Information pushing method and apparatus, computer device, storage medium, and computer program product

Abstract

An information pushing method, comprising: acquiring a palm image of a user acquired by a front-end device in a service processing process (201); performing palmprint recognition on the basis of the palm image to obtain identity information of the user (203); searching for push information matching the identity information of the user (205); and on the basis of the identity information of the user, generating an identity signature for use in the service processing process, feeding back the identity signature to the front-end device and feeding back the push information to the front-end device to instruct the front-end device to use the identity signature to perform service processing, and playing the push information in the service processing process (207).

Description

Information push method, device, computer equipment, storage medium and computer program product

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 202311237249X, filed on September 21, 2023, entitled “Information Push Method, Apparatus, Computer Equipment and Storage Medium,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to an information push method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0004] With the development of computer technology and biometrics, palmprint recognition has emerged. Palmprint recognition is a relatively new biometric identification technology proposed in the late 19th century. A palmprint is an image of the palm from the fingertips to the wrist. Many of its features can be used for identification, such as main lines, wrinkles, fine textures, ridge ends, and bifurcation points. Palmprint recognition is also a non-invasive identification method that is relatively user-friendly and requires minimal equipment. Currently, palmprint information is typically collected using specialized equipment for palmprint recognition.

[0005] However, the screens of current palmprint collection devices generally only display some necessary instruction information, such as reminding users where to place their palms, resulting in low screen utilization and waste of resources.

[0006] Summary of the Invention

[0007] The present application provides an information push method, apparatus, computer equipment, computer-readable storage medium, and computer program product.

[0008] In a first aspect, the present application provides an information push method, which is executed by a computer device, comprising:

[0009] Obtaining the user's palm image collected by the front-end device during business processing;

[0010] Performing palmprint recognition based on the palm image to obtain the user's identity information;

[0011] Searching for push information that matches the user's identity information; and

[0012] Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and the push information is fed back to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0013] In a second aspect, the present application further provides an information push device, comprising:

[0014] The data acquisition module is used to obtain the user's palm image collected by the front-end device during the service processing;

[0015] A palmprint recognition module, configured to perform palmprint recognition based on the palm image to obtain the user's identity information;

[0016] A push information search module, used to search for push information that matches the identity information of the user;

[0017] An information push module is used to generate an identity signature for use in the business processing process based on the user's identity information, feedback the identity signature to the front-end device, and feedback the push information to the front-end device to instruct the front-end device to use the identity signature for business processing, and play the push information during the business processing.

[0018] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0019] Obtaining the user's palm image collected by the front-end device during business processing;

[0020] Performing palmprint recognition based on the palm image to obtain the user's identity information;

[0021] Searching for push information that matches the user's identity information; and

[0022] Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and the push information is fed back to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0024] Obtaining the user's palm image collected by the front-end device during business processing;

[0025] Performing palmprint recognition based on the palm image to obtain the user's identity information;

[0026] Searching for push information that matches the user's identity information;

[0027] Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and the push information is fed back to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0028] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0029] Obtaining the user's palm image collected by the front-end device during business processing;

[0030] Performing palmprint recognition based on the palm image to obtain the user's identity information;

[0031] Searching for push information that matches the user's identity information;

[0032] Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and the push information is fed back to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0033] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0035] FIG1 is a diagram illustrating an application environment of an information push method according to an embodiment;

[0036] FIG2 is a schematic diagram of a flow chart of an information push method in one embodiment;

[0037] FIG3 is a schematic diagram of a palm authentication process according to one embodiment;

[0038] FIG4 is a block diagram of a system backend service of an information push system according to an embodiment;

[0039] FIG5 is a structural block diagram of a user terminal of an information push system according to an embodiment;

[0040] FIG6 is a structural block diagram of a front-end device of an information push system according to an embodiment;

[0041] FIG7 is a schematic diagram of a processing flow of an information push system according to an embodiment;

[0042] FIG8 is a timing diagram of the processing flow of an information push method according to an embodiment;

[0043] FIG9 is a schematic flow chart of an information push method in another embodiment;

[0044] FIG10 is a structural block diagram of an information push device according to an embodiment;

[0045] FIG11 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] 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 this application 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 relevant regulations.

[0048] The information push method provided in the embodiments of the present application can be applied in the application environment shown in FIG1 . In this embodiment, the front-end device 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated with the server 104 or placed on the cloud or other network servers. When a user performs business transactions that require identity authentication, the user can perform palm authentication using the palm authentication device on the front-end device 102. First, the user performs palm authentication using the palm authentication device on the front-end device 102. The front-end device 102 obtains the user's palm image and then submits the user's palm image to the server 104. The server 104 then obtains the user's palm image collected by the front-end device 102 during the business transaction. The server 104 then performs palm print recognition based on the palm image to obtain the user's identity information. The server then searches for push information that matches the user's identity information. Based on the user's identity information, the server generates an identity signature for use in the business transaction. The server then feeds the identity signature and push information back to the front-end device 102. The front-end device 102 then processes the business transaction using the signature information provided by the identity signature. The push information is then displayed on the display device provided by the front-end device 102 during the business transaction. The front-end device 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Front-end device 102 includes a palm authentication device and a display device. Users can record their palm image on the palm authentication device for palm authentication, while the display device is used to play the found push information. Server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0049] In an exemplary embodiment, as shown in FIG2 , an information push method is provided, which is described by taking the method applied to the server 104 in FIG1 as an example, and includes the following steps 201 to 207 . Among them:

[0050] Step 201: Acquire a user's palm image collected by a front-end device during service processing.

