Target object processing method

Abstract

The target object processing method provided by the embodiment of the invention comprises the steps of receiving a user picture of a first user sent by a first picture acquisition device, and performing feature extraction on the user picture of the first user to obtain a user feature of the first user; receiving a user picture of a second user sent by a second picture acquisition device and object processing information of the second user, and performing feature extraction on the user picture of the second user to obtain user features of the second user; and determining a display result of the target object in the display area according to the user characteristics of the first user, the user characteristics of the second user and the object processing information. Through the method, picture matching is performed on the received user pictures of the commodity display area and the commodity settlement area in a non-biological feature extraction manner, and the offline shopping guide marketing effect is analyzed, so that the risk management and control of biological recognition are met on the premise of avoiding user identity feature leakage and protecting user identity security.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and in particular to a target object processing method. Background Art

[0002] Biometric technology is a technology that uses the inherent physiological characteristics of the human body (such as fingerprints, faces, irises, etc.) and behavioral characteristics (such as handwriting, voice, gait, etc.) to identify personal identity through a close combination of computers with high-tech means such as optics, acoustics, biosensors and biostatistics principles; non-biometric technology (i.e. REI D) is a technology that establishes a correspondence between images of people captured by different cameras without overlapping views.

[0003] With the rapid development of computer technology and biometric technology, the application of biometric technology is becoming more and more extensive in all walks of life. Among them, biometric technology is widely used in store operations to measure the effectiveness of offline shopping guide marketing. However, as the scope of application of biometric technology becomes wider and wider, in order to protect users' personal privacy data, relevant departments are also increasingly strict in risk control of biometrics.

[0004] In view of this, how to use non-biometric technology to analyze the effectiveness of offline shopping guide marketing while meeting the risk control of biometrics is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, the embodiments of this specification provide two target object processing methods. One or more embodiments of this specification also relate to a target object processing device, a target object processing system, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0006] According to a first aspect of an embodiment of this specification, a target object processing method is provided, which is applied in a cloud, and includes:

[0007] Receiving a user picture of a first user sent by a first picture acquisition device, and performing feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by the first picture acquisition device performing picture acquisition on the first user passing through a display area of ​​a target object, and the user features of the first user do not include facial features of the first user;

[0008] Receiving a user picture of a second user and object processing information of the second user sent by a second picture acquisition device, and performing feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by the second picture acquisition device performing picture acquisition on the second user performing object processing in the object processing area, and the user features of the second user do not include facial features of the second user;

[0009] A display result of the target object in the display area is determined according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0010] According to a second aspect of an embodiment of this specification, a target object processing device is provided, including:

[0011] A first processing module is configured to receive a user picture of a first user sent by a first picture acquisition device, and perform feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by the first picture acquisition device performing picture acquisition on the first user passing through a display area of ​​a target object, and the user features of the first user do not include facial features of the first user;

[0012] A second processing module is configured to receive a user picture of a second user sent by a second picture acquisition device and object processing information of the second user, and perform feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by performing picture acquisition on the second user performing object processing in the object processing area by the second picture acquisition device, and the user features of the second user do not include facial features of the second user;

[0013] The determination module is configured to determine a display result of the target object in the display area according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0014] According to a third aspect of an embodiment of this specification, a target object processing method is applied to a target object processing system, wherein the target object processing system includes a cloud and a device end, wherein the device end includes a first image acquisition device and a second image acquisition device, and the method includes:

[0015] The first picture acquisition device acquires a picture of a first user passing through the display area of ​​the target object, obtains a user picture of the first user, and sends the user picture of the first user to the cloud;

[0016] The cloud receives the user image of the first user sent by the first image acquisition device, and performs feature extraction on the user image of the first user to obtain user features of the first user, wherein the user features of the first user do not include facial features of the first user;

[0017] The second image acquisition device acquires an image of a second user who is performing object processing in the object processing area, obtains a user image of the second user, and sends the user image of the second user to the cloud;

[0018] The cloud end receives the user image of the second user sent by the second image acquisition device and the object processing information of the second user, and performs feature extraction on the user image of the second user to obtain user features of the second user, wherein the user features of the second user do not include facial features of the second user, and determines the display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

[0019] According to a fourth aspect of an embodiment of this specification, a target object processing system is provided, the target object processing system comprising a cloud and a device end, wherein the device end comprises a first image acquisition device and a second image acquisition device, and the method comprises:

[0020] The first picture acquisition device is used to acquire a picture of a first user passing through the display area of ​​the target object, obtain a user picture of the first user, and send the user picture of the first user to the cloud;

[0021] The cloud is used to receive the user image of the first user sent by the first image acquisition device, and perform feature extraction on the user image of the first user to obtain user features of the first user, wherein the user features of the first user do not include facial features of the first user;

[0022] The second image acquisition device is used to acquire an image of a second user who is performing object processing in the object processing area, obtain a user image of the second user, and send the user image of the second user to the cloud;

[0023] The cloud end is used to receive the user image of the second user sent by the second image acquisition device and the object processing information of the second user, and perform feature extraction on the user image of the second user to obtain the user features of the second user, wherein the user features of the second user do not include the facial features of the second user, and determine the display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

[0024] According to a fifth aspect of an embodiment of this specification, a computing device is provided, including:

[0025] Memory and processor;

[0026] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the target object processing method are implemented.

[0027] According to a sixth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned target object processing method are implemented.

[0028] According to a seventh aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned target object processing method.

[0029] A target object processing method provided by an embodiment of the present specification is applied to the cloud, including: receiving a user picture of a first user sent by a first picture acquisition device, and performing feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by performing picture acquisition on the first user passing through a display area of ​​a target object by the first picture acquisition device, and the user features of the first user do not include facial features of the first user; receiving a user picture of a second user sent by a second picture acquisition device, and object processing information of the second user, and performing feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by performing picture acquisition on the second user performing object processing in an object processing area by the second picture acquisition device, and the user features of the second user do not include facial features of the second user; determining a display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

[0030] Specifically, the target object processing method applied to the cloud can extract features other than facial features from the user pictures received from the first picture acquisition device and the second picture acquisition device to obtain the user features of the first user and the user features of the second user, and receive the object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, when the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting user identity security, thereby meeting the risk control of biometric identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a scene diagram of a target object processing method provided by an embodiment of this specification;

[0032] Figure 2 is a flow chart of a target object processing method applied to the cloud provided by an embodiment of this specification;

[0033] Figure 3 It is a scene diagram of a shopping guide effect of a target object processing method provided by an embodiment of this specification;

[0034] Figure 4 is a flow chart of a target object processing method applied to a target object processing system provided by an embodiment of the present specification;

[0035] Figure 5 is a schematic diagram of the structure of a target object processing device provided by an embodiment of this specification;

[0036] Figure 6 is a schematic diagram of the structure of a target object processing system provided by an embodiment of this specification;

[0037] Figure 7 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0038] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0039] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0040] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0041] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0042] First, the terms involved in one or more embodiments of this specification are explained.

[0043] REID (Re-I Dent ificat ion, non-biometric technology): Re-identify people by establishing correspondences between images of people captured by different cameras without overlapping views.

[0044] Pos (Point of sale terminal): is an electronic cash register system and a multi-function terminal used by merchants to collect payments by swiping cards.

[0045] No risk: There will be no user complaints or the user complaints can be resolved, and the regulations of relevant departments will not be violated.

[0046] TG Planning: Product selection plan for store promotional areas.

