Information pushing method and device

Abstract

The invention discloses an information pushing method and device, and relates to the field of machine learning. According to one specific embodiment, the method comprises the steps that in response to determining that situation information changes, target recommendation information is determined based on current situation information, and the situation information comprises at least one of scene information, environment information and user information; determining a target pushing mode based on the current situation information and the target recommendation information; and pushing the target recommendation information by adopting the target pushing mode. According to the embodiment, the timeliness and effectiveness of pushing the recommendation information are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to the field of machine learning technology, and in particular to an information push method and apparatus. Background Technology

[0002] Most current information delivery technologies are based on presets or user questions. In real-time, real-world environments, it is difficult to accurately predict and analyze potential needs.

[0003] Furthermore, user needs often change in real time with changes in the environment. In many cases, users may not realize their needs in time due to a lack of information, which can lead to difficulties in subsequent tasks. For example, if the boarding gate changes, the user must find the gate to discover the need. For users with infants, information such as mother and baby rooms and stroller rentals can only be provided based on user input. Summary of the Invention

[0004] This application provides an information push method, apparatus, device, and storage medium.

[0005] According to a first aspect, embodiments of this application provide an information push method, the method comprising: in response to determining a change in contextual information, determining target recommendation information based on the current contextual information, wherein the contextual information includes at least one of scene information, environment information, and user information; determining a target push method based on the current contextual information and the target recommendation information; and pushing the target recommendation information using the target push method.

[0006] According to a second aspect, embodiments of this application provide an information push device, including: an acquisition module, a determination module, and a push module, wherein the acquisition module is configured to determine target recommendation information based on the current context information in response to a change in determined context information, the context information including at least one of scene information, environment information, and user information; the determination module is configured to determine a target push method based on the current context information and the target recommendation information; and the push module is configured to push the target recommendation information using the target push method.

[0007] According to a third aspect, embodiments of this application provide an electronic device including one or more processors; a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the information push method as described in any embodiment of the first aspect.

[0008] According to a fourth aspect, embodiments of this application provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the information push method as described in any embodiment of the first aspect.

[0009] This application, in response to changes in contextual information, determines target recommendation information based on the current contextual information; determines the target push method based on the current contextual information and the target recommendation information; and pushes the target recommendation information using the target push method. This enables the inference of users' potential needs and the proactive push of recommendation information when contextual information changes, reducing users' active search costs, reducing the omission of important information, and improving the timeliness and effectiveness of push recommendation information.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] Figure 1 This is an exemplary system architecture diagram to which this application can be applied; Figure 2a This is a flowchart of an embodiment of the information push method according to this application; Figure 2b This is a flowchart of yet another embodiment of the information push method according to this application; Figure 3 This is a flowchart of another embodiment of the information push method according to this application; Figure 4 This is a flowchart of an application scenario of the information push method according to this application; Figure 5 This is a schematic diagram of an embodiment of the information push device according to this application; Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing the server embodiments of this application. Detailed Implementation

[0012] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0013] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0014] Figure 1An exemplary system architecture 100 is shown, in which embodiments of the information push method of this application can be applied.

[0015] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, network 104, and server 105. Network 104 serves as a medium for providing communication links between terminal devices 101, 102, and 103 and server 105, and between the terminal devices themselves. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0016] Users can use terminal devices 101, 102, and 103 to interact with other terminal devices or servers 105 via network 104 to receive or send messages, etc. Client application software, such as video playback applications and communication applications, can be installed on terminal devices 101, 102, and 103.

[0017] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to mobile phones, laptops, AR glasses, VR headsets, etc. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software programs or software modules, or as a single software program or software module. No specific limitations are made here.

[0018] Server 105 can be a server that provides various services. For example, in response to a change in contextual information, it determines target recommendation information based on the current contextual information, which includes at least one of scene information, environment information, and user information; it determines a target push method based on the current contextual information and the target recommendation information; and it pushes the target recommendation information using the target push method.

[0019] It should be noted that server 105 can be either hardware or software. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules (for example, used to provide information push services), or as a single software program or software module. No specific limitations are made here.

