WO2020044094A1 - 资源推荐方法、装置、电子设备以及计算机可读介质 - Google Patents

资源推荐方法、装置、电子设备以及计算机可读介质 Download PDF

Info

Publication number
WO2020044094A1
WO2020044094A1 PCT/IB2018/057156 IB2018057156W WO2020044094A1 WO 2020044094 A1 WO2020044094 A1 WO 2020044094A1 IB 2018057156 W IB2018057156 W IB 2018057156W WO 2020044094 A1 WO2020044094 A1 WO 2020044094A1
Authority
WO
WIPO (PCT)
Prior art keywords
images
user
demand target
feature
physical location
Prior art date
Application number
PCT/IB2018/057156
Other languages
English (en)
French (fr)
Inventor
蔡山清
Original Assignee
优视科技新加坡有限公司
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 优视科技新加坡有限公司 filed Critical 优视科技新加坡有限公司
Publication of WO2020044094A1 publication Critical patent/WO2020044094A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0252Targeted advertisements based on events or environment, e.g. weather or festivals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0261Targeted advertisements based on user location
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/52Network services specially adapted for the location of the user terminal
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/55Push-based network services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30Services specially adapted for particular environments, situations or purposes
    • H04W4/35Services specially adapted for particular environments, situations or purposes for the management of goods or merchandise