[0047] In recent years, with the increasing demand for lean operations in stores, user identification for shelves can be used to measure the effectiveness of offline shopping guide marketing, and it is also of great value for analyzing consumer shopping behavior and pushing potential user applications. At the same time, relevant departments are increasingly strict with the risks of biometrics. As the law pays more and more attention to the protection of user portrait rights, biometrics for user identification results are often used as a kind of user privacy and need to be encrypted and stored. If the user's portrait is used privately without the user's consent, it will lead to the risk of leakage of the user's personal privacy data. However, in the shopping guide marketing scenario, it is a very important method to analyze the effect of shopping guide marketing by obtaining user characteristics. Therefore, it is very important to provide a solution that avoids the risk of leakage of users' personal privacy data, covers the application scenario area at a low cost, and can cover enough users.

[0048] The existing technologies include telecommunication equipment identification code technology, face recognition technology, location big data identification technology, point information point interception technology, and upper-level passenger flow algorithm technology. Among them, (1) telecommunication equipment identification code refers to the technology that relies on the front desk of the mobile phone to open. After the screen is actually turned off, the mobile phone will prohibit the permission within tens of seconds; (2) face recognition technology. Although the current face recognition technology is very mature, it is not allowed to be used in marketing scenarios to avoid the leakage of personal privacy data; (3) location big data, for example, media point basic data: the media's accurate description of the point address (detailed to the community / building) is the basis for accurate passenger flow. In actual applications, the quality of the address granularity filled in by the media can be judged by quality score, relevant monitoring reports can be established, and the media side can be pushed to re-enter the inventory and correct the problem in cooperation with product operations; (4) Point information point mounting: When the media point address information is accurate, it is necessary to complete the latitude and longitude information of the media point and the information point where it is located through geocoding. At present, this problem has been solved; (5) Upper passenger flow algorithm. Due to the low sampling rate problem of location-based service data, it is necessary to restore the resident scene passenger flow data based on the historical behavior of location-based service data. The coverage rate is calculated through the number of points placed by the media at the information point and the number of buildings and area of ​​the information point, and the passenger flow is compensated and restored using the resident passenger flow of the information point. Although the current technology can solve this problem, it lacks a large amount of underlying data support, such as information points, users, and member data, and the effect will be very poor.

[0049] Based on this, the embodiment of this specification proposes a target object processing method, which can extract features other than facial features from user pictures received from the first picture acquisition device and the second picture acquisition device to obtain user features of the first user and the second user, and receive object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, when the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting user identity security, thereby meeting the risk control of biometric identification.

[0050] In this specification, two target object processing methods are provided. This specification also involves a target object processing device, a target object processing system, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0051] See also Figure 1 , Figure 1 It is a scene diagram of a target object processing method provided by an embodiment of this specification.

[0052] This paper introduces the application of the target processing method to the commodity promotion scenario to determine the types of commodities displayed in the commodity promotion area. Figure 1 As shown, Figure 1 It includes a cloud 102, a display area 104, and a settlement area 106, wherein the display area 104 includes a first camera, commodity A and commodity B, and the settlement area 106 includes a second camera and a settlement platform.

[0053] Specifically, the user can select and purchase product A and product B in the display area 104. During the process of the user selecting products, the first camera will collect the user's picture in the display area and upload the user's picture in the display area to the cloud 102. After the user completes the selection and purchase of the products, some users will go to the settlement platform in the settlement area 106 to complete the purchase of the products. After the user completes the payment for the products, the second camera will collect the user's picture in the settlement area and upload the user's picture in the settlement area to the cloud 102. When the cloud receives the user's picture in the display area sent by the first camera in the display area 104 and the user's picture in the settlement area sent by the second camera in the settlement area, it will process the user's picture in the display area and the user's picture in the settlement area to obtain the user's picture in the display area. The physical features of the user picture (excluding facial features), and the physical features of the user in the settlement area (excluding facial features), and it is determined whether there are pictures with corresponding physical features between the display area user pictures and the settlement area user pictures, and finally, according to the judgment result, the number of users who purchase product A or product B in the display area 104 and settle the products in the settlement area 106 is analyzed, and based on the number of users and the number of users in the display area, the purchase conversion rate of the corresponding product is calculated, so as to determine the display products in the display area 104 according to the purchase conversion rate of the corresponding product. It should be noted that the higher the purchase conversion rate of the corresponding product, the more users purchase the product in the display area, and therefore, it can be determined to place the product in the display area for product promotion.

[0054] By applying the target object processing method of the embodiment of this specification, when the method is applied to a product promotion scenario, this target object processing method is used to perform image matching on the user pictures received in the product display area and the product settlement area using non-biometric feature extraction, and the offline shopping guide marketing effect is analyzed, which is beneficial to avoid the leakage of user identity characteristics and protect the security of user identity, thereby meeting the risk management of biometric identification.

[0055] Figure 2 This is a flowchart of a target object processing method applied to the cloud provided by an embodiment of the present specification, which specifically includes the following steps.

[0056] Step 202: Receive a user picture of a first user sent by a first picture acquisition device, and perform feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by the first picture acquisition device performing picture acquisition on the first user passing through a display area of ​​a target object, and the user features of the first user do not include facial features of the first user.

[0057] The display area of ​​the target object can be understood as a display area for displaying the target object. For example, in a commodity promotion scenario, the display area is a display position for the promotional commodities.

[0058] The first image acquisition device can be understood as an image acquisition device set in the display area of ​​the target object, wherein the image acquisition device here can be a device with a photo-taking function such as a camera, a scanner, etc., and the embodiments of this specification are not limited here.

[0059] The first user can be understood as a user who passes by the display area of ​​the target object and stays there for a certain period of time. For example, in a product promotion scenario, the target object is a promotional product, and the display area of ​​the target object is a display stand for the promotional product. The first user is a user who passes by the display stand for the promotional product and purchases the promotional product at the display stand for the promotional product.

[0060] The user picture of the first user can be understood as a picture taken by the first picture acquisition device of the first user passing through the display area of ​​the target object.

[0061] The user characteristics of the first user can be understood as the full body characteristics of the first user obtained after the cloud extracts the full body characteristics of the user picture of the first user. It should be noted that the full body characteristics here do not include the facial characteristics of the first user. Full body characteristics include: the user's height, body shape, face shape, user's clothing, user's hairstyle, etc. Facial features are the user's facial features, such as eyes, ears, nose, mouth and other features related to user privacy. In specific implementation, the cloud will first receive the user picture of the first user sent by the first image acquisition device passing through the display area of ​​the target object, and then extract the body characteristics of the received user picture of the first user to obtain the user body characteristics of the first user.

[0062] In actual applications, the first image acquisition device is set above the display screen of the display area of ​​the target object, and the first image acquisition device only extracts the user's body features, but not the user's facial features, thereby avoiding the risk of privacy leakage. It should be noted that the camera of the first image acquisition device here can be one or more, and it should be set according to actual needs, and this specification embodiment does not limit it here.

[0063] In another embodiment, when the cloud performs feature extraction on the received user image of the first user and obtains the user features of the first user, it will also compare the user features of the first user with the user features of historical users. If the user features of the first user match the user features of historical users, it means that the user features of the first user have been stored in the cloud, and there is no need to re-store the user features of the first user; if the user features of the first user do not match the historical user features, it means that the user features of the first user are new user features, and it is necessary to store the user features of the first user in the cloud. Therefore, it is possible to determine whether a new user has appeared by comparing the user features of the first user with the historical user features.