[0051] The front-end device 102 is a device for collecting user palm information. The front-end device 102 includes a palm authentication device and a display device. The user can record a palm image on the palm authentication device for palm authentication. The front-end device can also perform business processing. The business processing process can specifically be a process that requires signature authentication based on the user's identity information. For example, in one embodiment, the business processing process is a login process. In this case, the user can perform palm authentication on the front-end device 102 and provide an identity signature corresponding to the identity information to log in to the corresponding service.

[0052] In another embodiment, the business processing process is specifically a resource transfer settlement process. In this case, the user can provide a corresponding identity signature by performing palm authentication on the front-end device 102, and then the resource transfer settlement confirmation process can be performed based on the identity signature. The user's palm image refers to the palm image collected by the front-end device 102 and used for palm print recognition. The palm image contains the user's palm information. The front-end device 102 can specifically collect multiple images containing the user's palm and then filter to obtain the palm image that can be used for palm print recognition.

[0053] For example, the information push method of the present application is specifically applied to business processes that require palm print authentication. Since certain tasks that require identity information, such as resource transfer tasks that require confirmation of user identity information, involve tasks such as verification and order checking, the process is relatively long. In this case, information can be pushed to the user, thereby improving the effectiveness of the information push. Therefore, as shown in Figure 3, when a user performs business processing through the front-end device 102 and performs identity authentication through the palm authentication device of the front-end device 102, the palm print authentication processing can be implemented by the server 104 of the present application. At the same time, combined with the user's identity information, the corresponding information can be customized and pushed to the user, thereby ensuring the effectiveness of the information push. Therefore, the solution of the present application requires that the front-end device 102 first collect the user's palm image as the basic data for the palm print authentication process and the information push process. The server 104 directly obtains the user's palm image collected by the front-end device during the business processing process and begins the corresponding authentication process.

[0054] Step 203: Perform palm print recognition based on the palm image to obtain the user's identity information.

[0055] Palmprint recognition refers to a biometric identification technology that uses palmprints for identity verification. Palmprints refer to the various lines on the surface of the palm between the wrist and fingers. Palmprint morphology is genetically controlled; even if the skin peels off for some reason, the new lines retain their original structure. Everyone's palmprints are unique; even twins have similar, but never identical, lines. Therefore, palmprints can be used to non-invasively identify a user's identity, ensuring accuracy. In a specific embodiment, palmprint recognition can be performed by extracting palmprint features from a palm image. Palmprints contain far more information than a fingerprint. Line, point, texture, and geometric features can be extracted and combined to determine the user's identity.

[0056] For example, after obtaining a user's palm image from the front-end device 102, palmprint recognition can be performed based on the palm image. Specifically, feature extraction can be performed on the current palm image, and the various extracted palm features can be compared with features in a database. The feature data with the highest score is then found. The relevant palm data is then compared with the palm data in the back-end database to determine the palm features in the database corresponding to the palm image. The user's identity information can then be determined by searching for the user's identity information corresponding to the palm features in the database. The palmprint recognition process can first identify the hand area in the image, and then use a pre-established machine learning model to extract various feature information such as line features, point features, texture features, and geometric features of the palmprint in the hand image. This information is then compared with the palmprint features in the database, and the user's identity information is then determined based on the comparison results.

[0057] Step 205: Search for push information that matches the user's identity information.

[0058] Among them, push information refers to the media content that the user is interested in based on identity information, such as program preview push information, live broadcast push information, product push information or business push information, etc. The display form of push information can be content animated images or display videos, etc.

[0059] For example, to achieve more effective information push, various media contents of interest to the user can be determined in advance based on the user's browsing history or viewing history. In specific examples, collaborative filtering and content filtering techniques can be used to predict the user's interests and preferences, thereby determining the media contents of interest to be pushed. In one specific embodiment, the pushed information can specifically be live broadcast content. In this case, the live broadcast room that the user is following and is currently broadcasting can be searched for push notifications, and the live broadcast content can be displayed on the display device of the front-end device.

[0060] Step 207: Based on the user's identity information, generate an identity signature for use in the business processing process, feed back the identity signature to the front-end device, and feed back push information to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0061] The identity signature refers to data generated based on the target's identity information and used to authenticate the business process. It can include signature information. For example, after determining the user's identity information, a QR code corresponding to that identity information can be generated and used as the identity signature. The identity signature can be used as a credential to provide signature information during business processing, thereby facilitating the information push process.

[0062] For example, after finding push information that matches the user's identity information, the identity information used in the identity authentication process and the identity information used in the information push process are obtained. At this point, an identity signature can be generated based on the user's identity information for use during the service processing process. This identity signature can be generated based on the signature information matching the service type being processed. For general tasks, the identity signature can be automatically generated or pre-set by the user. The identity signature and push information are then directly fed back to the front-end device 102. Upon receiving these two pieces of information, the front-end device 102 can perform the corresponding service processing. The identity signature can be loaded into the original service processing process for authentication, and the service processing after authentication is executed. For push information, the push information can be displayed on the display device of the front-end device 102 while the service processing is being performed in the background of the front-end device 102. The user who provided the palm image can then view the pushed information on the front-end device 102. In a specific embodiment, the push information can specifically be live broadcast information of product recommendations. While watching the live broadcast, the user can collect or place an order for the recommended products through the front-end device 102, thereby improving the push effect of the information push.

