WO2019062841A1 - 品牌曝光效果分析方法及装置 - Google Patents

品牌曝光效果分析方法及装置 Download PDF

Info

Publication number
WO2019062841A1
WO2019062841A1 PCT/CN2018/108292 CN2018108292W WO2019062841A1 WO 2019062841 A1 WO2019062841 A1 WO 2019062841A1 CN 2018108292 W CN2018108292 W CN 2018108292W WO 2019062841 A1 WO2019062841 A1 WO 2019062841A1
Authority
WO
WIPO (PCT)
Prior art keywords
brand
image
identified
exposure
target
Prior art date
Application number
PCT/CN2018/108292
Other languages
English (en)
French (fr)
Inventor
戴威
Original Assignee
北京国双科技有限公司
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 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Publication of WO2019062841A1 publication Critical patent/WO2019062841A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
    • G06Q30/0242—Determining effectiveness of advertisements

Definitions

  • the present application relates to the field of new media technologies, and more particularly to a method and apparatus for analyzing brand exposure effects.
  • the present application provides a method and device for analyzing brand exposure effects to achieve quantitative evaluation and analysis of exposure effects of brands exposed in existing social networks.
  • the first aspect of the present application discloses a brand exposure effect analysis method, including:
  • the calculation results are summarized and counted to obtain a brand exposure trend.
  • the preset model is generated by the target brand material training, including:
  • the target platform includes a search platform and/or a material website;
  • the target brand material includes a brand product image, a brand logo, a brand advertisement material, or a combination of any elements
  • the training set is trained to obtain a corresponding preset model.
  • the training is performed on the training set to obtain a corresponding preset model, including:
  • the training set corresponding to each element is trained based on the tensorflow and the Faster-RCNN architecture to obtain a corresponding preset model.
  • the valid data includes: a brand exposure number and/or a brand exposure rate, and calculating valid data when each of the elements is exposed in the to-be-identified image set, and obtaining a calculation result corresponding to each of the elements, including:
  • the brand exposure rate being the product of the area of the brand in the image to be recognized and the total area of the image to be identified ;
  • the obtained brand exposure number and/or the brand exposure rate are taken as calculation results.
  • the summarizing and counting the calculation results to obtain a brand exposure trend including:
  • the calculation result is summarized and statistically generated to generate the brand exposure trend effect diagram, and the brand exposure area effect diagram includes a graph or a histogram.
  • a third aspect of the present application discloses a brand exposure effect analysis apparatus, including:
  • a collection unit configured to collect a to-be-identified image acquired from a social network within a preset time period, and generate a to-be-identified image collection, where the to-be-identified image is from a main section and/or a sub-section of the social network;
  • An identifier unit configured to identify the image to be identified in the to-be-identified image set based on a predetermined preset model, determine an element related to the target brand on the image to be recognized, and mark the preset
  • the model is generated by the target brand material training
  • a calculating unit configured to calculate valid data when each of the labeled elements is exposed in the to-be-identified image set, and obtain a calculation result corresponding to each of the elements
  • An analysis unit is configured to summarize and count the calculation results to obtain a brand exposure trend.
  • the device further comprises:
  • a search unit configured to acquire target brand material from a target platform, including a search platform and/or a material website, based on a crawler technology
  • a batch annotation unit configured to batch mark the target brand material, and generate a corresponding training set, where the target brand material includes a brand product image, a brand logo, a brand advertisement material, or a combination of any elements;
  • the training unit is configured to train the training set to obtain a corresponding preset model.
  • the valid data includes: a brand exposure number and/or a brand exposure rate
  • the calculating unit specifically includes: calculating the brand exposure number and/or location of each of the elements in the to-be-identified image set.
  • the brand exposure rate is the product of the area of the brand in the image to be recognized and the total area of the image to be recognized; the obtained brand exposure number and/or the brand exposure rate are used as calculation results.