Definitions

  • the present application relates to the field of computer technology, and particularly to the field of Internet technology, and in particular, to a resource recommendation method, apparatus, electronic device, and computer-readable storage medium. Background technique
  • the location-based service (LocationBasedService, LBS) system obtains the location information (geographical coordinates, Or geodetic coordinates), a value-added service that provides users with corresponding services under the support of a Geographic Information System (GIS) platform.
  • LBS LocationBasedService
  • GIS Geographic Information System
  • the characteristics of the LBS service are as follows: 1. High requirements on coverage. On the one hand, the coverage needs to be large enough. On the other hand, the coverage required includes indoors. Users use this function indoors most of the time, from high-rise buildings and underground facilities must ensure coverage to every corner. According to the range of coverage, it can be divided into three types of coverage positioning services: the entire local network, covering part of the local network, and providing roaming network service types. In addition to considering coverage, network structure and dynamically changing environmental factors may also prevent a telecommunications operator from guaranteeing service in the local network or roaming network. Second, positioning accuracy requirements based on user needs. Mobile phone positioning should provide different accuracy services according to different user service needs, and can provide users with the right to choose accuracy.
  • the probability of positioning accuracy within 50 meters introduced by the FCC in the United States is 67%, and the probability of positioning accuracy within 150 meters is 95%.
  • the positioning accuracy is related to the positioning technology used, and also depends on the external environment in which the service is provided, including the radio propagation environment, the density and geographical location of the base station, and the equipment used for positioning.
  • the LBS service is considered to be one of the killer services after the short message. It has a huge market size and good profit prospects, but the actual progress is relatively slow. However, with the improvement of the industrial chain, the mobile location and location service market is expected to grow. Since 2008, the global LBS operation market will begin to accelerate its growth, but at the same time, it must pay attention to the balance between business and network performance. It should ensure the performance of the business while ensuring network performance.
  • LBS location based service
  • Check-in applications such as public comment and word of mouth will break the business based on location information
  • Instagram, Flicker and other photo sharing websites can also add the current location information
  • Facebook, Twitter, MySpace, WeChat, Weibo, etc. as Representative social networks also have services such as location sharing and location check-in; map products have brought convenience to everyone's travel; there are also some market segments that use location information to provide services to users.
  • the purpose of this application is to propose a resource recommendation method, device, electronic device, and computer-readable medium to solve the above-mentioned problems in the prior art.
  • this application provides a resource recommendation method, which includes:
  • an embodiment of the present application provides a resource recommendation device, including:
  • a first program unit configured to determine a user's physical location and a user's demand target
  • a second program unit configured to determine a plurality of images configured with position annotations, and extract feature imaging elements from the plurality of images
  • a third program unit configured to filter, based on the characteristic imaging element, an image associated with the demand target from the plurality of images
  • a fourth program unit configured to perform resource recommendation according to a position label configured in an image associated with the demand target and the physical position.
  • an electronic device including:
  • an embodiment of the present application provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, implements any of the foregoing methods.
  • the physical location of the user and the user's needs are determined; a plurality of images configured with position annotations are determined, and feature imaging elements are extracted from the plurality of images; according to the Feature imaging elements, filtering images associated with the demand target from the plurality of images; and performing resource recommendation based on the position labels and the physical locations configured in the images associated with the demand target, thereby improving based on Location friendly.
  • FIG. 1 is a schematic flowchart of a resource recommendation method in Embodiment 1 of the present application.
  • FIG. 2 is a schematic structural diagram of a resource recommendation device in Embodiment 2 of the present application.
  • FIG. 3 is a schematic structural diagram of a resource recommendation device in Embodiment 3 of the present application.
  • FIG. 4 is a schematic structural diagram of a device / terminal / server in Embodiment 4 of the present application; [0030] FIG. 5 is a hardware structure of the device / terminal / server in Embodiment 5 of the present application. detailed description
  • FIG. 1 is a schematic flowchart of a resource recommendation method in Embodiment 1 of the present application; as shown in FIG. 1, it includes:
  • S101 Determine the physical location of the user and the user's demand target
  • the user's physical location and the user's demand target may be determined according to the analysis result of the user input.
  • the user input is at least one of text input or voice input.
  • the user input may be a text keyword entered in a dialog box, or a voice keyword entered in a dialog box.
  • the user input can also be: a picture entered in a dialog box, or an object specified or selected by the user in the application program interface, or an object selected or specified by the user in the candidate resources recommended by the application.
  • the parsing process for the user input may include: processing the text keywords, keyword extraction, or other processing, or converting the speech keywords into text keywords. Keyword extraction, etc .; or, capturing a specified or selected action from an application program interface, and matching with content configured on the application program interface.
  • an input interface may be configured in an application program, the input interface being used to capture the user input. [0039] If the application is allowed to read the location data of the user, the physical location of the user is determined by analyzing the GPS location data in the user input.
  • the physical location of the user can be determined by analyzing the data of the radio communication network (such as GSM network, CDMA network) in the user input.
  • the radio communication network such as GSM network, CDMA network
  • the user's demand is actually the ultimate purpose of characterizing the user's current actions, such as a tourist attraction, a restaurant, or the like.
  • S102 Determine a plurality of images configured with position labels, and extract feature imaging elements from the plurality of images;
  • an image library can be configured in the background, and all images in the image library carry position labels.
  • the image library can be established based on big data search technology, that is, the analysis is performed on the input of all users using the same application to generate an image, and position annotation is added to the image.
  • a feature library is established in advance based on a neural network.
  • crawl pictures from other data sources based on the search technology, to crawl those images with position markers, and store them in the background database.
  • the image can be specifically analyzed to determine whether the analysis result includes position data. That is, all images are parsed to determine the image that is configured with position annotation.
  • a mark may also be directly marked on the image with a position mark, and the mark corresponds to a data bit, which can be directly written into the header data of the image.
  • step S103 may specifically perform enhanced recognition processing on the multiple images to extract a characteristic imaging element from the multiple images.
  • the feature imaging element according to a pre-established feature library to filter out images associated with the demand target from the plurality of images.
  • a specific application scenario is: The collected images are not limited to pictures, and can be recommended for indoor positioning. For example, in large shopping malls, it is easy to get lost. It is more difficult to find where and on which floor a person is. If the other party sends a picture here, then based on the enhanced image analysis, you can know which position the other party is on. It can be used for indoor positioning. In the last example, because the user uploaded some images, according to These images can not only know that this building has a cafe, but also where and on which floor.
  • the enhancement processing may be performed on the image after step S102 and before step S103.
  • This application obtains a sample space of a picture of a user's location, and then obtains an index number of a sample point based on image matching, and hits feature imaging elements such as historical data of buildings or landscapes in the picture, local services, and adds these feature imaging elements to The description of the attribute information of the picture.
  • the image enhancement processing may further include adding attribute information of a photographer of the picture, that is, a user, to attribute information of the picture as a characteristic imaging element.
  • the attribute information may be classified and stored to form different types of feature imaging elements. There is a-correspondence relationship between the images in the feature library and the feature imaging elements.
  • S104 Perform resource recommendation according to a position label configured in an image associated with the demand target and the physical position.
  • step S104 according to the feature imaging element, an image associated with the demand target is filtered from the multiple images, and the feature image may be specifically imaged with the feature database established in advance Element, filtering the images related to the demand target from the multiple images, and it is critical for different users to construct users at the same geographical location at the same time.
  • the feature imaging element may be based on the same imaging object, for example, the same dining place, tourist attraction, etc., or may be based on a love with the same interest, such as having similar ages.
  • the geographic location and location labeling can be directly compared, and the image similarity can be compared to achieve resource recommendation.
  • an image with the same or similar feature imaging element may be determined first by comparing the similarity of the images, and then the comparison of the geographical position and the position label may be performed to determine the same geographical position or a certain geographical position.
  • the images in the location range finally form the recommended resources, which are shared among different users, and the users are aggregated, so that the shared recommendation of resources can be performed among different users, thereby improving the friendliness.
  • the similarity between the two images may be specifically determined through calculation of a color difference value.