[0063] The above-mentioned content push method first obtains the user's palm image collected by the front-end device during the business processing process to obtain basic data for palmprint authentication. Then, palmprint recognition is performed based on the palm image. The palmprint recognition obtains the user's identity information used in the business processing process. At the same time, push information matching the user's identity information is searched to obtain push information more closely related to the user. Then, based on the user's identity information, an identity signature is generated for use in the business processing process. The identity signature and push information are fed back to the front-end device so that the identity signature is used for business processing and the push information is played during the business processing. That is, by feeding back the identity signature and push information, the push information associated with the user can be displayed on the front-end palmprint recognition device during the business processing using the signature information provided by the identity signature. Therefore, the push information can be played when the business processing is performed based on the identity signature, effectively utilizing the screen, improving screen resource utilization, and avoiding resource waste. Moreover, the push information that is pushed is matched with the user's identity information, which can avoid the waste of resources caused by pushing useless information when randomly pushing information to users.

[0064] In an exemplary embodiment, the information push method also includes: searching for preset gesture information corresponding to the identity information; when receiving the collected gesture information based on the push information feedback from the front-end device, using the preset gesture information to perform gesture authentication on the collected gesture information; when the gesture authentication is passed, generating order information corresponding to the push information.

[0065] Preset gesture information is pre-set by the user and can be used for information authentication or order generation. Collected gesture information refers to user gestures captured by image capture devices such as the palm recognition device of the front-end device. Gesture authentication processing involves comparing the user's pre-stored preset gesture information with the real-time collected gesture information to determine whether an order generation action has been triggered, thereby generating the order information corresponding to the push information.

[0066] For example, push information specifically refers to information used to push product content, service content, or business content to users. The push information includes the pushed product content, service content, or business content. Users can determine whether to place an order for these contents based on the product content, service content, or business content contained in the push information, thereby obtaining the corresponding product or service. Orders for push information can be triggered by actions performed by the user on the front-end device. When a user is viewing a push information and determines that an order for the push information needs to be triggered, they can perform a corresponding action on the front-end device's image capture device (e.g., a palm authentication device for capturing palm images). The image capture device then captures these images as captured gesture information and sends them to the back-end for gesture authentication. The back-end, based on the user's pre-stored information, searches a database for preset gesture information corresponding to the identity information and then uses the preset gesture information to perform gesture authentication on the captured gesture information. Specifically, gesture authentication can be performed by comparing the image features of the preset gesture information with the image features of the captured gesture information. If gesture authentication passes, order information corresponding to the push information is directly generated, thereby providing the user with the corresponding product or service. In this embodiment, after the information is pushed, the order information corresponding to the pushed information is generated by receiving the preset gesture information provided by the user, which can effectively improve the efficiency of generating order information during the user's order processing.

[0067] In an exemplary embodiment, when the gesture authentication is passed, generating order information corresponding to the push information includes: when the gesture authentication is passed, searching for the business information corresponding to the push information; searching for the user's pre-configured receiving address information and recipient information based on the identity information; filling in the order form corresponding to the business information based on the receiving address information and recipient information, and generating order information corresponding to the push information.

[0068] The business information corresponding to the push information refers to the business content such as the goods or services displayed through the push information. The user's pre-configured delivery address information and recipient information refer to the logistics information pre-configured by the user in the background. The logistics and courier information that the user can pre-configure in the background mainly includes basic information such as the recipient's name, address, phone number, postal code, and courier company.

[0069] For example, during the order generation process, if gesture authentication is successful, the business information corresponding to the push information can be first searched, that is, the product or service content carried by the push information can be first determined. In one embodiment, the solution of the present application is applicable to pushing product information. In this case, when pushing information, the product serial number corresponding to the push information can be directly searched, and the product information can be obtained through the serial number. At the same time, in order to generate the order information, the user's shipping address information needs to be determined. In this case, since the user has pre-configured logistics information such as the receiving address and recipient information in the background, the user's pre-configured receiving address and recipient information can be directly searched based on the user's identity information. The business information and logistics information, which are essential for the order, are then entered into the order form, and the order information corresponding to the push information can be directly generated in the background. In one embodiment, after the order information is generated, the order information can also be pushed to the user's background account based on the target's identity, so that the user can confirm the generated order information and ensure the validity of the generated order information.

[0070] In an exemplary embodiment, performing gesture authentication processing on the collected gesture information by collecting gesture information includes: obtaining a gesture image in the collected gesture information; extracting a hand area image in the gesture image; extracting image features of the hand area image; comparing the image features of the hand area image with the image features of the collected gesture information to obtain a gesture feature comparison result; and determining a result of gesture authentication on the collected gesture information based on the gesture feature comparison result.

[0071] A gesture image is a complete image of the user's hand movements, while a hand region image is an image of the complete hand region after removing the background content from the gesture image. Image features are the characteristic information corresponding to hand movements extracted by a pre-trained machine learning model.