[0020] It should be noted that the information push method provided in the embodiments of this disclosure can be executed by server 105, terminal devices 101, 102, and 103, or by server 105 and terminal devices 101, 102, and 103 in cooperation with each other. Accordingly, all parts (e.g., units, sub-units, modules, and sub-modules) of the information push device can be entirely located in server 105, entirely located in terminal devices 101, 102, and 103, or separately located in server 105 and terminal devices 101, 102, and 103.

[0021] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0022] Figure 2a A flow 200 is shown as an embodiment of the information push method applicable to this application. The information push method includes the following steps: Step 201: In response to the change in the contextual information, determine the target recommendation information based on the current contextual information.

[0023] In this embodiment, the execution entity (e.g., Figure 1 The server 105 or terminal devices 101, 102, 103 can use data collection devices, such as mobile phones, VR (Virtual Reality) glasses, cameras, etc., to detect the user's context information in real time or periodically, and determine whether the context information has changed. If a change in the context information is detected, that is, if one or more of the scene information, environmental information and user information included in the context information are detected to have changed, then target recommendation information, that is, recommendation information that meets the user's potential target needs, can be determined based on the current context information.

[0024] The scene information can include scene type, scene elements, etc.; scene type can include conference, hotel, restaurant, airport, etc., and scene elements usually match the scene type. For example, if the scene type is scenic spot, scene elements can include ticket office, scenic spot gate, etc.

[0025] Here, the methods for generating scene information may include: collecting current scene data using acquisition devices (such as cameras, VR devices, etc.), preprocessing the current scene data (such as deleting, inserting, etc.); using scene analysis models, such as CNN (Convolutional Neural Network), Visual Transformer, etc., to perform scene analysis on the preprocessed current scene data; using computer vision techniques such as background segmentation, edge detection, and feature point extraction, such as VGG16 (Visual Geometry Group 16-layer) and VGG19 (Visual Geometry Group 19-layer), to determine the feature data of the main objects in the current scene data after scene analysis; and using recognition models or classification models based on the feature data to determine scene information.

[0026] The specific processing procedure is as follows: Figure 2b As shown, the scene data is preprocessed (e.g., inserting new data, deleting abnormal data, etc.). Based on the preprocessed data, the initial space xc is determined. The features of the initial space xc are input into the CNN to generate features of the standard space xo (i.e., features in the standard coordinate system) and baseline features (i.e., features in the standard pose or viewpoint, such as one or more of the following: spatial structure features rc, semantic features sc, category features oc, compression features cc, etc.). The features of the standard space xo are processed by LBS (Linear Blend Skinning) to obtain the features of the transformed space xd (i.e., features in the transformed coordinate system). The LBS is adjusted by parameters W (weight matrix) and Pε (deformation parameter). Further, the features of the standard space xo and the features of the transformed space xd are further processed by VGG to generate offset features (i.e., features that adapt to local image deformation). Deformation features (i.e., features that characterize internal structural changes) are generated based on the offset features and baseline features. High-level detail features, i.e., feature data, are generated based on the deformation features.

[0027] Environmental information may include location information, weather conditions, equipment status, traffic congestion, time information, and cultural background. User information may include user profiles, user surveys, user transaction data, online behavior data, and content preference data.

[0028] Specifically, if the contextual information changes, for example, the scenario type changes from a hotel to an airport, then the target recommendation information can be determined based on the current contextual information, namely user information, scenario information, and environmental information.

[0029] Here, the way the executing entity determines the target recommendation information based on the context information can be in various ways. For example, it can determine the target recommendation information based on the current context information, a preset mapping table between context information and recommendation information, or input the context information into a preset recommendation information generation model to generate the target recommendation information. This application does not limit this.

[0030] The number of target recommendation information can be one or more, and this application does not limit this.

[0031] Step 202: Determine the target push method based on the current context information and target recommendation information.

[0032] In this embodiment, after determining the target recommendation information, the executing entity can determine the target push method of the target recommendation information based on the preset context information and the mapping relationship between the target recommendation information and the target push method; alternatively, the context information and the target recommendation information can be input into a preset push method generation model to generate the target push method. This application does not limit this.

[0033] The targeted push methods can include various types, such as voice push, SMS push, image push, video push, etc.

