WO2020168841A1 - 网络资源推送方法、装置及存储介质 - Google Patents

网络资源推送方法、装置及存储介质 Download PDF

Info

Publication number
WO2020168841A1
WO2020168841A1 PCT/CN2020/070173 CN2020070173W WO2020168841A1 WO 2020168841 A1 WO2020168841 A1 WO 2020168841A1 CN 2020070173 W CN2020070173 W CN 2020070173W WO 2020168841 A1 WO2020168841 A1 WO 2020168841A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
scene
network resource
information
current
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/070173
Other languages
English (en)
French (fr)
Inventor
姚新明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to US17/426,419 priority Critical patent/US11483253B2/en
Publication of WO2020168841A1 publication Critical patent/WO2020168841A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H04L47/803—Application aware
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/76—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
    • H04L47/762—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions triggered by the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/78—Architectures of resource allocation
    • H04L47/781—Centralised allocation of resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H04L47/808—User-type aware
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1021—Server selection for load balancing based on client or server locations

Definitions

  • This application relates to the field of network technology, and in particular to methods, devices, storage media and electronic equipment for pushing network resources.
  • HTML Hyper-Text Markup Language
  • Page recommendation methods analyze and judge user behavior and other data through page embedding, so that users may be interested in recommendations Information about products, news, songs, videos, etc.
  • the embodiments of the present application propose methods, devices, storage media, and electronic equipment for pushing network resources to implement scenario-based pushing of network resources.
  • a method for pushing network resources including:
  • the scene judgment model established in advance is used to determine the scene where the user is located;
  • Receive the user’s current environment information sent by the device use the scene judgment model to determine the user’s current scene corresponding to the user’s current environment information according to the user’s current environment information, and based on the user’s current scene and the network the user visits
  • the association model between resource types pushes users the type of network resources corresponding to the user's current scene.
  • the current environment information of the user sent by the receiving device includes: current device data collected by the sensor sent by the receiving device.
  • the environmental information where the user accesses the network resource is obtained in the following ways:
  • the scenario where the user is determined includes:
  • the environment location information and the environment photos are input into a pre-established scene judgment model to obtain a corresponding scene.
  • the network resource information accessed by the user reported by the device includes:
  • the content tags include one or more of the following: news information tags and streaming media tags.
  • the device is an AR device, or a VR device, or an MR device.
  • pushing for the user a type of network resource corresponding to the scene where the user is currently located includes:
  • search for the association model between the scene of the user corresponding to the user and the type of network data accessed by the user determine the type of network data corresponding to the current scene according to the association model, and determine the type of network data according to Users push network resources.
  • a network resource pushing device which includes:
  • the scene judgment model saving module saves the scene judgment model, which is used to judge the scene according to the environmental information
  • the receiving and scene determination module receives the network resource information reported by the device and the environment information when the user accesses the network resource, and inputs the environment information when the user accesses the network resource into the scene determination model to obtain the scene where the user is located.
  • the user’s current scene and the network resource information accessed by the user are sent to the association model establishment module; the user’s current environment information sent by the device is received, and the user’s current environment information is input into the scene judgment model to obtain the user’s current scene, and The user's current scene is sent to the push module;
  • the association model establishment module establishes an association model between the user's scene and the type of network resource accessed by the user based on the user's scene and the user's access network resource information sent from the receiving and scene judgment module;
  • the push module receives the user's current scene sent from the receiving and scene determination module, and pushes the user's current scene to the user's current scene based on the association model between the user's scene established by the association model establishment module and the type of network resources the user accesses The corresponding type of network resource.
  • the environment information where the user accesses network resources received by the receiving and scene determination module includes:
  • Environmental location information collected by the device's own sensor, and environmental photos collected by the device's own camera are collected by the device's own sensor, and environmental photos collected by the device's own camera.
  • the network resource information accessed by the user reported by the device and received by the receiving and scene determination module includes:
  • the content tags clicked by the user and received by the receiving and scene determination module include one or more of the following: news information tags and streaming media tags.
  • the device is an AR device, or a VR device, or an MR device.
  • a non-transitory computer-readable storage medium that stores instructions that, when executed by a processor, causes the processor to perform the steps of the network resource pushing method described above.
  • An electronic device includes the non-transitory computer-readable storage medium as described above, and the processor that can access the non-transitory computer-readable storage medium.
  • the embodiment of this application establishes an association model between the user's current location and the type of network resource accessed by the user, and then when receiving the user's current environment information sent by the device, the corresponding scene is determined according to the user's current environment information, According to the association model between the scene where the user is located and the type of network resource accessed by the user, the network resource of the corresponding type is pushed to the user, thereby realizing the push of the network resource to the user based on the scene.
  • FIG. 1A is a schematic diagram of the application of the network resource pushing method according to an embodiment of this application.
  • FIG. 1B is a flowchart of a method for pushing network resources provided by an embodiment of this application.
  • FIG. 2 is a flowchart of a method for establishing an association model between a user's scene and the types of network resources accessed by the user according to an embodiment of the application;
  • FIG. 3 is a flowchart of a method for pushing network resources to a user according to an established association model between the user's scene and the type of network resource accessed by the user according to another embodiment of the application;
  • FIG. 4 is a schematic structural diagram of a network resource pushing device provided by an embodiment of the application.
  • FIG. 5 is a schematic structural diagram of an electronic device involved in an embodiment of the application.
  • the embodiments of the present application provide a network resource recommendation method, device, storage medium, and electronic equipment.
  • FIG. 1A is a schematic diagram of the application of the method for recommending network resources according to an embodiment of this application.
  • the scenario where the network resource recommendation method is applied includes: a device 10 and a server 20.
  • the device 10 and the server 20 may be connected through a communication network.
  • the communication network includes a wireless network and a wired network, wherein the wireless network includes one or a combination of a wireless wide area network, a wireless local area network, a wireless metropolitan area network, and a wireless personal network.
  • the network includes network entities such as routers and gateways, which are not shown in the figure.
  • the device 10 can exchange information with the server 20 through a communication network, for example, can download an application (such as a shopping application or a map application, etc.) from the server 20.
  • an application such as a shopping application or a map application, etc.
  • the server 20 can be used to receive the network resource information accessed by the user and the environmental information when the user accesses the network resource reported by the device 10; according to the environmental information when the user accesses the network resource, a pre-established scene determination model is used to determine The scene where the user is located; establish an association model between the scene where the user is located and the type of network resources the user accesses; receive the user’s current environment information sent by the device 10, and use the scene judgment model to determine the relationship with the user based on the user’s current environment information.
  • the current scene corresponding to the current environment information according to the association model between the user's current scene and the type of network resource accessed by the user, pushes the user a type of network resource corresponding to the determined current scene.
  • the device 10 can be used to receive the user's input on the device to authorize instructions for pushing network resources; detect that the user visits a webpage, and record the network access data of the user's visit to the webpage in real time; at the same time, obtain current information from its own cameras and sensors in real time.
  • Environmental information upload the user's identification information, user's network access data and current environmental information to the server 20; receive the network resources pushed by the server according to the current environmental information.
  • FIG. 1B is a flowchart of a method for pushing network resources provided by an embodiment of this application, and the specific steps are as follows:
  • Step 101 The server receives the network resource information accessed by the user and the environment information where the user accesses the network resource reported by the device.
