solution, the attention degree of a pedestrian to an advertising screen is jointly determined based on human face angle detection and eye line-of-sight angle detection, which improves the accuracy of human face detection and solves the problem of detection errors that may be caused by inconsistent gaze directions and human face orientations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present disclosure and used together with the description to explain the principles of the present disclosure.

[0056] Figure 1 It is a diagram of an application scenario of the information processing method provided by an embodiment of the present application;

[0057] Figure 2 It is a schematic flowchart of the first embodiment of the information processing method provided by an embodiment of the present application;

[0058] Figure 3 It is a schematic flowchart of the second embodiment of the information processing method provided by an embodiment of the present application;

[0059] Figure 4 Schematic flowchart of the third embodiment of the information processing method provided by the embodiments of the present application;

[0060] Figure 5 Schematic structural diagram of the embodiment of the information processing device provided by the embodiments of the present application;

[0061] Figure 6 Schematic structural diagram of the electronic device for executing the information processing method provided by the embodiments of the present application.

[0062] Through the above-mentioned drawings, the specific embodiments of the present disclosure have been shown, and more detailed descriptions will be given hereinafter. These drawings and the written description are not intended to limit the scope of the concept of the present disclosure in any way, but to illustrate the concept of the present disclosure to those skilled in the art by referring to specific embodiments. Specific Embodiments

[0063] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0064] First, the nouns involved in the embodiments of the present application are explained:

[0065] Euler angles: They are the rotation angles of an object around the three coordinate axes (x, y, z axes) of a coordinate system. Among them, the coordinate system can be a world coordinate system or an object coordinate system, and the rotation order is also arbitrary. Euler angles can be divided into two cases: 1. Static: That is, the rotation around the three axes of the world coordinate system. Since the coordinate axes remain stationary during the rotation of the object, it is called static. 2. Dynamic: That is, the rotation around the three axes of the object coordinate system. Since the coordinate axes rotate in the same way as the object during the rotation of the object, it is called dynamic.

[0066] Head pose estimation is the process of obtaining the pose angles of the head through a facial image. In 3D space, the rotation of an object can be represented by three Euler angles:

[0067] pitch: The pitch angle, which represents the rotation of the object around the x-axis. Generally speaking, it is raising the head;

[0068] yaw: The yaw angle, which represents the rotation of the object around the y-axis. Generally speaking, it is turning the head;

[0069] roll: The roll angle, which represents the rotation of the object around the z-axis with respect to the pitch angle. Generally speaking, it is shaking the head.

[0070] As one of the mainstream forms of modern cultural dissemination and commercial promotion, advertising is mainly presented in offline outdoor media in the forms of outdoor LED large screen advertising in commercial centers, highway T-shaped billboard advertising, community elevator frame posters, community elevator waiting area TVs, community lawn light boxes, community access control advertising, etc. Due to the increasing number of advertising forms and the increasing fragmentation of advertising effects, the effective reach rate of advertising has always troubled advertising companies and advertisers. Therefore, how to evaluate the advertising placement effect and determine the attention of advertising is the key factor in improving the advertising placement value.

[0071] At present, in the scheme of determining the attention of the already placed advertisement based on the product sales volume after the advertisement is placed and a small-scale manual survey, there are problems such as a certain degree of contingency, low scientificity and rigor because only some users can be surveyed, resulting in low accuracy of the determined advertisement attention.

[0072] In practical applications, there are many methods for calculating pedestrians' attention to the placed advertisement, and currently, it can also be determined based on face recognition. For example, a camera device is set on one side of the advertisement screen, and face detection and recognition are performed on the images collected by the camera device. Through the face angle information returned by face detection, that is, the Euler angle information such as the pitch angle, yaw angle, and roll angle of the face is detected. Comprehensive judgment of attention is made according to whether both the detected pitch angle and yaw angle are greater than the preset threshold. If both the pitch angle and yaw angle are greater than the preset threshold, it is determined that the pedestrian is in a state of attention to the advertisement, and the advertisement is marked as an effectively placed advertisement.

[0073] However, there are many missed detections and misjudgments in the advertising attention statistics method based on face recognition. For example, when the face angle threshold is set to 25 degrees, if it is detected that the face angle (pitch angle or yaw angle) of a pedestrian to the advertisement is greater than or equal to the face angle threshold of 25 degrees, it is determined that the pedestrian is in a non-attention state to the advertisement, but it will ignore the state where the angle is greater than 25 degrees but the pedestrian is actually looking sideways and paying attention to the screen. If it is detected that the face angle (pitch angle or yaw angle) of a pedestrian to the advertisement is less than the face angle threshold of 25 degrees, it is determined that the pedestrian is in a state of attention to the advertisement. Another example is that if the face angle threshold is set to 50 degrees, if it is detected that the face angle (pitch angle or yaw angle) of a pedestrian to the advertisement is less than 50 degrees, it will be determined that the pedestrian is in a state of attention to the advertisement, but it may also be the state where the pedestrian passes by the screen normally without paying attention to the screen. Therefore, there are examples of misjudgments and missed detections only relying on the set threshold.