  • a third aspect of the present application discloses a storage medium, where the storage medium includes a stored program, wherein, when the program is running, the device in which the storage medium is controlled performs a brand exposure effect analysis method disclosed in the first aspect of the present application. .
  • a fourth aspect of the present application discloses a processor for running a program, wherein the program is executed to execute a brand exposure effect analysis method as disclosed in the first aspect of the present application.
  • the present application discloses a brand exposure effect analysis method and device.
  • Generating a to-be-recognized image set by collecting the to-be-identified image acquired from the social network within a preset time period, the image to be recognized being from a main section and/or a sub-section of the social network; based on a predetermined preset model pair Identifying the to-be-identified image in the to-be-identified image set, determining an element related to the target brand on the image to be recognized, and marking, the preset model is trained by the target brand material; calculating each of the elements
  • the effective data at the time of exposure in the image set to be identified obtains a calculation result corresponding to each of the elements; the calculation result is summarized and counted to obtain a brand exposure trend.
  • the present invention identifies an element related to a target brand on each image to be identified in the image set to be recognized, and calculates valid data when the element is exposed in the image set to be identified, and performs statistics and analysis based on the valid data to obtain the
  • the elements correspond to the exposure trend of the brand, and achieve the purpose of quantitative evaluation and analysis of the brand exposure effect in the existing social network. Further, companies can understand the effects of their corporate brand display on social networks, and determine which way to promote at that time.
  • FIG. 1 is a schematic flow chart of a method for analyzing a brand exposure effect disclosed in an embodiment of the present application
  • FIG. 2 is a display manner of an element related to a target brand in a video disclosed in an embodiment of the present application
  • FIG. 3 is a diagram showing a result of batch labeling disclosed in an embodiment of the present application.
  • FIG. 5 is a diagram showing a result of analyzing a brand exposure effect disclosed in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a brand exposure effect analysis apparatus according to an embodiment of the present application.
  • the present application discloses a brand exposure effect analysis method for achieving the purpose of evaluating or analyzing a brand exposure effect in a social network.
  • FIG. 1 is a schematic flowchart diagram of a brand exposure effect analysis method disclosed in an embodiment of the present application.
  • the analysis may be performed according to different time periods. If there are many image collections to be identified, each image collection is analyzed in the following manner.
  • Step S101 Collecting an image to be recognized acquired from a social network within a preset time period, and generating an image set to be identified.
  • the preset time period can be specifically divided into a period of time in a regular time period such as morning, noon, night, and midnight.
  • step S101 an image to be recognized on the social network within a preset time period is acquired.
  • the image to be identified is from the main section and/or sub-section of the social network. That is to say, the image to be recognized specifically refers to a picture on a main section and/or a sub-section of a social network, a moving image, and the like.
  • Step S102 Identify the to-be-identified image in the to-be-identified image set based on a predetermined preset model, and determine an element related to the target brand on the image to be recognized, and mark the same.
  • the preset model is generated by training of the target brand material.
  • the specific process is shown in Figure 2:
  • Step S201 acquiring the target brand material from the target platform based on the crawler technology.
  • the target platform includes a search platform and/or a material website.
  • the target brand material includes a brand product image, a brand logo, a branded advertising material, or a combination of any of the elements.
  • step S201 based on the crawler technology, the brand product image, the brand logo logo, and the brand advertisement material that are required to be analyzed and evaluated are acquired from the search platform for batch collection and storage.
  • Step S202 batch labeling the target brand material to generate a corresponding training set.
  • a multi-person annotated platform or other annotation tool may be utilized, such as an image annotation tool labelimg to batch-label each element included in the target brand material to generate a training set corresponding to each element. It is also possible to automatically batch-label each element included in the target brand material by using an automatic annotation tool generated by the learning to generate a training set corresponding to each element.
  • Step S203 Train the training set to obtain a corresponding preset model.