[0034] It should be noted that if there are multiple pieces of target recommendation information, the target push method corresponding to each piece of target recommendation information can be the same or different, and the target push method corresponding to each piece of target recommendation information can be one or multiple. This application does not limit this.

[0035] Furthermore, if there are multiple target recommendation messages corresponding to the same target push method, the multiple target recommendation messages can be sorted according to a preset sorting rule to form a recommendation list, and the recommendation list can be pushed to the user terminal for display.

[0036] The preset sorting rules can be set according to actual needs, such as the order of execution, urgency, current popularity, distance sorting, etc.

[0037] Among some optional methods, the target push method is determined based on the current contextual information and target recommendation information, including: determining basic recommendation information based on scenario information; and determining target recommendation information based on environmental information, user information, and basic recommendation information.

[0038] In this implementation, contextual information may include scene information, user information, and environment information. The executing entity can input the scene information into a preset large language model to generate basic recommendation information, that is, recommendation information that meets the user's basic potential needs.

[0039] Furthermore, the implementing entity can determine the target recommendation information based on environmental information, user information, and basic recommendation information.

[0040] Here, the implementing entity can filter the basic recommendation information based on environmental information and user information to determine the target recommendation information; alternatively, it can input the environmental information, user information, and basic recommendation information into a preset first generation model to generate the target recommendation information. This application does not limit this approach.

[0041] In addition, the implementing entity can also determine the target recommendation information based on the scene elements included in the environmental information, user information, basic recommendation information, and scene information.

[0042] This implementation method determines basic recommendation information based on scene information; and determines target recommendation information based on environmental information, user information, and basic recommendation information. That is, it first generates basic recommendation information using scene information, and then makes fine adjustments using user information and environmental information. In other words, it uses scene information to constrain the scope of recommendation information, avoids overfitting of user information and environmental information, and effectively improves the accuracy of the generated recommendation information.

[0043] Step 203: Push target recommendation information using the target push method.

[0044] In this embodiment, after determining the target push method, the executing entity can use the target push method to push the target recommendation information.

[0045] Furthermore, after receiving the target recommendation information pushed to them, users can provide feedback on the target recommendation information according to their actual needs.

[0046] Furthermore, after receiving feedback from the user, the executing entity can invoke the corresponding intelligent agent or application for processing.

[0047] Specifically, if the target push method determined based on the current context information (e.g., the environment is 12 noon) and the target recommendation information (e.g., restaurants within a preset range with ratings higher than a preset value) is a mobile pop-up push, then the executing entity can use a mobile pop-up push to recommend restaurants within the preset range with ratings higher than a preset value and remind the user that it's time to dine. Furthermore, if the user selects one of the restaurants, the system automatically opens map navigation and searches all restaurant applications to find the most favorable purchase option for the user.

[0048] Figure 3 A flow 300 is shown as an embodiment of the information push method applicable to this application. The information push method includes the following steps: Step 301: In response to the change in the contextual information, determine the target recommendation information based on the current contextual information.

[0049] In this embodiment, the implementation details and technical effects of step 301 can be found in the description of step 201, and will not be repeated here.

[0050] Step 302: Determine the weights of the influencing factor parameters based on the current contextual information and target recommendation information.

[0051] In this embodiment, the executing entity can determine the weight of the influencing factor parameter based on the current context information and target recommendation information, as well as the preset mapping relationship between the context information and recommendation information and the weight of the influencing factor parameter; alternatively, it can directly input the current context information and target recommendation information into a preset second generation model to generate the weight of the influencing factor parameter. This application does not limit this approach.

[0052] Here, the impact factor parameters may include at least two of the following: urgency parameter, complexity parameter, privacy parameter, interaction strength parameter, and environmental noise parameter.

[0053] Among them, the urgency parameter is used to characterize the urgency of the target recommendation information push, the complexity parameter is used to characterize the complexity of the target recommendation information, the privacy parameter is used to characterize the degree of privacy protection of the target recommendation information, the interaction intensity parameter is used to characterize the degree of interaction between the user and the target recommendation information, and the environmental noise parameter is used to characterize the intensity of sound interference in the current environment corresponding to the target recommendation information.

[0054] Step 303: Determine the target push method based on the weights of the influence factor parameters.