  • the specific process is as follows: The two images to be compared are processed separately A white background monochrome image is formed, and the size of the convolution area is calculated according to the parameter s of the adjacent area of the central pixel; the convolution calculation is completed for each input pixel point on the white background monochrome image, and each input pixel is further calculated The image moment of a point is used to determine the similarity of the pixels according to the magnitude of the image moment of the pixel. If the image moments of all pixels of the two images are in the same threshold range, the similarity between the entire image is determined.
  • image filtering can be performed based on the range of labeled locations.
  • performing resource recommendation based on the position label configured in the image associated with the demand target and the physical location includes: according to the position label configured in the image associated with the demand target and the A recommendation queue is generated at a physical location, and the resources are recommended from high to low according to the recommendation priority of the resources in the recommendation queue.
  • FIG. 2 is a schematic structural diagram of a resource recommendation device in Embodiment 2 of the present application; as shown in FIG. 2, it includes:
  • a first program unit 201 configured to determine a physical location of a user and a demand target of the user
  • a second program unit 202 configured to determine a plurality of images configured with position annotations, and extract feature imaging elements from the plurality of images;
  • a third program unit 203 is configured to filter, based on the characteristic imaging element, an image associated with the demand target from the multiple images;
  • a fourth program unit 204 is configured to perform resource recommendation according to a position label configured in an image associated with the demand target and the physical position.
  • the first program unit 201 is further configured to determine the physical location of the user and the user's demand target according to the analysis result of the user input.
  • the user input is at least one of a text input or a voice input.
  • the first program unit 201 is further configured to capture the user input through a configured input interface.
  • the second program unit 202 is further configured to analyze all images to determine an image configured with a position label.
  • the second program unit 202 is further configured to perform enhanced recognition processing on the multiple images to extract feature imaging elements from the multiple images.
  • the third program unit 203 is further configured to: The collection database and the feature imaging element filter out images related to the demand target from the plurality of images.
  • FIG. 3 is a schematic structural diagram of a resource recommendation device in Embodiment 3 of the present application; as shown in FIG. 3, it includes the first program unit 201, the second program unit 202, the third program unit 203, The fourth program unit 204 further includes a fifth program unit 205, configured to pre-establish a feature library in the foregoing method embodiment based on a neural network.
  • the fourth program unit 204 is further configured to generate a recommendation queue according to the position label configured in the image associated with the demand target and the physical location, and prioritize the recommendation of resources in the recommendation queue. Levels are recommended from high to low order resources.
  • FIG. 4 is a schematic structural diagram of a device / terminal / server in Embodiment 4 of the present application; the device / terminal / server may include:
  • processors 401 one or more processors 401;
  • the computer-readable medium 402 may be configured to store one or more programs, [0076] when the one or more programs are executed by the one or more processors, so that the one or more processors Implement the resource recommendation method as described in any of the above embodiments.
  • the hardware structure of the device / terminal / server may include: a processor 501, a communication interface 502, and a computer readable Medium 503 and communication bus 504;
  • the processor 501, the communication interface 502, and the computer-readable medium 503 complete communication with each other through a communication bus 504;
  • the communication interface 502 may be an interface of a communication module, such as an interface of a GSM module;
  • the processor 501 may be specifically configured to: determine a user's physical location and a user's demand target; determine a plurality of images configured with position annotations, and extract feature imaging elements from the plurality of images; The feature imaging element selects an image associated with the demand target from the plurality of images; and performs resource recommendation based on a position label configured in the image associated with the demand target and the physical location.
  • the processor 501 may be a general-purpose processor, including a central processing unit (CPU), a network processor (Network Processor, NP), etc .; it may also be a digital signal processor (DSP), dedicated integration Circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic Pieces, discrete hardware components.
  • DSP digital signal processor
  • ASIC dedicated integration Circuit
  • FPGA off-the-shelf programmable gate array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the computer-readable medium 503 may be, but is not limited to, a random access memory (Random Access Memory, RAM), a read-only memory (Read Only Memory, ROM), and a programmable read-only storage medium (Programmable Read- Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPR0M), etc.
  • RAM Random Access Memory
  • ROM Read Only Memory
  • EEPR0M Electric Erasable Programmable Read-Only Memory
  • the process described above with reference to the flowchart may be implemented as a computer software program.
  • embodiments of the present application include a computer program product including a computer program borne on a computer-readable medium, the computer program containing program code configured to execute the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network through a communication section, and / or installed from a removable medium.
  • CPU central processing unit
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • the computer-readable medium may be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • Computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access storage media (RAM), read-only storage media (ROM), erasable Type programmable read-only storage medium (EPR0M or flash memory), optical fiber, portable compact disk read-only storage medium (CD-ROM), optical storage medium piece, magnetic storage medium piece, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal that is included in baseband or propagated as part of a carrier wave, and which carries computer-readable program code. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium.
  • the computer-readable medium may be A program configured to be sent, propagated, or transmitted for use by or in combination with an instruction execution system, device, or device.
  • Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • the computer program code configured to perform the operations of the present application may be written in one or more programming languages or combinations thereof, the programming languages including an object-oriented programming language such as Java, Smalltalk, C ++ It also includes conventional procedural programming languages such as "C" or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer, partly on a remote computer, or entirely on a remote computer or server.
  • the remote computer can be connected to a user's computer through any kind of network: including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider) Connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider Internet service provider
  • each block in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, which module, program segment, or portion of the code contains one or more logic functions configured to implement a specified logic function.
  • Executable instructions In the above specific embodiments, there is a specific sequence relationship, but these sequence relationships are only exemplary. In specific implementation, these steps may be fewer, more or the execution order may be adjusted. That is, in some alternative implementations, the functions marked in the boxes may occur in a different order than those marked in the drawings.
  • each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts may be implemented in a dedicated hardware-based system that performs the specified function or operation. Or, it can be implemented by a combination of dedicated hardware and computer instructions.
  • a processor includes a demand target determination unit, a feature extraction unit, a screening unit, and a recommendation unit. among them: [0088] a demand target determination unit configured to determine a physical location of the user and a demand target of the user;
  • a feature extraction unit configured to determine a plurality of images configured with position annotations, and extract a feature imaging element from the plurality of images
  • a screening unit configured to screen out images associated with the demand target from the plurality of images according to the characteristic imaging element
  • a recommendation unit configured to perform resource recommendation according to a position label configured in an image associated with the demand target and the physical position.
  • the names of these units do not constitute a limitation on the unit itself in some cases.
  • the demand target determination unit may also be described as a “unit that determines the physical location of the user and the user ’s demand target”.
  • the present application also provides a computer-readable medium on which a computer program is stored, and the program is executed by a processor to implement a method as described in any one of the foregoing embodiments.
  • the present application further provides a computer-readable medium, which may be included in the device described in the foregoing embodiments; or may exist separately without being assembled into the device.
  • the computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device causes the device to: determine a user's physical location and a user's demand target; determine a plurality of images configured with position annotations And extracting feature imaging elements from the plurality of images; filtering images associated with the demand target from the plurality of images according to the feature imaging elements; and according to the images associated with the demand target
  • the configured position label and the physical position are used for resource recommendation.
  • first, second, the first, or “the second” used in the various embodiments of the present application may modify various components with sequence and / or Importance is irrelevant, but these expressions do not limit the corresponding components.
  • the above expression is only configured for the purpose of distinguishing the element from other elements.
  • the first user equipment and the second user equipment represent different user equipments, although both are user equipments.
  • a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element.
  • an element eg, a first element
  • another element e.g., a second element
  • another element e.g., a second element
  • the one element is directly connected to the other element or the one element is indirectly connected to the other element via another element (eg, a third element).
  • an element for example, the first element
  • the second element no element (for example, the third element) is inserted between the two elements.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请公开了资源推荐方法、装置、电子设备以及计算机可读介质。该方法的一具体实施方式包括:确定用户的物理位置以及用户的需求目标;确定配置有位置标注的多个图像,并从所述多个图像中提取出特征成像元素;根据所述特征成像元素,从所述多个图像中筛选出关联于所述需求目标的图像;根据关联于所述需求目标的图像中配置的位置标注以及所述物理位置进行资源推荐。本申请实施例的技术方案提高了基于位置的交互友好性。

