WO2014079327A1 - 信息推送方法和系统、数字电视接收终端及计算机存储介质 - Google Patents

信息推送方法和系统、数字电视接收终端及计算机存储介质 Download PDF

Info

Publication number
WO2014079327A1
WO2014079327A1 PCT/CN2013/086915 CN2013086915W WO2014079327A1 WO 2014079327 A1 WO2014079327 A1 WO 2014079327A1 CN 2013086915 W CN2013086915 W CN 2013086915W WO 2014079327 A1 WO2014079327 A1 WO 2014079327A1
Authority
WO
WIPO (PCT)
Prior art keywords
frequency
photo
target
information
matching
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/CN2013/086915
Other languages
English (en)
French (fr)
Inventor
张祥
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.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen 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 Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Publication of WO2014079327A1 publication Critical patent/WO2014079327A1/zh
Priority to US14/712,945 priority Critical patent/US9596520B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0252—Targeted advertisements based on events or environment, e.g. weather or festivals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/4223—Cameras
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/8146—Monomedia components thereof involving graphical data, e.g. 3D object, 2D graphics
    • H04N21/8153—Monomedia components thereof involving graphical data, e.g. 3D object, 2D graphics comprising still images, e.g. texture, background image

Definitions

  • the present invention relates to the field of information push technology, and in particular, to an information push method and system, a digital television receiving terminal, and a computer storage medium.
  • An information pushing method includes the following steps:
  • An information push system comprising:
  • a photo acquisition module configured to obtain a photo of the environment in which the user is located
  • a target recognition module configured to identify a target from the photo and count the frequency or frequency of occurrence
  • the information pushing module is configured to push information about the target to the client according to the frequency or frequency.
  • the above information pushing method and the information pushing system adopt the science by acquiring the picture of the environment in which the user is located, and by identifying the relevant target object from the picture, and then pushing the relevant information of the target object according to the frequency or frequency of occurrence of the target object.
  • a digital television receiving terminal comprising: the information pushing system as described above.
  • the digital television receiving terminal can acquire a picture of the environment in which the television user is located, and by using the relevant target object from the picture, and then pushing the relevant information of the target according to the frequency or frequency of occurrence of the target object.
  • FIG. 1 is a flow chart of an information push method of an embodiment
  • Figure 2 is a flow chart for identifying an object from a photo in one embodiment
  • 3 is an effect diagram of a bitmap image after grayscale processing in one embodiment
  • 4 is an effect diagram of a photo after binarization processing in one embodiment
  • FIG. 5 is an effect diagram of a photo after denoising processing in an embodiment
  • FIG. 6 is a flow chart of information related to pushing the target to the client in an embodiment
  • 7 is a schematic structural diagram of an information push system of an embodiment
  • 8 is a schematic structural diagram of a target recognition module of an embodiment
  • 9 is a schematic structural diagram of a photo matching unit of an embodiment
  • FIG. 10 is a schematic structural diagram of an information push module of an embodiment.
  • FIG. 1 is a flowchart of an information pushing method according to an embodiment, which mainly includes the following steps:
  • Step S10 Obtain a photo of the environment in which the user is located.
  • a photo of the surroundings in the environment where the user terminal (that is, the information push terminal) is located may be obtained, where the environment of the user terminal includes, but is not limited to, a home environment, a conference environment, an office environment, etc.
  • a certain route (such as regular collection, real-time shooting, etc.) obtains a photo of the environment in which the user is located, and the photo can be used to extract the tag information of the relevant target.
  • the camera may be used to obtain a photo in real time through a camera. Specifically, the camera captures a photo of the environment in which the user is located at a set time, where the camera includes a set top camera, a computer camera, and a surveillance camera. The photograph is taken by means of regular shooting, so that the influence on the user equipment can be reduced while satisfying the required photograph.
  • the set-top box when taking a photo in a home environment that is taken with a set-top camera, shooting when the set-top box is idle, by detecting the set-top box CPU The usage rate is used to judge whether it is idle. When the CPU usage is lower than a certain threshold, it is judged to be idle, and the shooting operation can be performed without affecting the normal use of the client.
  • Step S30 identifying the target from the photo and counting the frequency or frequency of occurrence.
  • the image recognition technology is mainly used to identify the relevant target object from the photo, and the analysis may be performed from the external structural shape of the target object or some specific mark, and then the frequency of the target object may be counted or The frequency, for example, can identify the relevant item by identifying the mark of the product.
  • the mark of different goods has a distinct distinguishing feature, so the mark is used to identify the higher accuracy.
  • step S30 includes:
  • Step S350 matching the photo with the pre-stored identification picture.
  • the technical means of image matching is mainly used to identify related objects appearing in the photo; specifically, the process of image matching includes the following steps:
  • Step S351 Perform pattern matching on the matrix data of the photo with the matrix block of the recognized picture in the database.
  • the matrix data of the identification picture corresponding to each target object in the pre-existing database is pattern-matched with the matrix block in the photo, wherein the pattern matching process may adopt a universal invariant matrix feature matching algorithm.
  • Step S352 Calculate a degree of matching between the photo and the recognized picture.
  • the degree of matching between the portion of the marked portion and the portion of the photo can be calculated, that is, the degree of matching between the two.
  • Step S353 If the matching degree is greater than a set threshold, determine that the photo is successfully matched with the corresponding recognized picture.
  • the matching degree calculated by the preset threshold value is used.
  • the matching degree is greater than the threshold value, it indicates that the two have high similarity and have the same characteristics, and the two can be judged to be successful.
  • Step S360 adding 1 to the number of occurrences of the target corresponding to the successfully recognized recognition picture And update the frequency or frequency of the target.
  • the data matrix of the recognized picture of each target can be pre-stored corresponding to a target ID. After the photo is associated with the recognized image in the above matching process, the corresponding target ID is obtained and the matching data is sent to the server, and the number of occurrences of the corresponding object in the server is increased by one. , recalculate the frequency or frequency of the target, and update the original data.
  • the matching data is transmitted to a networked server for corresponding recording by identifying the relevant item in the set top box.
  • the amount of data may be too large, so in order to reduce the amount of data calculation in the recognition process and improve the recognition accuracy; preferably, step S30 is further included in step S350.
  • the pre-processing step is performed on the photo, and the pre-processing step specifically includes:
  • S330 And performing the binarization processing on the grayscale converted bitmap image; specifically, converting the pixels of the grayscale processed image into a black and white image, and the processing manner may be: setting the grayscale value of the image to be smaller than a certain one.
  • the pixels of the fixed threshold are all converted to black dots, and the points larger than a set threshold are converted to white dots, as shown in the figure. 4,
  • Figure 4 is a binarized image rendering, which can be further reduced by binarization.
  • S340 Removing the noise on the binarized bitmap image; specifically, optimizing the binarized image to remove noise, first identifying the noise point, and then removing the size block noise; for the noise discrimination, scanning may be performed.
  • the method of the picture data matrix when the black point is encountered in the scan, the adjacent pixels are recursively scanned, and when the continuous pixel is less than a certain value or greater than a certain value, it can be determined as small noise and large noise, as shown in the figure.
  • Figure 5 is an image rendering after denoising processing; since the noise may affect the judgment process of image recognition, the accuracy of recognition can be improved by the above-mentioned denoising optimization process.
  • Step S50 Push the related information of the target object to the user end according to the frequency or frequency.
  • step S50 specifically includes:
  • Step S510 Count the frequency or frequency of the target in the environment where the user is located in the set time period.
  • the frequency or frequency of occurrence of each target in the set time period is counted.
  • the total number and frequency of occurrence of the target in the environment of the user end are determined; by counting the frequency of occurrence of each target, it can be determined that the target accounts for a set period of time. The proportion of all targets present.
  • the frequency or frequency of the target object in the environment where the user terminal is located in the time period set by the statistics can quantify the degree of association between the user end and the target object, and obtain scientific and objective quantitative data. As a reference for information push.
  • the target is a product and needs to be promoted for the product
  • in the home environment there are more household goods for daily use.
  • In the venue environment there are more items such as meeting place equipment, in the office environment. Among them, there are more items such as office supplies.
  • By counting the frequency or frequency of occurrence of products in each occasion it is possible to obtain quantitative data of the frequency of occurrence of products in each occasion, and the products with higher frequency or frequency are more likely to appear.
  • the frequency or frequency of household daily goods is relatively high. Therefore, when information is promoted, statistical data is used as a reference, and information about household daily goods is emphasized for the user side in the home environment.
  • Step S520 Push the related information of the target object to the user end according to the frequency or frequency.
  • the frequency or frequency can be used as a reference, and when the related information of the target is pushed, the horizontal comparison and the vertical direction can be performed. Contrast, thereby adjusting the target information pushed to the client.
  • the target object is a product and needs to promote the advertisement information for the product
  • the product with a higher frequency or frequency is selected, and the advertisement information is preferentially pushed to the terminal of the user terminal (including a display medium such as a television or a computer), so that the push is made.
  • the advertising information has higher precision and achieves accurate advertising, which leads to better advertising effects.
  • FIG. 7 is a schematic structural diagram of an information push system according to an embodiment, which mainly includes: a photo acquisition module 10 , target recognition module 30 and information push module 50.
  • the photo obtaining module 10 is configured to obtain a photo of an environment in which the user is located.
  • the photo acquisition module 10 The photos around the environment where the user is located can be obtained, and the environment of the user terminal includes, but is not limited to, a home environment, a venue environment, and an office environment, and can be obtained through certain channels (such as periodic collection, real-time shooting, etc.). A photo to the environment in which the user is located, through which the photo can be used to extract tag information of the relevant object.
  • the photo capture module 10 The camera can be used to obtain a photo in real time through a camera. Specifically, the camera captures a photo of the environment in which the user is located at a set time.
  • the camera includes a set top camera, a computer camera, a surveillance camera, etc.
  • the photo passes. Shooting is done on a regular basis, which reduces the impact on the client device while meeting the desired photo.
  • photo acquisition module 10 When taking a photo in a home environment that is shot with a set-top box camera, shoot when the set-top box is idle, and check if the CPU of the set-top box is used to determine whether it is idle or not. When the usage rate is lower than a certain threshold, it is judged to be in an idle state, and the shooting operation can be performed without affecting the normal use of the user terminal.
  • the target identification module 30 is configured to identify an object from the photo and count the frequency or frequency of occurrence.
  • the target recognition module 30 The image recognition technology is mainly used to identify related objects from the photos, and can be identified and analyzed from the external structural shape of the target or certain specific marks.
  • the target recognition module 30 The related products can be identified by identifying the mark of the product. Generally, the mark of different goods has a large distinguishing feature, so the mark recognition has higher accuracy.
  • a photo matching unit 350 for the target recognition module 30, as shown in FIG. 8, further comprising: a photo matching unit 350 and a data recording unit 360 .
  • the photo matching unit 350 is configured to match the photo with the pre-stored identification picture.
  • the photo matching unit 350 The image matching method is mainly used to identify related objects appearing in the photo; specifically, as shown in FIG. 9, the photo matching unit 350 further includes: a pattern matching unit 351. The matching degree frequency calculating unit 352 and the matching determining unit 353.
  • the pattern matching unit 351 is configured to perform pattern matching on the matrix data of the photo with the matrix block of the recognized picture in the database.
  • the pattern matching unit 351 The matrix data of the identification picture corresponding to each target in the pre-existing database is pattern-matched with the matrix block in the photo, wherein the pattern matching process may adopt a universal invariant matrix feature matching algorithm.
  • the matching degree frequency calculation unit 352 is configured to calculate a degree of matching between the photo and the recognized picture.
  • the matching degree frequency calculation unit 352 It is possible to calculate the degree of matching between the portion of the marked portion and the portion of the photo, that is, the degree of matching between the two.
  • the matching determining unit 353 is configured to determine that the photo is successfully matched with the corresponding recognized picture if the matching degree is greater than the set threshold.
  • the matching determination unit 353 The matching degree calculated by the preset threshold is used. When the matching degree is greater than the threshold, it indicates that the two have high similarity and have the same characteristics, and it can be judged that the matching is successful.