[0074] Optionally, when a pedestrian faces the advertisement screen directly or at a small angle, but the human eye never focuses on the advertisement screen, for example, when looking sideways at a colleague and chatting while passing by the advertisement screen, based on the above method, it may be misjudged that the pedestrian is in a state of paying attention to the advertisement, resulting in a misjudgment result. When a pedestrian passes by the advertisement screen with a side face and the human eye looks sideways and pays attention to the advertisement screen, at this time, the face may not be detected, and based on the above method, it may be misjudged as a state of not paying attention.

[0075] Furthermore, when the pedestrian is at a very far or very close distance from the advertisement screen, the size and quality of the face image captured by the camera device vary greatly. When the pedestrian is far from the screen, the face image captured by the camera device is very small and does not reach the required image size for the algorithm. Based on the confidence judgment results determined by the current face recognition algorithm, the confidence jitters greatly, and false positives and missed detections are likely to occur. Moreover, when the pedestrian is walking at a relatively fast speed, the captured face image may be blurred. At this time, when making a focus judgment through the above face recognition algorithm, false positives and missed detections will also occur. That is, in the actual scenario, due to the large differences in the size or quality of the captured images, the confidence of the algorithm's detection results may fluctuate greatly, resulting in missed detections and false positives.

[0076] As can be seen from the above analysis, in the prior art, in the statistics of the attention degree of pedestrians to the advertisement screen, there are problems such as low accuracy of the determined attention degree due to different gaze directions and frontal face orientations of pedestrians, and low confidence of the detection results due to unqualified captured images, further leading to misjudgment of the attention degree results. For example, due to pedestrians passing by quickly or being very far or very close to the advertisement screen, the captured images are blurred or the face size is too small, etc., resulting in low confidence of the detection results due to unqualified image quality.

[0077] To address the above problems, the technical concept of this application can be summarized as follows: By combining face detection technology and eye gaze tracking technology, based on the detection results and confidence of face detection, and the detection results and confidence of eye gaze, jointly determine the attention degree of pedestrians to the advertisement screen, which can solve the problem of detection errors caused by inconsistent gaze directions and face orientations, and can also solve the problem of low confidence of the output results due to unqualified image quality, and further the problem of low detection accuracy.

[0078] Optionally, in the information processing method provided by the embodiments of the present application, on the basis of face angle detection, gaze angle detection is added, that is, based on the angle information and confidence values of the face direction and gaze direction in the captured image, the attention analysis result of the user to whom the face belongs towards the target object (advertising screen) is jointly determined, effectively solving the misjudgment that occurs when relying solely on face detection to identify inconsistent gaze directions and face orientations. The results of face detection and eye detection are voted on, and the confidence of the detection result is multiplied by the number of votes, avoiding the misjudgment phenomenon caused by setting a low threshold confidence, thereby improving the calculation accuracy of advertising attention and solving the above technical problems.

[0079] Exemplarily, Figure 1 is an application scenario diagram of the information processing method provided by the embodiments of the present application. As Figure 1 shown, the application scenario of the present application may include an advertising screen 11, a camera device 12, and an electronic device 13. Among them, the camera device 12 and the advertising screen 11 are set in the same area, and the camera device 12 can capture the image of the area where the advertising screen 11 is located.

[0080] Exemplarily, as Figure 1 shown, the camera device 12 is set at the top of the advertising screen 11. When a pedestrian passes by the advertising screen 11, the camera device 12 can capture an image including the face of the pedestrian 10 and transmit the image to the electronic device 13, so that the electronic device 13 can analyze the received image to determine the attention of the pedestrian to the advertisement on the advertising screen 11.

[0081] Optionally, in the embodiments of the present application, the electronic device may be a terminal device such as a PC or a mobile phone, or a server such as a background processing platform. The specific form of the electronic device can be determined according to actual scenario requirements and will not be elaborated here.

[0082] Exemplarily, the electronic device 13 may be implemented by including a processor 131 and a display 132. Among them, the processor 131 is used to process the image to be processed and determine the attention analysis result of the pedestrian to the target object, and the display 132 is used to present the processing result of the processor 131. Figure 1 Only one processor and one display are exemplarily shown for the electronic device in, and the actual composition of the electronic device can be determined according to the actual situation and will not be elaborated here.

[0083] Next, specific embodiments will be used to detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be elaborated in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0084] Figure 2 This is a schematic flowchart of the first embodiment of the information processing method provided by the embodiments of the present application. As Figure 2 shown, in the embodiments of the present application, the method may include the following steps:

[0085] S201. Obtain an image to be processed, where the image to be processed includes a human face facing a target object.