Description

资源推荐方法、 装置、 电子设备以及计算机可读介质 本申请要求在 2018 年 08 月 27 日提交中国专利局、 申请号为
201810979499. 3、 发明名称为“资源推荐方法、 装置、 电子设备以及 计算机可读介质” 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
[001]本申请涉及计算机技术领域, 具体涉及互联网技术领域, 尤其 涉及一种资源推荐方法、 装置、 电子设备以及计算机可读存储介质。 背景技术
[002]基于位置的服务(LocationBasedService, LBS)***是通过电 信移动运营商的无线电通讯网络(如 GSM网、 CDMA网)或外部定位方式(如 GPS)获取移动终端用户的位置信息(地理坐标, 或大地坐标), 在地理信 息***(Geographic Information System , GIS)平台的支持下, 为用户 提供相应服务的一种增值业务。
[003] LBS业务的特点主要有: 一、 覆盖率方面的要求高。 一方面要 求覆盖的范围足够大。 另一方面要求覆盖的范围包括室内。 用户大部分 时间是在室内使用该功能, 从高层建筑和地下设施必须保证覆盖到每个 角落。 根据覆盖率的范围, 可以分为三种覆盖率的定位服务: 在整个本 地网、 覆盖部分本地网和提供漫游网络服务类型。 除了考虑覆盖率外, 网络结构和动态变化的环境因素也可能使一个电信运营商无法保证在本 地网络或漫游网络中的服务。 二、 基于用户需求的定位精度要求。 手机 定位应该根据用户服务需求的不同提供不同的精度服务, 并可以提供给 用户选择精度的权利。 例如美国 FCC推出的定位精度在 50米以内的概率 为 67 %, 定位精度在 150米以内的概率为 95 %。 定位精度一方面与采用 的定位技术有关, 另外还要取决于提供业务的外部环境, 包括无线电传 播环境、 基站的密度和地理位置、 以及定位所用设备等。 [004] LBS服务被认为是继短信之后的杀手级业务之一, 有着巨大的 市场规模和良好的盈利前景, 但实际进展比较缓慢。 不过, 随着产业链 的完善,移动位置和位置服务市场有望日益壮大。自 2008年开始全球 LBS 运营市场将会开始加速成长, 但是在开展的同时要非常注意业务和网络 性能的平衡点, 应该在保障网络性能的同时最大可能的保证业务的开展。
[005]智能移动设备的普及和移动互联技术的发展,突破了传统的时 间和位置限制。 人们也逐渐***板和笔记本的移动 数据流量相比较去年同期增长了 65 %, 且预测在 2021年年末, 90 %的网 络流量将会被智能手机所支配。 可以发现, 智能移动设备已经有巨大的 应用市场, 而且在未来会表现得愈加重要。
[006]在为众多智能移动设备开发的应用软件中,基于用户地理位置 的服务 (Location Based Service, LBS)也已成为用户的日常, 且覆盖面 逐渐扩大。 例如: 大众点评、 口碑等签到类应用则在位置信息基础上, 对商家进行打破; Instagram和 Fl ickr等照片分享网站也可以添加当前 位置信息; 以 Facebook、 Twitter、 MySpace、 微信、 微博等为代表的社 交网络也已经具备了位置共享、 位置签到等服务; 地图类产品更是为大 家的出行带来了方便; 还有一些细分市场, 利用位置信息给用户提供服 务。
[007]但是, 上述基于位置信息的应用软件或者技术中,基于位置的 交互友好性亟待进一步提高。 发明内容
[008]本申请的目的在于提出一种资源推荐方法、装置、 电子设备以 及计算机可读介质, 来解决现有技术的上述问题。
[009]第一方面, 本申请提供了一种资源推荐方法, 其包括:
[0010]确定用户的物理位置以及用户的需求目标;
[0011 ]确定配置有位置标注的多个图像, 并从所述多个图像中提取 出特征成像元素; [0012]根据所述特征成像元素, 从所述多个图像中筛选出关联于所 述需求目标的图像;
[0013]根据关联于所述需求目标的图像中配置的位置标注以及所述 物理位置进行资源推荐。
[0014]第二方面, 本申请实施例提供了一种资源推荐装置, 其包括:
[0015]第一程序单元, 用于确定用户的物理位置以及用户的需求目 标;
[0016]第二程序单元, 用于确定配置有位置标注的多个图像, 并从 所述多个图像中提取出特征成像元素;
[0017]第三程序单元, 用于根据所述特征成像元素, 从所述多个图 像中筛选出关联于所述需求目标的图像;
[0018]第四程序单元, 用于根据关联于所述需求目标的图像中配置 的位置标注以及所述物理位置进行资源推荐。
[0019]第三方面, 本申请实施例提供了一种电子设备, 包括:
[0020]一个或多个处理器;
[0021 ]计算机可读介质, 用于存储一个或多个程序,
[0022]当所述一个或多个程序被所述一个或多个处理器执行, 使得 所述一个或多个处理器实现上述任一所述的方法。
[0023]第四方面, 本申请实施例提供了一种计算机可读介质, 其上 存储有计算机程序, 该程序被处理器执行时实现实现上述任一所述的方 法。
[0024]本申请提供的技术方案中, 通过确定用户的物理位置以及用 户的需求目标; 确定配置有位置标注的多个图像, 并从所述多个图像中 提取出特征成像元素; 根据所述特征成像元素, 从所述多个图像中筛选 出关联于所述需求目标的图像; 以及根据关联于所述需求目标的图像中 配置的位置标注以及所述物理位置进行资源推荐, 从而提高了基于位置 的交互友好性。 附图说明
[0025]通过阅读参照以下附图所作的对非限制性实施例所作的详细 描述, 本申请的其它特征、 目的和优点将会变得更明显: [0026] 图 1为本申请实施例一中资源推荐方法流程示意图;
[0027] 图 2为本申请实施例二中资源推荐装置的结构示意图;
[0028] 图 3为本申请实施例三中资源推荐装置的结构示意图;
[0029] 图 4为本申请实施例四中设备 /终端 /服务器的结构示意图; [0030] 图 5为本申请实施例五中设备 /终端 /服务器的硬件结构。 具体实施方式
[0031]下面结合附图和实施例对本申请作进一步的详细说明。 可以 理解的是, 此处所描述的具体实施例仅仅配置为解释相关发明, 而非对 该发明的限定。 另外还需要说明的是, 为了便于描述, 附图中仅示出了 与有关发明相关的部分。
[0032]需要说明的是, 在不冲突的情况下, 本申请中的实施例及实 施例中的特征可以相互组合。 下面将参考附图并结合实施例来详细说明 本申请。
[0033] 图 1为本申请实施例一中资源推荐方法流程示意图; 如图 1 所示, 其包括:
[0034] S 101、 确定用户的物理位置以及用户的需求目标;
[0035]本实施例中,步骤 S101中确定用户的物理位置以及用户的需 求目标时, 可以根据对用户输入的解析结果, 确定用户的物理位置以及 用户的需求目标。
[0036]本实施例中, 所述用户输入为文本输入或者语音输入中的至 少一种。 用户输入可以为在对话框中输入的文本关键词, 或者, 在对话 框中输入的语音关键词。 用户的输入还可以为: 在对话框中输入的图片, 或者, 用户在应用程序界面中指定或者选定的对象, 或者, 用户在应用 程序推荐的候选资源中选定或者指定的对象。
[0037]本实施例中, 对用户输入的解析过程可以包括: 对所述文本 关键词进行切分、 关键词提取等处理, 或者, 将语音关键词转换为文本 关键词, 在经过切分、 关键词提取等; 或者, 从应用程序界面中进行指 定或者选定动作的捕获, 再与该应用程序界面上配置的内容进行匹配。
[0038]为此, 可以在应用程序中配置输入接口, 该输入接口用于捕 获所述用户输入。 [0039]如果允许应用程序读取访问用户的位置数据, 则通过对用户 输入中 GPS位置数据进行解析, 确定出用户的物理位置。
[0040]如果不允许应用程序读取访问用户的位置数据, 则可以通过 对用户输入中的无线电通讯网络(如 GSM网、 CDMA网)数据进行解析, 确 定出用户的物理位置。