  • Step 102 The server uses a pre-established scene determination model to determine the scene where the user is located according to the environment information where the user is located when accessing the network resource.
  • the scene judgment model is used to judge the scene according to the environmental information.
  • Step 103 The server establishes an association model between the user's scene and the type of network resource accessed by the user.
  • the server can continuously execute the above steps 101-103 for each user in real time, so that the established association model between the user's scene and the type of network resource accessed by the user is continuously improved.
  • Step 104 The server receives the user's current environment information sent by the device, and uses the scene judgment model to determine the user's current scene corresponding to the user's current environment information according to the user's current environment information.
  • the association model between the types of network resources accessed by the user pushes the user the type of network resources corresponding to the determined user's current scene.
  • step 104 After the association model between a user's user scene and the type of network resource accessed by the user is established, step 104 may be executed.
  • the server can recommend to the user a commodity similar to the commodity that the user has visited or purchased in the scene, so as to implement scene-based recommendation.
  • Fig. 2 is a flowchart of a method for establishing an association model between a user's scene and the type of network resource accessed by the user according to an embodiment of the application, and the specific steps are as follows:
  • Step 201 The user inputs an authorization instruction for pushing network resources on the device.
  • Devices such as AR (Augmented Reality) devices, VR (Virtual Reality, virtual reality) devices, MR (Mixed Reality) devices, or other mobile devices (such as mobile phones).
  • AR Augmented Reality
  • VR Virtual Reality, virtual reality
  • MR Mated Reality
  • mobile phones such as mobile phones.
  • the authorization instruction includes authorization to the hardware device for obtaining environmental information.
  • the hardware device includes, for example, a camera and various sensors built into the device.
  • Step 202 The device detects that the user visits a webpage, and records the network access data of the user visiting the webpage in real time; meanwhile, it obtains current environment information from its own sensors and cameras in real time.
  • the user's network access data includes: the webpage address the user visits, the content label the user clicks (including: content type, content name, content attribute, etc.), the length of time the user stays on the webpage, etc.
  • Content types such as news, streaming media, commodities, etc., content attributes such as commodity inventory, etc.
  • Sensors such as gyroscopes, infrared sensors, distance sensors, etc., mainly collect the location information of the environment, including information such as geographic location and distance between objects.
  • the camera is used to capture images of the environment.
  • the gyroscope is also called an angular velocity sensor, and the measured physical quantity is, for example, the angular velocity of rotation when the device is deflected and tilted. Through the gyroscope, the movement status of the device can be detected.
  • Step 203 The device uploads the user's identification information, the user's network access data and current environment information to the server.
  • the device can locally cache the user's network access data and current environment information for the current page, and upload the user's network access data and current environment information for the current page to the application server before the current page is closed or redirected to ensure the upload The accuracy of the data, that is, to ensure the correspondence between the network access data of the user's current page and the current environment information.
  • Step 204 The server receives the user's identification information, the user's network access data and the current environment information sent by the device, and determines the current scene of the user according to the current environment information.
  • the artificial intelligence learning system can be used in advance to learn the environmental images in various scenes collected by the camera and combined with the environmental location information collected by the sensors to obtain the scene judgment model.
  • the server uses the scene judgment model to send the device to the device. Analyze the incoming current environment information to get the corresponding scene.
  • the server can analyze each image of the video collected by the camera, and infer the specific scene of the user using the device based on the environmental information, character information, and object information in the image.
  • Step 205 The server establishes an association model between the user's current scene and the type of network data accessed by the user according to the user's current scene and the user's network access data, and the association model is identified by the user's identification information.
  • a dictionary can be established between the user's scene and the type of network data the user accesses.
  • the server can perform the above steps 201-205 for each user in real time and continuously, so that the established association model between each user in different scenarios and the types of network resources accessed by the user is continuously improved.
  • Fig. 3 is a flowchart of a method for pushing network resources to a user according to an established association model between the user’s location and the type of network resource accessed by the user according to another embodiment of the application. The specific steps are as follows:
  • Step 301 The device determines that the user has authorized the network resource push. Wherein, this step includes the device determining that the user authorizes the hardware device that collects current environmental information.
  • Step 302 The device collects current environmental information in real time through its own sensors and cameras, and reports the collected environmental information and user identification information to the server in real time.
  • Step 303 The server receives the environment information sent by the device, and uses the scene judgment model to determine the corresponding scene according to the environment information.
  • Step 304 The server searches for an association model between the scene of the user corresponding to the user and the type of network data accessed by the user according to the identification information of the user, and determines the type of network data corresponding to the scene determined in step 303 according to the association model.
  • Step 305 The server searches for network data matching the network data type determined in step 304, and pushes the found network data to the user.
  • the server may display the pushed network data at the preset recommended location of the application page or HTML page accessed by the user.
  • Network data can be: URLs, text or pictures, etc.
  • the scenario targeted by this example is: a user uses an AR device in an indoor environment to shop on a shopping APP.
  • the AR device collects environmental pictures through the camera, collects environmental location information through the sensor, and records the user's network access data (such as: the name of the shopping APP visited by the user, the address of the visited webpage, the clicked product label (such as: name, inventory, etc.) )).
  • the user's network access data such as: the name of the shopping APP visited by the user, the address of the visited webpage, the clicked product label (such as: name, inventory, etc.)
  • the AR device determines that the user is about to jump to or close the current webpage, and then collects the environmental pictures collected by the camera during the user’s stay on the webpage, the environmental location information collected by the sensor, and the recorded user’s access data to the webpage and the user’s information on the webpage.
  • the length of stay is sent to the server.
  • the server uses the pre-established scene judgment model to calculate according to the environmental pictures collected by the camera and the environmental location information collected by the sensors from the AR device, and obtains that the user's scene is indoor and relatively static, and determines that the user is sitting on the sofa.
  • the scene judgment model can judge the scene according to the following elements:
  • Objects In this example, it is a sofa and an adult sits on a sofa, table and chair, TV, refrigerator, oven, table, etc.;
  • the current scene is an indoor family living room and is relatively static, and the user is sitting on the sofa.
  • Whether the angle of view is still or moving is inferred, for example, by analyzing the continuity between environmental pictures.
  • the server determines that the user has a high probability of accessing a certain type of merchandise when using the shopping APP in this scene. Search for the highest-selling product in this category of products, and push the label of the product to the recommended location of the web page the user is visiting.
  • the server also determines that there are children in the scene according to the scene judgment model, it will push the related content of children's books and stationery to the page of the shopping app that the user is viewing.
  • the viewing angle is determined to be constantly moving according to the scene determination model, you can also push news or family fun videos related to furniture decoration to the user;
  • the server can also count the types of products that the user has accessed most on the shopping APP in the same scenario within the most recent preset time period, and push relevant information about the types of products to the user.
  • the scenario targeted by this example is: a user uses an AR device in a mobile environment.
  • the AR device collects environmental pictures through a camera, and collects environmental location information through a sensor.
  • the AR device sends the environmental picture collected by the camera and the environmental location information collected by the sensor to the server.
  • the server captures visual information within the focus range of the user's field of view according to the environmental pictures collected by the camera, determines whether the user is looking for a restaurant or viewing a certain type of goods, and determines the geographic location of the user based on the environmental location information collected by the sensor. For example, the server can analyze the text appearing in the environmental picture, confirm that it is a restaurant name, and then determine that the user is looking for a restaurant.