[0086] In the embodiments of the present application, an electronic device may obtain an image to be processed collected by an imaging device. The imaging device is in the same environment as the target object and can collect videos or images of the environment where the target object is located in real time.

[0087] Optionally, since the main purpose of the embodiments of the present application is to determine the attention of a user (pedestrian) to a target object, therefore, the image to be processed obtained by the electronic device needs to include a human face facing the target object. Only when the image to be processed includes a human face facing the target object can the attention of the user to whom the human face belongs to the advertising screen be analyzed.

[0088] Optionally, the electronic device can obtain the image to be processed at least through the following two methods:

[0089] As an example, the imaging device can directly transmit the collected images and / or videos of the scene where the target object is located to the electronic device, and the electronic device analyzes the received images and / or videos to determine the image to be processed that includes a human face facing the target object from them.

[0090] As another example, if the imaging device has processing capabilities, after collecting the images and / or videos of the scene where the target object is located, it can first analyze them to determine the image to be processed that includes a human face facing the target object, and then transmit it to the electronic device so that the electronic device can directly obtain the image to be processed that includes a human face facing the target object.

[0091] It can be understood that the embodiments of the present application do not limit the method of obtaining the image to be processed, and there may be other methods. For example, after the imaging device obtains the images and / or videos of the scene where the target object is located, it can transmit them to other devices, and the electronic device can receive the processed image to be processed or unprocessed images and / or videos from other devices.

[0092] Exemplarily, in the embodiments of the present application, the target object may be an advertising screen, a notice board, a notification, etc. The embodiments of the present application do not limit the specific manifestation form of the target object, which can be determined according to the actual scene and will not be elaborated here.

[0093] S202. Process the image to be processed, and determine the face angle information of the face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information.

[0094] Optionally, in the embodiments of the present application, for an image to be processed including a face facing a target object, the electronic device may perform face processing on the image to be processed. When it is determined that the image to be processed includes a face, the face angle information of the face and the confidence value of the face angle information are determined.

[0095] Furthermore, the electronic device may also perform eye line-of-sight detection on the image to be processed. When it is determined that the image to be processed includes human eyes, the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information are determined.

[0096] It can be understood that, in the embodiments of the present application, a face angle threshold range and a line-of-sight angle threshold range are pre-configured in the electronic device. Based on the determined face angle information and the pre-configured face angle threshold range, the confidence value of the face angle information can be determined; based on the determined line-of-sight angle information and the pre-configured line-of-sight angle threshold range, the confidence value of the line-of-sight angle information can be determined.

[0097] Exemplarily, the angles in the face angle information and the line-of-sight angle information can be represented by the yaw angle and the pitch angle in the Euler angles. Therefore, in the embodiments of the present application, the face angle information may include: face yaw angle information and face pitch angle information, and the line-of-sight angle information of the eyes in the face may include: the left-eye line-of-sight yaw angle information and the left-eye line-of-sight pitch angle information corresponding to the left eye in the face, and / or, the right-eye line-of-sight yaw angle information and the right-eye line-of-sight pitch angle information corresponding to the right eye in the face.

[0098] For the specific implementation of this step, reference may be made to the description in the following Figure 3 embodiments shown, and details are not described herein again.

[0099] Optionally, when the electronic device obtains the image to be processed, it may also first detect whether the image to be processed is qualified. Only when the image to be processed is qualified, the electronic device performs the processes of face detection and line-of-sight detection. Exemplarily, the implementation manners of detecting whether the image to be processed is qualified may include one or more of the following manners: whether the quality of the image to be processed is qualified, whether the image to be processed is from a real face, etc. The embodiments of the present application do not limit the specific implementation manner of whether the image to be processed is qualified, and it may be determined according to the actual situation.

[0100] S203. Determine the attention analysis result of the user to whom the face belongs to the target object according to the face angle information and the confidence value of the face angle information, the line-of-sight angle information and the confidence value of the line-of-sight angle information.

[0101] In an embodiment of the present application, a face angle threshold range and a line-of-sight angle threshold range are pre-configured in the electronic device. Therefore, according to the face angle information and the pre-configured face angle threshold range, it can be determined whether the face angle information is valid. According to the line-of-sight angle information and the pre-configured line-of-sight angle threshold range, it can be determined whether the line-of-sight angle information is valid. Finally, based on the judgment result of whether the face angle information is valid, the confidence value of the face angle information, the judgment result of whether the line-of-sight angle information is valid, and the confidence value of the line-of-sight angle information, the attention analysis result of the user to whom the face belongs with respect to the target object is jointly determined.

[0102] For the specific implementation of this step, reference can be made to the description in the following Figure 4 embodiments shown, which will not be elaborated here.