[0041]本实施例中, 用户的需求实际上是表征用户当前动作的最终 目的, 比如是旅游景点、 还是餐饮等。
[0042] S102、 确定配置有位置标注的多个图像, 并从所述多个图像 中提取出特征成像元素;
[0043]本实施例中, 在后台可以配置一个图像库, 该图像库中的所 有图像均携带有位置标注。 该图像库可以基于大数据搜索技术建立, 即 对使用同一应用程序的所有用户的输入进行分析得到生成一个图像, 在 图像上增加位置标注。 比如, 基于神经网络预先建立特征库。
[0044]当然, 也可以基于搜索技术, 从其他数据源上图片的爬取, 爬取到那些有位置标注的图像, 并存储到后台的数据库中。 至于如何确 定爬取到的图像是有位置标注的, 具体可以对图像进行解析, 判断解析 结果中是否包括位置数据即可。 即对所有图像进行解析, 以确定配置有 位置标注的图像。
[0045]当然, 在其他实施例中, 也可以直接在有位置标注的图像进 行标记, 该标记对应一个数据位, 直接可以写到图像的头数据中。
[0046] S103、 根据所述特征成像元素, 从所述多个图像中筛选出关 联于所述需求目标的图像;
[0047]本实施例中,在步骤 S103中具体可以对所述多个图像进行增 强识别处理, 以从所述多个图像中提取出特征成像元素。
[0048]本实施例中, 根据预先建立的特征库与所述特征成像元素进 行全局定位和局部定位, 以从所述多个图像中筛选出关联于所述需求目 标的图像。 一种具体的应用场景比如为: 通过搜集到的图像, 不限于图 片, 可以进行室内定位推荐, 例如在大型的商场, 很容易迷失, 要想要 找到人在哪一层的哪个位置就比较难, 如果对方发了一张图片过来, 那 么这边根据增强型图像分析, 就能知道对方在那一层哪一个位置。 附带 能做到室内定位。 另外上次举的例子, 因为用户上传了一些图像, 根据 这些图像不仅能知道这个大厦有咖啡厅, 而且还能知道在哪一层的哪一 个位置。
[0049]当然, 对图像进行增强处理, 也可以在步骤 S102之后、步骤 S103之前执行。
[0050]本申请获取用户所在位置图片样本空间, 再基于图像匹配获 取样本点的索引号, 命中图片中建筑物或风景的历史资料、 本地服务等 特征成像元素, 并将这些特征成像元素添加到对图片的属性信息说明中。
[0051]另外, 对图像的增强处理还可以包括将图片的拍摄者即用户 的属性信息添加到图片的属性信息中, 作为特征成像元素。
[0052]当包括不同的属性信息时, 可以对属性信息进行分类存储, 以形成不同类的特征成像元素。 特征库中图像和特征成像元素之间具有 -对应关系。
[0053] S104、 根据关联于所述需求目标的图像中配置的位置标注以 及所述物理位置进行资源推荐。
[0054]本实施例中, 步骤 S104中根据所述特征成像元素, 从所述多 个图像中筛选出关联于所述需求目标的图像时, 具体可以根据预先建立 的特征库与所述特征成像元素, 从所述多个图像中筛选出关联于所述需 求目标的图像, 不同的用户因为在同一时间处于同一地理位置构建用户 关键。
[0055]本实施例中, 特征成像元素可以是基于对同一成像对象的, 比如, 对同一餐饮地点、 旅游景点等, 也可以是基于对具有相同兴趣爱 好的, 比如具有相似的年龄。
[0056]在进行资源的推荐时, 可以直接进行地理位置和位置标注得 比对, 图片相似度的比对等, 从而实现资源的推荐。
[0057]具体地, 可以首先通过图像相似度的比对, 确定出具有相同 或者相似特征成像元素的图像, 再进一步进行地理位置和位置标注的比 对, 从而确定出表示同一地理位置或者一定地理位置范围内图像, 最终 形成推荐的资源, 在不同的用户之间进行共享, 对用户进行了聚合, 使 得可在不同用户之间进行资源的共享推荐, 从而提高了友好性。
[0058]本实施例中, 具体可以通过颜色差值的计算, 确定两幅图像 之间的相似度。 具体的处理过程如下: 将进行比较的两幅图像分别处理 形成白色背景单色图像, 再根据中心像素的相邻区域的参数 s计算出卷 积区域大小; 对白色背景单色图像上的每个输入像素点完成卷积计算, 再进一步计算每个输入像素点的图像力矩, 根据像素点图像力矩的大小 判断像素点的相似性, 如果两幅图像所有像素点的图像力矩位于相同的 阈值范围, 则判定整副图像之间的相似度。
[0059]当确定一定地理位置范围内图像时, 可以基于标注的位置的 范围进行图像的筛选。
[0060]在一些实施例中, 根据关联于所述需求目标的图像中配置的 位置标注以及所述物理位置进行资源推荐包括: 根据关联于所述需求目 标的图像中配置的位置标注以及所述物理位置生成推荐队列, 根据推荐 队列中资源的推荐优先级从高低的顺序资源推荐。
[0061] 图 2为本申请实施例二中资源推荐装置的结构示意图; 如图 2所示, 其包括:
[0062]第一程序单元 201, 用于确定用户的物理位置以及用户的需 求目标;
[0063]第二程序单元 202 , 用于确定配置有位置标注的多个图像, 并从所述多个图像中提取出特征成像元素;
[0064]第三程序单元 203 用于根据所述特征成像元素, 从所述多 个图像中筛选出关联于所述需求目标的图像;
[0065]第四程序单元 204 用于根据关联于所述需求目标的图像中 配置的位置标注以及所述物理位置进行资源推荐。
[0066]进一步地, 第一程序单元 201进一步用于根据对用户输入的 解析结果, 确定用户的物理位置以及用户的需求目标。 所述用户输入为 文本输入或者语音输入中的至少一种。
[0067]进一步地, 第一程序单元 201进一步用于通过配置的输入接 口, 捕获所述用户输入。
[0068]进一步地, 第二程序单元 202进一步用于对所有图像进行解 析, 以确定配置有位置标注的图像。
[0069]进一步地, 第二程序单元 202进一步用于对所述多个图像进 行增强识别处理, 以从所述多个图像中提取出特征成像元素。
[0070]进一步地, 第三程序单元 203进一步用于根据预先建立的特 征库与所述特征成像元素, 从所述多个图像中筛选出关联于所述需求目 标的图像。
[0071] 图 3为本申请实施例三中资源推荐装置的结构示意图; 如图 3所示, 其包括上述实施例中的第一程序单元 201、 第二程序单元 202、 第三程序单元 203、 第四程序单元 204, 还包括, 第五程序单元 205, 用 于基于神经网络预先建立上述方法实施例中的特征库。
[0072]进一步地, 本实施例中, 第四程序单元 204进一步用于根据 关联于所述需求目标的图像中配置的位置标注以及所述物理位置生成推 荐队列, 根据推荐队列中资源的推荐优先级从高低的顺序资源推荐。
[0073] 图 4为本申请实施例四中设备 /终端 /服务器的结构示意图; 该设备 /终端 /服务器可以包括:
[0074]一个或多个处理器 401 ;
[0075]计算机可读介质 402 , 可以配置为存储一个或多个程序, [0076]当所述一个或多个程序被所述一个或多个处理器执行, 使得 所述一个或多个处理器实现如上述任一实施例中所述资源推荐方法。
[0077] 图 5为本申请实施例五中设备 /终端 /服务器的硬件结构; 如 图 5所示, 该设备 /终端 /服务器的硬件结构可以包括: 处理器 501, 通信 接口 502, 计算机可读介质 503和通信总线 504;
[0078]其中处理器 501、通信接口 502、计算机可读介质 503通过通 信总线 504完成相互间的通信;
[0079]可选的, 通信接口 502可以为通信模块的接口, 如 GSM模块 的接口;
[0080]其中, 处理器 501具体可以配置为: 确定用户的物理位置以 及用户的需求目标; 确定配置有位置标注的多个图像, 并从所述多个图 像中提取出特征成像元素; 根据所述特征成像元素, 从所述多个图像中 筛选出关联于所述需求目标的图像; 根据关联于所述需求目标的图像中 配置的位置标注以及所述物理位置进行资源推荐。