  • the data recording unit 360 is configured to add 1 to the number of occurrences of the target corresponding to the successfully recognized recognition picture. And update the frequency or frequency of the target.
  • the data recording unit 360 can pre-store the data matrix of the recognized picture of each target corresponding to a target ID. After the photo and the recognition image are associated in the above matching process, the corresponding target ID is obtained and the matching data is sent to the server, and the number of occurrences of the target corresponding to the server is increased by one. , recalculate the frequency or frequency of the target, and update the original data.
  • the matching data is transmitted to a networked server for corresponding recording by identifying the relevant item in the set top box.
  • the amount of operation data may be too large, so in order to reduce the amount of data calculation in the recognition process and improve the recognition accuracy; preferably, the pre-target recognition module 30 Also included is a photo conversion unit 310, a gradation conversion unit 320, a binarization processing unit 330, and a noise removal unit 340 disposed before the photo matching unit 350.
  • the photo conversion unit 310 is configured to generate a bitmap image of the photo.
  • the photo conversion unit 310 analyzes the photo BMP. After the header information, the picture data is decoded to obtain a bitmap file, and a matrix array of photos can be obtained for subsequent processing.
  • the gradation conversion unit 320 is configured to perform gradation conversion on the bitmap image.
  • the gradation conversion unit 320 can remove the color information in the image after performing the gradation conversion, thereby reducing the subsequent calculation amount.
  • the binarization processing unit 330 is configured to perform binarization processing on the gradation converted bitmap image.
  • the binarization processing unit 330 can further reduce the amount of calculation of subsequent processing by the binarization processing.
  • the noise removing unit 340 is configured to remove noise on the binarized bitmap image.
  • the noise removal unit 340 performs the above-described denoising optimization process, the accuracy of the recognition can be improved.
  • the information pushing module 50 is configured to push information about the target to the client according to the frequency or frequency.
  • the information pushing module 50 Mainly based on the frequency or frequency of the object appearing in the environment of the user end, the relevant information of the target object, such as advertisement information and promotion information, can be pushed to the user end to display information about the attribute or feature of the target object.
  • the information push module 50 further includes a statistics unit 510 and a push unit 520.
  • the statistic unit 510 is configured to count the frequency or frequency of the target in the environment where the user is located in the set time period.
  • the statistical unit 510 Counting the frequency or frequency of occurrence of each target in the time period set by statistics; by counting the frequency of occurrence of each target, the total number and frequency of occurrence of the target in the environment where the user is located can be determined; by counting each target The frequency of occurrence determines the proportion of the target that appears in all targets during the set time period.
  • the frequency or frequency of the target object in the environment where the user terminal is located in the time period set by the statistics can quantify the degree of association between the user end and the target object, and obtain scientific and objective quantitative data. As a reference for information push.
  • the target is a product and needs to be promoted for the product
  • in the home environment there are more household goods for daily use.
  • In the venue environment there are more items such as meeting place equipment, in the office environment. Among them, there are more items such as office supplies.
  • By counting the frequency or frequency of occurrence of products in each occasion it is possible to obtain quantitative data on the frequency of occurrence of products in each occasion, and the frequency or frequency is higher to appear more commodities, such as household goods in the home environment.
  • the frequency or frequency of occurrence is relatively high. Therefore, when the information is promoted, the statistical data is used as a reference, and the information about the household daily goods is emphasized for the user side in the home environment.
  • the pushing unit 520 pushes related information of the target to the client according to the frequency.
  • the pushing unit 520 According to calculating the frequency or frequency of each target in the environment where the user is located, the frequency or frequency can be used as a reference, and when the related information of the target is pushed, the horizontal comparison and the vertical comparison can be performed, thereby adjusting the user to the user. Target information pushed by the end.
  • the target object is a product and needs to promote the advertisement information for the product
  • the product with a higher frequency or frequency is selected, and the advertisement information is preferentially pushed to the terminal of the user terminal (including a display medium such as a television or a computer), so that the push is made.
  • the advertising information has higher precision and achieves accurate advertising, which leads to better advertising effects.
  • the information push system of the present invention has a one-to-one correspondence with the information push method of the present invention, and the technical features and advantageous effects of the embodiment of the above information push method are applicable to the embodiment of the information push system.
  • a digital television receiving terminal comprising: the information pushing system as described above.
  • the digital television receiving terminal can acquire a picture of the environment in which the user is located, and by uploading relevant objects from the picture, and then pushing relevant information of the target according to the frequency or frequency of occurrence of the target, By using scientific and objective statistical data as a reference for pushing information to TV, it has higher precision.
  • the digital TV receiving terminal can perform accurate advertisement delivery, thereby bringing better advertising effects.
  • the information pushing method and system of the present invention collects photos of the environment in which the user is located, and uses scientific and objective technical means to collect the target object at the user end by identifying relevant objects from the photos.
  • the frequency or frequency of occurrence in the environment, with statistical data as a reference the relevant information of the relevant target is pushed to the users of different habits, and the pushed information has higher precision and can be used for high-precision advertising. Delivery, reduce advertising costs, and improve advertising effectiveness. In addition, it can also play an important role in advertising effectiveness surveys, market research of commodities, etc. It can provide accurate data reference and advanced technical support.
  • the storage medium may be a magnetic disk, an optical disk, or a read-only storage memory ( Read-Only Memory (ROM) or Random Access Memory (RAM).
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • the present invention further provides a storage medium comprising a computer readable program, which can implement the present invention in any of the above manners when the computer readable program in the storage medium is executed Information push method.
  • the method of the embodiment of the present invention as described above may be installed on the corresponding machine device in the form of software, and the above-mentioned information push process is completed by controlling the relevant processing device while the software is running.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Computer Graphics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)