[0064] In a possible implementation of the present specification, the user pictures of the first user taken by the first picture acquisition device may contain pictures that are not suitable for feature extraction, for example, the user features in the pictures are blurred, the angle of the pictures is not correct, the blank space occupies a large area in the pictures, etc. If all the pictures taken by the first picture acquisition device are uploaded to the cloud, it will cause inaccurate feature extraction and waste of resources. Therefore, it is necessary to set preset shooting conditions for the user pictures taken by the first picture acquisition device to implement the screening of user pictures, which specifically includes the following steps.

[0065] The receiving a user picture of a first user sent by a first picture acquisition device includes:

[0066] A user picture of a first user, which is sent by a first picture acquisition device, taken within a preset time period and meets a first preset shooting condition, is received.

[0067] Among them, the first image acquisition device and the first user are consistent with the first image acquisition device and the first user in the above-mentioned target object processing method, and the embodiments of this specification are not repeated here.

[0068] The preset time period can be understood as the time period preset in advance by the user for analyzing the user images sent by the image acquisition device received by the cloud. For example, the preset time period can be set in days (for example, three days), that is, the cloud receives user images sent by the image acquisition device within three days; the preset time period can also be set in time units (for example, 3 pm on the same day to 10 pm on the next day), that is, the cloud receives user images sent by the image acquisition device between 3 pm on the same day and 10 pm on the next day.

[0069] The first preset shooting condition can be understood as the condition for the first image acquisition device to acquire user images. It should be noted that, in the embodiment of the present specification, the condition for the first image acquisition device to acquire user images is that when the user appears within a circular range of one meter from the first image acquisition device in the object display area and enters a range of one hundred degrees from the camera angle of the first acquisition device, the user's image is acquired. For example, when the distance between the user and the acquisition device is ninety meters, and the angle between the user's feet or other body features and the straight line where the camera of the acquisition device is located and the vertical straight line from the acquisition device to the ground is less than or equal to one hundred degrees, the acquisition device will capture the body features of the user that meet the preset shooting conditions to obtain a user image.

[0070] In a specific implementation, the user picture of the first user received by the cloud is a user picture of the first user taken by the first picture acquisition device within a preset time period, passing through the display area of ​​the target object and meeting the first preset shooting condition.

[0071] In actual applications, the first image acquisition device has requirements for the quality of user images. Therefore, when the first image acquisition device takes user images, it will collect images of users within a preset distance range of the display area of ​​the target object. It is not necessary for the user to get very close. It is best for the user to stand vertically in front of the first image acquisition device. That is, the display area of ​​the target object can be taken within one meter and one hundred degrees from the first image acquisition device, and the user enters and stays. Taking the display selection plan for store promotion positions as an example, the preset time period is set to one day. The shooting distance in the first preset shooting condition is within one meter from the first image acquisition device, and the shooting angle is within a one-hundred-degree angle with the first image acquisition device. Therefore, as long as the first user passes through the product promotion area while meeting the first preset shooting condition, the first image acquisition device will take a picture of the first user and upload the user picture of the first user taken to the cloud.

[0072] By applying the method of the embodiments of this specification, the first image acquisition device can take a picture of the first user who meets the first preset shooting condition, thereby ensuring that the picture acquired by the first image acquisition device meets the high accuracy requirement, thereby achieving that the user pictures uploaded to the cloud meet the high quality requirement.

[0073] In a possible implementation of the present specification, by setting preset shooting conditions for the first image acquisition device, the cloud can ensure the accuracy of feature extraction when extracting features from the image sent by the first image acquisition device, but it will also increase the amount of calculation for the first image acquisition device. Therefore, it is also possible to upload the image to the cloud and let the cloud screen user images suitable for feature extraction. That is, when the cloud receives the user image of the first user sent by the first image acquisition device, it records the time of receiving the user image of the first user and determines the user images within a preset time period. Specifically, the following steps are included.

[0074] The receiving a user picture of a first user sent by a first picture acquisition device includes:

[0075] Receiving an initial user picture of a first user sent by a first picture acquisition device, and recording a receiving time of the initial user picture of the first user;

[0076] From the initial user pictures of the first user, the user pictures of the first user whose receiving time is within a preset time period and meets the first preset shooting condition are screened out.

[0077] Among them, the first image acquisition device, the first user, the preset time period, and the first preset shooting condition are consistent with the first image acquisition device, the first user, the preset time period, and the first preset shooting condition in the above-mentioned target object processing method, and the embodiments of this specification are not repeated here.

[0078] The initial user picture of the first user can be understood as the first user picture of the first user sent by the first collection device and received by the cloud within a preset time period. Continuing with the above example, assuming that the preset time period is in time units (for example, 3 pm on the same day to 10 pm on the next day), then the initial user picture of the first user is the first user picture of the user sent by the collection device and received by the cloud at 3 pm on the same day.

[0079] In specific implementation, when the cloud receives the user picture sent by the first image acquisition device, it will record the upload time corresponding to the user picture in real time. When receiving the task of obtaining user pictures within a preset time period sent by the user, it will match the initial user picture and other user pictures within the time period based on the start time of the preset time period. Finally, it will filter out the user picture of the first user that meets the first preset shooting condition from the obtained initial user picture and other user pictures.

[0080] Continuing with the above example, the user picture of the first user sent by the first picture acquisition device and received by the cloud may also be the user picture of the first user passing through the product promotion area and sent by the first picture acquisition device. After receiving the user picture of the first user, the cloud will record the time of receiving the user picture in real time, and determine the user pictures included in the preset time period based on the recorded time, and then filter the user pictures according to the first preset shooting conditions to obtain the user pictures of the first user that meet the conditions.

[0081] By applying the method of the embodiments of this specification, user images that meet the first preset condition are screened through the cloud, which can save terminal resources of the first image acquisition device, reduce the computing power of the first image acquisition device, and improve the efficiency of user image acquisition.

[0082] In a possible implementation of the present specification, after the cloud completes receiving the user picture of the first user sent by the first picture acquisition device, since the picture occupies a large amount of memory in the cloud, it will cause a waste of memory space in the cloud. Therefore, the cloud will also digitize the user picture to obtain the first digitized user identifier of the first user, so as to reduce the memory space occupied, which specifically includes the following steps.

[0083] After obtaining the user characteristics of the first user, the method further includes:

[0084] The user characteristics of the first user are numerically processed to obtain a first numerical user identifier of the first user, and the user picture of the first user is deleted.

[0085] Among them, the first user, the user characteristics of the first user, and the user picture of the first user are consistent with the first user, the user characteristics of the first user, and the user picture of the first user in the above-mentioned target object processing method, and are not repeated here in this embodiment of the present specification.

[0086] The first digitized user identifier may be understood as a user feature identifier corresponding to the user feature obtained after the cloud performs digitization processing on the obtained user feature of the first user.

[0087] In specific implementation, after the user picture of the first user is obtained in the cloud, the user picture of the first user is also digitized to obtain a digitized user identifier corresponding to each user picture.

[0088] Continuing with the above example, after the initial user picture M is received in the cloud, the initial user picture M will be digitized to obtain the first digitized user identifier 1 corresponding to the initial user picture M of the first user, and the initial user picture M will be deleted. Similarly, after the second user picture N is received in the cloud, the second user picture N will be digitized to obtain the second digitized user identifier 2 corresponding to the second user picture N of the first user, and the second user picture N will be deleted.

[0089] By applying the method of the embodiments of this specification, the acquired user images are digitized through the cloud to obtain a digitized user identifier corresponding to the user image, and the user image is deleted. The digitization of the image can reduce the occupancy rate of the cloud storage space on the one hand, and compared with subsequent image comparison, the digitization comparison is faster and more accurate on the other hand. After the digitization processing is completed, the user image is deleted, which can also reduce the occupancy rate of the cloud storage space, thereby improving the cloud's processing efficiency of the image.