  • the server determines that the user is indeed looking for a restaurant based on the analysis result within the latest preset time period, and records the user identification, time, geographic location, and user behavior: looking for the relationship between the restaurant.
  • the server when the server receives the environmental picture collected by the camera and the environmental location information collected by the sensor from the AR device, it can determine the user behavior according to the association relationship established in step 4), for example: if the user behavior is searching Restaurant, the restaurant information in the current geographic location is pushed to the visual location of the AR device through voice or images.
  • the server can perform real-time analysis of step 3) based on the environmental pictures and environmental location information continuously sent by the AR device, and if it is found that the user's behavior in the same geographic location and the same time period has changed according to the analysis result, then Update the user behavior in the association relationship recorded in step 4).
  • This example is aimed at users who use AR devices to frequently access shopping apps regardless of time and place.
  • the AR device collects environmental pictures through the camera, collects environmental location information through the sensor, and records the user's network access data (such as: the name of the shopping APP visited by the user, the address of the web page visited, and the product label clicked (such as: name, inventory, etc.) )).
  • the user's network access data such as: the name of the shopping APP visited by the user, the address of the web page visited, and the product label clicked (such as: name, inventory, etc.)
  • the AR device sends the environmental picture collected by the camera, the environmental location information collected by the sensor, the recorded user's access data to the webpage, and the user's staying time on the webpage to the server.
  • the server determines that the user frequently visits shopping apps regardless of time and location based on the environmental pictures collected by the camera, the environmental location information collected by the sensors, the user's access data to the webpage, and the user's stay on the webpage.
  • This example is aimed at a user using an AR device to access the map APP.
  • the AR device collects environmental pictures through the camera, collects environmental location information through the sensor, and records the user's network access data (such as the name of the map APP accessed by the user, the web address accessed, etc.).
  • the AR device sends the environmental picture collected by the camera, the environmental location information collected by the sensor, and the recorded user's access data to the webpage to the server.
  • the server uses the environmental pictures collected by the camera and the environmental location information collected by the sensors to analyze the pedestrian flow information on the road using a preset algorithm. At the same time, it is authorized by the user to report the geographic location information to form the data information of the pedestrian flow on the road at the geographic location.
  • the traffic data information is pushed to the page of the map APP used by the user in real time.
  • the server when the server finds that the number of people using the map APP through AR, VR, and MR devices has reached a preset number, it can calculate an adjusted route for AR, VR, and MR device users based on the calculated road congestion status information, and Push to users.
  • Fig. 4 is a schematic structural diagram of a network resource pushing device provided by an embodiment of the application.
  • the device is located on a server.
  • the device mainly includes: a scene judgment model storage module 41, a receiving and scene judgment module 42, an association model establishment module 43, and a pushing module 44, of which:
  • the scene judgment model saving module 41 saves the scene judgment model, which is used to judge the scene according to the environmental information.
  • the receiving and scene determination module 42 receives the network resource information that the user accesses and the environment information where the user accesses the network resource reported by the device, and inputs the environment information where the user accesses the network resource into the scene determination saved by the scene determination model storage module 41 Model to obtain the user's scene, send the user's scene and the network resource information accessed by the user to the association model establishment module 43; receive the user's current environment information sent by the device, and input the user's current environment information into the scene judgment
  • the scene determination model saved by the model saving module 41 obtains the current scene of the user, and sends the current scene of the user to the pushing module 44.
  • the association model establishment module 43 establishes an association model between the user's scene and the type of network resource accessed by the user according to the scene where the user is located and the network resource information the user visits from the receiving and scene determination module 42.
  • the pushing module 44 receives the user’s current scene sent from the receiving and scene determination module 42, and pushes the user’s current scene based on the association model between the user’s scene and the type of network resources accessed by the user established by the association model establishment module 43.
  • the type of network resource corresponding to the current scene is not limited to the current scene.
  • the environment information received by the receiving and scene determination module 42 when the user accesses network resources includes: environment location information collected by the device's own sensor, and environment photos collected by the device's own camera.
  • the network resource information reported by the device and reported by the device received by the receiving and scene determination module 42 includes: the webpage address accessed by the user and the content tag clicked; or including: the webpage address accessed by the user, the clicked content tag and the user The length of time spent on the page.
  • the content tags clicked by the user received by the receiving and scene determination module 42 include: news tags, or/and streaming media tags.
  • the aforementioned devices are AR devices, or VR devices, or MR devices.
  • the embodiment of the present application also provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores instructions, which when executed by a processor causes the processor to execute steps 101-104, or Steps 201-205, or steps of the network resource pushing method described in any one of steps 301-305.
  • the storage medium may include: read only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and so on.
  • An embodiment of the present application further provides an electronic device, including the non-transitory computer-readable storage medium as described above, and the processor that can access the non-transitory computer-readable storage medium.
  • the electronic device in the embodiment of the present application is, for example, a computer device, which may be the server or device in the embodiment of the present application.
  • FIG. 5 shows the structure of an electronic device involved in an embodiment of the present application.
  • the electronic device may include one or more processing core processors 501, one or more memories 502, a power supply 503, an input unit 504 and other components.
  • the memory 502 is a computer-readable storage medium.
  • the structure shown in FIG. 5 does not constitute a limitation on the server or the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange different components. among them:
  • the processor 501 is the control center of the computing device. It uses various interfaces and lines to connect various parts of the entire electronic device. It runs or executes software programs and/or modules stored in the memory 502, and calls Data, perform various functions of electronic equipment and process data, so as to monitor the electronic equipment as a whole.
  • the processor 501 may include one or more processing cores; the processor 501 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, user interface, and application programs, etc.
  • the adjustment processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 501.
  • the memory 502 can be used to store software programs and modules.
  • the processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502.
  • the memory 502 may mainly include a storage program area and a storage data area.
  • the storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of electronic equipment, etc.
  • the memory 502 may include a high-speed random access memory, and may also include a non-volatile (non-transitory) memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 502 may further include a memory controller to provide the processor 501 with access to the memory 502.
  • the electronic device also includes a power supply 503 for supplying power to various components.
  • the power supply 503 may be logically connected to the processor 501 through a power management system, so that functions such as charging, discharging, and power consumption management can be managed through the power management system.
  • the power supply 503 may also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components.
  • the electronic device may further include an input unit 504, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • an input unit 504 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • the electronic device may also include a display unit, etc., which will not be repeated here.
  • the processor 501 in the computer will load the executable file corresponding to the process of one or more application programs into the memory 502 according to the following instructions, and the processor 501 will run the executable file stored in The application program in the storage 502 realizes the method for pushing network resources of the server or device in the foregoing embodiment.
  • the embodiment of this application establishes an association model between the user's current location and the type of network resource accessed by the user, and then when receiving the user's current environment information sent by the device, the corresponding scene is determined according to the user's current environment information, According to the association model between the user's scene and the type of network resource accessed by the user, the corresponding type of network resource is pushed for the user, thereby realizing the push of the user's network resource based on the scene.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种网络资源推送方法、装置及存储介质。方法包括：服务器接收设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息(101)；服务器根据用户访问网络资源时所在的环境信息，采用预先建立的场景判定模型确定用户所在的场景(102)；服务器建立用户所在场景与用户访问的网络资源类型之间的关联模型(103)；服务器接收设备发来的用户当前所在的环境信息，根据用户当前所在的环境信息，采用场景判定模型确定与用户当前所在的环境信息对应的当前场景，根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与确定的当前场景对应类型的网络资源(104)。