  • the training set corresponding to each element may be trained based on the tensorflow and the Faster-RCNN architecture to obtain a corresponding preset model.
  • tensorflow is an artificial intelligence learning system, which is mainly used in many machine deep learning fields such as speech recognition or image recognition.
  • the Faster-RCNN architecture is used to achieve target detection.
  • the principle of target detection is as follows: firstly, the image is normalized, the candidate region is extracted therefrom, and then the feature is extracted from the extracted candidate region using the depth network, and the position of the candidate frame is adjusted.
  • the method of adjusting the network structure may also be adopted to remove the module for filtering small pixel objects.
  • the reference size of the candidate frame can also be adjusted to improve the recognition of smaller objects such as the logo and the product logo. After adjusting the reference size of the candidate frame as shown in FIG. 4, the identified public vehicle and the public logo.
  • features such as inception and Resnet can be used for feature extraction, so that the training effect of the model is more precise.
  • the preset model trained in the above manner can adaptively identify each element in the image related to the target brand material.
  • Step S103 Calculate valid data when each of the labeled elements is exposed in the to-be-identified image set, and obtain a calculation result corresponding to each of the elements.
  • the valid data includes: brand exposure number and/or brand exposure rate and the like.
  • only one or all of the brand exposure number and the brand exposure rate may be calculated. The more valid data is calculated, the more the calculated results are, the more favorable the analysis of subsequent advertising effects is.
  • the effective data for exposure in each of the images to be recognized in the image set to be identified is calculated for each element. For example, the number of brand exposures and brand exposures of a determined element in each image to be identified are calculated.
  • the brand exposure number refers to the number of exposures of the element in the image to be recognized, and the brand exposure is the product of the area of the brand in the image to be recognized and the total area of the image to be recognized.
  • the resulting brand exposure and/or brand exposure is used as the calculation result.
  • Step S104 Summarize and count the calculation results to obtain a brand exposure trend.
  • a change trend of elements related to the target brand material in the image set to be identified may be formed. This trend can be reflected in the generation of a brand exposure trend rendering, which includes a graph or a histogram. As shown in Fig. 5, three curves are indicated, indicating that the brand exposure area is below 20%, and the trend of 20% to 50% and 50% or more.
  • the above steps S101 to S104 are processes for analyzing the set of to-be-identified images collected in a preset time period.
  • the method for analyzing a brand exposure effect disclosed in the embodiment of the present application generates a to-be-identified image set by collecting an image to be recognized obtained from a social network within a preset time period, where the image to be recognized is from a main section of the social network. And/or a sub-block; identifying the image to be recognized in the to-be-identified image set based on a predetermined preset model, determining an element related to the target brand on the image to be recognized, and marking, the pre- The model is generated by the target brand material training; calculating valid data when each of the elements is exposed in the image set to be identified, and obtaining a calculation result corresponding to each of the elements; summarizing and counting the calculation result to obtain a brand Exposure trend.
  • the present invention identifies an element related to a target brand on each image to be identified in the image set to be recognized, and calculates valid data when the element is exposed in the image set to be identified, and performs statistics and analysis based on the valid data to obtain the
  • the elements correspond to the exposure trend of the brand, and achieve the purpose of quantitative evaluation and analysis of the brand exposure effect in the existing social network. Further, companies can understand the effects of their corporate brand display on social networks, and determine which way to promote at that time.
  • the embodiment of the present application further discloses a brand exposure effect analysis device.
  • the brand exposure effect analysis device 600 mainly includes:
  • the collecting unit 601 is configured to collect the to-be-identified image acquired from the social network within a preset time period, and generate a to-be-identified image set, where the to-be-identified image is from a main section and/or a sub-section of the social network.
  • the labeling unit 602 is configured to identify the image to be identified in the to-be-identified image set based on a predetermined preset model, determine an element related to the target brand on the image to be recognized, and mark the pre- Let the model be generated by the target brand material training.