[0103] The information processing method provided by the embodiment of the present application includes obtaining a to-be-processed image, where the to-be-processed image includes a face facing a target object, processing the to-be-processed image to determine the face angle information of the face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information, and finally determining the attention analysis result of the user to whom the face belongs with respect to the target object based on the face angle information and the confidence value of the face angle information, the line-of-sight angle information and the confidence value of the line-of-sight angle information. In this technical solution, based on face angle detection and eye line-of-sight angle detection, the attention degree of pedestrians to the advertising screen is jointly determined, which improves the accuracy of face detection and solves the problem of detection errors that may be caused by inconsistent gaze directions and face orientations.

[0104] Optionally, on the basis of the above embodiment, Figure 3 is a schematic flowchart of the second embodiment of the information processing method provided by the embodiment of the present application. As Figure 3 shown, the above S202 can be implemented through the following steps:

[0105] S301. Perform face detection on the to-be-processed image, and calculate the face angle information of the face and the confidence value of the face angle information.

[0106] In an embodiment of the present application, when the electronic device obtains the to-be-processed image, it first performs face detection on the to-be-processed image to determine the face part in the to-be-processed image. Then, based on a preset algorithm, the face angle information of the face can be determined. Furthermore, by comparing the face angle information with the face angle threshold range pre-configured in the electronic device, the confidence value of the face angle information can be determined.

[0107] Exemplarily, in this embodiment, the face angle information includes: the face yaw angle information (FaceYawAngel, that is, the left - right yaw angle of the face) and the face pitch angle information (FacePitchAngel, that is, the up - down pitch angle of the face) in the Euler angles of the face direction, where both the face yaw angle information and the face pitch angle information are represented by corresponding face angle confidence scores (FaceAngelConfidenceScore).

[0108] Exemplarily, the specific steps for calculating the Euler angles of the face direction can be as follows: First, define a 3D face model with n key points (for example, the left eye corner, the right eye corner, the nose tip, the left mouth corner, the right mouth corner, the mandible, etc.), and n can be defined according to one's own tolerance for accuracy, and n is a positive integer; Second, use face detection and facial key point detection to obtain the 2D face key points corresponding to the 3D face key points in the above 3D face model, then use the solvePnP function of Opencv to solve for the rotation vector, and finally convert the rotation vector into Euler angles, so as to obtain the face angle information of the face.

[0109] S302. Perform eye detection on the image to be processed, and determine the eye map information in the face.

[0110] In the embodiment of the present application, while the electronic device performs face detection on the image to be processed, it can also perform eye detection on the image to be processed, and according to the eye detection information, calculate and expand the coordinates of the eye key points, calculate the target eye area, and then perform human eye image segmentation on the effective eye area in the target eye area to obtain the eye map information in the face.

[0111] Optionally, this step S302 can be specifically implemented through the following steps:

[0112] A1. Perform eye detection on the image to be processed, and determine the eye key point information in the face.

[0113] Exemplarily, the detection of eyes in the image to be processed by the electronic device can include two directions. One direction is: First, locate the face area in the image to be processed, that is, perform face detection, and then find the human eyes within the face area to determine the eye key point information in the face. The other direction is: directly detect the eye area in the image to be processed and determine the eye key point information.

[0114] It can be understood that the specific method for eye detection can be determined according to the actual scenario and will not be elaborated here.

[0115] A2. Expand the eye area corresponding to the eye key point information to obtain the target eye area.

[0116] In the embodiments of the present application, since the occupied area of the eye region in the image to be processed may be small, there may be certain errors in the detected eye key point information. Moreover, the execution of the eye gaze tracking algorithm requires complete eye map information. Therefore, the eye region corresponding to the eye key point information can be expanded. For example, the size of the eye region corresponding to the eye key point information is multiplied by a certain coefficient (such as 2.0) to obtain an enlarged eye region, that is, the target eye region.

[0117] A3. Perform human eye image segmentation on the target eye region to obtain the eye map information in the human face.

[0118] Exemplarily, for the target eye region obtained by expanding the eye region, since the gray level changes significantly around the human eye, the region where the eye is located can be determined through the gray level curve, and then human eye image segmentation is performed on the effective eye region to obtain the eye map information of the eye part in the human face.

[0119] S303. Based on the above eye map information, perform gaze tracking detection on the user to whom the human face belongs, and determine the gaze angle information and the confidence value of the gaze angle information of the eyes in the human face.

[0120] In the embodiments of the present application, the electronic device can perform gaze tracking detection based on the cropped eye map information to determine the gaze angle information and the confidence value of the gaze angle information of the target eye. Optionally, the gaze angle information includes left eye gaze angle information and right eye gaze angle information.