Abstract

本发明提供一种信息推送方法，包括如下步骤：获取用户端所处环境的照片；从所述照片中识别出目标物并统计出现的频数或频率；根据所述频数或频率向所述用户端推送所述目标物的相关信息。此外，还提供一种信息推送系统、数字电视接收终端及计算机存储介质，本发明的技术方案，釆用科学、客观的技术手段统计用户端所处环境中目标物出现频繁程度的量化数据，并以该统计数据作为推送的参考，具有更高的精准度。

Description

信息推送方法和系统、数字电视接收终端及计算机存储介质
技术领域
本发明涉及信息推送技术领域，特别是涉及一种信息推送方法和系统、数字电视接收终端及计算机存储介质。
背景技术
目前，在市场经济条件下，竞争越发激烈，把握准确信息占据了极其重要的作用，对于信息推送来说，如何向用户端推送精准度更高的信息成为了信息推送者不断改进的地方，传统的信息推送技术，一般是通过人工调查获得一定的样本数据，然后将其作为信息推送的主要参考，这种技术缺乏技术手段来保障，可靠性低，导致向用户端推送的信息的精准度低。
发明内容
基于此，有必要提供一种能提高向用户端推送信息的精准度的信息推送方法、信息推送系统及数字电视接收终端。
一种信息推送方法，包括如下步骤：
获取用户端所处环境的照片；
从所述照片中识别出目标物并统计出现的频数或频率；
根据所述频数或频率向所述用户端推送所述目标物的相关信息。
此外，还有必要提供一种能提高向用户端推送信息的精准度的信息推送系统。
一种信息推送系统，包括：
照片获取模块，用于获取用户端所处环境的照片；
目标识别模块，用于从所述照片中识别出目标物并统计出现的频数或频率；
信息推送模块，用于根据所述频数或频率向所述用户端推送所述目标物的相关信息。
上述信息推送方法和信息推送系统，通过获取用户端所处环境的图片，并通过从图片中识别出相关的目标物，再根据目标物出现的频数或频率来推送目标物的相关信息，采用科学、客观的技术手段统计用户端所处环境中目标物出现频繁程度的量化数据，并以该统计数据作为推送的参考，具有更高的精准度。
一种数字电视接收终端，包括：如上述的信息推送系统。通过所述信息推送系统，数字电视接收终端可以获取电视用户端所处环境的图片，并通过从图片中识别出相关的目标物，再根据目标物出现的频数或频率来推送目标物的相关信息，采用科学、客观的技术手段统计电视用户端所处环境中目标物出现频繁程度的量化数据，并以该统计数据作为向电视推送的参考。
附图说明
图 1 为一个实施例的信息推送方法流程图；
图 2 为一个实施例中从照片中识别出目标物的流程图；
图 3 为一个实施例中的灰度处理后的位图图像的效果图；
图 4 为一个实施例中的二值化处理后的照片的效果图；
图 5 为一个实施例中去噪点处理后的照片的效果图；
图 6 为一个实施例中的向所述用户端推送所述目标物的相关信息的流程图；
图 7 为一个实施例的信息推送系统结构示意图；
图 8 为一个实施例的目标识别模块的结构示意图；
图 9 为一个实施例的照片匹配单元的结构示意图；
图 10 为一个实施例的信息推送模块的结构示意图。
具体实施方式
下面结合附图对本发明的信息推送方法的具体实施方式作详细描述。
如图 1 所示，图 1 为一个实施例的信息推送方法流程图，主要包括如下步骤：
步骤 S10 ，获取用户端所处环境的照片。
在本实施例中，可以获取用户端（即信息推送的终端）所处环境的场合中周围的照片，所述用户端所处环境包括但不限于家庭环境、会场环境及办公室环境等，可以通过一定的途径（例如定期收集、实时拍摄等）获取到用户端所处环境的照片，通过该照片可以用于提取相关目标物的标记信息。
在一个实施例中，可以通过摄像头来实时获取照片，具体的，通过摄像头在设定的时间拍摄用户端所处环境的照片，其中，所述摄像头包括机顶盒摄像头、电脑摄像头以及监控摄像头等，优选的，所述照片通过采用定期拍摄的方式进行拍摄，这样可以在满足所需照片的前提下减少对用户端设备的影响。
例如，获取利用机顶盒摄像头进行拍摄的家庭环境中的照片时，在机顶盒闲置时进行拍摄，通过检测机顶盒 CPU 的使用率来判断是否处于闲置状态，当 CPU 使用率低于某个阀值时，判断为闲置状态，可以进行拍摄操作，而不影响用户端的正常使用。
步骤 S30 ，从所述照片中识别出目标物并统计出现的频数或频率。
在本实施例中，主要是采用图像识别技术手段从照片中识别出相关的目标物，可以从目标物的外部结构形状或某些特定标记进行分析处理进行识别，然后统计目标物出现的频数或频率，例如，可以通过识别商品的标记来识别相关的商品，一般情况下，不同商品的标记都是具有较为明显的区别特征，所以采用标记来识别具有较高的准确性。
在一个实施例中，如图 2 所示，所述步骤 S30 的过程包括：
步骤 S350 ，将所述照片与预存的识别图片进行匹配。
在本实施例中，主要是利用图像匹配的技术手段来识别照片中的出现的相关目标物；具体的，图片匹配的过程包括如下步骤：
步骤 S351 、将所述照片的矩阵数据分别与数据库中的识别图片的矩阵块进行模式匹配。
在本步骤中，将预存在数据库里的各个目标物对应的识别图片的矩阵数据与照片中的矩阵块进行模式匹配，其中，模式匹配过程可以采用通用不变矩阵特征匹配算法。
对于商品来说，一般可以通过识别其标记作为识别图片来匹配照片识别相关商品。
步骤 S352 、计算所述照片与所述识别图片之间的匹配度。
例如，对于商品来说，可以计算标记部分图片与照片中部分之间的匹配度，即作为两者的匹配度。
步骤 S353 、若所述匹配度大于设定阀值，则判定所述照片与对应的识别图片匹配成功。
在本步骤中，利用预设阀值判决计算的匹配度，当匹配度大于阀值时，说明两者相似度高，具有相同特征，可以判断两者匹配成功。
步骤 S360 ，将匹配成功的识别图片对应的目标物出现的次数加 1 ，并更新所述目标物的频数或频率。
在本实施例中，可以预存每个目标物的识别图片的数据矩阵都对应一个目标 ID ，在上述匹配过程中关联照片与识别图片后，获取相应的目标 ID 并将匹配数据发送到服务器，在服务器相对应的目标物出现的次数加 1 ，重新计算目标物出现的频数或频率，并对原有数据进行更新。
例如，在采用机顶盒来识别家庭环境的商品时，通过在机顶盒识别相关商品后，将匹配数据发送至联网的服务器进行相应记录。
在一个实施例中，考虑到图片匹配过程中，可能运算数据量过大，所以为了减少识别过程中的数据运算量及提高识别准确性；优选的，步骤 S30 还包括在步骤 S350 前对照片进行预处理步骤，该预处理步骤具体包括：
