An information processing method, an electronic device, and a computer-readable storage medium

Abstract

An embodiment of the present application discloses an information processing method, which includes: determining the facial pose information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component; determining a target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information; where the target access parameter characterizes the access pose of the first user to the first object; determining a target object based on the first object and the target access parameter. An embodiment of the present application also discloses an electronic device and a computer-readable storage medium.

Description

Technical Field

[0001] The present application relates to information processing technology in the field of information processing, and particularly relates to an information processing method, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the development of offline stores, how to reduce the store operation cost while improving the shopping experience of users has become an important issue faced by the current development of offline stores; in order to improve the shopping experience of users, usually during the shopping process of users, salespersons actively recommend products to users according to experience for users to choose; however, the products recommended to users according to human experience are not the products that users want. Summary of the Invention

[0003] To solve the above technical problems, embodiments of the present application are expected to provide an information processing method, an electronic device, and a computer-readable storage medium, which solve the problem that the products recommended to users according to human experience are not the products that users want.

[0004] The technical solution of the present application is realized as follows:

[0005] An information processing method, the method includes:

[0006] Determine the facial pose information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component;

[0007] Based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information, determine a target access parameter; wherein, the target access parameter characterizes the access pose of the first user to the first object;

[0008] Based on the first object and the target access parameter, determine a target object.

[0009] In the above solution, the determining the facial pose information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component includes:

[0010] When the distance between the first user and the first object satisfies a target distance range, collect a first image of the first user through the image acquisition component, and analyze the first image to obtain the facial pose information;

[0011] Collect a second image of the first object through the image acquisition component, and determine the first orientation information based on the second image;

[0012] Determine the second orientation information when the first image is collected through the image acquisition component;

[0013] Determine the third orientation information when the second image is collected through the image acquisition component.

[0014] In the above solution, determining the target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information includes:

[0015] Based on the facial pose information, determine a first angle between the line of sight of the first user and a first connection line when the first image is collected through the image acquisition component; wherein, the first connection line is the connection line between the position where the image acquisition component is located and the position where the face of the first user is located;

[0016] Based on the first orientation information, determine a second angle between a second connection line and the plumb line of the first object when the second image is collected through the image acquisition component; wherein, the second connection line is the connection line between the position where the image acquisition component is located and the position where the first object is located;

[0017] Based on the second orientation information and the third orientation information, determine a third angle between the first connection line and the second connection line;

[0018] Based on the first angle, the second angle, and the third angle, determine a target angle between the line of sight of the first user and the plumb line; wherein, the target access parameter includes the target angle.

[0019] In the above solution, determining the target object based on the first object and the target access parameter includes:

[0020] Based on the target angle, determine a first target interest degree of the first user in the first object;

[0021] Based on the first object and the first target interest degree, determine the target object.

[0022] In the above solution, determining the first target interest degree of the first user in the first object based on the target angle includes:

[0023] In the case where it is determined that the first user contacts the first object and the target angle is less than the target threshold angle, determine the first interest degree of the first user in the first object;

[0024] In the case where the first user does not contact the first object and the target angle is greater than or equal to the target threshold angle, determine the second degree of interest of the first user in the first object;

[0025] In the case where the first user does not contact the first object and the target angle is less than the target threshold angle, determine the third degree of interest of the first user in the first object based on the target angle and the target attenuation coefficient;

[0026] Determine the first target degree of interest based on at least one of the first degree of interest, the second degree of interest, and the third degree of interest.

[0027] In the above solution, the determining the target object based on the first object and the first target degree of interest includes:

[0028] Determine the first browsing trajectory of the first user based on multiple first objects browsed by the first user;

[0029] Determine the target object based on the first browsing trajectory, the first target degree of interest of the first user in each first object, and the object recommendation model.

[0030] In the above solution, the method further includes:

[0031] Obtain the second browsing trajectories of multiple second users browsing second objects and the second target degrees of interest of the second users in each second object according to the sampling period;

[0032] Update the object recommendation model based on the second browsing trajectories and the second target degrees of interest.

[0033] In the above solution, the method further includes:

[0034] Obtain the third browsing trajectories of multiple third users browsing third objects and the third target degrees of interest of the third users in each third object;

[0035] For each third object, determine the activity value of each third object based on the third target degree of interest;

[0036] Obtain the layout diagram of the third object;

[0037] For each third object, establish a correspondence relationship between each third object, the position of the third object in the layout diagram, and the activity value based on the layout diagram;

[0038] Adjust the pose of the third object based on the correspondence relationship and the layout diagram.