[0121] Among them, the left eye gaze angle information may include the left eye gaze yaw angle (LeftEyeGazeYawAngel, that is, the left-right yaw angle of the left eye gaze) and the left eye gaze pitch angle (LeftEyeGazeYawAngel, that is, the up-down pitch angle of the left eye gaze). The confidence value of the left eye gaze angle information is the left eye gaze angle confidence score LeftEyeGazeConfidenceScore. The right eye gaze angle information may include the right eye gaze yaw angle (RightEyeGazeYawAngel, that is, the left-right yaw angle of the right eye gaze) and the right eye gaze pitch angle (RightEyeGazeYawAngel, that is, the up-down pitch angle of the right eye gaze). The confidence value of the right eye gaze angle information is the right eye gaze angle confidence score RightEyeGazeConfidenceScore.

[0122] The information processing method provided by the embodiments of the present application performs face detection on the image to be processed, calculates the face angle information of the face and the confidence value of the face angle information, performs eye detection on the image to be processed, determines the eye map information in the face, and based on this eye map information, performs line-of-sight tracking detection on the user to whom the face belongs, and determines the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information. In this technical solution, face and eye detections are respectively performed and corresponding confidence values are calculated, laying a foundation for the subsequent determination of the accuracy of the target object's attention analysis results.

[0123] Optionally, on the basis of the above embodiments, Figure 4 It is a schematic flowchart of the third embodiment of the information processing method provided by the embodiments of the present application. As Figure 4 shown, the above S203 can be implemented through the following steps:

[0124] S401. Based on a preset face angle threshold range, face angle information, and the confidence value of the face angle information, determine a first attention result based on the face and a first attention score corresponding to the first attention result.

[0125] In the embodiments of the present application, a face angle threshold range, that is, a face yaw angle threshold range and a face pitch angle threshold range, are preset in the electronic device. Optionally, in order to better match the actual scenario, the acquisition camera of a general camera device is located at the top of the target object. For example, on the upper side of the screen of an advertising screen. Therefore, when a pedestrian views the target object, there will be a predictable angle with the camera device. Therefore, the face pitch angle threshold range can be set asymmetrically.

[0126] Exemplarily, the face yaw angle threshold range is -20 to 20 degrees, and the face pitch angle threshold range is -15 to 40 degrees. It can be understood that this embodiment only gives an example of the face yaw angle threshold range and the face pitch angle threshold range, and their specific values can be set according to actual needs and will not be elaborated here.

[0127] In specific implementation, the electronic device first determines the relationship between the determined face angle information and the preset face angle threshold range. For example, according to whether the face angle information is within the preset face angle threshold range, the first attention result is determined.

[0128] Optionally, if the face angle information is within the preset face angle threshold range, it is determined that the first attention result is attention, which is represented by the value "1"; if the face angle information is not within the preset face angle threshold range, it is determined that the first attention result is non-attention, which is represented by the value "0".

[0129] Exemplarily, the first attention score corresponding to the first attention result can be determined according to the value of the first attention result and the confidence value of the face angle information. For example, the first attention score can be equal to the product value of the value of the first attention result and the confidence value of the face angle information.

[0130] S402. Based on a preset line-of-sight angle threshold range, line-of-sight angle information, and the confidence value of the line-of-sight angle information, determine the second attention result of the eyes' line of sight in the face and the second attention score of the second attention result.

[0131] In the embodiments of the present application, a line-of-sight angle threshold range is also preset in the electronic device, that is, a line-of-sight yaw angle threshold range and a line-of-sight pitch angle threshold range. Optionally, similar to the reason for setting the face pitch angle threshold range asymmetrically, the set line-of-sight pitch angle threshold range is also asymmetric.

[0132] Exemplarily, the line-of-sight yaw angle threshold range is -25 to 25 degrees, and the line-of-sight pitch angle threshold is -15 to 30 degrees. It can be understood that this embodiment only gives an example of the line-of-sight yaw angle threshold range and the line-of-sight pitch angle threshold range, and their specific values can be set according to actual needs and will not be elaborated here.

[0133] In specific implementation, the electronic device first determines the relationship between the determined above-mentioned line-of-sight angle information (left-eye line-of-sight angle information and / or right-eye line-of-sight angle information) and the preset line-of-sight angle threshold range. For example, based on whether the line-of-sight angle information is within or outside the preset line-of-sight angle threshold range, determine the second attention result.

[0134] Optionally, if the line-of-sight angle information is within the preset line-of-sight angle threshold range, determine that the second attention result is attention, which is represented by the value "1"; if the line-of-sight angle information is not within the preset line-of-sight angle threshold range, determine that the second attention result is non-attention, which is represented by the value "0".

[0135] Similarly, the second attention score corresponding to the second attention result can be determined according to the value of the second attention result and the confidence value of the line-of-sight angle information. For example, the second attention score can be equal to the product value of the value of the second attention result and the confidence value of the line-of-sight angle information.

[0136] It can be understood that the embodiments of the present application are explained with the line-of-sight angle information of one eye. When the to-be-processed image includes the information of both the left and right eyes, it is necessary to determine the second attention result and the corresponding second attention score for each eye respectively.