  • the calculating unit 603 is configured to calculate valid data when each of the elements is exposed in the image set to be identified, and obtain a calculation result corresponding to each of the elements.
  • the calculating unit 603 specifically includes: calculating the brand exposure number and/or location of each of the elements in the to-be-identified image set.
  • the brand exposure rate is the product of the area of the brand in the image to be recognized and the total area of the image to be recognized; the obtained brand exposure number and/or the brand exposure rate are used as calculation results.
  • the analyzing unit 604 is configured to summarize and count the calculation results to obtain a brand exposure trend.
  • the brand exposure effect analysis device further includes: a preset unit 605.
  • the preset unit 605 includes:
  • a search unit for acquiring target brand material from a target platform based on a crawler technology, the target platform including a search platform and/or a material website.
  • the batch annotation unit is configured to batch mark the target brand material, and generate a corresponding training set, where the target brand material includes a brand product image, a brand logo, a brand advertisement material, or a combination of any elements.
  • the batch annotation unit may batch-label the elements included in the target brand material by using a multi-person annotated platform or a labelimg tool to generate a training set corresponding to each element.
  • the batch annotation unit may also automatically batch label each element included in the target brand material by using an automatic annotation tool generated by the learning to generate a training set corresponding to each element.
  • the training unit is configured to train the training set to obtain a corresponding preset model.
  • the training unit may train the training set corresponding to each element based on the tensorflow and the Faster-RCNN architecture to obtain a corresponding preset model.
  • each of the above units may be implemented by a hardware device composed of a processor and a memory. Specifically, each of the above units and modules is stored in the memory as a program unit, and the program unit stored in the memory is executed by the processor to implement analysis of the brand exposure effect.
  • the processor includes a kernel, and the kernel removes the corresponding program unit from the memory.
  • the kernel can be set to one or more, and the analysis of the brand exposure effect can be achieved by adjusting the kernel parameters.
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one Memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • the embodiment of the present application provides a processor, where the processor is configured to run a program, where the program is executed to execute the brand exposure effect analysis method.
  • the embodiment of the present application provides a device, including a processor, a memory, and a program stored on the memory and executable on the processor.
  • the processor executes the program, the following steps are implemented: collecting the preset time period from Generating an image to be recognized on the social network, generating a set of images to be identified, the image to be recognized being from a main section and/or a sub-section of the social network; and in the set of images to be identified based on a predetermined preset model Identifying an image to be identified, determining an element related to the target brand on the image to be recognized, and marking that the preset model is generated by the target brand material; calculating each of the elements in the image set to be identified
  • the effective data at the time of exposure obtains the calculation result corresponding to each of the elements; the calculation result is summarized and counted, and the brand exposure trend is obtained.
  • the valid data includes: brand exposure number and/or brand exposure rate.
  • calculating valid data when each of the elements is exposed in the to-be-identified image set, and obtaining a calculation result corresponding to each of the elements comprising: calculating, by the each of the elements in the to-be-identified image set Brand exposure and/or the brand exposure, the brand exposure is the product of the area of the brand in the image to be identified and the total area of the image to be identified; the number of exposures of the brand to be obtained and/or the exposure of the brand Rate as a calculation result.
  • the summarizing and counting the calculation results to obtain a brand exposure trend comprising: summarizing and counting the calculation results, generating the brand exposure trend effect diagram, and the brand exposure area effect diagram includes a graph Or a histogram.
  • the process of training the preset model by the target brand material comprises: acquiring a target brand material from a target platform based on a crawler technology, the target platform comprises a search platform and/or a material website; and labeling the target brand in batches
  • the material generates a corresponding training set, and the target brand material includes a brand product picture, a brand logo, a combination of any one of the brand advertisement materials or any element; training the training set to obtain a corresponding pre- Set the model.
  • the multi-labeled platform or the labelimg tool may be used to batch-label the elements included in the target brand material to generate a training set corresponding to each element.