[0090] Step 204: Receive a user picture of the second user sent by a second picture acquisition device and object processing information of the second user, and perform feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by the second picture acquisition device by performing picture acquisition on the second user performing object processing in the object processing area, and the user features of the second user do not include facial features of the second user.

[0091] The object processing area can be understood as an area for performing settlement processing on the object. For example, in a commodity promotion scenario, the processing area is a settlement area for settling commodities.

[0092] The second image acquisition device can be understood as an image acquisition device set in the object settlement area, wherein the image acquisition device here can be a camera, a camera, a scanner and other devices with a photo-taking function, and the embodiments of this specification are not limited here.

[0093] The second user can be understood as a user who performs settlement processing for the object in the settlement area. For example, in a product promotion scenario, the settlement of the object is the settlement place for the promotional product, and the second user is the user who performs settlement processing for the purchased product.

[0094] The user picture of the second user can be understood as a picture taken by the second picture acquisition device of the second user who is performing object processing in the object processing area.

[0095] The object processing information of the second user can be understood as information about the user processing the object in the object processing area, for example, the user performs settlement processing on the object in the object processing area, or the user performs exchange processing, return processing, etc. on the object in the object processing area.

[0096] The user characteristics of the second user can be understood as the full body characteristics of the second user obtained after the cloud extracts the full body characteristics of the user picture of the second user. It should be noted that the full body characteristics here do not include the extraction of the facial characteristics of the second user. In specific implementation, while receiving the user picture of the first user collected by the first picture acquisition device, the cloud will also receive the user picture of the second user collected by the second picture acquisition device. Similarly, the cloud will extract the body characteristics of the user picture of the second user collected by the second picture acquisition device to obtain the user body characteristics of the second user. It should be noted that the user picture of the second user collected by the second picture acquisition device received by the cloud is taken after monitoring that the second user has completed the object processing in the object processing area. Therefore, the cloud will also receive the object processing information of the second user.

[0097] In actual applications, the second image acquisition device is set above the object processing screen in the object processing area, and the second image acquisition device only extracts the user's body features, but not the user's facial features, thereby avoiding the risk of privacy leakage. It should be noted that the camera of the second image acquisition device here can be one or more, and should be set according to actual needs, and this specification embodiment does not limit this.

[0098] In a possible implementation of the present specification, the user picture of the second user taken by the second picture acquisition device may contain pictures that are not suitable for feature extraction, for example, the user features in the picture are blurred, the angle of the picture is not correct, the blank space occupies a large area in the picture, etc. If all the pictures taken by the second picture acquisition device are uploaded to the cloud, it will cause inaccurate feature extraction and waste of resources. Therefore, it is necessary to set preset shooting conditions for the user pictures taken by the second picture acquisition device to screen the user pictures, which specifically includes the following steps.

[0099] The receiving the user picture of the second user sent by the second picture acquisition device includes:

[0100] A user picture of a second user, which is sent by a second picture acquisition device, taken within a preset time period and meets a second preset shooting condition, is received.

[0101] Among them, the second image acquisition device, the second user, and the preset time period are consistent with the second image acquisition device, the second user, and the preset time period in the above-mentioned target object processing method, and are not elaborated herein in the embodiments of this specification.

[0102] The second preset shooting condition can be understood as the condition for the second image acquisition device to acquire user images. It should be noted that, in the embodiment of the present specification, the condition for the second image acquisition device to acquire user images is when the user appears within a circular range of one meter from the second image acquisition device in the object processing area, and the angle between the second user's feet (or other body features) and the camera of the second acquisition device is within a range of 100 degrees, and after it is detected that the user has completed the processing operation on the object, the user's image is acquired. For example, when the distance between the user and the acquisition device is ninety meters, and the angle between the user's feet or other body features and the straight line where the camera of the acquisition device is located is less than or equal to 100 degrees from the vertical straight line between the acquisition device and the ground, and it is detected that the user has completed the settlement processing of the goods, the acquisition device will capture the body features of the user that meets the preset shooting conditions to obtain the user's image.

[0103] In a specific implementation, the user picture of the second user received by the cloud is a user picture of the second user taken by a second picture acquisition device within a preset time period, passing through an object processing area, and meeting a second preset shooting condition.

[0104] In actual applications, the user image of the second user received by the cloud is a user image taken by the second image acquisition device of the user who processes the object in the object processing area within a preset time period, and is taken by the second user who meets the second preset shooting condition. It should be noted that since the interval between the user's stay in the product display area and the product processing area will not exceed one day, the second preset shooting condition here also includes shooting timing, that is, multiple timings such as the user scanning the code of the product, adding the product to the purchase, clicking the checkout, and completing the payment.

[0105] The second picture acquisition device has requirements for the quality of user pictures. Therefore, when the second picture acquisition device takes pictures of users, after detecting that the user has completed the processing of the object, it will collect pictures of users within the preset distance range of the object processing area. It is not necessary for the user to get very close. It is better for the user to stand vertically in front of the second picture acquisition device. That is, in the object processing area, pictures can be taken within one meter and one hundred degrees from the second picture acquisition device, after the user enters and stays to complete the object processing task. Taking the display selection plan of the store promotion position as an example, the preset time period is set to one day. In the second preset shooting condition, the second user completes the settlement of the goods. The shooting distance is within one meter from the second picture acquisition device, and the shooting angle is within a one hundred degree angle with the second picture acquisition device. Therefore, as long as the second user meets the second preset shooting condition, the second user can scan the code in front of the second picture acquisition device in the commodity settlement area to purchase goods. After the second user completes the payment for the purchased goods, the second picture acquisition device will take a picture of the second user and upload the captured user picture of the second user to the cloud.

[0106] In another embodiment, when the user picture of the first user obtained from the object display area includes multiple first users, and the user picture of the second user obtained from the object processing area includes only one second user, the cloud will match the multiple first users based on the one second user. Therefore, the first picture acquisition device, or the second picture acquisition device, will capture all users who meet the preset shooting conditions at the same time when capturing user pictures.

[0107] Because the shooting timing of the second picture acquisition device is associated with the object processing process of the second user, when the second user fails to perform object processing or terminates object processing on the product, the user picture of the second user captured by the second picture acquisition device is deleted.

[0108] By applying the method of the embodiments of the present specification, the second picture acquisition device can ensure that the picture acquired by the second picture acquisition device meets the high accuracy requirement by taking a picture of the second user who meets the second preset shooting condition, thereby achieving that the user picture uploaded to the cloud meets the high quality requirement. The purpose of adding the shooting time to the second preset shooting condition is that if the user takes the picture as soon as he enters the settlement area, it is very likely that although the user takes the product to the settlement area, he does not purchase it when he finally scans the code for settlement, which will result in invalid data. However, if the picture is taken when the payment is completed, such a problem will not occur.

[0109] In a possible implementation of the present specification, by setting preset shooting conditions for the first image acquisition device, the cloud can ensure the accuracy of feature extraction when extracting features from the image sent by the first image acquisition device, but it will also increase the amount of calculation for the first image acquisition device. Therefore, it is also possible to upload the image to the cloud and let the cloud screen user images suitable for feature extraction, that is, when the cloud receives the user image of the second user sent by the second image acquisition device, it records the time of receiving the user image of the second user, which specifically includes the following steps.

[0110] The receiving the user picture of the second user sent by the second picture acquisition device includes:

[0111] Receiving an initial user picture of a second user that meets a preset shooting time and is sent by a second picture acquisition device, and recording a receiving time of the initial user picture of the second user;

[0112] From the initial user pictures of the second user, the user pictures of the second user whose receiving time is within the preset time period and meets the first preset shooting condition are screened out.