S310 ，将所述照片生成位图图像；具体地，通过解析照片 BMP 头信息后，解码图片数据获得位图文件，可以获得照片的矩阵数组，用于进行后续处理。
S320 ，将所述位图图像进行灰度转换；具体地，灰度转换后可以去除图像中的彩色信息，减少后续的计算量，灰度处理后的效果如图 3 所示，其中，（ 3.1 ）为原图，（ 3.2 ）为灰度处理后的效果图；每一个图片像素都包含 RGB 相原色数据，灰度处理后可以使得图片像素的 RGB 都相等，这里可以简单的取 R 、 G 、 B 与各自权重乘积的和为图像像素的 RGB 值，如： R=G=B=（R*0.3+G*0.59 + B*0.11）。
S330 ，将所述灰度转换后的位图图像进行二值化处理；具体地，即将灰度处理后的图像的各像素转换为的黑白图像，处理方式可以为将图像灰度值小于某一个设定阀值的像素点全部转换为黑色的点，而大于一个设定阀值的点转换为白色的点，如图 4 所示，图 4 为一个二值化处理后的图像效果图，通过二值化处理可以进一步减少后续处理的计算量。
S340 ，去除所述二值化处理后的位图图像上的噪点；具体地，即对二值化后图像进行优化处理去除噪点，首先判别出噪点，然后去除大小块噪点；对于噪点判别可以采取扫描图片数据矩阵的方式，在扫描中当遇到黑色点后，递归扫描相邻像素，当遇到连续像素小于某个值或大于某个值时，可以判定为小噪点和大块噪点，如图 5 所示，图 5 为一个去噪点处理后的图像效果图；由于噪点可能影响到图像识别的判断过程，所以通过上述去噪点优化处理后，可以提高识别的准确性。
步骤 S50 ，根据所述频数或频率向所述用户端推送所述目标物的相关信息。
在本实施例中，主要以目标物在用户端所处环境中出现的频数或频率作为参考，向用户端推送目标物的相关信息，如广告信息、推广信息等可以展示目标物属性或特征的信息。如图 6 所示，步骤 S50 的过程具体包括：
步骤 S510 ，统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率。
在本步骤中，经过一定的时间累计后，统计设定的时间段内各个目标物出现的频数或频率。通过统计各个目标物出现的频数，以确定该目标物在用户端所处环境中出现的总次数和频繁程度；通过统计各个目标物出现的频率，可以确定该目标物在设定时间段内占所有目标物出现的比例。
上述由统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率，可以实现将用户端与目标物之间关联程度的量化，获得科学、客观的量化数据，作为信息推送的参考。
例如，当目标物为商品，需要为商品进行信息推广时，在家庭环境中，出现较多的是家庭日用商品，在会场环境中，出现较多的是会议场所器材等商品，在办公室环境中，出现较多的是办公用品等商品。通过对各个场合中商品出现的频数或频率进行统计，可以得到各个场合中出现商品频繁程度的量化数据，频数或频率较高的为出现较多的商品。如在家庭环境中，家庭日用商品出现的频数或频率较高，所以在进行信息推广时，以统计的数据作为参考，对于家庭环境中的用户端着重推广家庭日用商品的相关信息。
步骤 S520 ，根据所述频数或频率向所述用户端推送所述目标物的相关信息。
在本实施例中，根据计算各个目标物在用户端所处环境中出现的频数或频率，可以以该频数或频率作为参考，在对目标物的相关信息进行推送时，可以进行横向比较及纵向对比，从而调整向用户端推送的目标物信息。
例如，当目标物为商品，需要为商品进行广告信息推广时，选择出现频数或频率较高的商品，将其广告信息进行重点推送至用户端的终端（包括电视、电脑等显示媒介），使得推送的广告信息具有更高的精准度，实现精准的广告投放，从而带来更好的广告效应。
下面结合附图对本发明的信息推送方法对应系统的具体实施方式作详细描述。
如图 7 所示，图 7 为一个实施例的信息推送系统结构示意图，主要包括：照片获取模块 10 、目标识别模块 30 以及信息推送模块 50 。
所述照片获取模块 10 ，用于获取用户端所处环境的照片。
在本实施例中，照片获取模块 10 可以获取用户端所处环境的场合中周围的照片，所述用户端所处环境包括但不限于家庭环境、会场环境及办公室环境等，可以通过一定的途径（例如定期收集、实时拍摄等）获取到用户端所处环境的照片，通过该照片可以用于提取相关目标物的标记信息。
在一个实施例中，照片获取模块 10 可以通过摄像头来实时获取照片，具体的，通过摄像头在设定的时间拍摄用户端所处环境的照片，其中，所述摄像头包括机顶盒摄像头、电脑摄像头以及监控摄像头等，优选的，所述照片通过采用定期拍摄的方式进行拍摄，这样可以在满足所需照片的前提下减少对用户端设备的影响。
例如，照片获取模块 10 获取利用机顶盒摄像头进行拍摄的家庭环境中的照片时，在机顶盒闲置时进行拍摄，通过检测机顶盒 CPU 的使用率来判断是否处于闲置状态，当 CPU 使用率低于某个阀值时，判断为闲置状态，可以进行拍摄操作，而不影响用户端的正常使用。
所述目标识别模块 30 ，用于从所述照片中识别出目标物并统计出现的频数或频率。
在本实施例中，目标识别模块 30 主要是采用图像识别技术手段从照片中识别出相关的目标物，可以从目标物的外部结构形状或某些特定标记进行分析处理进行识别。
例如，目标识别模块 30 可以通过识别商品的标记来识别相关的商品，一般情况下，不同商品的标记都是具有较大的区别特征的，所以采用标记识别具有较高的准确性。
对于所述目标识别模块 30 ，如图 8 所示，进一步包括：照片匹配单元 350 和数据记录单元 360 。
照片匹配单元 350 ，用于将所述照片与预存的识别图片进行匹配。
在本实施例中，照片匹配单元 350 主要是利用图像匹配的技术手段来识别照片中的出现的相关目标物；具体地，如图 9 所示，照片匹配单元 350 进一步包括：模式匹配单元 351 、匹配度频率计算单元 352 以及匹配判定单元 353 。
模式匹配单元 351 ，用于将所述照片的矩阵数据分别与数据库中的识别图片的矩阵块进行模式匹配。
在本实施例中，模式匹配单元 351 将预存在数据库里的各个目标物对应的识别图片的矩阵数据与照片中的矩阵块进行模式匹配，其中，模式匹配过程可以采用通用不变矩阵特征匹配算法。
例如，对于商品来说，一般可以通过识别其标记作为识别图片来匹配照片识别相关商品。
匹配度频率计算单元 352 ，用于计算所述照片与所述识别图片之间的匹配度。