[0072] For example, the solution of this application can utilize computer vision technology to perform gesture authentication. First, a front-end device captures an image containing the gesture as gesture information. The gesture image can be captured by one or more cameras on the front-end device. After capturing the image, the front-end device processes the image, for example, by removing portions of the image that do not contain the hand and identifying the angle and position of the gesture in other images to select the optimal image as the gesture image. The server backend can then perform gesture authentication based on the gesture image submitted by the front-end device. First, through a series of processes, including preprocessing and hand region localization, the hand region image is extracted from the gesture image. Next, image features of the hand region image are extracted based on a pre-trained machine learning model. The extracted hand region image features primarily include visual features and semantic features. Visual features include color, texture, and contour, while semantic features represent an understanding of the image content. After extracting the image features of the hand region image, the image features of the hand region image and the image features of the collected gesture information can be directly compared. Specifically, the similarity between the two image features can be calculated as the gesture feature comparison result. The process of determining the result of gesture authentication for the collected gesture information based on the gesture feature comparison result can be determined based on whether the similarity between the two features is greater than a preset similarity threshold. When the gesture feature comparison result indicates that the similarity between the two features is greater than or equal to the preset similarity threshold, it indicates that the gesture provided by the front-end device is similar to the gesture pre-stored in the system by the user. In this case, it can be determined that the preset gesture information provided by the front-end device has passed the gesture authentication process. If the gesture feature comparison result indicates that the similarity between the two features is less than the preset similarity threshold, it indicates that the gesture provided by the front-end device is weakly related to the gesture pre-stored in the system by the user. In this case, a message indicating authentication failure can be fed back, prompting the user to re-authenticate the gesture. In this embodiment, gesture authentication is completed using a machine learning approach through hand region image extraction, image feature extraction, and feature comparison, effectively ensuring the accuracy and efficiency of gesture authentication.

[0073] In an exemplary embodiment, extracting a hand area image from a gesture image includes: removing noise and enhancing information on the gesture image to obtain a preprocessed image; determining the hand area in the preprocessed image through gesture positioning; determining a segmentation contour corresponding to the hand area through color positioning; and performing image segmentation on the preprocessed image based on the segmentation contour to obtain a hand area image.

[0074] For example, the process of extracting the hand region image from a gesture image can include first performing noise removal and information enhancement on the gesture image to obtain a preprocessed image; then determining the hand region in the preprocessed image through gesture localization; then determining the segmentation contour corresponding to the hand region through color localization; and finally, performing image segmentation on the preprocessed image based on the segmentation contour to obtain a hand region image. Noise removal and information enhancement can improve the information density of the gesture image, thereby ensuring the accuracy of gesture authentication. Regarding determining the hand region in the preprocessed image through gesture localization, the gesture localization process primarily locates the hand region within the complex background of the gesture image, thereby achieving separation of the gesture from the background. After gesture localization, an algorithm is used to segment the current gesture from the background region. The segmentation algorithm can specifically be color segmentation, which uses the difference between the hand color and the background color to determine the segmentation contour corresponding to the hand region through color localization. The preprocessed image is then segmented based on the segmentation contour to obtain a hand region image. By pre-establishing a color model and then combining skin color, motion, and gesture authentication contour shape information for image segmentation, segmentation accuracy can be significantly improved, resulting in a more effective hand region image. In this embodiment, by performing preprocessing, gesture positioning, and color segmentation on the gesture image, the accuracy of hand region recognition in the image can be effectively improved, thereby ensuring the accuracy of gesture recognition processing.

[0075] In an exemplary embodiment, step 201 includes: collecting user's palm streaming media data through the front-end device during business processing; identifying palm information and image quality information of each frame image in the palm streaming media data; performing image screening processing on the palm streaming media data based on the palm information and image quality information to obtain the user's palm image collected by the front-end device.

[0076] The palm streaming image refers to video content of the user's palm captured by the palm authentication device on the front-end device. The palm streaming image contains multiple frames. Palm information includes palm size and angle, while image quality information includes image contrast, brightness, and clarity.

[0077] For example, during the palm image acquisition process, to improve the accuracy of palmprint recognition, the captured image information can be processed on the front-end device to obtain a palm image containing more palmprint information. Therefore, the front-end device can first use a camera to capture the user's current palm streaming data. After acquiring the palm streaming data, the front-end device can also prioritize multiple images within the palm streaming data. The prioritization can be based on palm information such as palm size and palm angle, as well as image quality information such as image contrast, image brightness, and clarity. After obtaining this data, the palm streaming data is then filtered using a comprehensive evaluation based on corresponding coefficient indicators to determine the optimal palm image, thereby obtaining a palm image suitable for palmprint recognition. This palm image can then be sent to the back-end for palmprint recognition processing. In this embodiment, palm image screening based on palm information and image quality information can effectively improve the reliability of palm images, thereby enhancing the accuracy of palmprint recognition and ensuring the effectiveness of information push.

[0078] In an exemplary embodiment, step 205 includes: searching for historical browsing records and historical playback records corresponding to the identity information; performing preference prediction processing based on the historical browsing records and historical playback records to obtain push information that matches the user's identity information.

[0079] Browsing history refers to the records of users browsing product or service pages through the push system's front-end page. Playback history refers to the records of users watching various live broadcasts or recommended content videos through the push system's front-end page. Preference prediction refers to predicting a user's interests and preferences based on their browsing history and playback history, and then delivering relevant information to the user.

[0080] Exemplarily, the system architecture of the information push method of the present application may also include a user terminal in addition to the front-end device and the back-end server. The back-end server provides various services to the user through the front-end application on the user terminal. In the process of using the front-end application, the user will generate various historical browsing records and historical playback records. The back-end server can search the historical browsing records and historical playback records corresponding to the identity information from the background based on the user's consent. Then, the back-end performs preference prediction processing through a pre-trained machine learning model to obtain the user's interests and preferences. Then, based on the interests and preferences, an associated search is performed among all the content to be pushed, so as to accurately identify the push information that the user is interested in, thereby achieving accurate information push processing and ensuring the accuracy of the information push. In this embodiment, by analyzing the user's historical browsing records and historical playback records, and performing preference prediction to determine the push information corresponding to the user, the effectiveness of the identity information push processing process can be effectively guaranteed.