[0113] Among them, the second picture acquisition device, the second user, the user picture of the second user, the preset time period, and the first preset shooting condition are consistent with the second picture acquisition device, the second user, the user picture of the second user, the preset time period, and the first preset shooting condition in the above-mentioned target object processing method, and the embodiments of this specification are not repeated here.

[0114] The initial user picture of the second user can be understood as the first user picture of the second user sent by the second acquisition device and received by the cloud within the preset time period. Continuing with the above example, assuming that the preset time period is in time units (for example, 3 pm on the same day to 10 pm on the next day), then the initial user picture of the second user is the first user picture of the user sent by the acquisition device and received by the cloud at 3 pm on the same day.

[0115] In specific implementation, the user picture sent by the second picture acquisition device received by the cloud is the picture of the second user that meets the shooting time and shooting opportunity. After receiving the user picture of the second user in the cloud, the corresponding upload time of the user picture will be recorded in real time. When receiving the task of obtaining the user picture within the preset time period sent by the user, the initial user picture and other user pictures within the time period will be matched based on the start time of the preset time period. Finally, the user picture of the second user that meets the first preset shooting condition will be screened out from the obtained initial user picture and other user pictures. It should be noted that the second preset shooting condition adds the shooting opportunity on the basis of the first preset shooting condition. Therefore, when the shooting opportunity is determined, when the cloud screens the user pictures of the second user, it only needs to screen out the user pictures that meet the first preset shooting condition.

[0116] Continuing with the above example, the user picture of the second user sent by the second picture acquisition device and received by the cloud may also be a user picture of the second user completing commodity settlement in the commodity settlement area and sent by the second picture acquisition device. After receiving the user picture of the second user, the cloud will record the time of the received user picture in real time, and determine the user pictures included in the preset time period based on the recorded time, and then filter the user pictures according to the first preset shooting conditions to obtain the user pictures of the second user that meet the conditions.

[0117] By applying the method of the embodiment of this specification, user images that meet the second preset condition are screened through the cloud, which can save terminal resources of the second image acquisition device, reduce the computing power of the second image acquisition device, and improve user image acquisition efficiency.

[0118] In a possible implementation of the present specification, after the cloud completes receiving the user picture of the second user sent by the second picture acquisition device, since the picture occupies a large amount of memory in the cloud, it will cause a waste of memory space in the cloud. Therefore, the cloud will also process the user picture to obtain a second numerical user identifier of the second user, so as to reduce the memory space occupied, which specifically includes the following steps.

[0119] After obtaining the user characteristics of the second user, the method further includes:

[0120] The user characteristics of the second user are digitized to obtain a second digitized user identifier of the second user, and the user picture of the second user is deleted.

[0121] Among them, the user characteristics of the second user and the user picture of the second user are consistent with the user characteristics of the second user and the user picture of the second user in the above-mentioned target object processing method, and are not described in detail in this embodiment of the specification.

[0122] The second digitized user identifier can be understood as a user feature identifier corresponding to the user feature obtained after the cloud performs digitization processing on the obtained user feature of the second user.

[0123] In specific implementation, after the user picture of the second user is obtained in the cloud, the user picture of the second user is also digitized, so as to obtain a digitized user identifier corresponding to each user picture.

[0124] Continuing with the above example, after the initial user picture P is received in the cloud, the initial user picture P will be digitized to obtain the first digitized user identifier 1' corresponding to the initial user picture P of the second user, and the initial user picture P will be deleted. Similarly, after the second user picture Q is received in the cloud, the second user picture Q will be digitized to obtain the second digitized user identifier 2' corresponding to the second user picture Q of the second user, and the second user picture Q will be deleted.

[0125] By applying the method of the embodiments of this specification, the acquired user images are digitized through the cloud to obtain a digitized user identifier corresponding to the user image, and the user image is deleted. The digitization of the image can reduce the occupancy rate of the cloud storage space on the one hand, and compared with subsequent image comparison, the digitization comparison is faster and more accurate on the other hand. After the digitization processing is completed, the user image is deleted, which can also reduce the occupancy rate of the cloud storage space, thereby improving the cloud's processing efficiency of the image.

[0126] Step 206: Determine a display result of the target object in the display area according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0127] Among them, the user characteristics of the first user, the user characteristics of the second user, and the object processing information are consistent with the user characteristics of the first user, the user characteristics of the second user, and the object processing information in the above-mentioned target object processing method, and are not repeated in this embodiment of the present specification.

[0128] The display result can be understood as the number of users who match the users who purchase the target object in the display area of ​​the target object and the users who settle the account for the object in the object processing area, that is, the number of users who purchase the target object in the display area of ​​the target object and settle the account for the target object in the object processing area. For example, in a product promotion scenario, the number of users who purchase the product at the display position of the promotional product and settle the account for the product in the settlement area. For example, the purchase conversion rate of the target product in the display area (promotional product) = the number of people who make transactions for the target product in the display area / the number of people who pass by the display area; the purchase conversion rate of other products in the display area (the impact of traffic attraction on products around the target product) = the number of people who make transactions for other products in the display area / the number of people who pass by the display area; the conversion rate of people who stay in the display area but do not purchase products = the number of people who do not have the target product and make transactions for other products in the display area / the number of people who pass by the display area; the no-shopping conversion rate = the number of people who have been to the display area but have not settled the account / the number of people who pass by the display area. It should be noted that

[0129] In a specific implementation, the cloud determines the display result of the target object in the display area by comparing the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0130] In actual applications, the number of promotional products purchased in the display area is obtained by comparing the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0131] In a possible implementation of the present specification, the display result of the target object in the display area is determined based on a first digitized user identifier corresponding to the user characteristics of the first user, a second digitized user identifier corresponding to the user characteristics of the second user, and object processing information, and specifically includes the following steps.

[0132] The determining, according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information, a display result of the target object in the display area includes:

[0133] A display result of the target object in the display area is determined according to the first digitized user identifier, the second digitized user identifier, and the object processing information.

[0134] Among them, the first digitized user identifier, the second digitized user identifier, and the object processing information are consistent with the first digitized user identifier, the second digitized user identifier, and the object processing information in the above-mentioned target object processing method, and are not repeated in this embodiment of the present specification.

[0135] In a specific implementation, the cloud determines that the display result of the target object in the display area is obtained according to the first digitized user identifier, the second digitized user identifier, and the object processing information.

[0136] In actual applications, the quantity of the promotional merchandise purchased in the display area is obtained based on the first digitized user identifier, the second digitized user identifier, and the object processing information.

[0137] By applying the method of the embodiment of this specification, the user characteristics are digitized to determine the display result of the target object in the display area, which can reduce the amount of calculation in the cloud and improve the data processing efficiency in the cloud.

[0138] In a possible implementation of the present specification, in order to determine the display result of the target object in the display area, it is first necessary to determine the target digitized user identifier based on the first digitized user identifier and the second digitized user identifier, and determine the target user based on the target digitized user identifier, and then determine the number of target users who have a processing relationship with the target object based on the object processing information of the target user, and then determine the display result of the target object in the display area based on the number of target users who have a processing relationship with the target object, which specifically includes the following steps.

[0139] The determining, according to the first digitized user identifier, the second digitized user identifier, and the object processing information, a display result of the target object in the display area includes:

[0140] According to the first digitized user identifier and the second digitized user identifier, determining the second digitized user identifier matching the first digitized user identifier as a target digitized user identifier, and determining the second user corresponding to the target digitized user identifier as a target user;

[0141] Determining the number of target users having an object processing relationship with the target object according to the object processing information of the target user;

[0142] A display result of the target object in the display area is determined according to the number of target users having an object processing relationship with the target object.