[0055] In this embodiment, after obtaining the weights of the influence factor parameters, the executing entity can sort the influence factor parameters in descending order of weight, and determine the target push method of the target recommendation information based on one or more of the top-ranked influence factor parameters.

[0056] Specifically, the top-ranked influence factor parameters are complexity and privacy. The executing entity can determine the push method that matches the complexity and privacy parameters, such as image push, as the target push method.

[0057] Step 304: Push target recommendation information using the target push method.

[0058] In this embodiment, the implementation details and technical effects of step 304 can be found in the description of step 203, and will not be repeated here.

[0059] In some optional methods, the target push method is determined based on the weight of the impact factor parameters, including: determining the target parameter from the impact factor parameters based on the weight of the impact factor parameters; determining the parameter value of the target parameter based on the current context information and target recommendation information, and determining the push method that matches the parameter value of the target parameter as the target push method.

[0060] In this implementation, after obtaining the weights of the impact factor parameters, the executing entity can sort the impact factor parameters in descending order of weight, and determine one or more impact factor parameters that are ranked first as target parameters.

[0061] Furthermore, the executing entity can determine the parameter values ​​of the target parameters based on the current context information and target recommendation information, and determine the target push method based on the preset mapping relationship between the parameter values ​​of the target parameters and the push method.

[0062] Here, the parameter values ​​of the target parameters can be represented in various ways, such as numerical ratings, level ratings, descriptive evaluations, and comprehensive ratings.

[0063] Specifically, parameter values ​​can be represented by tiered data; the higher the tier, the greater the impact. If the target parameter is an urgency parameter and its value is at the first tier, target recommendation information can be pushed via a pop-up window. If the urgency parameter's value is at the second tier, target recommendation information can be pushed via voice notification.

[0064] If the target parameter is a complexity parameter and its value is at the first level, then target recommendation information can be pushed via image push; if the complexity parameter value is at the second level, then target recommendation information can be pushed via video push.

[0065] If the target parameter is a privacy parameter and the privacy parameter value is at the first level, then the target recommendation information can be pushed using the mobile push method (sending a short message to the user's device through the mobile operating system); if the privacy parameter value is at the second level, then the target recommendation information can be pushed using the AR push method.

[0066] If the target parameter is an interaction intensity parameter, and the parameter value is at the first level, then the target recommendation information can be pushed using a touchscreen push method; if the parameter value is at the second level, then the target recommendation information can be pushed using a voice assistant method; if the parameter value is at the third level, then the target recommendation information can be pushed using an AR push method.

[0067] If the target parameter is the environmental noise level parameter, and the parameter value of the environmental noise level parameter is at the first level, such as a silent environment, then the target recommendation information can be pushed through vibration and text reminders.

[0068] This implementation determines the target parameter based on the weights of the influence factor parameters; it then determines the parameter value of the target parameter based on the current context information and the target recommendation information, and identifies the push method that matches the parameter value of the target parameter as the target push method. This achieves the determination of the target push method based on specific parameter values, thereby improving the accuracy of the determined target push method.

[0069] In some optional methods, the target recommendation information is determined based on environmental information, user information, and basic recommendation information, including: inputting environmental information, user information, and basic recommendation information into a preset first generation model to generate the target recommendation information; and the weights of the influencing factor parameters are determined based on the current context information and the target recommendation information, including: inputting the current context information and the target recommendation information into a preset second generation model to generate the weights of the influencing factor parameters.

[0070] In this implementation, the executing entity can input environmental information, user information, and basic recommendation information into a preset first generation model to generate target recommendation information; further, it can input the target recommendation information and the current context information into a preset second generation model to generate the weights of the influencing factor parameters, and determine the target push method based on the weights of the influencing factor parameters, and push the target recommendation information using the target push method.

[0071] The first and second generative models can be any neural network models, such as large language models or generative adversarial network models.

[0072] Here, the first generative model can be trained based on environmental information, user information, and basic recommendation information samples labeled with target recommendation information, while the second generative model can be trained based on recommendation information and contextual information samples labeled with the weights of influencing factor parameters.

[0073] Among them, environmental information, user information and basic recommendation information samples labeled with target recommendation information can be constructed based on preset heuristic rules.