[0137] Further, in the above S401 and S402 of the present application, the confidence values of the face angle information and the confidence values of the line-of-sight angle information are both confidence values after normalization processing.

[0138] Optionally, the confidence values of the face angle information and the line-of-sight angle information are respectively normalized so that they are between 0 and 1, which can simplify the subsequent calculation process and improve the accuracy of subsequent processing.

[0139] S403. Determine the attention analysis result of the user to whom the face belongs to the target object according to the first attention result, the first attention score, the second attention result, and the second attention score.

[0140] Exemplarily, when the first attention result and the first attention score corresponding to the face angle, and the second attention result and the second attention score corresponding to the eye line of sight are determined, the value results in terms of the face angle and the line-of-sight angle can be determined based on the values of the first attention result and the second attention result, and then, based on the attention score corresponding to each attention result, the attention analysis result of the user to whom the face belongs to the target object is finally determined.

[0141] Exemplarily, this step S403 can be specifically implemented through the following steps:

[0142] B1. Determine at least one target attention result with a true value according to the values of the first attention result and the second attention result. A true value of the attention result indicates attention.

[0143] In the embodiments of the present application, different meanings represented by different values of the first attention result can be set. Specifically, if the value of the attention result is true, it indicates attention, which can be represented by the value "1"; if the value of the attention result is false, it indicates no attention, which can be represented by the value "0".

[0144] Therefore, the electronic device can select at least one target attention result with a true value according to the values of the first attention result and the second attention result for subsequent judgment processes.

[0145] B2. Determine the attention analysis result of the user to whom the face belongs to the target object according to the number of target attention results, the attention score of each target attention result, and a preset attention score threshold.

[0146] In the embodiments of the present application, the electronic device may preset the corresponding relationship between the number of attention results with a true value, the attention scores of the attention results, and a preset attention score threshold. For example, when the number of target attention results is 1 and the attention score corresponding to the target attention result is greater than or equal to the first score threshold, it is determined that the attention analysis result is true, that is, attention; when the number of target attention results is 2 and the attention scores corresponding to the two target attention results are both greater than or equal to the second score threshold, it is determined that the attention analysis result is true, that is, attention; when the number of target attention results is 3 and the attention scores corresponding to the three target attention results are both greater than or equal to the third score threshold, it is determined that the attention analysis result is true, that is, attention.

[0147] Among them, the first score threshold > the second score threshold > the third score threshold. The embodiments of the present application do not limit the specific values of the first score threshold, the second score threshold, and the third score threshold, which can be determined according to actual needs. For example, the first score threshold is 0.8, the second score threshold is 0.65, and the third score threshold is 0.55.

[0148] Correspondingly, in the embodiments of the present application, the electronic device may determine the attention analysis result of the user to whom the face belongs to the target object according to the number of target attention results, the attention scores of each target attention result, and the preset attention score threshold.

[0149] For example, among the face angle information corresponding to the first attention result and the first attention score, the left eye line-of-sight angle information corresponding to the second attention result and the second attention score, and the right eye line-of-sight angle information corresponding to the third attention result and the third attention score, if only the second attention result corresponding to the left eye line-of-sight angle information has a true value, at this time, it is judged whether the second attention score is greater than the first score threshold. If so, it is determined that the final attention analysis result is attention; if not, it is determined that the final attention analysis result is non-attention. If the first attention result corresponding to the face angle information and the second attention result corresponding to the left eye line-of-sight angle information both have true values, at this time, it is judged whether the first attention score and the second attention score are both greater than the second score threshold. If so, it is determined that the final attention analysis result is attention; if not, it is determined that the final attention analysis result is non-attention. If the first attention result corresponding to the face angle information, the second attention result corresponding to the left eye line-of-sight angle information, and the third attention result corresponding to the right eye line-of-sight angle information all have true values, at this time, it is judged whether the first attention score, the second attention score, and the third attention score are all greater than the third score threshold. If so, it is determined that the final attention analysis result is attention; if not, it is determined that the final attention analysis result is non-attention.

[0150] The information processing method provided by the embodiments of the present application determines a first attention result based on the face and a first attention score corresponding to the first attention result based on a preset face angle threshold range, face angle information, and a confidence value of the face angle information. A second attention result of the eye line of sight in the face and a second attention score corresponding to the second attention result are determined based on a preset line of sight angle threshold range, line of sight angle information, and a confidence value of the line of sight angle information. Finally, based on the first attention result, the first attention score, the second attention result, and the second attention score, a concern analysis result of the user to whom the face belongs for the target object is determined. In this technical solution, by voting on the results of face angle detection and eye line of sight angle detection and multiplying by their respective attention scores, an accurate concern analysis result can be determined, improving the accuracy of concern judgment. At the same time, it can also solve the problem of inaccurate output of the concern analysis result due to unqualified images to be processed.