例如，对于商品来说，匹配度频率计算单元 352 可以计算标记部分图片与照片中部分之间的匹配度，即作为两者的匹配度。
匹配判定单元 353 ，用于若所述匹配度大于设定阀值，则判定所述照片与对应的识别图片匹配成功。
在本实施例中，匹配判定单元 353 利用预设阀值判决计算的匹配度，当匹配度大于阀值时，说明两者相似度高，具有相同特征，可以判断两者匹配成功。
数据记录单元 360 ，用于将匹配成功的识别图片对应的目标物出现的次数加 1 ，并更新所述目标物的频数或频率。
在一个实施例中，数据记录单元 360 可以预存每个目标物的识别图片的数据矩阵都对应一个目标 ID ，在上述匹配过程中关联照片与识别图片后，获取相应的目标 ID 并将匹配数据发送到服务器，在服务器降对应的目标物出现的次数加 1 ，重新计算目标物出现的频数或频率，并对原有数据进行更新。
例如，在采用机顶盒来识别家庭环境的商品时，通过在机顶盒识别相关商品后，将匹配数据发送至联网的服务器进行相应记录。
在一个实施例中，考虑到图片匹配过程中，可能运算数据量过大，所以为了减少识别过程中的数据运算量及提高识别准确性；优选的，预目标识别模块 30 还包括设置在照片匹配单元 350 前的照片转换单元 310 、灰度转换单元 320 、二值化处理单元 330 以及噪点去除单元 340 。
照片转换单元 310 ，用于将所述照片生成位图图像。
本实施例中，照片转换单元 310 通过解析照片 BMP 头信息后，解码图片数据获得位图文件，可以获得照片的矩阵数组，用于进行后续处理。
灰度转换单元 320 ，用于将所述位图图像进行灰度转换。
本实施例中，灰度转换单元 320 进行灰度转换后可以去除图像中的彩色信息，减少后续的计算量，
二值化处理单元 330 ，用于将所述灰度转换后的位图图像进行二值化处理。
本实施例中，二值化处理单元 330 通过二值化处理可以进一步减少后续处理的计算量。
噪点去除单元 340 ，用于去除所述二值化处理后的位图图像上的噪点。
本实施例中，噪点去除单元 340 通过上述去噪点优化处理后，可以提高识别的准确性。
信息推送模块 50 ，用于根据所述频数或频率向所述用户端推送所述目标物的相关信息。
在本实施例中，信息推送模块 50 主要以目标物在用户端所处环境中出现的频数或频率作为参考，向用户端推送目标物的相关信息，如广告信息、推广信息等可以展示目标物属性或特征的信息。具体地，如图 10 所示，信息推送模块 50 进一步包括：统计单元 510 和推送单元 520 。
统计单元 510 ，用于统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率。
在本实施例中，经过一定的时间累计后，统计单元 510 统计设定的时间段内各个目标物出现的频数或频率；通过统计各个目标物出现的频数，可以确定该目标物在用户端所处环境中出现的总次数和频繁程度；通过统计各个目标物出现的频率，可以确定该目标物在设定时间段内占所有目标物出现的比例。
上述由统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率，可以实现将用户端与目标物之间关联程度的量化，获得科学、客观的量化数据，作为信息推送的参考。
例如，当目标物为商品，需要为商品进行信息推广时，在家庭环境中，出现较多的是家庭日用商品，在会场环境中，出现较多的是会议场所器材等商品，在办公室环境中，出现较多的是办公用品等商品。通过对各个场合中商品出现的频数或频率进行统计，可以得到各个场合中出现商品频繁程度的量化数据，频数或频率较高的为出现较多的商品，如在家庭环境中，家庭日用商品出现的频数或频率较高，所以在进行信息推广时，以统计的数据作为参考，对于家庭环境中的用户端着重推广家庭日用商品的相关信息。
推送单元 520 ，根据所述频率向所述用户端推送所述目标物的相关信息。
在本实施例中，推送单元 520 根据计算各个目标物在用户端所处环境中出现的频数或频率，可以以该频数或频率作为参考，在对目标物的相关信息进行推送时，可以进行横向比较及纵向对比，从而调整向用户端推送的目标物信息。
例如，当目标物为商品，需要为商品进行广告信息推广时，选择出现频数或频率较高的商品，将其广告信息进行重点推送至用户端的终端（包括电视、电脑等显示媒介），使得推送的广告信息具有更高的精准度，实现精准的广告投放，从而带来更好的广告效应。
本发明的信息推送系统与本发明的信息推送方法一一对应，在上述信息推送方法的实施例阐述的技术特征及其有益效果均适用于信息推送系统的实施例中。
一种数字电视接收终端，包括：如上述的信息推送系统。通过所述信息推送系统，数字电视接收终端可以获取用户端所处环境的图片，并通过从图片中识别出相关的目标物，再根据目标物出现的频数或频率来推送目标物的相关信息，通过采用科学、客观的统计数据作为向电视推送信息的参考，具有更高的精准度。可以通过该数字电视接收终端进行精准的广告投放，从而带来更好的广告效应。
综上所述，本发明的信息推送方法和系统，通过获取用户端所处环境的照片，并通过从照片中识别出相关的目标物，使用科学客观的技术手段来统计目标物在用户端所处环境中的出现的频数或频率，再以统计的数据作为参考，对不同习惯的用户端进行相关目标物的相关信息的推送，推送的信息具有更高精准度，可以用于进行高精度广告投放，减少广告成本，提高广告效应。另外，在广告效果调查，商品的市场调查等方面也可以起到重要作用，可以提供精准的数据参考及先进的技术支持。
本领域普通技术人员可以理解实现上述实施方式中的全部或部分流程，以及对应的系统，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各实施方式的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体（ Read-Only Memory ， ROM ）或随机存储记忆体（ Random Access Memory ， RAM ）等。
因此，根据上述本发明实施例方案，本发明还提供一种包含计算机可读程序的存储介质，当该存储介质中的计算机可读程序执行时，可以实现上述任何一种方式中的本发明的信息推送方法。
如上所述的本发明实施例的方法，可以以软件的形式安装于相应的机器设备上，并在该软件运行时通过控制相关的处理设备来完成上述的信息推送的过程。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (19)