[0039] An electronic device, the electronic device comprising: a processor, a memory, and a communication bus;

[0040] The communication bus is used to implement a communication connection between the processor and the memory;

[0041] The processor is used to execute an information processing program in the memory to implement the following steps:

[0042] Determine the facial gesture information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component;

[0043] Based on the facial gesture information, the first orientation information, the second orientation information, and the third orientation information, determine a target access parameter; wherein, the target access parameter characterizes the access gesture of the first user to the first object;

[0044] Based on the first object and the target access parameter, determine a target object.

[0045] A computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the steps of the above information processing method.

[0046] The information processing method, electronic device, and computer-readable storage medium provided by the embodiments of the present application, by determining the facial gesture information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component; based on the facial gesture information, the first orientation information, the second orientation information, and the third orientation information, determine a target access parameter; wherein, the target access parameter characterizes the access gesture of the first user to the first object; based on the first object and the target access parameter, determine a target object; thus, considering the access gesture of the first user to the first object and the first object to determine the target object that the first user is interested in, so as to recommend the target object to the first user subsequently, and no longer rely on human experience to determine the target object, solving the problem that the goods recommended to the first user based on human experience are not the goods that the first user wants, and improving the accuracy of recommending the target object to the first user. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic flowchart of an information processing method provided by an embodiment of the present application;

[0048] Figure 2 It is a schematic flowchart of another information processing method provided by an embodiment of the present application;

[0049] Figure 3 Schematic diagram of the first included angle in an information processing method provided by an embodiment of the present application;

[0050] Figure 4 Schematic diagram of the second included angle in an information processing method provided by an embodiment of the present application;

[0051] Figure 5 Schematic diagram of the third included angle in an information processing method provided by an embodiment of the present application;

[0052] Figure 6 Schematic diagram of the target angle in an information processing method provided by an embodiment of the present application;

[0053] Figure 7 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0054] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0055] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] An embodiment of the present application provides an information processing method. Referring to Figure 1 as shown, the method includes the following steps:

[0057] Step 101, determine the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component.

[0058] Among them, the facial pose information may include: facial orientation information and facial expression information. The first user may be a customer in an offline target store; the first object may be a commodity in the target store related to the position of the first user; the first orientation information includes the direction and position of the image acquisition component relative to the first object; the second orientation information includes the direction and position of the first user relative to the image acquisition component; the third orientation information includes the direction and position of the first object relative to the image acquisition component; the image acquisition component may be a camera set in the target store.

[0059] In an embodiment of the present application, a first image of a first user can be obtained, and the facial pose information of the first user can be obtained by analyzing the first image; the face of the first user can also be scanned by an infrared measurement component to obtain the facial pose information of the first user; the position information of the first user, the position information of the image acquisition component, and the position information of the first object can be obtained. Taking the first object as a reference point, the first azimuth information of the first object relative to the image acquisition component can be determined through the position information of the first object and the position information of the image acquisition component; taking the image acquisition component as a reference point, the second azimuth information of the first user relative to the image acquisition component can be determined through the position information of the first user and the position information of the image acquisition component; taking the image acquisition component as a reference point, the third azimuth information of the first object relative to the image acquisition component can be determined through the position information of the first object and the position information of the image acquisition component.

[0060] In a feasible implementation manner, when the first user is in a target store, a camera in the target store can collect a first image of the first user, and determine the facial pose information of the first user through the first image, and can detect the direction and position of the camera relative to the target commodity, the direction and position of the first user relative to the camera, and the direction and position of the target commodity relative to the camera. Among them, the target commodity is a commodity related to the position of the first user.

[0061] Step 102: Determine a target access parameter based on the facial pose information, the first azimuth information, the second azimuth information, and the third azimuth information.

[0062] Among them, the target access parameter characterizes the access pose of the first user to the first object; the target access parameter can be the visual access angle of the first user to the first object; the target access parameter can also be the visual access angle and access expression of the first user to the first object.

[0063] In an embodiment of the present application, the line-of-sight direction of the first user can be determined according to the facial pose information of the first user, and the target access parameter can be determined according to the line-of-sight direction, the first azimuth information, the second access information, and the third azimuth information.

[0064] Step 103: Determine a target object based on the first object and the target access parameter.

[0065] In an embodiment of the present application, a plurality of candidate objects of interest to the first user can be determined according to the target access parameter and the first object, and the target object can be determined from the plurality of candidate objects to recommend the target object to the first user. Among them, the target object can be a target recommended commodity determined from the commodity database of the target store.

[0066] In a feasible implementation, the number of the first objects can be multiple, which are respectively product A1, product A2, and product A3. The historical products that the first user has browsed and is interested in can be determined from product A1, product A2, and product A3 according to the access parameters of the first user for product A1, the access parameters of the first user for product A2, and the access parameters of the first user for product A3. And the products related to or similar to the historical products can be determined from the product database as candidate products according to the historical products, and the product with the highest sales volume can be determined from the candidate products as the target product.