[0151] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0152] Figure 5 It is a schematic structural diagram of an embodiment of the information processing device provided by the embodiments of the present application. Referring to Figure 5 As described above, the device may include: an acquisition module 501, a processing module 502, and a determination module 503.

[0153] Among them, the acquisition module 501 is used to acquire an image to be processed, and the image to be processed includes: a face facing the target object;

[0154] The processing module 502 is used to process the image to be processed, and determine the face angle information of the face and the confidence value of the face angle information, the line of sight angle information of the eyes in the face, and the confidence value of the line of sight angle information;

[0155] The determination module 503 is used to determine a concern analysis result of the user to whom the face belongs for the target object according to the face angle information and the confidence value of the face angle information, the line of sight angle information and the confidence value of the line of sight angle information.

[0156] In a possible design of the embodiment of the present application, the processing module 502 is specifically used for:

[0157] Perform face detection on the image to be processed, and calculate the face angle information of the face and the confidence value of the face angle information;

[0158] Perform eye detection on the image to be processed, and determine the eye map information in the face;

[0159] Based on the eye diagram information, perform line-of-sight tracking detection on the user to whom the face belongs, and determine the line-of-sight angle information of the eyes in the face and the confidence value of the line-of-sight angle information.

[0160] Optionally, the processing module 502 is configured to perform eye detection on the image to be processed to determine the eye diagram information in the face, specifically:

[0161] The processing module 502 is specifically configured to:

[0162] Perform eye detection on the image to be processed to determine the eye key point information in the face;

[0163] Expand the eye region corresponding to the eye key point information to obtain a target eye region;

[0164] Perform human eye image segmentation on the target eye region to obtain the eye diagram information in the face.

[0165] In another possible design of the embodiment of the present application, the determination module 503 is specifically configured to:

[0166] Based on a preset face angle threshold range, the face angle information, and the confidence value of the face angle information, determine a first attention result based on the face and a first attention score corresponding to the first attention result;

[0167] Based on a preset line-of-sight angle threshold range, the line-of-sight angle information, and the confidence value of the line-of-sight angle information, determine a second attention result of the eye line of sight in the face and a second attention score corresponding to the second attention result;

[0168] According to the first attention result, the first attention score, the second attention result, and the second attention score, determine an attention analysis result of the user to whom the face belongs with respect to the target object.

[0169] Optionally, the determination module 503 is configured to determine an attention analysis result of the user to whom the face belongs with respect to the target object according to the first attention result, the first attention score, the second attention result, and the second attention score, specifically:

[0170] The determination module 503 is specifically configured to:

[0171] According to the values of the first attention result and the second attention result, determine at least one target attention result with a true value, and a true value of the attention result indicates attention;

[0172] According to the number of target attention results, the attention score of each target attention result, and a preset attention score threshold, determine an attention analysis result of the user to whom the face belongs with respect to the target object.

[0173] In still another possible design of the embodiment of the present application, the face angle information includes: face yaw angle information and face pitch angle information;

[0174] The line-of-sight angle information of the eyes in the face includes: the left-eye line-of-sight yaw angle information and the left-eye line-of-sight pitch angle information corresponding to the left eye in the face, and / or, the right-eye line-of-sight yaw angle information and the right-eye line-of-sight pitch angle information corresponding to the right eye in the face.

[0175] In yet another possible design of the embodiment of the present application, the confidence values of the face angle information and the confidence values of the line-of-sight angle information are both confidence values after normalization processing.

[0176] The device provided by the embodiment of the present application can be used to execute Figures 2 to 4 the method in the illustrated embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0177] It should be noted that it should be understood that the division of each module of the above device is only a division of logical functions. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a certain processing element of the above device to perform the functions of the above processing module. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or can be independently implemented. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element or the instruction in the form of software.

[0178] For example, the above-mentioned modules may be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), etc. For another example, when a certain module above is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0179] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0180] Figure 6 Schematic diagram of the structure of an electronic device for executing an information processing method provided in an embodiment of the present application. As Figure 6As shown in the figure, the electronic device may include: a processor 61, a memory 62, a communication interface 63, and a system bus 64. The memory 62 and the communication interface 63 are connected to the processor 61 through the system bus 64 to complete communication with each other. The memory 62 is used to store computer-executable instructions, and the communication interface 63 is used to communicate with other devices. When the processor 61 executes the computer-executable instructions, the solutions of the embodiments are implemented as described above. Figures 2 to 4 The solutions of the embodiments shown above.

[0181] In this Figure 6 Among them, the above-mentioned processor 61 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0182] The memory 62 may include a random access memory (RAM), may also include a read-only memory (ROM), and may also include a non-volatile memory, such as at least one disk memory.

[0183] The communication interface 63 is used to implement communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries).