  1. 一种信息推送方法，其特征在于，包括如下步骤：
    获取用户端所处环境的照片；
    从所述照片中识别出目标物并统计出现的频数或频率；
    根据所述频数或频率向所述用户端推送所述目标物的相关信息。
  2. 根据权利要求 1 所述的信息推送方法，其特征在于，所述从所述照片中识别出目标物并统计出现的频数或频率的步骤包括：
    将所述照片与预存的识别图片进行匹配；
    将匹配成功的识别图片对应的目标物出现的次数加 1 ，并更新所述目标物的频数或频率。
  3. 根据权利要求 2 所述的信息推送方法，其特征在于，在将所述照片与预存的识别图片进行匹配步骤前还包括：
    将所述照片生成位图图像；
    将所述位图图像进行灰度转换；
    将所述灰度转换后的位图图像进行二值化处理；
    去除所述二值化处理后的位图图像上的噪点。
  4. 根据权利要求 2 所述的信息推送方法，其特征在于，所述将所述照片与预存的识别图片进行匹配的步骤包括：
    将所述照片的矩阵数据分别与数据库中的识别图片的矩阵块进行模式匹配；
    计算所述照片与所述识别图片之间的匹配度；
    若所述匹配度大于设定阀值，则判定所述照片与对应的识别图片匹配成功。
  5. 根据权利要求 1 所述的信息推送方法，其特征在于，所述根据所述频数或频率向所述用户端推送所述目标物的相关信息的步骤包括：
    统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率；
    根据所述频率或频率向所述用户端推送所述目标物的相关信息。
  6. 根据权利要求 1 所述的信息推送方法，其特征在于，所述目标物包括商品的标识。
  7. 一种信息推送系统，其特征在于，包括：
    照片获取模块，用于获取用户端所处环境的照片；
    目标识别模块，用于从所述照片中识别出目标物并统计出现的频数或频率；
    信息推送模块，用于根据所述频数或频率向所述用户端推送所述目标物的相关信息。
  8. 根据权利要求 7 所述的信息推送系统，其特征在于，所述目标识别模块包括：
    照片匹配单元，用于将所述照片与预存的识别图片进行匹配；
    数据记录单元，用于将匹配成功的识别图片对应的目标物出现的次数加 1 ，并更新所述目标物的频数或频率。
  9. 根据权利要求 8 所述的信息推送系统，其特征在于，所述预处理单元包括：
    照片转换单元，用于将所述照片生成位图图像；
    灰度转换单元，用于将所述位图图像进行灰度转换；
    二值化处理单元，用于将所述灰度转换后的位图图像进行二值化处理；
    噪点去除单元，用于去除所述二值化处理后的位图图像上的噪点。
  10. 根据权利要求 8 所述的信息推送系统，其特征在于，所述照片匹配单元包括：
    模式匹配单元，用于将所述照片的矩阵数据分别与数据库中的识别图片的矩阵块进行模式匹配；
    匹配度频率计算单元，用于计算所述照片与所述识别图片之间的匹配度；
    匹配判定单元，用于若所述匹配度大于设定阀值，则判定所述照片与对应的识别图片匹配成功。
  11. 根据权利要求 7 所述的信息推送系统，其特征在于，所述信息推送模块包括：
    统计单元，用于统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率；
    推送单元，用于根据所述频数或频率向所述用户端推送所述目标物的相关信息。
  12. 根据权利要求 7 所述的信息推送系统，其特征在于，所述目标物包括商品的标识。
  13. 一种数字电视接收终端，其特征在于，包括：如权利要求 7 至 12 任一项所述的信息推送系统。
  14. 一个或多个包含计算机可执行指令的计算机存储介质，所述计算机可执行指令用于执行一种信息推送方法，其特征在于，所述方法包括以下步骤：
    获取用户端所处环境的照片；
    从所述照片中识别出目标物并统计出现的频数或频率；
    根据所述频数或频率向所述用户端推送所述目标物的相关信息。
  15. 根据权利要求 14 所述的计算机存储介质，其特征在于，所述从所述照片中识别出目标物并统计出现的频数或频率的步骤包括：
    将所述照片与预存的识别图片进行匹配；
    将匹配成功的识别图片对应的目标物出现的次数加 1 ，并更新所述目标物的频数或频率。
  16. 根据权利要求 15 所述的计算机存储介质，其特征在于，在将所述照片与预存的识别图片进行匹配步骤前还包括：
    将所述照片生成位图图像；
    将所述位图图像进行灰度转换；
    将所述灰度转换后的位图图像进行二值化处理；
    去除所述二值化处理后的位图图像上的噪点。
  17. 根据权利要求 15 所述的计算机存储介质，其特征在于，所述将所述照片与预存的识别图片进行匹配的步骤包括：
    将所述照片的矩阵数据分别与数据库中的识别图片的矩阵块进行模式匹配；
    计算所述照片与所述识别图片之间的匹配度；
    若所述匹配度大于设定阀值，则判定所述照片与对应的识别图片匹配成功。
  18. 根据权利要求 14 所述的计算机存储介质，其特征在于，所述根据所述频数或频率向所述用户端推送所述目标物的相关信息的步骤包括：
    统计设定的时间段内所述目标物在所述用户端所处环境中出现的频数或频率；
    根据所述频率或频率向所述用户端推送所述目标物的相关信息。
  19. 根据权利要求 14 所述的计算机存储介质，其特征在于，所述目标物包括商品的标识。
PCT/CN2013/086915 2012-11-21 2013-11-12 信息推送方法和系统、数字电视接收终端及计算机存储介质 Ceased WO2014079327A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/712,945 US9596520B2 (en) 2012-11-21 2015-05-15 Method and system for pushing information to a client