[0067] The information processing method provided by the embodiments of the present application determines the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component; based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information, the target access parameter is determined; wherein, the target access parameter characterizes the access pose of the first user to the first object; based on the first object and the target access parameter, the target object is determined; in this way, considering the access pose of the first user to the first object and the first object to determine the target object that the first user is interested in, so as to recommend the target object to the first user subsequently, and no longer rely on human experience to determine the target object, solving the problem that the products recommended to the first user relying on human experience are not the products that the first user wants, and improving the accuracy of recommending the target object to the first user.

[0068] Based on the foregoing embodiments, the embodiments of the present application provide an information processing method, as shown in Figure 2 The method includes the following steps:

[0069] Step 201, when the distance between the first user and the first object satisfies the target distance range, collect the first image of the first user through the image acquisition component, and analyze the first image to obtain the facial pose information.

[0070] In the embodiments of the present application, the position of the first user can be detected in real time, and based on the position of the first user, a first object related to the position of the first user is determined, where the first object is an object within an effective distance range from the first user; the effective distance range is greater than the target distance range. When the distance between the first user and the first object is less than or equal to the target distance, it is determined that the distance between the first user and the first object meets the target distance range. At this time, a first image of the first user can be collected by an image acquisition component, and a face region image is determined from the first image, so as to determine the facial pose information of the first user based on the face region image, ensuring the effectiveness of the determined facial pose information of the first user, avoiding inaccurate facial pose information determined due to the excessive distance between the first user and the first object, and further improving the accuracy of the determined facial pose information.

[0071] In a feasible implementation manner, when the first user moves in a target store, the position of the first user can be detected in real time. When it is determined based on the position of the first user that the distance between the first user and a certain commodity is less than or equal to the target distance, a first image of the first user can be collected by an image acquisition component, and face recognition is performed on the first image to extract a face region image from the first image, and the face region image is input into a face facial pose recognition model to determine the facial pose information of the first user.

[0072] Step 202: Collect a second image of the first object by an image acquisition component, and determine a first orientation information based on the second image.

[0073] In the embodiments of the present application, the image acquisition component for collecting the first image and the second image is the same image acquisition component; the second image can be input into a first orientation recognition model, so that the first orientation recognition model analyzes the second image to determine the first orientation information of the image acquisition component relative to the first object; among them, the first orientation recognition model can be obtained by pre-collecting a large number of sample images of sample objects for model training. Among them, the first object and the sample object can be commodities in a target store.

[0074] Step 203: Determine a second orientation information when the first image is collected by the image acquisition component.

[0075] In the embodiments of the present application, a second orientation recognition model can be obtained, and the first image is input into the second orientation recognition model. The second orientation recognition model processes the first image to determine the second orientation information of the first user relative to the image acquisition component. Among them, the second orientation recognition model can be obtained by pre-collecting a large number of sample images of sample users for model training.

[0076] Step 204: Determine the third orientation information when the second image is captured by the image acquisition component.

[0077] In an embodiment of the present application, a third orientation recognition model can be obtained, and the second image is input into the third orientation recognition model. The third orientation recognition model processes the third image to determine the third orientation information of the first object relative to the image acquisition component. Among them, the third orientation recognition model can be trained by pre-collecting a large number of sample images of sample objects.

[0078] Step 205: Based on the facial pose information, determine the first angle between the line of sight of the first user and the first connection line when the first image is captured by the image acquisition component.

[0079] Among them, the first connection line is the connection line between the position where the image acquisition component is located and the position where the face of the first user is located; the line of sight of the first user can be determined by the facial orientation information of the first user.

[0080] In an embodiment of the present application, a visual angle recognition model can be obtained, and the facial pose information is processed by the visual angle recognition model to determine the first angle between the line of sight of the first user and the first connection line when the image acquisition component captures the first image of the first user. Among them, the visual angle recognition model is trained by pre-collecting a large number of sample facial pose information of sample users.

[0081] In a feasible line-of-sight method, refer to Figure 3 As shown, the camera is represented by A, the first user is represented by B, the connection line between A and B is the first connection line L1, the line of sight of the first user is represented by L2, and the first angle is the angle a between L1 and L2.

[0082] Step 206: Based on the first orientation information, determine the second angle between the second connection line and the vertical line of the first object when the second image is captured by the image acquisition component.

[0083] Among them, the second connection line is the connection line between the position where the image acquisition component is located and the position where the first object is located.