[0081]处理器 501 可以是通用处理器, 包括中央处理器 (Central Processing Unit , 简称 CPU)、 网络处理器 (Network Processor , 简称 NP)等; 还可以是数字信号处理器 (DSP)、 专用集成电路 (ASIC)、 现成可 编程门阵列 (FPGA)或者其它可编程逻辑器件、 分立门或者晶体管逻辑器 件、 分立硬件组件。 可以实现或者执行本申请实施例中的公开的各方法、 步骤及逻辑框图。 通用处理器可以是微处理器或者该处理器也可以是任 何常规的处理器等。
[0082]计算机可读介质 503可以是, 但不限于, 随机存取存储介质 ( Random Access Memory, RAM) , 只读存储介质 (Read Only Memory, ROM) , 可编程只读存储介质 (Programmable Read-Only Memory, PROM) , 可擦除只读存储介质 ( Erasable Programmable Read-Only Memory , EPROM ) , 电可擦除只读存储介质 ( Electric Erasable Programmable Read-Only Memory, EEPR0M) 等。
[0083]特别地, 根据本申请的实施例, 上文参考流程图描述的过程 可以被实现为计算机软件程序。 例如, 本申请的实施例包括一种计算机 程序产品, 其包括承载在计算机可读介质上的计算机程序, 该计算机程 序包含配置为执行流程图所示的方法的程序代码。 在这样的实施例中, 该计算机程序可以通过通信部分从网络上被下载和安装, 和 /或从可拆卸 介质被安装。 在该计算机程序被中央处理单元 (CPU) 执行时, 执行本申 请的方法中限定的上述功能。
[0084]需要说明的是, 本申请所述的计算机可读介质可以是计算机 可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。 计 算机可读介质例如可以但不限于是电、 磁、 光、 电磁、 红外线、 或半导 体的***、 装置或器件, 或者任意以上的组合。 计算机可读存储介质的 更具体的例子可以包括但不限于: 具有一个或多个导线的电连接、 便携 式计算机磁盘、硬盘、 随机访问存储介质 (RAM) 、 只读存储介质 (ROM) 、 可擦式可编程只读存储介质 (EPR0M或闪存) 、 光纤、 便携式紧凑磁盘只 读存储介质 (⑶ -ROM) 、 光存储介质件、 磁存储介质件、 或者上述的任 意合适的组合。 在本申请中, 计算机可读存储介质可以是任何包含或存 储程序的有形介质, 该程序可以被指令执行***、 装置或者器件使用或 者与其结合使用。 而在本申请中, 计算机可读的信号介质可以包括在基 带中或者作为载波一部分传播的数据信号, 其中承载了计算机可读的程 序代码。 这种传播的数据信号可以采用多种形式, 包括但不限于电磁信 号、 光信号或上述的任意合适的组合。 计算机可读的信号介质还可以是 计算机可读存储介质以外的任何计算机可读介质, 该计算机可读介质可 以发送、 传播或者传输配置为由指令执行***、 装置或者器件使用或者 与其结合使用的程序。 计算机可读介质上包含的程序代码可以用任何适 当的介质传输, 包括但不限于: 无线、 电线、 光缆、 RF等等, 或者上述 的任意合适的组合。
[0085]可以以一种或多种程序设计语言或其组合来编写配置为执行 本申请的操作的计算机程序代码, 所述程序设计语言包括面向对象的程 序设计语言一诸如 Java、 Smal ltalk、 C++, 还包括常规的过程式程序设 计语言一诸如” C”语言或类似的程序设计语言。 程序代码可以完全地在 用户计算机上执行、 部分地在用户计算机上执行、 作为一个独立的软件 包执行、 部分在用户计算机上部分在远程计算机上执行、 或者完全在远 程计算机或服务器上执行。 在涉及远程计算机的情形中, 远程计算机可 以通过任意种类的网络: 包括局域网 (LAN)或广域网 (WAN)—连接到用户 计算机, 或者, 可以连接到外部计算机 (例如利用因特网服务提供商来 通过因特网连接) 。
[0086] 附图中的流程图和框图, 图示了按照本申请各种实施例的系 统、 方法和计算机程序产品的可能实现的体系架构、 功能和操作。 在这 点上, 流程图或框图中的每个方框可以代表一个模块、 程序段、 或代码 的一部分, 该模块、 程序段、 或代码的一部分包含一个或多个配置为实 现规定的逻辑功能的可执行指令。 上述具体实施例中有特定先后关系, 但这些先后关系只是示例性的, 在具体实现的时候, 这些步骤可能会更 少、 更多或执行顺序有调整。 即在有些作为替换的实现中, 方框中所标 注的功能也可以以不同于附图中所标注的顺序发生。 例如, 两个接连地 表示的方框实际上可以基本并行地执行, 它们有时也可以按相反的顺序 执行, 这依所涉及的功能而定。 也要注意的是, 框图和 /或流程图中的每 个方框、 以及框图和 /或流程图中的方框的组合, 可以用执行规定的功能 或操作的专用的基于硬件的***来实现, 或者可以用专用硬件与计算机 指令的组合来实现。
[0087]描述于本申请实施例中所涉及到的单元可以通过软件的方式 实现, 也可以通过硬件的方式来实现。 所描述的单元也可以设置在处理 器中, 例如, 可以描述为: 一种处理器包括需求目标确定单元、 特征提 取单元、 筛选单元、 推荐单元。 其中: [0088]需求目标确定单元, 配置为确定用户的物理位置以及用户的 需求目标;
[0089]特征提取单元, 配置为确定配置有位置标注的多个图像, 并 从所述多个图像中提取出特征成像元素;
[0090]筛选单元, 配置为根据所述特征成像元素, 从所述多个图像 中筛选出关联于所述需求目标的图像;
[0091]推荐单元, 配置为根据关联于所述需求目标的图像中配置的 位置标注以及所述物理位置进行资源推荐。
[0092]其中, 这些单元的名称在某种情况下并不构成对该单元本身 的限定, 例如, 需求目标确定单元还可以被描述为“确定用户的物理位 置以及用户的需求目标的单元” 。
[0093]作为另一方面, 本申请还提供了一种计算机可读介质, 其上 存储有计算机程序, 该程序被处理器执行时实现如上述任一实施例中所 描述的方法。
[0094]作为另一方面, 本申请还提供了一种计算机可读介质, 该计 算机可读介质可以是上述实施例中描述的装置中所包含的; 也可以是单 独存在, 而未装配入该装置中。 上述计算机可读介质承载有一个或者多 个程序, 当上述一个或者多个程序被该装置执行时, 使得该装置: 确定 用户的物理位置以及用户的需求目标; 确定配置有位置标注的多个图像, 并从所述多个图像中提取出特征成像元素; 根据所述特征成像元素, 从 所述多个图像中筛选出关联于所述需求目标的图像; 根据关联于所述需 求目标的图像中配置的位置标注以及所述物理位置进行资源推荐。
[0095]在本申请的各种实施方式中所使用的表述“第一”、 “第二”、 “所述第一”或“所述第二”可修饰各种部件而与顺序和 /或重要性无关, 但是这些表述不限制相应部件。 以上表述仅配置为将元件与其它元件区 分开的目的。 例如, 第一用户设备和第二用户设备表示不同的用户设备, 虽然两者均是用户设备。 例如, 在不背离本申请的范围的前提下, 第一 元件可称作第二元件, 类似地, 第二元件可称作第一元件。
[0096]当一个元件(例如,第一元件)称为与另一元件(例如,第二元 件) “(可操作地或可通信地)联接”或“(可操作地或可通信地)联接至” 另一元件(例如, 第二元件)或“连接至”另一元件(例如, 第二元件)时, 应理解为该一个元件直接连接至该另一元件或者该一个元件经由又一个 元件(例如, 第三元件)间接连接至该另一个元件。 相反, 可理解, 当元 件(例如, 第一元件)称为“直接连接”或“直接联接”至另一元件(第二 元件)时, 则没有元件(例如, 第三元件)***在这两者之间。
[0097] 以上描述仅为本申请的较佳实施例以及对所运用技术原理的 说明。 本领域技术人员应当理解, 本申请中所涉及的发明范围, 并不限 于上述技术特征的特定组合而成的技术方案, 同时也应涵盖在不脱离上 述发明构思的情况下, 由上述技术特征或其等同特征进行任意组合而形 成的其它技术方案。 例如上述特征与本申请中公开的 (但不限于) 具有 类似功能的技术特征进行互相替换而形成的技术方案。