[0074] Here, heuristic rules are guiding rules or guidelines developed based on experience, knowledge, and intuition. In the absence of a fully accurate algorithm or model, they summarize guiding rules through understanding and analysis of the problem, which are used to guide decision-making, problem-solving, or pattern recognition.

[0075] This implementation improves the accuracy of the generated target recommendation information by inputting environmental information, user information, and basic recommendation information into a preset first generation model; and by inputting the current context information and target recommendation information into a preset second generation model to generate the weights of the influencing factor parameters.

[0076] In some alternative approaches, the method further includes: updating user information based on feedback information received from the user regarding the target recommendation information; and updating a preset first generation model and a preset second generation model based on the updated user information.

[0077] In this implementation, after the executing entity pushes the target recommendation information to the user's terminal, it can monitor the user's feedback information on the target recommendation information in real time or periodically. If feedback information is detected, the user information is updated according to the feedback information.

[0078] The feedback information can include various types, such as click behavior related to the target recommended information, such as click-through rate, click depth (the position of the clicked content in the recommendation list composed of multiple target recommended information), multi-click behavior (continuously clicking multiple recommended information), browsing behavior, such as dwell time, page scrolling behavior, etc.; interactive behavior, such as collection, saving, sharing, liking, etc.; conversion behavior, such as placing an order, subscribing, following, etc.; evaluation behavior, such as rating, commenting, etc.

[0079] Furthermore, the executing entity can update the model parameters of the first and second generation models based on the updated user information.

[0080] This implementation responds to user feedback regarding target recommendation information, updates user information based on the feedback, and then updates the preset first generation model and the preset second generation model based on the updated user information. This achieves timely model updates and helps to further improve the accuracy of the generated target recommendation information.

[0081] In some optional methods, scene information includes scene type, which includes: hotel, airport, conference, scenic spot, restaurant, forest, river.

[0082] In this implementation, in response to the detection of a change in contextual information, the executing entity can determine basic recommendation information based on the contextual information, and then determine target recommendation information based on the basic recommendation information, user information, and environmental information.

[0083] The scene information can include scene type, which can include hotels, airports, conferences, scenic spots, restaurants, forests, rivers, etc.

[0084] Specifically, the implementing entity can use the VR glasses worn by the user to collect scene data and identify the scene type and elements based on the scene data. If the implementing entity switches from an airport to a scenic area based on the detected scene type, and the user is standing at the entrance of the scenic area, basic recommendation information can be determined based on the scene type and scene elements, such as the scenic area name, the main gate, and the ticket office. Based on user information (such as having children), environmental information (such as rain in two hours), and basic recommendation information, target recommendation information can be determined. There can be multiple target recommendation information items, such as three: Recommendation 1: The ticket office is located at location A, and the ticket purchase methods are method M and method N, with method M being the most favorable; Recommendation 2: The amusement area within the scenic area is located at location C, the public toilet area is located at location D, and the scenic viewing area is located at location L; Recommendation 3: It will rain in two hours, please take precautions or evacuate in advance. Furthermore, the target push method is determined based on the target recommendation information and contextual information. For example, the target push method for recommendation information 1 and recommendation information 2 is VR push, and the target push method for recommendation information 3 is mobile push, and the target recommendation information is pushed using the target push method.

[0085] This implementation method generates and pushes target recommendation information under different scene types by setting scene types including: hotels, airports, conferences, scenic spots, restaurants, forests, and rivers.

[0086] Compared with the embodiment corresponding to FIG2, the above embodiments of this application, the process 300 in this embodiment, reflects the response to the determination of changes in context information, determining target recommendation information based on the current context information; determining the weight of the influencing factor parameter based on the current context information and the target recommendation information; determining the target push method based on the weight of the influencing factor parameter; and pushing the target recommendation information using the target push method, taking into account the influence of the weight of the influencing factor parameter on the push method, thereby improving the timeliness and effectiveness of information push.

[0087] See also Figure 4 , Figure 4 This is a flowchart of an application scenario of the information push method according to this embodiment.