  • the automatic annotation tool generated by the learning device may be used to automatically batch-label each element included in the target brand material to generate a training set corresponding to each element.
  • the training set corresponding to each element may be trained based on the tensorflow and the Faster-RCNN architecture to obtain a corresponding preset model.
  • the device disclosed in the embodiment of the present application may be a server, a PC, a PAD, a mobile phone, or the like.
  • the embodiment of the present application further provides a storage medium, where a program is stored, and the program implements the brand exposure effect analysis method when executed by the processor.
  • the present application also provides a computer program product, when executed on a data processing device, is adapted to perform a process of initializing a method of acquiring a to-be-identified image acquired from a social network within a preset time period to generate a to-be-identified a collection of images, the image to be identified is from a main section and/or a sub-section of the social network; and the image to be recognized in the to-be-identified image set is identified based on a predetermined preset model, and the to-be-identified image is determined Identifying an element related to the target brand on the image, and marking, the preset model is generated by the target brand material training; calculating valid data when each of the elements is exposed in the to-be-identified image set, and obtaining corresponding elements The calculation result is summarized; the calculation result is summarized and counted, and the brand exposure trend is obtained.
  • the valid data includes: brand exposure number and/or brand exposure rate.
  • calculating valid data when each of the elements is exposed in the to-be-identified image set, and obtaining a calculation result corresponding to each of the elements comprising: calculating, by the each of the elements in the to-be-identified image set Brand exposure and/or the brand exposure, the brand exposure is the product of the area of the brand in the image to be identified and the total area of the image to be identified; the number of exposures of the brand to be obtained and/or the exposure of the brand Rate as a calculation result.
  • the summarizing and counting the calculation results to obtain a brand exposure trend comprising: summarizing and counting the calculation results, generating the brand exposure trend effect diagram, and the brand exposure area effect diagram includes a graph Or a histogram.
  • the process of training the preset model by the target brand material comprises: acquiring a target brand material from a target platform based on a crawler technology, the target platform comprises a search platform and/or a material website; and labeling the target brand in batches