[0143] Among them, the first digitized user identifier and the second digitized user identifier are consistent with the first digitized user identifier and the second digitized user identifier in the above-mentioned target object processing method, and are not described in detail in this embodiment of the specification.

[0144] The target digitized user identifier can be understood as the user identifier in the second digitized user identifier that matches the first digitized user identifier. For example, the second digitized user identifier includes A, B, C, D, and E, and the first digitized user identifier includes A, B, 1, 2, and 3. Then the user identifiers in the second digitized user identifier that match the first digitized user identifier include A and B. Therefore, the target digitized user identifier can be determined to be A and B.

[0145] The target user may be understood as a user corresponding to the target numerical user identifier.

[0146] In specific implementation, before determining the display result of the target object in the display area, the cloud first needs to determine the target user and the number of target users. Specifically, first, based on the first digitized user identifier and the second digitized user identifier, determine the target digitized user identifier that is consistent with the first digitized user identifier and the second digitized user identifier, and determine the second user corresponding to the target digitized user identifier as the target user; then, after determining the target user, determine the number of target users based on the object processing information; finally, determine the display result of the target object in the display area based on the number of target users. It should be noted that the object processing information here includes the settlement information of the target user in the object processing area.

[0147] Continuing with the above example, after determining that the target numerical user identifiers are A and B, the users corresponding to the target numerical user identifiers A and B can be determined as target users; based on the settlement behavior of the target users in the commodity settlement area, it can be determined that the commodities purchased by the user with the target numerical user identifier A come from the display area, and the commodities purchased by the user with the target numerical user identifier B come from the display area. Therefore, it can be determined that the number of target users who purchase commodities from the display area is 1, and the display result of the target object in the display area can be determined to be 1.

[0148] By applying the method of the embodiment of this specification, the user characteristics are digitized to determine the display result of the target object in the display area, which can reduce the amount of calculation in the cloud and improve the data processing efficiency in the cloud.

[0149] In a possible implementation of the present specification, in order to better determine the display result of the target object in the display area, taking the promotional product as the target object, the promotion area of ​​the promotional product as the display area of ​​the target object, and the product settlement area as the object processing area as an example, the following steps are specifically included.

[0150] The target object is a promotional commodity, the display area of ​​the target object is a promotion area of ​​the promotional commodity, and the object processing area is a commodity settlement area.

[0151] In the specific implementation, the specific calculation is explained by taking the target object as the promotional product, the promotion area of ​​the promotional product as the display area of ​​the target object, and the product settlement area as the object processing area as an example.

[0152] like Figure 3 As shown, Figure 3 It is a scene diagram of a shopping guide effect of a target object processing method provided by an embodiment of this specification. Figure 3 It includes three parts: display area 302, cloud 304, and settlement area 306.

[0153] Specifically, the TG plan (i.e., the store promotion display selection plan) of the display area 302 includes product A and product B. When the first user meets the first preset shooting condition, the first camera will use REI D technology to obtain the user's full body features (without processing the face), and upload it to the cloud for feature digitization. Usually, about 75% of the users who enter the store will purchase goods and settle the goods in the settlement area 306. When the second user meets the second preset shooting condition, the second camera will use REI D technology to obtain the full body features of the settlement user (without processing the face), and upload it to the cloud for feature digitization. After the cloud completes the reception of the first picture sent by the first camera and the second picture sent by the second camera within the preset time period, it will analyze the user's purchase situation based on the first picture and the second picture, thereby determining the display position of the goods.

[0154] In a possible implementation of the present specification, when the promotional product is the target object, the promotion area of ​​the promotional product is the display area of ​​the target object, and the product settlement area is the object processing area, the number of users who have completed transactions with the promotional product in the promotion area is determined based on the number of target users who have a product settlement relationship with the promotional product, and specifically includes the following steps.

[0155] The determining, according to the number of target users having an object processing relationship with the target object, a display result of the target object in the display area includes:

[0156] The number of users who have completed transactions with the promotional product in the promotion area of ​​the promotional product is determined according to the number of target users who have a product settlement relationship with the promotional product.

[0157] In specific implementation, the cloud determines the number of users who have completed transactions for the promotional product in the promotional area of ​​the promotional product based on the number of target users who have a product settlement relationship with the promotional product.

[0158] In actual applications, in the promotion area of ​​the promotional product, the number of users who have settled the promotional products indicates the number of users who have made transactions in the promotion area.

[0159] In a possible implementation of the present specification, the purchase conversion rate of the promotional product is determined according to the number of users who have completed transactions with the promotional product in the promotion area and the number of first users, which specifically includes the following steps.

[0160] After determining the number of users who have completed transactions with the promotional product in the promotional area of ​​the promotional product, the method further includes:

[0161] The number of the first user is determined, and the purchase conversion rate of the promotional product is determined according to the number of users who have completed transactions for the promotional product in the promotion area of ​​the promotional product and the number of the first user.

[0162] In specific implementation, the cloud determines the purchase conversion rate of the promotional product based on the number of first users and the number of users who have completed transactions with the promotional product in the promotion area of ​​the promotional product.

[0163] In actual applications, the purchase conversion rate of the promotional goods is the ratio of the number of users who have completed transactions with the promotional goods in the promotional area of ​​the promotional goods to the number of first users, that is, the purchase conversion rate of the promotional goods = the number of users who have completed transactions with the promotional goods in the promotional area of ​​the promotional goods / the number of first users.

[0164] In a possible implementation of the present specification, when a target user stops at a promotional area to purchase a promotional product but does not settle the purchase for the promotional product at a product settlement area, the non-purchase conversion rate of the promotional product can be determined based on the number of target users in the promotional area and the number of users who did not settle the purchase for the target product at the settlement area, which specifically includes the following steps.

[0165] After determining the second user corresponding to the target digitized user identifier as the target user, the method further includes:

[0166] Determining the number of target users that have no object processing relationship with the target object according to the object processing information of the target user;

[0167] The non-purchase conversion rate of the promotional product is determined according to the number of the first users and the number of the target users having no object processing relationship with the target object.

[0168] The target user's object processing information may be understood as information on the target user's processing of the object in the object processing area, such as the target user's historical purchase information in the object processing area, the target user's historical return and exchange information in the object processing area, etc.

[0169] In specific implementation, the non-purchase conversion rate of the promotional product is determined based on the number of first users and the number of target users who have no object processing relationship with the target object, wherein the target users who have no object processing relationship with the target object are users who pass by the object display area but do not process the object in the object processing area.

[0170] In actual applications, the non-purchase conversion rate of promotional products is the ratio of the number of target users who do not have an object processing relationship with the target object to the number of first users. It should be noted that the second user who did not settle in the object processing area cannot be matched with the first user in the product display area, that is, the conversion rate of staying in the display area but not purchasing products = the number of target users who do not have an object processing relationship with the target object / the number of first users.

[0171] In a possible implementation of the present specification, after completing the analysis of the target user's target object in the promotion area and the settlement area, the cloud will delete the first digitized user identifier, the second digitized user identifier, and the object processing information, which specifically includes the following steps.

[0172] After determining the display result of the target object in the display area according to the first digitized user identifier, the second digitized user identifier, and the object processing information, the method further includes:

[0173] The first digitized user identifier, the second digitized user identifier, and the object processing information are deleted.

[0174] Among them, the first digitized user identifier, the second digitized user identifier and the object processing information are consistent with the first digitized user identifier, the second digitized user identifier and the object processing information in the above-mentioned target object processing method, and are not described in detail in this embodiment of the specification.