[0088] exist Figure 4In the application scenario, the executing entity can use the image acquisition device worn by the user to collect scene data and identify the scene information included in the context information 401 based on the scene data, such as scene type and scene elements. If the executing entity detects that the scene type has changed from an airport to a restaurant, such as when a user enters a Western restaurant, it can determine basic recommendation information based on the scene type and scene elements, such as tables, chairs, and decorative paintings. Furthermore, the user information and environmental information included in the basic recommendation information and context information are input into the preset first generation model 402 to generate target recommendation information. The number of target recommendation information can include multiple items, such as 3 items, namely recommendation information 1: The current restaurant's dish features are XXX, and the dish that matches the user's preference is dish B; recommendation information 2: Is it necessary to display dining etiquette, tableware placement, and dining order; recommendation information 3: If the meal is not over, the tableware placement method is YYY, and is it necessary to display animation?

[0089] Furthermore, the target recommendation information and contextual information are input into the preset second generation model 403 to generate the weights of the influencing factor parameters 404 (urgency parameter, complexity parameter, privacy parameter, interaction intensity parameter, and environmental noise parameter). The target parameters, such as the interaction intensity parameter, are determined based on the weights of the influencing factor parameters. The parameter values ​​of the target parameters are determined based on the target recommendation information and contextual information. The push method that matches the parameter value of the target parameters is determined as the target push method 405, such as VR push. The target recommendation information is then pushed using the target push method, such as VR push target recommendation information.

[0090] Furthermore, if user feedback information 406 regarding the target recommendation information is detected, such as the user selecting to display dining etiquette, tableware placement, and dining order, the intelligent agent 407 can be invoked to generate and display the specific dining etiquette, tableware placement, and dining order.

[0091] Furthermore, the user information is updated based on the feedback information and the execution results of the feedback information, and the first generation model and the second generation model are updated based on the updated user information.

[0092] The information push method provided in the embodiments of this disclosure determines target recommendation information based on the current context information in response to a change in the context information; determines the target push method based on the current context information and the target recommendation information; and pushes the target recommendation information using the target push method, thereby effectively improving the timeliness and effectiveness of pushing recommendation information.

[0093] Further reference Figure 5 As an implementation of the methods shown in the above figures, this application provides an embodiment of an information push device, which is similar to... Figure 1Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0094] like Figure 5 As shown, the information push device 500 of this embodiment includes: an acquisition module 501, a determination module 502, and a push module 503.

[0095] The acquisition module 501 can be configured to determine target recommendation information based on the current context information in response to a change in the context information. The context information includes at least one of scene information, environment information, and user information.

[0096] The determination module 502 can be configured to determine the target push method based on the current context information and target recommendation information.

[0097] The push module 503 can be configured to push the target recommendation information using a target push method.

[0098] In some optional embodiments of this example, the determining module further includes a first determining unit and a second determining unit, wherein the first determining unit is configured to determine the weight of the influencing factor parameter based on the current context information and the target recommendation information; and the second determining unit is configured to determine the target push method based on the weight of the influencing factor parameter.

[0099] In some optional embodiments of this example, the second determining unit may be further configured to determine the target parameter based on the weight of the influence factor parameter. Based on the current contextual information and target recommendation information, the parameter values ​​of the target parameters are determined, and the push method that matches the parameter values ​​of the target parameters is determined as the target push method.

[0100] In some optional embodiments of this example, the acquisition module further includes a third determining unit and a fourth determining unit, wherein the third determining unit is configured to determine basic recommendation information based on the scene information; and the fourth determining unit is configured to determine target recommendation information based on environmental information, user information, and the basic recommendation information.

[0101] In some optional embodiments of this example, the fourth determining unit is configured to input environmental information, user information, and basic recommendation information into a preset first generation model to generate target recommendation information; the first determining unit is configured to input current context information and target recommendation information into a preset second generation model to generate weights of influencing factor parameters.

[0102] In some optional embodiments of this invention, the device further includes a feedback module and an update module. The feedback module is configured to update the user information based on the feedback information received from the user regarding the target recommendation information. The update module is configured to update a preset first generation model and a preset second generation model based on the updated user information.

[0103] In some optional ways of this embodiment, the scene types include: hotel, airport, conference, scenic spot, restaurant, forest, and river.

[0104] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in this disclosed technical solution all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0105] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0106] like Figure 6 The diagram shown is a block diagram of an electronic device according to an embodiment of the information push method of this application.