Description

网络资源推送方法、装置及存储介质
本申请要求于2019年02月21日提交的申请号为201910128860.6、发明名称为“网络资源推送方法、装置及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及网络技术领域，尤其涉及网络资源推送方法、装置及存储介质和电子设备。
背景技术
现有的资讯类、流媒体、商城等应用或HTML(Hyper-Text Markup Language，超文本标记语言)页面的推荐方法通过页面埋点对用户行为等数据分析和研判，以便为用户推荐可能感兴趣的商品、新闻资讯、歌曲、视频等信息。
发明内容
本申请实施例提出网络资源推送方法、装置及存储介质和电子设备，以实现基于场景的网络资源推送。
本申请的技术方案是这样实现的：
一种网络资源推送方法，该方法包括：
接收设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息；
根据用户访问网络资源时所在的环境信息，采用预先建立的场景判定模型确定用户所在的场景；
建立用户所在场景与用户访问的网络资源类型之间的关联模型；
接收设备发来的用户当前所在的环境信息，根据用户当前所在的环境信息，采用场景判定模型确定与用户当前所在的环境信息对应的用户当前所在 场景，根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源。
所述接收设备发来的用户当前所在的环境信息包括：接收设备发来的通过传感器采集的当前设备数据。
所述用户访问网络资源时所在的环境信息通过以下方式获取：
通过设备自带的传感器采集环境位置信息，通过设备自带的摄像头采集环境照片；
所述确定用户所在的场景包括：
将所述环境位置信息与所述环境照片输入预先建立的场景判定模型，得到对应的场景。
所述设备上报的用户访问的网络资源信息包括：
用户访问的网页地址和点击的内容标签；
或者包括：用户访问的网页地址、点击的内容标签和用户在网页的停留时长。
所述内容标签包括以下中的一个或多个：新闻资讯标签、流媒体标签。
所述设备为AR设备，或者VR设备，或者MR设备。
所述根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源包括：
根据用户的标识信息，查找该用户对应的用户所在场景与用户访问的网络数据类型之间的关联模型，根据该关联模型确定与当前场景对应的网络数据类型，并根据该确定的网络数据类型为用户推送网络资源。
一种网络资源推送装置，该装置包括：
场景判定模型保存模块，保存场景判定模型，该模型用于根据环境信息判定场景；
接收及场景判定模块，接收到设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息，将用户访问网络资源时所在的环境信 息输入场景判定模型，得到用户所在的场景，将用户所在的场景和用户访问的网络资源信息发送给关联模型建立模块；接收设备发来的用户当前所在的环境信息，将用户当前所在的环境信息输入场景判定模型，得到用户当前所在的场景，将用户当前所在的场景发送给推送模块；
关联模型建立模块，根据接收及场景判定模块发来的用户所在的场景和用户访问的网络资源信息，建立用户所在场景与用户访问的网络资源类型之间的关联模型；
推送模块，接收到接收及场景判定模块发来的用户当前所在的场景，根据关联模型建立模块建立的用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源。
所述接收及场景判定模块接收的用户访问网络资源时所在的环境信息包括：
通过设备自带的传感器采集的环境位置信息，通过设备自带的摄像头采集的环境照片。
所述接收及场景判定模块接收的设备上报的用户访问的网络资源信息包括：
用户访问的网页地址和点击的内容标签；
或者包括：用户访问的网页地址、点击的内容标签和用户在网页的停留时长。
所述接收及场景判定模块接收的用户点击的内容标签包括以下中的一个或多个：新闻资讯标签、流媒体标签。
所述设备为AR设备，或者VR设备，或者MR设备。
一种非瞬时计算机可读存储介质，所述非瞬时计算机可读存储介质存储指令，所述指令在由处理器执行时使得所述处理器执行如上所述的网络资源推送方法的步骤。
一种电子设备，包括如上所述的非瞬时计算机可读存储介质、以及可 访问所述非瞬时计算机可读存储介质的所述处理器。
本申请实施例通过建立用户所在场景与用户访问的网络资源类型之间的关联模型，之后当接收到设备发来的用户当前所在的环境信息时，根据用户当前所在的环境信息确定对应的场景，根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送对应类型的网络资源，从而实现了基于场景对用户进行网络资源推送。
附图说明
图1A为本申请实施例的网络资源推送方法应用示意图；
图1B为本申请一实施例提供的网络资源推送方法流程图；
图2为本申请一实施例提供的建立用户所在场景与用户访问的网络资源类型之间的关联模型的方法流程图；
图3为本申请另一实施例提供的根据建立的用户所在场景与用户访问的网络资源类型之间的关联模型为用户推送网络资源的方法流程图；
图4为本申请实施例提供的网络资源推送装置的结构示意图；
图5为本申请实施例所涉及的电子设备的结构示意图。
具体实施方式
发明人经过分析发现：现有的网络资源推荐方法中，通常只考虑用户以往的访问网络资源的行为，而未考虑用户处在不同的真实场景下对不同网络资源的需求。因此，本申请实施例提供了一种网络资源推荐方法、装置、存储介质、电子设备。
图1A为本申请实施例的网络资源推荐方法的应用示意图。请参阅图1，应用该网络资源推荐方法的场景中包括：设备10和服务器20。设备10与服务器20之间可以通过通信网络连接。该通信网络包括无线网络以及有线网络，其中无线网络包括无线广域网、无线局域网、无线城域网、以及无线个人网中的一种或多种的组合。网络中包括路由器、网关等等网络实体， 图中并未示意出。设备10可以通过通信网络与服务器20进行信息交互，比如可以从服务器20下载应用(如，购物类应用或地图类应用等)。
其中，所述服务器20可以用于接收设备10上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息；根据用户访问网络资源时所在的环境信息，采用预先建立的场景判定模型确定用户所在的场景；建立用户所在场景与用户访问的网络资源类型之间的关联模型；接收设备10发来的用户当前所在的环境信息，根据用户当前所在的环境信息，采用场景判定模型确定与用户当前所在的环境信息对应的当前场景，根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与确定的当前场景对应类型的网络资源。
所述设备10可以用于接收用户在设备上输入对网络资源推送的授权指示；检测到用户访问一网页，实时记录用户访问该网页的网络访问数据；同时，实时从自身的摄像头和传感器获取当前环境信息；将用户的标识信息、用户的网络访问数据和当前环境信息上传到服务器20；接收服务器根据当前环境信息推送的网络资源。
下面结合附图及具体实施例对本申请再作进一步详细的说明。
图1B为本申请一实施例提供的网络资源推送方法流程图，其具体步骤如下：
步骤101：服务器接收设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息。
步骤102：服务器根据用户访问网络资源时所在的环境信息，采用预先建立的场景判定模型确定用户所在的场景。