[0084] In an embodiment of the present application, a first orientation angle recognition model can be obtained, and the first orientation information is input into the first angle recognition model to determine the second angle between the second connection line and the vertical line of the first object; among them, the second angle can also be understood as the azimuth angle of the image acquisition component relative to the first object; the vertical line refers to the connection line between the center of gravity of the first object and the center of gravity of the earth, and is also called the plumb line of the first object.

[0085] In a feasible implementation method, refer to Figure 4As shown, the camera is represented by A, and the first object is represented by C. The first object can be placed on the exhibition stand. The connection line between A and C is the second connection line L3. The vertical line of the first object is represented by L4, and the second included angle is the included angle b between L3 and L4.

[0086] Step 207: Based on the second orientation information and the third orientation information, determine the third included angle between the first connection line and the second connection line.

[0087] In the embodiment of the present application, the fourth included angle between the first user and the reference line of the image acquisition component can be determined based on the second orientation information, and the fifth included angle between the first object and the reference line of the image acquisition component can be determined based on the third orientation information. According to the fourth included angle and the fifth included angle, the third included angle between the first connection line and the second connection line is determined.

[0088] In a feasible implementation manner, referring to Figure 5 As shown, the reference line is L5, the fourth included angle is the included angle c between L5 and L1, the fifth included angle is the included angle d between L5 and L3, and the third included angle is the included angle d - c between L1 and L3.

[0089] Step 208: Based on the first included angle, the second included angle, and the third included angle, determine the target angle between the line of sight of the first user and the vertical line.

[0090] Among them, the target access parameter includes the target angle; the target angle can be understood as the visual access angle of the first user to the first object when the image acquisition component acquires the first image.

[0091] In the embodiment of the present application, the target angle between the line of sight of the first user and the vertical line can be calculated according to the first included angle, the second included angle, and the third included angle.

[0092] In a feasible line-of-sight manner, referring to Figure 6 As shown, the target angle is represented by m, the first included angle is represented by a, the second included angle is represented by b, the third included angle is represented by d - c, and m = 180° - (a + b + d - c).

[0093] Step 209: Based on the target angle, determine the first target interest degree of the first user in the first object.

[0094] In the embodiment of the present application, the first target interest degree of the first user in the first object can be determined according to the target angle corresponding to each time within the target time period; the first target interest degree is used to represent the degree of interest of the first user in the first object.

[0095] It should be noted that step 209 can be implemented through steps a1 - a4:

[0096] Step a1: When it is determined that the first user contacts the first object and the target angle is less than the target threshold angle, determine the first degree of interest of the first user in the first object.

[0097] In the embodiments of the present application, when the first user contacts the first object and the target angle is greater than or equal to the target threshold angle, at this time, the first user may accidentally touch the first object during the movement, and the degree of interest of the first user in the first object may not be calculated. When the first user contacts the first object and the target angle is less than the target threshold angle, it can be determined that the first user is interested in the first object, and the degree of interest of the first user in the first object is determined as the first degree of interest. Of course, it can also be determined that the first user is not interested in the first object when the first user contacts the first object and the target angle is greater than or equal to the target threshold angle, that is, it can be understood that the degree of interest of the first user in the first object is 0.

[0098] In a feasible implementation manner, the target threshold angle is 90°, the first degree of interest is represented by h1(t), and h1(t) = 1. Where t represents the moment when the first image is collected.

[0099] Step a2: When the first user does not contact the first object and the target angle is greater than or equal to the target threshold angle, determine the second degree of interest of the first user in the first object.

[0100] In the embodiments of the present application, when the first user does not contact the first object and the target angle is greater than or equal to the target threshold angle, it can be determined that the first user is not interested in the first object, and at this time, the degree of interest of the first user in the first object can be determined as the second degree of interest.

[0101] In a feasible implementation manner, the second degree of interest is represented by h2(t), and h2(t) = 0.

[0102] Step a3: When the first user does not contact the first object and the target angle is less than the target threshold angle, determine the third degree of interest of the first user in the first object based on the target angle and the target attenuation coefficient.

[0103] In the embodiments of the present application, when the first user does not contact the first object and the target angle is less than the target threshold angle, it indicates that the first user is watching / browsing the first object without contact, and the third degree of interest of the first user in the first object can be calculated.

[0104] In a feasible implementation manner, the target angle is m, then when the first image is collected, the third degree of interest of the first user in the first object is Where α is a preset target attenuation coefficient.

[0105] Step a4: Determine a first target interest level based on at least one of a first interest level, a second interest level, and a third interest level.

[0106] It should be noted that the first interest level can be understood as the interest level when the first user contacts the first object and views / browses the first object; the second interest level is the interest level when the first user passes by the first object without viewing / browsing the first object; the third interest level is the interest level when the first user does not contact the first object but views / browses the first object.