[0107] 600 is a block diagram of an electronic device according to an embodiment of the information push method of this application. For example... Figure 6 As shown, the electronic device includes one or more processors 601, a memory 602, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take the 601 processor as an example.

[0108] The memory 602 is the non-transitory computer-readable storage medium provided in this application. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the information push method provided in this application. The non-transitory computer-readable storage medium of this application stores computer instructions for causing a computer to perform the information push method provided in this application.

[0109] Memory 602, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the information push method in the embodiments of this application (e.g., appendix). Figure 5 The acquisition module 501, determination module 502, and push module 503 are shown. The processor 601 executes various functional applications and data processing of the server by running non-transient software programs, instructions, and modules stored in the memory 602, thereby realizing the information push method in the above method embodiment.

[0110] The memory 602 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the information-pushing electronic device. Furthermore, the memory 602 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 602 may optionally include memory remotely located relative to the processor 601, and these remote memories can be connected to the information-pushing electronic device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] The electronic device for the information push method may further include an input device 603 and an output device 604. The processor 601, memory 602, input device 603, and output device 604 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0112] Input device 603 can receive input digital or character information, as well as key signal inputs related to user settings and function control of electronic devices for quality monitoring of live video streams, such as touchscreens, keypads, mice, trackpads, touchpads, joysticks, one or more mouse buttons, trackballs, joysticks, etc. Output device 604 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The display device may include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device may be a touchscreen.

[0113] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] These computational programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0117] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0118] The technical solution according to the embodiments of this application effectively improves the timeliness and effectiveness of pushing recommendation information.

[0119] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0120] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An information push method, the method comprising: In response to a change in the context information, target recommendation information is determined based on the current context information, wherein the context information includes at least one of scene information, environment information, and user information; Based on the current context information and the target recommendation information, the target push method is determined; The target recommendation information is pushed using the target push method described above.

2. The method according to claim 1, wherein, The step of determining the target push method based on the current context information and the target recommendation information includes: Based on the current context information and the target recommendation information, the weights of the influencing factor parameters are determined. The influencing factor parameters include at least two of the following: urgency parameter, complexity parameter, privacy parameter, interaction strength parameter, and environmental noise parameter. The target push method is determined based on the weights of the aforementioned impact factor parameters.

3. The method according to claim 2, wherein, The determination of the target push method based on the weights of the influence factor parameters includes: Based on the weights of the impact factor parameters, the target parameters are determined from the impact factor parameters; Based on the current context information and the target recommendation information, the parameter value of the target parameter is determined, and the push method that matches the parameter value of the target parameter is determined as the target push method.

4. The method according to claim 2, wherein, The contextual information includes: scene information, environment information, and user information, and the determination of target recommendation information based on the current contextual information includes: Based on the scenario information, basic recommendation information is determined; Based on the environmental information, the user information, and the basic recommendation information, target recommendation information is determined.

5. The method according to claim 4, wherein, The step of determining target recommendation information based on the environmental information, the user information, and the basic recommendation information includes: The environmental information, user information, and basic recommendation information are input into a preset first generation model to generate target recommendation information; and The step of determining the weights of the influencing factor parameters based on the current context information and the target recommendation information includes: The current context information and the target recommendation information are input into a preset second generation model to generate the weights of the influencing factor parameters.

6. The method according to claim 5, further comprising: In response to receiving feedback from the user regarding the target recommendation information, the user information is updated based on the feedback information; The preset first generation model and the preset second generation model are updated based on the updated user information.

7. An information push device, the device comprising: The acquisition module is configured to determine target recommendation information based on the current context information in response to a change in the determined context information, wherein the context information includes at least one of scene information, environment information, and user information; The determination module is configured to determine the target push method based on the current context information and the target recommendation information; The push module is configured to push the target recommendation information using the target push method.

8. The apparatus according to claim 7, wherein, The determining module includes: The first determining unit is configured to determine the weights of the influencing factor parameters based on the current context information and the target recommendation information. The influencing factor parameters include at least two of the following: urgency parameter, complexity parameter, privacy parameter, interaction strength parameter, and environmental noise parameter. The second determining unit is configured to determine the target push method based on the weights of the influence factor parameters.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores information that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

Images