其中，场景判定模型用于根据环境信息判定场景。
步骤103：服务器建立用户所在场景与用户访问的网络资源类型之间的关联模型。
服务器可以实时地、持续地对每个用户执行上述步骤101-103，以使得 建立的用户所在场景与用户访问的网络资源类型之间的关联模型不断完善。
步骤104：服务器接收设备发来的用户当前所在的环境信息，根据用户当前所在的环境信息，采用场景判定模型确定与用户当前所在的环境信息对应的用户当前所在场景，根据建立的用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与确定的用户当前所在场景对应类型的网络资源。
当一个用户的用户所在场景与用户访问的网络资源类型之间的关联模型建立后，就可执行步骤104了。
通过本申请实施例的方法，服务器确定用户当前所在的场景后，可以将用户在该场景中曾经访问过或购买过的商品类似的商品推荐给用户，以实现基于场景的推荐。
图2为本申请一实施例提供的建立用户所在场景与用户访问的网络资源类型之间的关联模型的方法流程图，其具体步骤如下：
步骤201：用户在设备上输入对网络资源推送的授权指示。
设备如：AR(Augmented Reality，增强现实)设备、VR(Virtual Reality，虚拟现实)设备、MR(Mixed Reality，混合现实)设备或其他移动设备(如：手机)等。
由于在使用本申请实施例中的网络资源推荐方法时，要采集用户的隐私信息包括：用户所在环境信息等，因此，在使用本方法前，需要经过用户的授权。其中，所述授权指示包括对获取环境信息的硬件设备的授权。该硬件设备例如包括：摄像头和设备内置的各种传感器等等。
步骤202：设备检测到用户访问一网页，实时记录用户访问该网页的网络访问数据；同时，实时从自身的传感器和摄像头获取当前环境信息。
用户的网络访问数据包括：用户访问的网页地址、用户点击的内容标签(包括：内容类型、内容名称、内容属性等)、用户在网页的停留时长等。 内容类型如：新闻资讯、流媒体、商品等，内容属性如：商品的库存等。
传感器如：陀螺仪、红外传感器、距离传感器等，主要采集环境的位置信息，包括：地理位置、物体之间的距离等信息。摄像头用于采集环境的图像。其中，陀螺仪又称为角速度传感器，测量的物理量例如是设备偏转、倾斜时的转动角速度等。通过陀螺仪，可以检测到设备的运动状态。
步骤203：设备将用户的标识信息、用户的网络访问数据和当前环境信息上传到服务器。
设备可在本地缓存用户针对当前页面的网络访问数据和当前环境信息，并在当前页面关闭或跳转前，将用户针对当前页面的网络访问数据和当前环境信息上传到应用服务器，以保证上传的数据的准确性，即，保证用户的当前页面的网络访问数据和当前环境信息的对应关系。
步骤204：服务器接收设备发来的用户的标识信息、用户的网络访问数据和当前环境信息，根据该当前环境信息确定用户当前所在场景。
在实际应用中，可预先采用人工智能学习系统对摄像头采集的各种场景下的环境图像并结合传感器采集的环境位置信息进行学习，得到场景判定模型，此后，服务器采用该场景判定模型对设备发来的当前环境信息进行分析，得到对应的场景。
例如，服务器可以通过对摄像头采集的视频的每幅图像进行分析,根据图像中的环境信息、人物信息和物体信息，推断用户使用设备的具体场景。
步骤205：服务器根据用户当前所在场景与用户的网络访问数据，建立用户所在场景与用户访问的网络数据类型之间的关联模型，该关联模型以用户的标识信息标识。
在实际应用中，可在用户所在场景与用户访问的网络数据类型之间建立字典。
服务器可以实时地、持续地对每个用户执行上述步骤201-205，以使得建立的每个用户处于不同场景与该用户访问的网络资源类型之间的关联模型 不断完善。
图3为本申请另一实施例提供的根据建立的用户所在场景与用户访问的网络资源类型之间的关联模型为用户推送网络资源的方法流程图，其具体步骤如下：
步骤301：设备确定用户已对网络资源推送进行授权。其中，该步骤包括设备确定用户对采集当前环境信息的硬件设备进行授权。
步骤302：设备通过自带的传感器和摄像头实时采集当前环境信息，将采集的环境信息和用户标识信息实时上报服务器。
步骤303：服务器接收设备发来的环境信息，根据该环境信息采用场景判定模型确定对应的场景。
步骤304：服务器根据用户的标识信息，查找该用户对应的用户所在场景与用户访问的网络数据类型之间的关联模型，根据该关联模型确定步骤303确定的场景对应的网络数据类型。
步骤305：服务器查找与步骤304确定的网络数据类型匹配的网络数据，将查找到的网络数据推送给用户。
例如：服务器可在用户访问的应用的页面或HTML页面的预设推荐位置处显示推送的网络数据。网络数据可以是：网址、文字或图片等。
以下给出本申请的具体应用示例：
示例一、
该示例针对的场景是：用户在室内环境使用AR设备在一购物APP上购物。
1)AR设备通过摄像头采集环境图片，通过传感器采集环境位置信息，同时记录用户的网络访问数据(如：用户访问的购物APP名称、访问的网页地址、点击的商品标签(如：名称、库存等))。
2)AR设备确定用户即将跳转或关闭当前网页，则将用户在该网页停留期间摄像头采集的环境图片、传感器采集的环境位置信息以及记录的用户对该网页的访问数据、用户在该网页的停留时长发送给服务器。
3)服务器根据AR设备发来的摄像头采集的环境图片和传感器采集的环境位置信息，采用预先建立的场景判定模型进行计算，得到用户所在场景为室内且相对静止，且判定用户坐在沙发上。
具体地，场景判定模型可根据如下要素判定场景：
1、环境：本示例中为房间；
2、人：本示例中为多人，包括大人和儿童；
3、物：本示例中为沙发且成人坐在沙发上、桌椅、电视、冰箱、烤箱、桌子等；
4、视角：相对静止。
则可以判定：当前场景为室内家庭客厅且相对静止，且用户坐在沙发上。所述视角是静止还是在动，例如是通过分析环境图片之间的连续性推断的。
4)服务器根据之前建立的该用户的用户所在场景与用户访问的网络数据类型之间的关联模型，确定该用户在该场景下使用该购物APP时大概率访问某类商品，则在该购物APP上搜索该类商品中销量最高的商品，将该商品的标签推送到用户正在访问的网页的推荐位置处。
另外，若服务器根据场景判定模型，还判定出场景内有儿童，则将幼儿图书、文具的相关内容推送到用户正查看的该购物app的页面展示。
另外，若根据场景判定模型判定视角为不停地动，则还可以向用户推送家具装修相关的新闻或家庭趣事视频；
另外，服务器还可统计该用户在最近预设时长内在相同场景下在该购物APP上访问最多的商品类型，将该类型商品的相关信息推送给用户。
示例二、
该示例针对的场景是：用户在移动环境使用AR设备。
1)AR设备通过摄像头采集环境图片，通过传感器采集环境位置信息。
2)AR设备将摄像头采集的环境图片和传感器采集的环境位置信息发送给服务器。
3)服务器根据摄像头采集的环境图片，捕获用户视野焦点范围内视觉信息，确定用户是在寻找餐厅或者查看某类商品，根据传感器采集的环境位置信息等确定用户所在的地理位置。例如服务器可以分析出环境图片中出现的文字，确认其为餐厅名称，进而确定用户是在寻找餐厅。
4)服务器根据最近预设时长内的分析结果，确定用户确实是在寻找餐厅，则记录用户标识、时间、地理位置与用户行为：寻找餐厅之间的关联关系。
5)之后，当服务器再接收到AR设备发来的摄像头采集的环境图片和传感器采集的环境位置信息时，则可根据步骤4)建立的关联关系，确定用户行为，例如：若用户行为为寻找餐厅，则将当前地理位置内的餐厅信息通过语音或图像等形式推送到AR设备的可视位置。