  • the material generates a corresponding training set, and the target brand material includes a brand product picture, a brand logo, a combination of any one of the brand advertisement materials or any element; training the training set to obtain a corresponding pre- Set the model.
  • the multi-labeled platform or the labelimg tool may be used to batch-label the elements included in the target brand material to generate a training set corresponding to each element.
  • the automatic annotation tool generated by the learning device may be used to automatically batch-label each element included in the target brand material to generate a training set corresponding to each element.
  • the training set corresponding to each element may be trained based on the tensorflow and the Faster-RCNN architecture to obtain a corresponding preset model.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the application can take the form of an entirely hardware embodiment, an entirely software embodiment or a combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)

Abstract

本申请公开了一种品牌曝光效果分析方法及装置，通过集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合；基于预先确定的预设模型对待识别图像集合中的待识别图像进行识别，确定待识别图像上与目标品牌相关的元素，并标注；计算各个元素在待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；对计算结果进行汇总和统计，得到品牌曝光趋势。本申请通过对待识别图像集合中各个待识别图像上与目标品牌相关的元素进行识别，并计算确定该元素在待识别图像集合中曝光时的有效数据，基于该有效数据得到该元素对应品牌的曝光趋势，实现对现有社交网络中的品牌曝光效果进行量化评估和分析的目的。

Description

品牌曝光效果分析方法及装置
本申请要求于2017年09月30日提交中国专利局、申请号为201710915100.0、发明名称为“品牌曝光效果分析方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及新媒体技术领域，更具体地说涉及一种品牌曝光效果分析方法及装置。
背景技术
随着社交网络的快速发展，每天有32亿多张的图片被分享到社交媒体上。图片已经成为信息传播、品牌曝光的重要或主要形式。越来越多的企业通过各种方式将广告图像在社交网络中进行显示。
但是，目前并没有一种有效的方式可以评估或分析采用各种方式将广告图像在社交网络中显示时的品牌曝光效果。从而无法使企业了解到哪段时间，采用哪种推广方式，使品牌进行曝光所带来的效果好。
因此，目前亟需一种对社交网络中进行曝光的品牌的显示效果进行评估或分析的方案。
发明内容
有鉴于此，本申请提供了一种品牌曝光效果分析方法及装置，以实现对现有社交网络中进行曝光的品牌的曝光效果进行量化评估和分析的目的。
为了实现上述目的，现提出的方案如下：
本申请第一方面公开了一种品牌曝光效果分析方法，包括：
集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；
基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进 行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；
计算标注的各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；
对所述计算结果进行汇总和统计，得到品牌曝光趋势。
优选的，所述预设模型由所述目标品牌素材训练生成，包括：
基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；
批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；
对所述训练集进行训练，得到对应的预设模型。
优选的，所述对所述训练集进行训练，得到对应的预设模型，包括：
基于tensorflow和Faster-RCNN架构对对应各个元素的所述训练集进行训练，得到对应的预设模型。
优选的，所述有效数据包括：品牌曝光数和/或品牌曝光率，计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果，包括：
计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；
将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
优选的，所述对所述计算结果进行汇总和统计，得到品牌曝光趋势，包括：
对所述计算结果进行汇总和统计，生成所述品牌曝光趋势效果图，所述品牌曝光区域效果图包括曲线图或柱状图。
本申请第三方面公开了一种品牌曝光效果分析装置，包括：
集合单元，用于集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；
标注单元，用于基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；
计算单元，用于计算标注的各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；
分析单元，用于对所述计算结果进行汇总和统计，得到品牌曝光趋势。
优选的，所述装置还包括：
搜索单元，用于基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；