[0081] In an exemplary embodiment, preference prediction processing is performed based on historical browsing records and historical playback records to obtain push information that matches the user's identity information, including: determining the similarity between the user and each user set based on the historical browsing records and historical playback records; determining the user's similar user set based on the similarity; searching for preference content of the similar user set; and obtaining push information that matches the user's identity information based on the preference content.

[0082] User sets are pre-classified using clustering and other methods based on their browsing and playback history. These sets are called user sets. Users in each user set share the same or similar interests and preferences. Once a user set is generated, the browsing and playback history of the users within the set can be analyzed to determine the preferences of the user set. A similar user set is the user set with the highest similarity to the user.

[0083] For example, the solution of the present application can predict user preferences by analyzing similar users. First, the similarity between the user and each user set is determined based on historical browsing and playback records to determine which user set is most similar to the current user. In one embodiment, the similarity calculation process can be based on the user's historical browsing and playback records to establish a user preference feature vector. The similarity between the user and each user set is then determined by comparing the user's preference features with the user set features corresponding to each user set. For the user set features corresponding to each user set, the features of each user in the user set can be determined first, and then the user set features of the user set can be obtained by averaging. The similarity distance can be either Euclidean distance or cosine distance. Once the Euclidean distance or cosine distance is obtained, the similarity between the user and each user set can be determined. Once the similar user sets are obtained, the user set settings can be used to find the shared preferences of the similar user sets. Based on the preferences, push information matching the user's identity information can then be obtained. Specifically, based on the user's historical browsing and playback records, the preferred content can be filtered out to exclude the information that the user has already browsed, and then the filtered preferred content can be pushed. In this embodiment, by finding a set of similar users with similar characteristics and then implementing information push based on the shared preferences of the similar user set, the effectiveness of the push information search can be effectively guaranteed, thereby improving the effect of information push.

[0084] In an exemplary embodiment, the push information includes live broadcast push information; searching for push information that matches the user's identity information includes: determining the live broadcast content that the user is interested in based on the identity information; searching for the live broadcast room that is in a live broadcast state in the live broadcast content that the user is interested in; filtering the target live broadcast room based on the live broadcast information of the live broadcast room, and using the live broadcast information of the target live broadcast room as the push information that matches the user's identity information.

[0085] The live streaming content that users follow refers to the live streamers or live streaming programs they follow. The live streaming information of a live streaming room can include the room's popularity, the host's popularity, the live streaming type, and the length of time the user has been following the live streaming room. Based on this live streaming information, a live streaming room can be selected from the live streaming rooms that the user follows to be pushed to.

[0086] For example, to improve the effectiveness of information push, live content currently being broadcast can be pushed to a front-end device as push information for playback. Therefore, when performing information push, the live content that the user is already following can be determined based on the user's identity information. The status of these live content can then be searched to determine the live rooms currently live among the live content that the user is following. Based on live information such as the live room's popularity, the host's popularity, the live broadcast type, and the length of time the user has been following the live broadcast, a target live room can be filtered out from these live broadcast rooms, and the live broadcast information of the target live room can then be used as push information matched with the user's identity information. In a specific embodiment, a live broadcast room currently broadcasting a recommendation (e.g., a live broadcast room recommending a product) can be filtered out based on the live broadcast type, and the live broadcast information of the target live room can then be used as push information matched with the user's identity information. In this case, the process of generating push information can first obtain the target live room after filtering it out, then obtain the target live room's video stream data and service recommendation data; then generate video push information based on the video stream data and service recommendation data; and then feed the video push information back to the front-end device via the content distribution network. At this point, the live broadcast information and recommended information can be displayed simultaneously on the display device of the front-end device. The user can determine whether to place an order based on the live broadcast content and recommended information. In a specific embodiment, the information push method of the present application is implemented by an information push system, which includes a system back-end service as shown in Figure 4, a user terminal as shown in Figure 5, and a front-end device as shown in Figure 6. The system back-end service is connected to the user terminal and the front-end device respectively. The system back-end service can include a video account live broadcast service and an identity authentication service. The video account live broadcast service can be used to provide live broadcast services, recommendation services, or setting services for various video accounts. The identity authentication service includes a palm print authentication service and a gesture authentication service, which provides services for the palm print recognition and gesture authentication processes. On the user terminal, services can be provided to the user through the front-end application. The video account module of the front-end application includes a video account live broadcast module for providing users with live broadcast video accounts, and a video account follow module. Users can follow the video accounts of interest through the video account follow module. In addition, it also includes a video account setting module. Users can use the gesture module in the video account setting module to enter preset gesture information for gesture authentication and can also pre-set logistics information for generating orders. The front-end device consists of a 3D camera module and a front-end application module. The 3D camera module uses information such as the user's palm and gestures for authentication. The palm recognition module extracts palm images from the video captured by the 3D camera module for back-end palmprint recognition. The processing module handles business operations, and push notifications are displayed on the processing module's page. The gesture module handles gesture authentication related processing on the front end.The final result page module can display the results of the business processing or the order generation results of the user placing an order based on the push information. In this embodiment, the live content is recommended by determining the live content that the user is interested in, thereby effectively improving the push effect of the information push in combination with the live information push method.

[0087] In an exemplary embodiment, filtering a target live broadcast room based on the live broadcast information of the live broadcast room, and using the live broadcast information of the target live broadcast room as push information that matches the identity information of the user includes: filtering the target live broadcast room based on the live broadcast information of the live broadcast room to obtain the live broadcast information of the target live broadcast room; searching for the to-be-pushed service corresponding to the front-end device; determining the target service associated with the live broadcast information among the services to be pushed; and using the target service and the live broadcast information as push information that matches the identity information of the user.