服务器可根据AR设备不断发来的环境图片和环境位置信息，实时进行步骤3)的分析，且若根据分析结果，发现该用户在同一地理位置的同一时间段内的用户行为发生了变化，则更新步骤4)中记录的关联关系中的用户行为。
示例三、
该示例针对的是用户使用AR设备经常性地不分时间和地点地访问购物类app。
1)AR设备通过摄像头采集环境图片，通过传感器采集环境位置信息， 同时记录用户的网络访问数据(如：用户访问的购物APP名称、访问的网页地址、点击的商品标签(如：名称、库存等))。
2)AR设备将摄像头采集的环境图片、传感器采集的环境位置信息以及记录的用户对网页的访问数据、用户在网页的停留时长发送给服务器。
3)服务器根据摄像头采集的环境图片、传感器采集的环境位置信息以及用户对网页的访问数据、用户在网页的停留时长，确定用户经常性地不分时间和地点地访问购物类app，则向用户推送会员优惠信息、或/和推荐办理付费会员以享受优惠，或/和推荐信用卡信息，或/和推荐移动支付工具中的消费贷等信息。
示例四、
该示例针对的是用户使用AR设备访问地图APP。
1)AR设备通过摄像头采集环境图片，通过传感器采集环境位置信息，同时记录用户的网络访问数据(如：用户访问的地图APP名称、访问的网页地址等)。
2)AR设备将摄像头采集的环境图片、传感器采集的环境位置信息以及记录的用户对网页的访问数据发送给服务器。
3)服务器通过摄像头采集的环境图片和传感器采集的环境位置信息，采用预设算法分析路面人流信息，同时经过用户授权上报地理位置信息，形成该地理位置的路面人流量的数据信息，将路面人流量的数据信息实时推送到用户使用的地图APP的页面上。
另外，当服务器发现通过AR、VR、MR设备等使用该地图APP的人数达到预设数量时，则可根据计算得到的道路拥堵状况信息，为AR、VR、MR设备用户计算出调整路线，并推送给用户。
图4为本申请实施例提供的网络资源推送装置的结构示意图，该装置位 于服务器上，该装置主要包括：场景判定模型保存模块41、接收及场景判定模块42、关联模型建立模块43和推送模块44，其中：
场景判定模型保存模块41，保存场景判定模型，该模型用于根据环境信息判定场景。
接收及场景判定模块42，接收到设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息，将用户访问网络资源时所在的环境信息输入场景判定模型保存模块41保存的场景判定模型，得到用户所在的场景，将用户所在的场景和用户访问的网络资源信息发送给关联模型建立模块43；接收设备发来的用户当前所在的环境信息，将用户当前所在的环境信息输入场景判定模型保存模块41保存的场景判定模型，得到用户当前所在的场景，将用户当前所在的场景发送给推送模块44。
关联模型建立模块43，根据接收及场景判定模块42发来的用户所在的场景和用户访问的网络资源信息，建立用户所在场景与用户访问的网络资源类型之间的关联模型。
推送模块44，接收到接收及场景判定模块42发来的用户当前所在的场景，根据关联模型建立模块43建立的用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源。
在实际应用中，接收及场景判定模块42接收的用户访问网络资源时所在的环境信息包括：通过设备自带的传感器采集的环境位置信息，通过设备自带的摄像头采集的环境照片。
在实际应用中，接收及场景判定模块42接收的设备上报的用户访问的网络资源信息包括：用户访问的网页地址和点击的内容标签；或者包括：用户访问的网页地址、点击的内容标签和用户在网页的停留时长。
在实际应用中，接收及场景判定模块42接收的用户点击的内容标签包括：新闻资讯标签，或/和流媒体标签。
在实际应用中，上述设备为AR设备，或者VR设备，或者MR设备。
本申请实施例还提供一种非瞬时计算机可读存储介质，所述非瞬时计算机可读存储介质存储指令，所述指令在由处理器执行时使得所述处理器执行如步骤101-104，或者步骤201-205，或者步骤301-305任一项所述的网络资源推送方法的步骤。所述存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
本申请实施例还提供一种电子设备，包括如上所述的非瞬时计算机可读存储介质、以及可访问所述非瞬时计算机可读存储介质的所述处理器。
本申请实施例的电子设备例如为计算机设备，其可以是本申请实施例中的服务器或设备。图5示出了本申请实施例所涉及的电子设备的结构。
该电子设备可以包括一个或者一个以上处理核心的处理器501、一个或一个以上存储器502、电源503和输入单元504等部件。存储器502为计算机可读存储介质。图5示出的结构并不构成对服务器或设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器501是该计算设备的控制中心，利用各种接口和线路连接整个电子设备的各个部分，通过运行或执行存储在存储器502内的软件程序和/或模块，以及调用存储在存储器502内的数据，执行电子设备的各种功能和处理数据，从而对电子设备进行整体监控。可选地，处理器501可包括一个或多个处理核心；处理器501可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器501中。
存储器502可用于存储软件程序以及模块，处理器501通过运行存储在存储器502的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器502可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据电子设备的使用所创建的数据等。此外，存储器502可以包括高速随机存取存储器，还可以包括非易失性(非瞬时)存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器502还可以包括存储器控制器，以提供处理器501对存储器502的访问。
电子设备还包括给各个部件供电的电源503，优选的，电源503可以通过电源管理系统与处理器501逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源503还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该电子设备还可包括输入单元504，该输入单元504可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。
尽管未示出，电子设备还可以包括显示单元等，在此不再赘述。具体在本申请实施例中，计算机中的处理器501会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器502中，并由处理器501来运行存储在存储器502中的应用程序，从而实现前述实施例中，服务器或设备的网络资源推送方法。
本申请实施例通过建立用户所在场景与用户访问的网络资源类型之间的关联模型，之后当接收到设备发来的用户当前所在的环境信息时，根据用户当前所在的环境信息确定对应的场景，根据用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送对应类型的网络资源，从而实现了基 于场景对用户进行网络资源推送。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。