[0107] In an embodiment of the present application, when the distance between the first user and the first object satisfies a target distance range, the first target interest level of the first user in the first object within a target time period can be determined. Among them, the first target interest level is determined according to the interest level of the first user in the first object at different times within the target time period. The target time period is the time period corresponding to when the distance between the first user and the first object satisfies the target distance range.

[0108] In a feasible implementation manner, within the target time period, the first user may not contact the first object at time t1 but is viewing the first object. At this time, the interest level of the first user in the first object at time t1 is the third interest level. At time t2, the first user contacts the first object and views the first object. At this time, the interest level of the first user in the first object at time t2 is the first interest level. At time t3, the first user leaves the first object. At this time, the first user does not contact the first object and does not view the first object. The interest level of the first user in the first object at time t3 is the second interest level. The third interest level corresponding to time t1, the first interest level corresponding to time t2, and the second interest level corresponding to time t3 can be added up or averaged to obtain the first target interest level.

[0109] In another feasible implementation manner, within the target time period, the first user may not contact the first object and does not view the first object all the time. Then, the first target interest level of the first user within the target time period is the second interest level.

[0110] Step 210: Determine a target object based on the first object and the first target interest level.

[0111] In an embodiment of the present application, based on the first target interest level of the first object, a first browsing object that the first user is interested in can be determined from the first object, and based on the first browsing object, multiple candidate objects that the first user is interested in can be determined from a commodity database, so as to determine a target object from the multiple candidate objects; among them, the first browsing object can be an object in the first object whose first target interest level is greater than an interest level threshold.

[0112] It should be noted that Step 210 can be implemented through Steps b1 - b2:

[0113] Step b1: Determine the first browsing trajectory of the first user based on multiple first objects browsed by the first user.

[0114] Among them, the multiple first objects browsed by the first user refer to multiple first browsing objects.

[0115] In the embodiment of the present application, the browsing time corresponding to each first browsing object browsed by the first user can be determined, and the first browsing trajectory of the first user can be determined according to the multiple first browsing objects and the browsing time.

[0116] Step b2: Determine the target object based on the first browsing trajectory, the first target interest degree of the first user for each first object, and the object recommendation model.

[0117] In the embodiment of the present application, the first browsing trajectory and the first target interest degree of the first user for each first browsing object can be input into the object recommendation model, so that the object recommendation model matches the first browsing trajectory with the historical browsing trajectory to obtain a candidate browsing trajectory that matches the first browsing trajectory, and determines the target browsing trajectory from the candidate browsing trajectories according to the first target interest degree of each first browsing object and the historical target interest degree of the objects on each candidate browsing trajectory, and uses the objects other than the first object in the target browsing trajectory as candidate objects, and determines the target object from the multiple candidate objects according to the historical target interest degree of each candidate object. Among them, the object recommendation model can be trained according to the historical browsing trajectories of historical users browsing historical objects and the historical target interest degrees of historical objects.

[0118] In a feasible implementation, the first browsing trajectory of the first user when browsing products after entering the target store is n1 - n2 - n3, where n1, n2, and n3 represent different products. The first target interest degree corresponding to n1 is represented by m1, the first target interest degree corresponding to n2 is represented by m2, and the first target interest degree corresponding to n3 is represented by m3. Through the object recommendation model, n1 - n2 - n3 can be matched with the historical browsing trajectories of historical users to obtain candidate browsing trajectories n1 - n2 - n3 - n5 - n7, n1 - n2 - n3 - n4 - n6, and n1 - n2 - n3 - n8 - n9. Then, m1 can be matched with the historical target interest degree corresponding to n1 in each candidate browsing trajectory to obtain the first matching degree, m2 can be matched with the historical target interest degree corresponding to n2 in each candidate browsing trajectory to obtain the second matching degree, m3 can be matched with the historical target interest degree corresponding to n3 in each candidate browsing trajectory to obtain the third matching degree, and according to the first matching degree, second matching degree, and third matching degree corresponding to each candidate browsing trajectory, the matching value corresponding to each candidate browsing trajectory is determined, and the candidate browsing trajectory corresponding to the maximum matching value is determined as the target browsing trajectory from the 3 candidate browsing trajectories. When the target browsing trajectory is n1 - n2 - n3 - n5 - n7, n5 and n7 can be used as candidate objects, and the object with the largest historical target interest degree is determined as the target object from n5 and n7. Among them, the matching value can be the average of the first matching degree, the second matching degree, and the third matching degree.