[0088] For example, in addition to being able to push remote business orders via live broadcast information, the solution of this application can also leverage remote live broadcast services to push various types of business information at the location of the front-end device. In this case, the target live broadcast room can be filtered based on the live broadcast information of the live broadcast room to obtain the live broadcast information of the target live broadcast room, thereby obtaining a portion of the information stream that can be pushed. The services to be pushed corresponding to the front-end device can then be found, and the target services associated with the live broadcast information can be determined. The services to be pushed refer to services that can be provided to users on the front-end device. For example, in a scenario where a user visits a storefront for shopping, the services to be pushed can be the categories of goods available in the storefront. The target services associated with the live broadcast information can refer to recommended content in the storefront that is identical or similar to the live broadcast information. For example, for a live broadcast with goods, the same or similar goods in the live broadcast with goods can be used as the target services associated with the live broadcast information. The target services and live broadcast information are then used as push information that matches the user's identity information. The user can directly determine whether to place an order for the service content contained in the push information based on the recommended content in the push information. As for the ordering process, it can also be achieved by providing preset gesture information. At this time, settlement can be completed directly on the front-end device without generating an order for delivery processing, thereby extremely accelerating the business process and improving the processing efficiency of the business push process.

[0089] In an exemplary embodiment, the method further includes, when receiving a service completion message fed back by the front-end device, generating push resume information corresponding to the push information, and pushing the resume information to the user terminal of the user.

[0090] For example, when the business processing executed on the front-end device is completed, the user may need to leave the front-end device, and at this time the pushed live broadcast information may not have been completed, and the user also wants to continue watching the pushed live broadcast information. Therefore, in order to ensure the continuity of the live broadcast push, when the business completion message fed back by the front-end device is received, the push continuation information corresponding to the push information can continue to be generated according to the pushed live broadcast signal. The push continuation information can be pushed to the user's user terminal, and at this time, the user can continue to watch the live broadcast on the user terminal. In this embodiment, by pushing the live broadcast continuation information after the business processing is completed, the live content continues to be played on the user's user terminal, thereby effectively ensuring the continuity of the live broadcast push and improving the push effect of the information push.

[0091] This application also provides an application scenario, which applies the above-mentioned information push method. Specifically, the application of the information push method in this application scenario is as follows:

[0092] The complete flow chart can be specifically referred to Figure 7. First, users can watch various live broadcasts on the front-end application of the information push system through the user terminal, and set the information of their own video accounts. At the same time, in order to improve the convenience of placing orders, palm print information for palm print recognition and preset gesture information for gesture authentication can also be set on the front end. At the same time, logistics information can also be set so that order information can be directly generated after the order is placed. When the user performs business settlement processing at a store that can perform palm authentication, the solution of this application can be used to push information to the user, thereby improving the effectiveness of information push. First, when the user needs to perform business settlement processing, the 3D camera of the front-end device of the store can be used to record the palm image. The front-end device collects the user's palm streaming media data; identifies the palm information and image quality information of each frame image in the palm streaming media data; performs image screening processing on the palm streaming media data based on the palm information and image quality information to obtain the user's palm image collected by the front-end device. The backend of the information push processing system then performs palm print recognition based on the palm image to obtain the user's identity information. Specifically, the system first obtains a gesture image from the collected gesture information; performs noise removal and information enhancement on the gesture image to obtain a preprocessed image; determines the hand region in the preprocessed image through gesture positioning; determines the segmentation contour corresponding to the hand region through color positioning; and performs image segmentation on the preprocessed image based on the segmentation contour to obtain a hand region image. It then extracts image features from the hand region image; compares the image features of the hand region image with those of the preset gesture information to obtain a gesture feature comparison result; and determines the result of gesture authentication for the collected gesture information based on the gesture feature comparison result. After gesture authentication is completed and the identity information is obtained, the system searches for historical browsing and playback records corresponding to the identity information. A feature extraction model is used to extract user features and obtain user set features corresponding to each user set. A similarity distance parameter is determined between the user's features and the features of each user set; the similarity between the user and each user set is determined based on the similarity distance parameter; similarity between the user and each user set is determined based on the similarity; and similar user sets are determined based on the similarity. The preferred content of the similar user sets is searched; and based on the preferred content, live broadcast push information corresponding to the identity information is obtained. Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and push information is fed back to the front-end device to use the identity signature for business processing, and push information of the live video content is played during the business processing.The user can make corresponding gestures in the 3D camera of the front-end device according to the push information, and then the front-end device will feedback the collected gesture information to the back-end system based on the collected information. The back-end system will search for the preset gesture information corresponding to the identity information, and use the preset gesture information to perform gesture authentication on the collected gesture information; when the gesture authentication is passed, the business information corresponding to the push information will be searched; based on the identity information, the user's pre-configured receiving address information and recipient information will be searched; based on the receiving address information and recipient information, the order form corresponding to the business information will be filled in to generate the order information corresponding to the push information.