Claims (14)

  1. 一种网络资源推送方法，其特征在于，该方法包括：
    接收设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息；
    根据用户访问网络资源时所在的环境信息，采用预先建立的场景判定模型确定用户所在的场景；
    建立用户所在场景与用户访问的网络资源类型之间的关联模型；
    接收设备发来的用户当前所在的环境信息，根据用户当前所在的环境信息，采用场景判定模型确定与用户当前所在的环境信息对应的用户当前所在场景；
    根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源。
  2. 根据权利要求1所述的方法，其特征在于，所述接收设备发来的用户当前所在的环境信息包括：接收设备发来的通过传感器采集的当前设备数据。
  3. 根据权利要求1所述的方法，其特征在于，所述用户访问网络资源时所在的环境信息通过以下方式获取：
    通过设备自带的传感器采集环境位置信息，通过设备自带的摄像头采集环境照片；
    所述确定用户所在的场景包括：
    将所述环境位置信息与所述环境照片输入预先建立的场景判定模型，得到对应的场景。
  4. 根据权利要求1所述的方法，其特征在于，所述设备上报的用户访问的网络资源信息包括：
    用户访问的网页地址和点击的内容标签；
    或者包括：用户访问的网页地址、点击的内容标签和用户在网页的停留时长。
  5. 根据权利要求4所述的方法，其特征在于，所述内容标签包括以下中的一个或多个：新闻资讯标签、流媒体标签。
  6. 根据权利要求1所述的方法，其特征在于，所述设备为AR设备，或者VR设备，或者MR设备。
  7. 根据权利要求1所述的方法，其特征在于，所述根据所述用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源包括：
    根据用户的标识信息，查找该用户对应的用户所在场景与用户访问的网络数据类型之间的关联模型，根据该关联模型确定与当前场景对应的网络数据类型，并根据该确定的网络数据类型为用户推送网络资源。
  8. 一种网络资源推送装置，其特征在于，该装置包括：
    场景判定模型保存模块，保存场景判定模型，该模型用于根据环境信息判定场景；
    接收及场景判定模块，接收到设备上报的用户访问的网络资源信息以及用户访问网络资源时所在的环境信息，将用户访问网络资源时所在的环境信息输入场景判定模型，得到用户所在的场景，将用户所在的场景和用户访问的网络资源信息发送给关联模型建立模块；接收设备发来的用户当前所在的环境信息，将用户当前所在的环境信息输入场景判定模型，得到用户当前所在的场景，将用户当前所在的场景发送给推送模块；
    关联模型建立模块，根据接收及场景判定模块发来的用户所在的场景和用户访问的网络资源信息，建立用户所在场景与用户访问的网络资源类型之间的关联模型；
    推送模块，接收到接收及场景判定模块发来的用户当前所在的场景，根 据关联模型建立模块建立的用户所在场景与用户访问的网络资源类型之间的关联模型，为用户推送与用户当前所在场景对应类型的网络资源。
  9. 根据权利要求8所述的装置，其特征在于，所述接收及场景判定模块接收的用户访问网络资源时所在的环境信息包括：
    通过设备自带的传感器采集的环境位置信息，通过设备自带的摄像头采集的环境照片。
  10. 根据权利要求8所述的装置，其特征在于，所述接收及场景判定模块接收的设备上报的用户访问的网络资源信息包括：
    用户访问的网页地址和点击的内容标签；
    或者包括：用户访问的网页地址、点击的内容标签和用户在网页的停留时长。
  11. 根据权利要求10所述的装置，其特征在于，所述接收及场景判定模块接收的用户点击的内容标签包括以下中的一个或多个：新闻资讯标签、流媒体标签。
  12. 根据权利要求6所述的装置，其特征在于，所述设备为AR设备，或者VR设备，或者MR设备。
  13. 一种非瞬时计算机可读存储介质，所述非瞬时计算机可读存储介质存储指令，其特征在于，所述指令在由处理器执行时使得所述处理器执行如权利要求1至7中任一项所述的网络资源推送方法的步骤。
  14. 一种电子设备，其特征在于，包括如权利要求11所述的非瞬时计算机可读存储介质、以及可访问所述非瞬时计算机可读存储介质的所述处理器。
PCT/CN2020/070173 2019-02-21 2020-01-03 网络资源推送方法、装置及存储介质 Ceased WO2020168841A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/426,419 US11483253B2 (en) 2019-02-21 2020-01-03 Network resource pushing method, device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910128860.6A CN111597429A (zh) 2019-02-21 2019-02-21 网络资源推送方法、装置及存储介质
CN201910128860.6 2019-02-21