[0119] Based on the foregoing embodiments, in other embodiments of the present application, the information processing method further includes:

[0120] Step 211: Obtain the second browsing trajectories of multiple second users browsing the second objects and the second target interest degrees of each second object by the second users according to the sampling period.

[0121] Among them, the second user can be a customer who entered the target store during the historical first time period. The second object refers to the second browsing object of the second user; among them, the determination processes of the second browsing object and the first browsing object are the same, and the embodiments of the present application will not elaborate herein.

[0122] In the embodiments of the present application, multiple second browsing trajectories and second target interest degrees can be obtained periodically according to the sampling period. Among them, the sampling period can be one week or two weeks to ensure the timeliness of the obtained second browsing trajectories and second target interest degrees. The determination processes of the second browsing trajectories and the second target interest degrees are similar to the processes of determining the first browsing trajectories and the first target interest degrees, and the embodiments of the present application will not elaborate herein.

[0123] Step 212: Update the object recommendation model based on the second browsing trajectories and the second target interest degrees.

[0124] In an embodiment of the present application, the second browsing trajectory and the second target interest degree can be used as sample data to periodically update the object recommendation model to ensure the timeliness of the object recommendation model.

[0125] Step 213: Obtain the third browsing trajectories of multiple third users browsing third objects and the third target interest degrees of each third user for each third object.

[0126] Among them, the third user can be a customer who enters the target store within a historical second time period; the third object can be the third browsing object of the third user.

[0127] It should be noted that the implementation process of step 213 is similar to that of step 211, and the embodiments of the present application will not elaborate here.

[0128] Step 214: For each third object, determine the activity value of each third object based on the third target interest degree.

[0129] In an embodiment of the present application, for any third object, the third target interest degrees of multiple third users for the third object can be determined, and the third target interest degrees can be calculated to determine the activity value of the third object.

[0130] In a feasible implementation manner, for any third object, the third object can be commodity E. The third target interest degrees of each third user for commodity E can be obtained respectively to obtain multiple third target interest degrees for the third object, and the average value or the sum of the third target interest degrees can be calculated to obtain the activity value of commodity E.

[0131] Step 215: Obtain the layout diagram of the third object.

[0132] In an embodiment of the present application, the layout diagram of the third object can be determined according to the position of the third object in the target store; the layout diagram of the third object can also be understood as the distribution diagram of the third object in the target store.

[0133] Step 216: For each third object, based on the layout diagram, establish a correspondence relationship among each third object, the position of the third object in the layout diagram, and the activity value.

[0134] It should be noted that the correspondence relationship can be presented in various forms.

[0135] In a feasible implementation manner, the correspondence relationship can be presented through a heat map.

[0136] Step 217: Based on the correspondence relationship and the layout diagram, adjust the pose of the third object.

[0137] In an embodiment of the present application, the layout of the third object can be determined to be reasonable according to the corresponding relationship and the layout diagram, so as to adjust the position and display angle of the third object subsequently; wherein, the pose of the third object includes the position of the third object and the display angle of the third object.

[0138] In a feasible implementation manner, the third object can be a commodity in an electronic display cabinet, and the display position of the commodity on the display interface of the electronic display cabinet can be adjusted according to the corresponding relationship and the layout diagram; in another feasible implementation manner, the third object can be a commodity in a target store, and the display position and display angle of the commodity in the target store can be adjusted according to the corresponding relationship and the layout diagram.

[0139] It should be noted that the descriptions of the same steps and the same content in this embodiment and other embodiments can be referred to the descriptions in other embodiments, and will not be repeated here.

[0140] The information processing method provided by the embodiment of the present application considers the access pose of the first user to the first object and the first object to determine the target object that the first user is interested in, so as to recommend the target object to the first user subsequently, and no longer relies on human experience to determine the target object, solving the problem that the commodity recommended to the first user relying on human experience is not the commodity that the first user wants, and improving the accuracy of recommending the target object to the first user.

[0141] Based on the foregoing embodiments, an embodiment of the present application provides an electronic device, which can be applied to Figures 1-2 the information determination method provided by the corresponding embodiment, with reference to Figure 7 As shown, the electronic device 3 may include: a processor 31, a memory 32, and a communication bus 33, wherein:

[0142] The communication bus 33 is used to implement the communication connection between the processor 31 and the memory 32;

[0143] The processor 31 is configured to execute the information processing program in the memory 32 to implement the following steps:

[0144] Determine the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component;

[0145] Based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information, determine the target access parameter; wherein, the target access parameter characterizes the access pose of the first user to the first object;

[0146] Based on the first object and the target access parameter, determine the target object.