[0093] In another application scenario, the timing diagram corresponding to the information push process implemented in this application can be shown in Figure 8. First, the user watches the live broadcast through the user terminal and sets live broadcast preferences, while also setting up the identity authentication process and logistics information. The user then arrives at the store and performs the corresponding business processing. The business processing process involves identity authentication. In this case, the user can directly perform identity authentication by scanning the palm on the front-end device. The front-end device then sends the corresponding palm image back to the back-end system. The back-end system performs palm print recognition based on the palm image to obtain the user's identity information. At the same time, it searches for the corresponding push information based on the user's identity information and then sends the identity signature and push information back to the front-end device. While performing back-end business processing based on the identity signature, the front-end device can also play the push information on the display device. The user can enter preset gesture information on the front-end device based on the push information, and the back-end system searches for the preset gesture information corresponding to the identity information. The preset gesture information is then used to perform gesture authentication on the collected gesture information. When the gesture authentication is successful, the order information corresponding to the push information is generated and pushed to the user terminal and the front-end device.

[0094] In one embodiment, the complete process of the classification model processing method of the present application can be shown in FIG9 , including:

[0095] Step 902: Acquire the user's palm image collected by the front-end device during the service processing.

[0096] Step 904: perform palm print recognition based on the palm image to obtain the user's identity information.

[0097] Step 906: Determine the live broadcast content that the user is interested in based on the identity information.

[0098] Step 908: Search for a live broadcast room in the live broadcast content that the user is following.

[0099] Step 910: Filter the target live broadcast room based on the live broadcast information of the live broadcast room to obtain the video stream data and recommendation data of the target live broadcast room.

[0100] Step 912: Generate video push information based on the video stream data and the service recommendation data.

[0101] Step 914: Feedback the video push information to the front-end device via the content distribution network.

[0102] Step 916: Based on the user's identity information, generate an identity signature for use in the business processing process, feed back the identity signature to the front-end device, and feed back push information to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

[0103] Step 918: Search for preset gesture information corresponding to the identity information.

[0104] Step 920: When the collected gesture information fed back by the front-end device based on the push information is received, gesture authentication is performed on the collected gesture information using the preset gesture information.

[0105] Step 922: When the gesture authentication is passed, the order information corresponding to the push information is generated.

[0106] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0107] Based on the same inventive concept, the embodiments of the present application also provide an information push device for implementing the aforementioned information push method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more information push device embodiments provided below can be referred to the limitations of the information push method above and will not be repeated here.

[0108] In an exemplary embodiment, as shown in FIG10 , an information push device is provided, including:

[0109] The data acquisition module 1001 is used to acquire the user's palm image collected by the front-end device during the service processing;

[0110] Palmprint recognition module 1003, used to perform palmprint recognition based on palm images to obtain user identity information;

[0111] Push information search module 1005, used to search for push information that matches the user's identity information;

[0112] The information push module 1007 is used to generate an identity signature for use in the business processing process based on the user's identity information, feedback the identity signature to the front-end device, and feedback push information to the front-end device to instruct the front-end device to use the identity signature for business processing, and play the push information during the business processing.

[0113] In one embodiment, an order generation module is also included, which is used to: search for preset gesture information corresponding to the identity information; when the collected gesture information based on the push information feedback from the front-end device is received, use the preset gesture information to perform gesture authentication on the collected gesture information; when the gesture authentication is passed, generate order information corresponding to the push information.

[0114] In one embodiment, the order generation module is also used to: when the gesture authentication is passed, search for the business information corresponding to the push information; search for the user's pre-configured receiving address information and recipient information based on the identity information; fill in the order form corresponding to the business information based on the receiving address information and recipient information, and generate the order information corresponding to the push information.

[0115] In one embodiment, the order generation module is also used to: obtain a gesture image from the collected gesture information; extract a hand area image from the gesture image; extract image features of the hand area image; compare the image features of the hand area image with the image features of the preset gesture information to obtain a gesture feature comparison result; and determine a result of gesture authentication of the collected gesture information based on the gesture feature comparison result.

[0116] In one embodiment, the order generation module is also used to: remove noise and enhance information on the gesture image to obtain a preprocessed image; determine the hand area in the preprocessed image through gesture positioning; determine the segmentation contour corresponding to the hand area through color positioning; and perform image segmentation on the preprocessed image based on the segmentation contour to obtain a hand area image.

[0117] In one embodiment, the data acquisition module 1001 is specifically used to: collect the user's palm streaming media data through the front-end device during business processing; identify the palm information and image quality information of each frame image in the palm streaming media data; perform image screening processing on the palm streaming media data based on the palm information and image quality information to obtain the user's palm image collected by the front-end device.

[0118] In one embodiment, the push information search module 1005 is specifically used to: search for historical browsing records and historical playback records corresponding to the identity information; perform preference prediction processing based on the historical browsing records and historical playback records to obtain push information matching the user's identity information.

[0119] In one embodiment, the push information search module 1005 is also used to: determine the similarity between the user and each user set based on historical browsing records and historical playback records; determine the user's similar user set based on the similarity; search for preferred content of the similar user set; and obtain push information that matches the user's identity information based on the preferred content.

[0120] In one embodiment, the push information search module 1005 is further used to: extract user features through a feature extraction model and obtain user set features corresponding to each user set; determine a similarity distance parameter between the user's features and the features of each user set; and determine the similarity between the user and each user set based on the similarity distance parameter.

[0121] In one embodiment, the push information includes live broadcast push information; the push information search module 1005 is also used to: determine the live broadcast content that the user is interested in based on the identity information; search for the live broadcast room that is in the live broadcast state in the live broadcast content that the user is interested in; filter the target live broadcast room based on the live broadcast information of the live broadcast room, and use the live broadcast information of the target live broadcast room as push information that matches the user's identity information.