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210476618.6A CN103841438B (zh) 2012-11-21 2012-11-21 信息推送方法、信息推送系统及数字电视接收终端
CN201210476618.6 2012-11-21

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/712,945 Continuation US9596520B2 (en) 2012-11-21 2015-05-15 Method and system for pushing information to a client

Publications (1)

Publication Number Publication Date
WO2014079327A1 true WO2014079327A1 (zh) 2014-05-30

Family

ID=50775528

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/086915 Ceased WO2014079327A1 (zh) 2012-11-21 2013-11-12 信息推送方法和系统、数字电视接收终端及计算机存储介质

Country Status (3)

Country Link
US (1) US9596520B2 (zh)
CN (1) CN103841438B (zh)
WO (1) WO2014079327A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109509038A (zh) * 2018-12-27 2019-03-22 盯盯拍（深圳）云技术有限公司 信息推送方法以及信息推送装置
CN117938950A (zh) * 2024-03-22 2024-04-26 深圳有为通讯科技有限公司 一种基于手机启屏的学习内容推送系统

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105488516A (zh) * 2014-10-08 2016-04-13 中兴通讯股份有限公司 一种图像处理方法及装置
CN105118339A (zh) * 2015-09-30 2015-12-02 广东小天才科技有限公司 一种基于情境学习的教学方法及装置
CN105302904A (zh) * 2015-10-29 2016-02-03 努比亚技术有限公司 信息推送方法和装置
CN105243909A (zh) * 2015-10-29 2016-01-13 高大伟 一种知识体系三维测评系统
CN106657300A (zh) * 2016-12-09 2017-05-10 捷开通讯(深圳)有限公司 一种应用程序的推送方法以及推送应用程序的移动终端
US20190019058A1 (en) * 2017-07-13 2019-01-17 Endgame, Inc. System and method for detecting homoglyph attacks with a siamese convolutional neural network
JP6888474B2 (ja) * 2017-08-10 2021-06-16 トヨタ自動車株式会社 デジタルサイネージ制御装置、デジタルサイネージ制御方法、プログラム、記録媒体
JP7155074B2 (ja) * 2019-07-03 2022-10-18 富士フイルム株式会社 情報提案システム、情報提案方法、プログラムおよび記録媒体
JP7155073B2 (ja) 2019-07-03 2022-10-18 富士フイルム株式会社 情報提案システム、情報提案方法、プログラムおよび記録媒体
CN114816826B (zh) * 2022-06-28 2022-09-23 杭银消费金融股份有限公司 一种应用系统的推送缺陷识别方法及设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101789111A (zh) * 2009-12-30 2010-07-28 中国科学院自动化研究所 一种场所广告与电子广告数据实时交互的系统
CN102637183A (zh) * 2011-02-12 2012-08-15 北京千橡网景科技发展有限公司 用于在社交网络中向用户推荐好友的方法和设备
CN102682091A (zh) * 2012-04-25 2012-09-19 腾讯科技（深圳）有限公司 基于云服务的视觉搜索方法和系统

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8732025B2 (en) * 2005-05-09 2014-05-20 Google Inc. System and method for enabling image recognition and searching of remote content on display
US7660468B2 (en) * 2005-05-09 2010-02-09 Like.Com System and method for enabling image searching using manual enrichment, classification, and/or segmentation
WO2009024990A1 (en) * 2007-08-20 2009-02-26 Yogesh Chunilal Rathod System of processing portions of video stream data
US8064641B2 (en) * 2007-11-07 2011-11-22 Viewdle Inc. System and method for identifying objects in video
US9195898B2 (en) 2009-04-14 2015-11-24 Qualcomm Incorporated Systems and methods for image recognition using mobile devices
US20110208570A1 (en) 2010-02-24 2011-08-25 Dehai Kong Apparatus, system, and method for individualized and dynamic advertisement in cloud computing and web application
US8799756B2 (en) * 2012-09-28 2014-08-05 Interactive Memories, Inc. Systems and methods for generating autoflow of content based on image and user analysis as well as use case data for a media-based printable product

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101789111A (zh) * 2009-12-30 2010-07-28 中国科学院自动化研究所 一种场所广告与电子广告数据实时交互的系统
CN102637183A (zh) * 2011-02-12 2012-08-15 北京千橡网景科技发展有限公司 用于在社交网络中向用户推荐好友的方法和设备
CN102682091A (zh) * 2012-04-25 2012-09-19 腾讯科技（深圳）有限公司 基于云服务的视觉搜索方法和系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109509038A (zh) * 2018-12-27 2019-03-22 盯盯拍（深圳）云技术有限公司 信息推送方法以及信息推送装置
CN117938950A (zh) * 2024-03-22 2024-04-26 深圳有为通讯科技有限公司 一种基于手机启屏的学习内容推送系统

Also Published As

Publication number Publication date
US9596520B2 (en) 2017-03-14
US20150249871A1 (en) 2015-09-03
CN103841438B (zh) 2016-08-03
CN103841438A (zh) 2014-06-04

Similar Documents

Publication Publication Date Title
WO2014079327A1 (zh) 信息推送方法和系统、数字电视接收终端及计算机存储介质
WO2018223857A1 (zh) 文本行识别方法及系统
WO2022071647A1 (en) Video quality assessment method and apparatus
WO2019161615A1 (zh) 账单录入方法、系统、光学字符识别服务器和存储介质
WO2021177758A1 (en) Methods and systems for denoising media using contextual information of the media
WO2016090652A1 (zh) 视频压缩方法及装置
WO2017028601A1 (zh) 智能终端的语音控制方法、装置及电视机系统
WO2022240030A1 (ko) 반려동물 생애 관리 시스템 및 그 방법
WO2016110007A1 (zh) 基于三维点云的三维人脸识别装置和方法
WO2018149300A1 (zh) 疾病概率的检测方法、装置、设备及计算机可读存储介质
WO2017005066A1 (zh) 录制音视频同步时间戳的方法和装置
WO2018023926A1 (zh) 电视与移动终端的互动方法及系统
WO2018032693A1 (zh) 电视显示内容的处理方法、装置及系统
CN106060537A (zh) 一种视频质量评估方法及装置
WO2017096769A1 (zh) 显示设备的色彩校准方法及色彩校准系统
WO2022250388A1 (ko) 비디오 품질을 평가하는 전자 장치 및 그 동작 방법
WO2022005060A1 (ko) 유해 동영상 파일을 필터링 하기 위한 장치 및 방법
WO2018045682A1 (zh) 音画同步测试方法及装置
WO2022045613A1 (ko) 비디오 품질 향상 방법 및 장치
WO2024167173A1 (en) Full frame media stabilization in electronic devices
WO2019061042A1 (zh) 曝光补偿的方法、装置及计算机可读存储介质
WO2019019217A1 (zh) 基于双面打印机的智能广告系统及方法
WO2017113600A1 (zh) 视频播放方法及装置
WO2019056750A1 (zh) 信息唯一性识别方法、应用服务器、系统及存储介质
WO2017201893A1 (zh) 视频处理方法和装置

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: 13856452

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 1205A DATED 01.10.2015)

122 Ep: pct application non-entry in european phase

Ref document number: 13856452

Country of ref document: EP

Kind code of ref document: A1