[0175] In a specific implementation, after the cloud completes the analysis of the user's purchase situation, the first digitized user identifier, the second digitized user identifier, and the object processing information are deleted to save storage space in the cloud.

[0176] In a possible implementation of the present specification, when the cloud analyzes the processing relationship between the target user and the target object, it will also send a recommendation of the object to be processed to the user terminal of the target user in real time based on the stored object processing information of the second user, which specifically includes the following steps.

[0177] After determining the display result of the target object in the display area, the method further includes:

[0178] According to the object processing information of the second user, the second user is matched with the object to be processed, and the matched object to be processed is recommended to the user terminal of the second user.

[0179] The object processing information of the second user is consistent with the object processing information of the second user in the above-mentioned target object processing method, and will not be elaborated in detail in this embodiment of the specification.

[0180] In specific implementation, after receiving the object processing information of the second user, the cloud will also match the second user with the object to be processed according to the object processing information of the second user, thereby recommending the matched object to be processed to the corresponding second user's terminal. For example, after receiving the commodity settlement information of user Xiaomei, the cloud will analyze Xiaomei's purchasing tendency according to the commodity settlement information, thereby sending commodities related to the shopping tendency to Xiaomei's terminal in a targeted manner. Xiaomei's commodity settlement information includes: m pieces of food shopping information, n pieces of fruit shopping information, and y pieces of daily necessities shopping information. Therefore, the cloud will determine Xiaomei's purchasing tendency for each type of commodity based on the commodity settlement information, and send the corresponding commodity to Xiaomei's terminal.

[0181] In actual applications, the object processing area will obtain relevant information about the final settlement user to analyze the user portrait of the specified potential user and push the offline contact products in the terminal program of the corresponding user. When the second user settles the goods in the object processing area, he can settle the goods in cash or by electronic payment. However, when the user settles the goods in cash, the contact information of the second user cannot be stored in the object processing area. Therefore, the matching object to be processed cannot be recommended to the corresponding second user's terminal program.

[0182] It should be noted that the object processing area only collects relevant information of the user. For the related object recommendation function of the application, the user can freely choose whether to allow the recommended function. That is, the related object recommendation function of the application provided in the embodiment of this specification needs to provide consumers with the ability to turn off the recommendation. Currently, the related object recommendation function of the application has an intelligent push switch, and the user can choose to turn it off on his own, and a text description related to the collection of offline shopping behaviors will be added to the privacy terms to remind users.

[0183] The method of the embodiment of this specification is applied to realize the association of the camera REI D and the transaction data. In addition to using millimeter wave radar and POS settlement clicks, there are other implementation methods for the optimization of shooting time and the number of shootings, which are not limited in this embodiment of this specification. Taking photos at multiple times itself may also improve the accuracy of REI D, satisfying the risk control of biometric identification.

[0184] The target object processing method applied to the cloud of the embodiment of this specification can extract features other than facial features from the user pictures received from the first picture acquisition device and the second picture acquisition device to obtain the user features of the first user and the user features of the second user, and receive the object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, in the case where the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting the security of user identity, thereby meeting the risk control of biometric identification.

[0185] Figure 4 It is a flow chart of a target object processing method applied to a target object processing system provided by an embodiment of the present specification, which specifically includes the following steps.

[0186] like Figure 4 As shown, the target object processing system includes a cloud and a device end, wherein the device end includes a first image acquisition device and a second image acquisition device, and the method includes:

[0187] Step 402: the first picture acquisition device acquires a picture of a first user passing through the display area of ​​the target object, obtains a user picture of the first user, and sends the user picture of the first user to the cloud;

[0188] Step 404: the cloud receives the user picture of the first user sent by the first picture acquisition device, and performs feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user features of the first user do not include facial features of the first user;

[0189] Step 406: the second picture acquisition device acquires pictures of the second user who is performing object processing in the object processing area, obtains a user picture of the second user, and sends the user picture of the second user to the cloud;

[0190] Step 408: The cloud receives the user image of the second user sent by the second image acquisition device, and the object processing information of the second user, and performs feature extraction on the user image of the second user to obtain user features of the second user, wherein the user features of the second user do not include facial features of the second user, and determines the display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

[0191] The target object processing method applied to the target object processing system of the embodiment of this specification can extract features other than facial features from the user pictures received from the first picture acquisition device and the second picture acquisition device to obtain the user features of the first user and the user features of the second user, and receive the object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, in the case where the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting the security of user identity, thereby meeting the risk control of biometric identification.

[0192] Corresponding to the above method embodiment, this specification also provides a target object processing device embodiment, Figure 5 Schematic diagram of a target object processing device provided by an embodiment of this specification. Figure 5 As shown, the device comprises:

[0193] The first processing module 502 is configured to receive a user picture of a first user sent by a first picture acquisition device, and perform feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by the first picture acquisition device performing picture acquisition on the first user passing through the display area of ​​the target object, and the user features of the first user do not include facial features of the first user;

[0194] The second processing module 504 is configured to receive a user picture of a second user sent by a second picture acquisition device and object processing information of the second user, and perform feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by the second picture acquisition device performing picture acquisition on the second user performing object processing in the object processing area, and the user features of the second user do not include facial features of the second user;

[0195] The determination module 506 is configured to determine a display result of the target object in the display area according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

[0196] Optionally, the first processing module 502 is further configured to:

[0197] A user picture of a first user, which is sent by a first picture acquisition device, taken within a preset time period and meets a first preset shooting condition, is received.

[0198] Optionally, the first processing module 502 is further configured to:

[0199] Receiving an initial user picture of a first user sent by a first picture acquisition device, and recording a receiving time of the initial user picture of the first user;

[0200] From the initial user pictures of the first user, the user pictures of the first user whose receiving time is within a preset time period and meets the first preset shooting condition are screened out.

[0201] Optionally, the second processing module 504 is further configured to:

[0202] A user picture of a second user, which is sent by a second picture acquisition device, taken within a preset time period and meets a second preset shooting condition, is received.

[0203] Optionally, the second processing module 504 is further configured to:

[0204] Receiving an initial user picture of a second user that meets a preset shooting time and is sent by a second picture acquisition device, and recording a receiving time of the initial user picture of the second user;

[0205] From the initial user pictures of the second user, the user pictures of the second user whose receiving time is within the preset time period and meets the first preset shooting condition are screened out.

[0206] Optionally, the device further comprises:

[0207] The numerical processing module is configured as follows:

[0208] Numerically processing the user characteristics of the first user to obtain a first numerical user identifier of the first user, and deleting the user picture of the first user; and

[0209] The user characteristics of the second user are digitized to obtain a second digitized user identifier of the second user, and the user picture of the second user is deleted.

[0210] Optionally, the determining module 506 is further configured to:

[0211] A display result of the target object in the display area is determined according to the first digitized user identifier, the second digitized user identifier, and the object processing information.

[0212] Optionally, the determining module 506 is further configured to:

[0213] According to the first digitized user identifier and the second digitized user identifier, determining the second digitized user identifier matching the first digitized user identifier as a target digitized user identifier, and determining the second user corresponding to the target digitized user identifier as a target user;

[0214] Determining the number of target users having an object processing relationship with the target object according to the object processing information of the target user;

[0215] A display result of the target object in the display area is determined according to the number of target users having an object processing relationship with the target object.

[0216] Optionally, the target object is a promotional commodity, the display area of ​​the target object is a promotion area of ​​the promotional commodity, and the object processing area is a commodity settlement area;

[0217] Accordingly, the determining module 506 is further configured to:

[0218] The number of users who have completed transactions with the promotional product in the promotion area of ​​the promotional product is determined according to the number of target users who have a product settlement relationship with the promotional product.