[0184] The system bus 64 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0185] Optionally, the embodiments of the present application further provide a computer-readable storage medium. Computer instructions are stored in the computer-readable storage medium. When the computer instructions run on a computer, the computer executes the methods of the embodiments as described above. Figures 2 to 4 The methods of the embodiments shown above.

[0186] Optionally, the embodiments of the present application further provide a chip for running instructions. The chip is used to execute the methods of the embodiments as described above. Figures 2 to 4 The methods of the embodiments shown above.

[0187] An embodiment of the present application also provides a program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the methods of the above-mentioned Figures 2 to 4 illustrated embodiments can be implemented.

[0188] In the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after; in a formula, the character " / " represents a "division" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or multiple items (items). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0189] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application. In the embodiments of the present application, the magnitude of the sequence numbers of the above processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0190] Those skilled in the art will readily think of other implementations of the present disclosure after considering the specification and practicing the application disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include well-known common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0191] It should be understood that the present disclosure is not limited to the exact structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. An information processing method, characterized in that, Including: Obtain an image to be processed, where the image to be processed includes a human face facing a target object; Process the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face, and the confidence value of the line-of-sight angle information; Based on a preset face angle threshold range, the face angle information, and the confidence value of the face angle information, determine a first attention result based on the human face and a first attention score corresponding to the first attention result; Based on a preset line-of-sight angle threshold range, the line-of-sight angle information, and the confidence value of the line-of-sight angle information, determine a second attention result of the line of sight of the eyes in the human face and a second attention score of the second attention result; According to the values of the first attention result and the second attention result, determine at least one target attention result with a value of true, where a true value of the attention result indicates attention; According to the number of target attention results, the attention score of each target attention result, and a preset attention score threshold, determine the attention analysis result of the user to whom the human face belongs for the target object.

2. The method according to claim 1, wherein The processing of the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face, and the confidence value of the line-of-sight angle information includes: Perform face detection on the image to be processed and calculate the face angle information of the human face and the confidence value of the face angle information; Perform eye detection on the image to be processed to determine the eye map information in the human face; Based on the eye map information, perform line-of-sight tracking detection on the user to whom the human face belongs to determine the line-of-sight angle information of the eyes in the human face and the confidence value of the line-of-sight angle information.

3. The method according to claim 2, wherein The performing eye detection on the image to be processed to determine the eye map information in the human face includes: Perform eye detection on the image to be processed to determine the eye key point information in the human face; Expand the eye region corresponding to the eye key point information to obtain a target eye region; Perform human eye image segmentation on the target eye region to obtain the eye map information in the human face.

4. The method according to any one of claims 1 to 3, characterized in that, The face angle information includes: face yaw angle information and face pitch angle information; The line-of-sight angle information of the eyes in the human face includes: the left eye line-of-sight yaw angle information and left eye line-of-sight pitch angle information corresponding to the left eye in the human face, and / or, the right eye line-of-sight yaw angle information and right eye line-of-sight pitch angle information corresponding to the right eye in the human face.

5. The method according to any one of claims 1 to 3, characterized in that, The confidence value of the face angle information and the confidence value of the line-of-sight angle information are both confidence values after normalization processing.

6. An information processing apparatus, characterized in that, Including: An acquisition module, a processing module, and a determination module; The acquisition module is used to acquire an image to be processed, where the image to be processed includes a human face facing a target object; The processing module is used to process the image to be processed to determine the face angle information of the human face and the confidence value of the face angle information, the line-of-sight angle information of the eyes in the human face, and the confidence value of the line-of-sight angle information; The determining module is configured to determine an attention analysis result of the user to whom the face belongs with respect to the target object according to the face angle information, the confidence value of the face angle information, the line-of-sight angle information, and the confidence value of the line-of-sight angle information; Specifically, the determining module is configured to determine a first attention result based on the face and a first attention score corresponding to the first attention result based on a preset face angle threshold range, the face angle information, and the confidence value of the face angle information; Determine a second attention result of the eye line of sight in the face and a second attention score of the second attention result based on a preset line-of-sight angle threshold range, the line-of-sight angle information, and the confidence value of the line-of-sight angle information; Determine an attention analysis result of the user to whom the face belongs with respect to the target object according to the first attention result, the first attention score, the second attention result, and the second attention score; Specifically, the determining module is configured to determine at least one target attention result with a true value according to the values of the first attention result and the second attention result, and a true value of the attention result indicates attention; Determine an attention analysis result of the user to whom the face belongs with respect to the target object according to the number of the target attention results, the attention score of each target attention result, and a preset attention score threshold.

7. An electronic device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, the method described in any one of claims 1-5 above is implemented.

8. A computer-readable storage medium, characterized in that, Computer instructions are stored in the computer-readable storage medium, and when the computer instructions run on a computer, the computer is caused to execute the method described in any one of claims 1-5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it is used to implement the method described in any one of claims 1-5.

Images