Publications (1)

Publication Number Publication Date
WO2020168841A1 true WO2020168841A1 (zh) 2020-08-27

Family

ID=72143729

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/070173 Ceased WO2020168841A1 (zh) 2019-02-21 2020-01-03 网络资源推送方法、装置及存储介质

Country Status (3)

Country Link
US (1) US11483253B2 (zh)
CN (1) CN111597429A (zh)
WO (1) WO2020168841A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116095137B (zh) * 2022-12-21 2023-08-18 北京隆道网络科技有限公司 基于供应链管理的数据智能采集推送方法及系统
CN121188280B (zh) * 2025-09-23 2026-03-03 北京轩辕传媒有限公司 基于rpa的浏览器多任务自动化操作方法和系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160034483A1 (en) * 2014-07-31 2016-02-04 Kobo Incorporated Method and system for discovering related books based on book content
CN109040202A (zh) * 2018-07-16 2018-12-18 佛山市影腾科技有限公司 一种信息推送方法、装置及服务器
CN109241451A (zh) * 2018-11-08 2019-01-18 北京点网聚科技有限公司 一种内容组合推荐方法、装置及可读存储介质
CN109359247A (zh) * 2018-12-07 2019-02-19 广州市百果园信息技术有限公司 内容推送方法及存储介质、计算机设备

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833570A (zh) * 2010-03-23 2010-09-15 深圳市五巨科技有限公司 一种移动终端页面推送优化的方法和装置
KR20130000160A (ko) * 2011-06-22 2013-01-02 광주과학기술원 사용자 적응형 증강현실 이동통신 장치와 서버 및 그 방법
KR20140121764A (ko) * 2012-01-05 2014-10-16 비자 인터네셔널 서비스 어소시에이션 트랜잭션 영상 캡처 장치, 방법 및 시스템
CN103595747A (zh) * 2012-08-16 2014-02-19 腾讯科技（深圳）有限公司 用户信息推荐方法和系统
US9141188B2 (en) * 2012-10-05 2015-09-22 Elwha Llc Presenting an augmented view in response to acquisition of data inferring user activity
WO2015014189A1 (zh) * 2013-08-02 2015-02-05 优视科技有限公司 一种访问网站的方法及装置
CN107424043B (zh) * 2017-06-15 2021-06-25 北京三快在线科技有限公司 一种产品推荐方法及装置，电子设备
CN108134691B (zh) * 2017-12-18 2019-10-01 Oppo广东移动通信有限公司 模型构建方法、网络资源预加载方法、装置、介质及终端
CN121505214A (zh) * 2018-04-19 2026-02-10 腾讯科技（深圳）有限公司 增强现实数据处理方法、装置、计算机设备和存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160034483A1 (en) * 2014-07-31 2016-02-04 Kobo Incorporated Method and system for discovering related books based on book content
CN109040202A (zh) * 2018-07-16 2018-12-18 佛山市影腾科技有限公司 一种信息推送方法、装置及服务器
CN109241451A (zh) * 2018-11-08 2019-01-18 北京点网聚科技有限公司 一种内容组合推荐方法、装置及可读存储介质
CN109359247A (zh) * 2018-12-07 2019-02-19 广州市百果园信息技术有限公司 内容推送方法及存储介质、计算机设备

Also Published As

Publication number Publication date
US11483253B2 (en) 2022-10-25
CN111597429A (zh) 2020-08-28
US20220109640A1 (en) 2022-04-07

Similar Documents

Publication Publication Date Title
JP7277064B2 (ja) 空間的３ｄ環境に対するコンテンツのマッチング
CN112219205B (zh) 内容到空间3d环境的匹配
US10462602B2 (en) Passive check-in
US11263662B2 (en) Systems and methods for automatic hashtag embedding into user generated content using machine learning
KR101842631B1 (ko) 위치-관련 소셜 데이터의 실제-세계 뷰
RU2654133C2 (ru) Просмотр трехмерных объектов в документах
US10419560B2 (en) Presenting additional content items to a social networking system user based on receiving an indication of boredom
US9317173B2 (en) Method and system for providing content based on location data
US9223902B1 (en) Architectures for content identification
US10692103B2 (en) Systems and methods for hashtag embedding based on user generated content for creating user specific loyalty identifiers
CN110415009A (zh) 用于视频内修改的计算机化系统和方法
WO2020168841A1 (zh) 网络资源推送方法、装置及存储介质
EP4478294A2 (en) Outputting warped images from captured video data
JP2020126688A (ja) 接客支援装置、接客支援方法、及びプログラム
WO2018177303A1 (zh) 媒体内容推荐方法、装置及存储介质
US20130257906A1 (en) Generating publication based on augmented reality interaction by user at physical site
US20170140427A1 (en) Method and apparatus for recommending product features on which inadequate time is spent by a user
US9852135B1 (en) Context-aware caching
KR20230096805A (ko) 인공지능 기반 지오태깅을 이용한 메타버스 라이프로깅 방법 및 장치
KR20220076783A (ko) 로드뷰 영상 서비스 장치
US20180338009A1 (en) Determining online system user eligibility for receiving content using a polygon representing a physical location associated with the content
CN108255305A (zh) 一种沉浸式三维虚拟显示系统和方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20760329

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 24/01/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20760329

Country of ref document: EP

Kind code of ref document: A1