[0147] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component, so as to implement the following steps:

[0148] When the distance between the first user and the first object satisfies the target distance range, collect a first image of the first user through the image acquisition component, and analyze the first image to obtain the facial pose information;

[0149] Collect a second image of the first object through the image acquisition component, and determine the first orientation information based on the second image;

[0150] Determine the second orientation information when collecting the first image through the image acquisition component;

[0151] Determine the third orientation information when collecting the second image through the image acquisition component.

[0152] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information, so as to implement the following steps:

[0153] Based on the facial pose information, determine a first angle between the line of sight of the first user and the first connection line when collecting the first image through the image acquisition component; wherein, the first connection line is the connection line between the position where the image acquisition component is located and the position where the face of the first user is located;

[0154] Based on the first orientation information, determine a second angle between the second connection line and the vertical line of the first object when collecting the second image through the image acquisition component; wherein, the second connection line is the connection line between the position where the image acquisition component is located and the position where the first object is located;

[0155] Based on the second orientation information and the third orientation information, determine a third angle between the first connection line and the second connection line;

[0156] Based on the first angle, the second angle, and the third angle, determine the target angle between the line of sight of the first user and the vertical line; wherein, the target access parameter includes the target angle.

[0157] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the target object based on the first object and the target access parameter, so as to implement the following steps:

[0158] Based on the target angle, determine the first target interest degree of the first user in the first object;

[0159] Determine a target object based on a first object and a first target interest level.

[0160] In other embodiments of the present application, the processor 31 is configured to execute an information processing program in the memory 32 to determine a first target interest level of a first user in a first object based on a target angle, so as to implement the following steps:

[0161] When it is determined that the first user contacts the first object and the target angle is less than a target threshold angle, determine a first interest level of the first user in the first object;

[0162] When it is determined that the first user does not contact the first object and the target angle is greater than or equal to the target threshold angle, determine a second interest level of the first user in the first object;

[0163] When it is determined that the first user does not contact the first object and the target angle is less than the target threshold angle, determine a third interest level of the first user in the first object based on the target angle and a target attenuation coefficient;

[0164] Determine the first target interest level based on at least one of the first interest level, the second interest level, and the third interest level.

[0165] In other embodiments of the present application, the processor 31 is configured to execute an information processing program in the memory 32 to determine a target object based on a first object and a first target interest level, so as to implement the following steps:

[0166] Determine a first browsing trajectory of the first user based on a plurality of first objects browsed by the first user;

[0167] Determine the target object based on the first browsing trajectory, the first target interest level of the first user in each first object, and an object recommendation model.

[0168] In other embodiments of the present application, the processor 31 is configured to execute an information processing program in the memory 32 to implement the following steps:

[0169] Obtain second browsing trajectories of a plurality of second users browsing second objects and second target interest levels of the second users in each second object according to a sampling period;

[0170] Update the object recommendation model based on the second browsing trajectories and the second target interest levels.

[0171] In other embodiments of the present application, the processor 31 is configured to execute an information processing program in the memory 32 to implement the following steps:

[0172] Obtain third browsing trajectories of a plurality of third users browsing third objects and third target interest levels of the third users in each third object;

[0173] For each third object, determine the activity value of each third object based on the third target interest level;

[0174] Obtain the layout diagram of the third object;

[0175] For each third object, based on the layout diagram, establish a correspondence relationship among each third object, the position of the third object in the layout diagram, and the activity value;

[0176] Based on the correspondence relationship and the layout diagram, adjust the pose of the third object.

[0177] It should be noted that for the specific implementation process of the steps executed by the processor in this embodiment, reference can be made to Figures 1-2 the implementation process in the information processing method provided in the corresponding embodiment, which will not be elaborated here.

[0178] In the electronic device provided in the embodiment of the present application, by considering the access posture of the first user to the first object and the first object, the target object that the first user is interested in is determined, so as to recommend the target object to the first user subsequently. Instead of relying on human experience to determine the target object, the problem that the products recommended to the first user based on human experience are not the products that the first user wants is solved, and the accuracy of recommending the target object to the first user is improved.

[0179] Based on the foregoing embodiments, an embodiment of the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement Figures 1-2 the steps of the information processing method provided in the corresponding embodiment.

[0180] It should be noted that the above computer-readable storage medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it may also be various electronic devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0181] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including that element.

[0182] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0183] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0184] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in one or more flows and / or one or more blocks. Figure 1 in one or more flows and / or one or more blocks Figure 1 of the means for implementing the functions specified in the block or blocks.

[0185] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction means that implements the functions specified in one or more flows and / or one or more blocks. Figure 1 in one or more flows and / or one or more blocks Figure 1 of the block or blocks.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows and / or one or more blocks. Figure 1 in one or more flows and / or one or more blocks Figure 1 of the block or blocks.