Claims

权 利 要 求 书
1.一种资源推荐方法, 其特征在于, 包括:
确定用户的物理位置以及用户的需求目标;
确定配置有位置标注的多个图像, 并从所述多个图像中提取出特征 成像元素;
根据所述特征成像元素, 从所述多个图像中筛选出关联于所述需求 目标的图像;
根据关联于所述需求目标的图像中配置的位置标注以及所述物理位 置进行资源推荐。
2.根据权利要求 1所述的方法, 其特征在于, 确定用户的物理位置 以及用户的需求目标包括: 根据对用户输入的解析结果, 确定用户的物 理位置以及用户的需求目标。
3.根据权利要求 2所述的方法, 其特征在于, 所述用户输入为文本 输入或者语音输入中的至少一种。
4.根据权利要求 2所述的方法, 其特征在于, 还包括: 通过配置的 输入接口, 捕获所述用户输入。
5.根据权利要求 1所述的方法, 其特征在于, 还包括: 对所有图像 进行解析, 以确定配置有位置标注的图像。
6.根据权利要求 1所述的方法, 其特征在于, 还包括: 对所述多个 图像进行增强识别处理, 以从所述多个图像中提取出特征成像元素。
7.根据权利要求 6所述的方法, 其特征在于, 根据所述特征成像元 素, 从所述多个图像中筛选出关联于所述需求目标的图像包括: 根据预 先建立的特征库与所述特征成像元素, 从所述多个图像中筛选出关联于 所述需求目标的图像。
8.根据权利要求 7所述的方法, 其特征在于, 还包括: 基于神经网 络预先建立特征库。
9.根据权利要求 7所述的方法, 其特征在于, 根据预先建立的特征 库与所述特征成像元素, 从所述多个图像中筛选出关联于所述需求目标 的图像包括, 根据预先建立的特征库与所述特征成像元素进行全局定位 和局部定位, 以从所述多个图像中筛选出关联于所述需求目标的图像。
10. 根据权利要求 l所述的方法, 其特征在于, 根据关联于所述需 求目标的图像中配置的位置标注以及所述物理位置进行资源推荐包括: 根据关联于所述需求目标的图像中配置的位置标注以及所述物理位置生 成推荐队列, 根据推荐队列中资源的推荐优先级从高低的顺序资源推荐。
11. 一种资源推荐装置, 其特征在于, 包括:
第一程序单元, 用于确定用户的物理位置以及用户的需求目标; 第二程序单元, 用于确定配置有位置标注的多个图像, 并从所述多 个图像中提取出特征成像元素;
第三程序单元, 用于根据所述特征成像元素, 从所述多个图像中筛 选出关联于所述需求目标的图像;
第四程序单元, 用于根据关联于所述需求目标的图像中配置的位置 标注以及所述物理位置进行资源推荐。
12. —种电子设备, 包括:
一个或多个处理器;
计算机可读介质, 用于存储一个或多个程序,
当所述一个或多个程序被所述一个或多个处理器执行, 使得所述一 个或多个处理器实现如权利要求 1-9中任一所述的方法。
13. —种计算机可读介质, 其上存储有计算机程序, 其特征在于, 该程序被处理器执行时实现如权利要求 1-9中任一所述的方法。
PCT/IB2018/057156 2018-08-27 2018-09-18 资源推荐方法、装置、电子设备以及计算机可读介质 WO2020044094A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810979499.3A CN109168127A (zh) 2018-08-27 2018-08-27 资源推荐方法、装置、电子设备以及计算机可读介质
CN201810979499.3 2018-08-27