[0122] In one embodiment, the push information search module 1005 is also used to: filter the target live broadcast room based on the live broadcast information of the live broadcast room, obtain the video stream data and recommendation data of the target live broadcast room; generate video push information based on the video stream data and business recommendation data; and feed back the video push information to the front-end device through the content distribution network.

[0123] In one embodiment, the push information search module 1005 is also used to: filter the target live broadcast room based on the live broadcast information of the live broadcast room to obtain the live broadcast information of the target live broadcast room; search for the service to be pushed corresponding to the front-end device; determine the target service associated with the live broadcast information among the services to be pushed; and use the target service and the live broadcast information as push information that matches the user's identity information.

[0124] In one embodiment, a push-resume module is further included, which is used to: when receiving a service completion message fed back by the front-end device, generate a push-resume message corresponding to the push information, and push the resume message to the user terminal.

[0125] Each module in the above-mentioned information push device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0126] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 11. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data related to information push. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an information push method is implemented.

[0127] Those skilled in the art will understand that the structure shown in FIG11 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0129] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0130] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of each of the above-described method embodiments.

[0131] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0132] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. An information push method, executed by a computer device, comprising: Acquire the user's palm image collected by the front-end device during business processing; Performing palmprint recognition based on the palm image to obtain identity information of the user; Searching for push information that matches the identity information of the user; and Based on the user's identity information, an identity signature is generated for use in the business processing process, the identity signature is fed back to the front-end device, and the push information is fed back to the front-end device to instruct the front-end device to use the identity signature for business processing and play the push information during the business processing.

2. The method according to claim 1, further comprising: Searching for preset gesture information matching the identity information of the user; When receiving the collected gesture information fed back by the front-end device based on the pushed information, performing gesture authentication on the collected gesture information using the preset gesture information; When the gesture authentication is passed, the order information corresponding to the push information is generated.

3. The method according to claim 2, wherein when the gesture authentication is passed, generating the order information corresponding to the push information comprises: When the gesture authentication is passed, searching for the service information corresponding to the push information; Searching for the recipient address information and recipient information pre-configured by the user based on the identity information; An order form corresponding to the business information is filled in based on the receiving address information and the recipient information to generate order information corresponding to the push information.

4. According to the method of claim 2 or 3, the step of performing gesture authentication on the collected gesture information using the preset gesture information comprises: Acquire a gesture image in the collected gesture information; Extracting a hand area image from the gesture image; Extracting image features of the hand region image; Comparing the image features of the hand area image with the image features of the preset gesture information to obtain a gesture feature comparison result; Based on the gesture feature comparison result, a result of gesture authentication of the collected gesture information is determined.

5. According to the method of claim 4, extracting the hand area image in the gesture image comprises: removing noise and enhancing information from the gesture image to obtain a preprocessed image; determining a hand region in the preprocessed image by gesture positioning; Determining a segmentation contour corresponding to the hand region by color positioning; The preprocessed image is segmented based on the segmentation contour to obtain a hand area image.

6. According to the method according to any one of claims 1 to 5, the step of obtaining the palm image of the user collected by the front-end device during the service processing comprises: Collect user's palm streaming media data during business processing through front-end equipment; Identifying palm information and image quality information of each frame image in the palm streaming media data; The palm streaming media data is subjected to image screening processing based on the palm information and the image quality information to obtain a palm image of the user collected by the front-end device.

7. The method according to any one of claims 1 to 6, wherein searching for push information matching the identity information of the user comprises: Searching for historical browsing records and historical playback records corresponding to the identity information; Preference prediction processing is performed based on the historical browsing records and the historical playing records to obtain push information that matches the identity information of the user.

8. The method according to claim 7, wherein the performing preference prediction processing based on the historical browsing records and the historical playback records to obtain push information matching the identity information of the user comprises: Determining the similarity between the user and each user set based on the historical browsing records and the historical playing records; Determine a similar user set of the user based on the similarity; Finding the preference content of the similar user set; Based on the preferred content, push information matching the identity information of the user is obtained.

9. The method according to claim 8, wherein determining the similarity between the user and each user set based on the historical browsing record and the historical playing record comprises: Extracting the features of the users through a feature extraction model, and obtaining the user set features corresponding to each user set; Determining a similarity distance parameter between the user's characteristics and the characteristics of each user set; The similarity between the user and each user set is determined based on the similarity distance parameter.

10. The method according to any one of claims 1 to 9, wherein the push information includes live broadcast push information; The searching for push information matching the identity information of the user includes: Determine the live broadcast content that the user is interested in based on the identity information; Finding a live broadcast room in the live broadcast content followed by the user that is in a live broadcast state; A target live broadcast room is filtered based on the live broadcast information of the live broadcast room, and the live broadcast information of the target live broadcast room is used as push information matching the identity information of the user.

11. The method according to claim 10, wherein feeding back the push information to the front-end device comprises: Filter a target live broadcast room based on the live broadcast information of the live broadcast room, and obtain video stream data and recommendation data of the target live broadcast room; Generate video push information based on the video stream data and the service recommendation data; The video push information is fed back to the front-end device through a content distribution network.

12. An information push device, comprising: The data acquisition module is used to acquire the user's palm image collected by the front-end device during the service processing; A palmprint recognition module, used to perform palmprint recognition based on the palm image to obtain the identity information of the user; A push information search module, used to search for push information matching the identity information of the user; and An information push module is used to generate an identity signature for use in the business processing process based on the user's identity information, feed back the identity signature to the front-end device, and feed back the push information to the front-end device to instruct the front-end device to use the identity signature for business processing, and play the push information during the business processing.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images