[0187] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. An information processing method, the method comprising: Determining the facial pose information of a first user, the first orientation information of an image acquisition component relative to a first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component; Determining a target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information; wherein the target access parameter characterizes the access pose of the first user to the first object; Determining a target object based on the first object and the target access parameter; The determining a target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information includes: Determining a first angle between the line of sight of the first user and a first line when collecting a first image through the image acquisition component based on the facial pose information; wherein the first line is the line between the position where the image acquisition component is located and the position where the face of the first user is located; Determining a second angle between a second line and the vertical line of the first object when collecting a second image through the image acquisition component based on the first orientation information; wherein the second line is the line between the position where the image acquisition component is located and the position where the first object is located; Determining a third angle between the first line and the second line based on the second orientation information and the third orientation information; Determining a target angle between the line of sight of the first user and the vertical line based on the first angle, the second angle, and the third angle; wherein the target access parameter includes the target angle.

2. The method according to claim 1, wherein the determining the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component includes: When the distance between the first user and the first object satisfies a target distance range, collecting a first image of the first user through the image acquisition component and analyzing the first image to obtain the facial pose information; Collecting a second image of the first object through the image acquisition component and determining the first orientation information based on the second image; Determining the second orientation information when collecting the first image through the image acquisition component; Determining the third orientation information when collecting the second image through the image acquisition component.

3. The method according to claim 1, wherein the determining a target object based on the first object and the target access parameter includes: Determining a first target interest degree of the first user in the first object based on the target angle; Determining the target object based on the first object and the first target interest degree.

4. The method according to claim 3, wherein the determining a first target interest degree of the first user in the first object based on the target angle includes: When it is determined that the first user contacts the first object and the target angle is less than the target threshold angle, determine the first degree of interest of the first user in the first object; When the first user does not contact the first object and the target angle is greater than or equal to the target threshold angle, determine the second degree of interest of the first user in the first object; When the first user does not contact the first object and the target angle is less than the target threshold angle, determine the third degree of interest of the first user in the first object based on the target angle and the target attenuation coefficient; Based on the first degree of interest, the second degree of interest and the third degree of interest, determine the first target degree of interest.

5. The method according to claim 4, wherein the determining the target object based on the first object and the first target degree of interest comprises: Based on a plurality of the first objects browsed by the first user, determine the first browsing trajectory of the first user; Based on the first browsing trajectory, the first target degree of interest of the first user in each of the first objects and an object recommendation model, determine the target object.

6. The method according to claim 5, further comprising: According to a sampling period, obtain the second browsing trajectories of a plurality of second users browsing second objects and the second target degrees of interest of the second users in each of the second objects; Based on the second browsing trajectories and the second target degrees of interest, update the object recommendation model.

7. The method according to claim 1, further comprising: Obtain the third browsing trajectories of a plurality of third users browsing third objects and the third target degrees of interest of the third users in each of the third objects; For each third object, determine the activity value of each third object based on the third target degree of interest; Obtain the layout diagram of the third object; For each of the third objects, based on the layout diagram, establish a correspondence relationship between each of the third objects, the position of the third object in the layout diagram and the activity value; Based on the correspondence relationship and the layout diagram, adjust the pose of the third object.

8. An electronic device, the electronic device comprising: A processor, a memory and a communication bus; The communication bus is used to implement the communication connection between the processor and the memory; The processor is used to execute the information processing program in the memory to implement the following steps: Determine the facial pose information of the first user, the first orientation information of the image acquisition component relative to the first object, the second orientation information of the first user relative to the image acquisition component, and the third orientation information of the first object relative to the image acquisition component; Based on the facial pose information, the first orientation information, the second orientation information and the third orientation information, determine the target access parameter; wherein the target access parameter characterizes the access pose of the first user to the first object; Based on the first object and the target access parameter, determine the target object; Determining a target access parameter based on the facial pose information, the first orientation information, the second orientation information, and the third orientation information includes: determining, based on the facial pose information, a first angle between the line of sight of the first user and a first connection line when collecting a first image through the image acquisition component; wherein the first connection line is a connection line between the position where the image acquisition component is located and the position where the face of the first user is located; determining, based on the first orientation information, a second angle between a second connection line and the vertical line of the first object when collecting a second image through the image acquisition component; wherein the second connection line is a connection line between the position where the image acquisition component is located and the position where the first object is located; determining, based on the second orientation information and the third orientation information, a third angle between the first connection line and the second connection line; determining, based on the first angle, the second angle, and the third angle, a target angle between the line of sight of the first user and the vertical line; wherein the target access parameter includes the target angle.

9. A computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the steps of the information processing method according to any one of claims 1 to 7.

Images