[0219] The target object processing device of the embodiment of this specification can extract features other than facial features from the user pictures received from the first picture acquisition device and the second picture acquisition device to obtain the user features of the first user and the user features of the second user, and receive the object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, when the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting the security of user identity, thereby meeting the risk control of biometric identification.

[0220] The above is a schematic scheme of a target object processing device of this embodiment. It should be noted that the technical scheme of the target object processing device and the technical scheme of the target object processing method described above belong to the same concept, and the details not described in detail in the technical scheme of the target object processing device can be referred to the description of the technical scheme of the target object processing method described above.

[0221] Figure 6 Schematic diagram of a target object processing system provided by an embodiment of this specification. Figure 6 As shown, the target object processing system includes: a first image acquisition device 602 , a cloud 604 , and a second image acquisition device 606 .

[0222] The first picture acquisition device 602 is used to acquire a picture of a first user passing through the display area of ​​the target object, obtain a user picture of the first user, and send the user picture of the first user to the cloud;

[0223] The cloud 604 is used to receive the user picture of the first user sent by the first picture acquisition device, and perform feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user features of the first user do not include facial features of the first user;

[0224] The second picture acquisition device 606 is used to acquire a picture of a second user who is performing object processing in the object processing area, obtain a user picture of the second user, and send the user picture of the second user to the cloud;

[0225] The cloud 604 is used to receive the user picture of the second user sent by the second picture acquisition device and the object processing information of the second user, and perform feature extraction on the user picture of the second user to obtain the user features of the second user, wherein the user features of the second user do not include the facial features of the second user, and determine the display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

[0226] The target object processing system of the embodiment of this specification can extract features other than facial features from the user pictures received from the first picture acquisition device and the second picture acquisition device to obtain the user features of the first user and the user features of the second user, and receive the object processing information of the second user; according to the user features of the first user, the user features of the second user, and the object processing information of the second user, determine the display result of the target object in the display area. Then, when the target object processing method is applied to the commodity promotion scenario, the user pictures received in the commodity display area and the commodity settlement area are matched by non-biological feature extraction through this target object processing method, and the offline shopping guide marketing effect is analyzed, which is conducive to avoiding the leakage of user identity features and protecting the security of user identity, thereby meeting the risk control of biometric identification.

[0227] Figure 7 7 is a block diagram of a computing device 700 provided in one embodiment of the present specification. The components of the computing device 700 include but are not limited to a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and the database 750 is used to store data.

[0228] The computing device 700 also includes an access device 740, which enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 740 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0229] In one embodiment of the present specification, the above components of the computing device 700 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0230] The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 700 may also be a mobile or stationary server.

[0231] The processor 720 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned target object processing method.

[0232] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the target object processing method described above are of the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the target object processing method described above.

[0233] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the target object processing method.

[0234] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the target object processing method described above are of the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the target object processing method described above.

[0235] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned target object processing method.

[0236] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the target object processing method described above are of the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the target object processing method described above.

[0237] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0238] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0239] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0240] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0241] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A target object processing method, applied in the cloud, comprising: Receiving a user picture of a first user sent by a first picture acquisition device, and performing feature extraction on the user picture of the first user to obtain user features of the first user, wherein the user picture of the first user is obtained by the first picture acquisition device performing picture acquisition on the first user passing through a display area of ​​a target object, and the user features of the first user do not include facial features of the first user; Receiving a user picture of a second user and object processing information of the second user sent by a second picture acquisition device, and performing feature extraction on the user picture of the second user to obtain user features of the second user, wherein the user picture of the second user is obtained by the second picture acquisition device performing picture acquisition on the second user performing object processing in the object processing area, and the user features of the second user do not include facial features of the second user; A display result of the target object in the display area is determined according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information.

2. According to the method of claim 1, the receiving the user picture of the first user sent by the first picture acquisition device comprises: A user picture of a first user, which is sent by a first picture acquisition device, taken within a preset time period and meets a first preset shooting condition, is received.

3. The method according to claim 1, wherein receiving the user picture of the first user sent by the first picture acquisition device comprises: Receiving an initial user picture of a first user sent by a first picture acquisition device, and recording a receiving time of the initial user picture of the first user; From the initial user pictures of the first user, the user pictures of the first user whose receiving time is within a preset time period and meets the first preset shooting condition are screened out.

4. The method according to claim 1, wherein receiving the user picture of the second user sent by the second picture acquisition device comprises: A user picture of a second user, which is sent by a second picture acquisition device, taken within a preset time period and meets a second preset shooting condition, is received.

5. The method according to claim 1, wherein receiving the user picture of the second user sent by the second picture acquisition device comprises: Receiving an initial user picture of a second user that meets a preset shooting time and is sent by a second picture acquisition device, and recording a receiving time of the initial user picture of the second user; From the initial user pictures of the second user, the user pictures of the second user whose receiving time is within the preset time period and meets the first preset shooting condition are screened out.

6. The method according to claim 1, after obtaining the user characteristics of the first user, further comprising: Numerically processing the user characteristics of the first user to obtain a first numerical user identifier of the first user, and deleting the user picture of the first user; Correspondingly, after obtaining the user characteristics of the second user, the method further includes: The user characteristics of the second user are digitized to obtain a second digitized user identifier of the second user, and the user picture of the second user is deleted.

7. The method according to claim 6, wherein determining the display result of the target object in the display area according to the user characteristics of the first user, the user characteristics of the second user, and the object processing information comprises: A display result of the target object in the display area is determined according to the first digitized user identifier, the second digitized user identifier, and the object processing information.

8. The method according to claim 7, wherein determining the display result of the target object in the display area according to the first digitized user identifier, the second digitized user identifier, and the object processing information comprises: According to the first digitized user identifier and the second digitized user identifier, determining the second digitized user identifier matching the first digitized user identifier as a target digitized user identifier, and determining the second user corresponding to the target digitized user identifier as a target user; Determining the number of target users having an object processing relationship with the target object according to the object processing information of the target user; A display result of the target object in the display area is determined according to the number of target users having an object processing relationship with the target object.

9. The method according to claim 8, wherein the target object is a promotional commodity, the display area of ​​the target object is a promotion area of ​​the promotional commodity, and the object processing area is a commodity settlement area; Accordingly, determining the display result of the target object in the display area according to the number of target users having an object processing relationship with the target object includes: The number of users who have completed transactions with the promotional product in the promotion area of ​​the promotional product is determined according to the number of target users who have a product settlement relationship with the promotional product.

10. A target object processing method, applied to a target object processing system, the target object processing system comprising a cloud end and a device end, wherein: The device end includes a first picture acquisition device and a second picture acquisition device, and the method includes: The first picture acquisition device acquires a picture of a first user passing through the display area of ​​the target object, obtains a user picture of the first user, and sends the user picture of the first user to the cloud; The cloud receives the user image of the first user sent by the first image acquisition device, and performs feature extraction on the user image of the first user to obtain user features of the first user, wherein the user features of the first user do not include facial features of the first user; The second image acquisition device acquires an image of a second user who is performing object processing in the object processing area, obtains a user image of the second user, and sends the user image of the second user to the cloud; The cloud end receives the user image of the second user sent by the second image acquisition device and the object processing information of the second user, and performs feature extraction on the user image of the second user to obtain user features of the second user, wherein the user features of the second user do not include facial features of the second user, and determines the display result of the target object in the display area according to the user features of the first user, the user features of the second user, and the object processing information.

Images