Publications (1)

Publication Number Publication Date
WO2020044094A1 true WO2020044094A1 (zh) 2020-03-05

Family

ID=64896676

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2018/057156 WO2020044094A1 (zh) 2018-08-27 2018-09-18 资源推荐方法、装置、电子设备以及计算机可读介质

Country Status (2)

Country Link
CN (1) CN109168127A (zh)
WO (1) WO2020044094A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112781581A (zh) * 2020-12-25 2021-05-11 北京小狗吸尘器集团股份有限公司 应用于扫地机的移动至儿童推车路径生成方法、装置

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7156242B2 (ja) * 2019-10-18 2022-10-19 トヨタ自動車株式会社 情報処理装置、プログラム及び制御方法
CN113923252B (zh) * 2021-09-30 2023-11-21 北京蜂巢世纪科技有限公司 图像显示装置、方法和***

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105589938A (zh) * 2015-12-13 2016-05-18 公安部第三研究所 基于fpga的图像检索***及检索方法
CN106528834A (zh) * 2016-11-17 2017-03-22 百度在线网络技术(北京)有限公司 基于人工智能的图片资源推送方法及装置
CN106899644A (zh) * 2015-12-21 2017-06-27 北京奇虎科技有限公司 拍照处理方法和服务器
CN107316042A (zh) * 2017-07-18 2017-11-03 盛世贞观(北京)科技有限公司 一种绘画图像检索方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11003830B2 (en) * 2016-09-26 2021-05-11 Adobe Inc. Providing location-based font recommendations
CN108197215A (zh) * 2017-12-28 2018-06-22 努比亚技术有限公司 一种推荐方法、服务器及计算机可读存储介质
CN108256500A (zh) * 2018-02-05 2018-07-06 广东欧珀移动通信有限公司 信息的推荐方法、装置、终端及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105589938A (zh) * 2015-12-13 2016-05-18 公安部第三研究所 基于fpga的图像检索***及检索方法
CN106899644A (zh) * 2015-12-21 2017-06-27 北京奇虎科技有限公司 拍照处理方法和服务器
CN106528834A (zh) * 2016-11-17 2017-03-22 百度在线网络技术(北京)有限公司 基于人工智能的图片资源推送方法及装置
CN107316042A (zh) * 2017-07-18 2017-11-03 盛世贞观(北京)科技有限公司 一种绘画图像检索方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112781581A (zh) * 2020-12-25 2021-05-11 北京小狗吸尘器集团股份有限公司 应用于扫地机的移动至儿童推车路径生成方法、装置
CN112781581B (zh) * 2020-12-25 2023-09-12 北京小狗吸尘器集团股份有限公司 应用于扫地机的移动至儿童推车路径生成方法、装置

Also Published As

Publication number Publication date
CN109168127A (zh) 2019-01-08

Similar Documents

Publication Publication Date Title
US8055271B2 (en) Intelligent location-to-cell mapping using annotated media
ES2731948T3 (es) Método y aparato para almacenamiento en caché flexible de medios distribuidos
US8483715B2 (en) Computer based location identification using images
CN106845470B (zh) 地图数据采集方法和装置
AU2014386727B2 (en) Polygon-based indexing of places
US20140343984A1 (en) Spatial crowdsourcing with trustworthy query answering
US20160307101A1 (en) Method, device, and server for friend recommendation
WO2019000880A1 (zh) 实景导航方法、装置、设备及计算机可读存储介质
US8788762B2 (en) Methods and apparatuses for data resource provision
CN103080930A (zh) 用于辨识和映射内容的方法和装置
US11663751B2 (en) System and method for selecting scenes for browsing histories in augmented reality interfaces
TW201211916A (en) Method and apparatus for recognizing objects in media content
CN107077507B (zh) 一种信息推送方法、装置和***
WO2017071122A1 (zh) 一种用于获取无线接入点的接入信息的方法与设备
WO2020044094A1 (zh) 资源推荐方法、装置、电子设备以及计算机可读介质
CN112434811A (zh) 知识图谱构建方法及装置、计算设备、存储介质
CN111782980B (zh) 地图兴趣点的挖掘方法、装置、设备及存储介质
US20220036113A1 (en) Surrogate Metadata Aggregation for Dynamic Content Assembly
CN104520848A (zh) 按照出席者搜索事件
KR102149914B1 (ko) 클라우드 소싱 기반 관심 지점 정보 업데이트 방법, 및 이를 위한 장치
CN114708545A (zh) 基于图像的对象侦测方法、装置、设备和存储介质
CN104572830A (zh) 推荐拍摄信息的处理方法及装置
US20120165043A1 (en) Mobile communication based tagging
CN111797266B (zh) 图像处理方法和装置、存储介质和电子设备
CN113610034A (zh) 识别视频中人物实体的方法、装置、存储介质及电子设备

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: 18931885

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18931885

Country of ref document: EP

Kind code of ref document: A1