批量批注单元，用于批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；
训练单元，用于对所述训练集进行训练，得到对应的预设模型。
优选的，所述有效数据包括：品牌曝光数和/或品牌曝光率，所述计算单元，具体包括：计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
本申请第三方面公开了一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行如本申请第一方面公开的品牌曝光效果分析方法。
本申请第四方面公开了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行如本申请第一方面公开的的品牌曝光效果分析方法。
经由上述技术方案可知，本申请公开一种品牌曝光效果分析方法及装置。通过集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训 练生成；计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；对所述计算结果进行汇总和统计，得到品牌曝光趋势。本申请通过对待识别图像集合中各个待识别图像上与目标品牌相关的元素进行识别，并计算确定该元素在待识别图像集合中曝光时的有效数据，基于该有效数据进行统计和分析，得到该元素对应品牌的曝光趋势，实现对现有社交网络中的品牌曝光效果进行量化评估和分析的目的。进一步，使得企业能够了解到自己的企业品牌在社交网路中显示时所能够带来的效果，从而确定在那段时间，采用哪种方式进行推广。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1为本申请实施例公开的一种品牌曝光效果分析方法的流程示意图；
图2为本申请实施例公开的一种与目标品牌相关的元素在视频中的显示方式；
图3为本申请实施例公开的一种批量标注的结果显示图；
图4为本申请实施例公开的另一种批量标注的结果显示图；
图5为本申请实施例公开的品牌曝光效果分析结果显示图；
图6为本申请实施例公开的一种品牌曝光效果分析装置的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
由背景技术可知，目前并没有一种有效的方式可以对社交网络中的品牌曝 光效果进行评估或分析。因此，本申请公开了一种品牌曝光效果分析方法，以实现对社交网络中的品牌曝光效果进行评估或分析的目的。
如图1所示，为本申请实施例公开的一种品牌曝光效果分析方法的流程示意图。
在具体实现过程中，可以根据不同的时间段进行分析，若需要识别的图像集合很多，则采用下述方式对每一个图像集合进行分析。
步骤S101：集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合。
以一个预设时间段为分析周期。该预设时间段可以具体分为上午，中午，晚上和午夜等常规时间段内的一段时间。
在执行步骤S101时，获取预设时间段内社交网络上的待识别图像。该待识别图像来自所述社交网络的主版块和/或子版块。也就是说，可选的，该待识别图像具体是指社交网络的主版块和/或子版块上的图片，动态图像等。
步骤S102：基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注。
在具体实现中，所述预设模型由目标品牌素材训练生成。具体过程如图2所示：
步骤S201：基于爬虫技术，从目标平台获取目标品牌素材。
该目标平台包括搜索平台和/或素材网站。该目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合。
在步骤S201中，基于爬虫技术，从搜索平台上获取所需要进行分析和评价的品牌产品图片，品牌标志logo，品牌广告物料中任一一个进行批量地采集和存储。
例如，要进行评价分析的是A品牌的效果，可以从百度或者谷歌等搜索平台上批量采集A品牌的品牌产品图片，品牌标志logo或品牌广告物料中的任意一个活组合，进行批量存储。
步骤S202：批量标注所述目标品牌素材，生成相应的训练集。
在具体实现中，可以利用多人标注的平台或其他的标注工具，如图片标注工具labelimg对所述目标品牌素材中包含的各个元素进行批量标注，生成对应 各个元素的训练集。也可以利用机器经由学习生成的自动标注工具对目标品牌素材中包含的各个元素进行自动的批量标注，生成对应各个元素的训练集。
例如，将大众汽车品牌作为目标品牌素材，则需要对与大众汽车品牌相关的元素进行标注，如图3所示，通过对图片中的大众汽车、大众汽车logo进行标注。
需要说明的是，在本申请中，对于进行批量标注的方式并不仅限于以上公开的方式，还可以是其他可进行标注的方式。
步骤S203：对所述训练集进行训练，得到对应的预设模型。
在具体实现中，对上述对应各个元素的训练集，可以基于tensorflow和Faster-RCNN架构对对应各个元素的训练集进行训练，得到对应的预设模型。
其中，tensorflow是一种人工智能学习系统，主要被用于语音识别或图像识别等多项机器深度学习领域。
Faster-RCNN架构则是用于实现目标检测。具体进行目标检测的原理为：先将图像进行归一化处理，从中提取候选区域，然后使用深度网络从提取的候选区域中提取特征，并调整候选框的位置。可选的，也可以采用调整网络结构的方式，从而去掉对于小块像素物体过滤的模块。可选的，也可以调整候选框的基准大小，提高对车标、产品logo等较小的物体的识别。如图4所示出的调整候选框的基准大小后，识别的大众车辆以及大众logo。
其中，在Faster-RCNN架构中的提取特征的操作，可以使用inception、Resnet等模型进行特征提取，使得模型的训练效果加精准。
通过上述方式训练得到的预设模型，可以自适应识别一张图片中的与目标品牌素材相关的各个元素。
步骤S103：计算标注的各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果。
在步骤S103中，有效数据包括：品牌曝光数和/或品牌曝光率等。
在具体实现中，可以仅计算品牌曝光数和品牌曝光率中的任一一个，或者全部。计算的有效数据越多所得到的计算结果则对后续广告效果的分析越有利。
针对每个元素都计算其在待识别图像集合中的各个待识别图像中曝光时 的有效数据。例如，计算确定的一元素在各个待识别图像中的品牌曝光数和品牌曝光率。品牌曝光数指该元素在待识别图像中的曝光次数，品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积。
将得到的品牌曝光数和/或品牌曝光率作为计算结果。
步骤S104：对所述计算结果进行汇总和统计，得到品牌曝光趋势。
在具体实现中，通过对得到的计算结果进行汇总和统计，可以形成待识别图像集合中，与目标品牌素材相关的元素的变化趋势。该变化趋势可以通过生成品牌曝光趋势效果图体现，该品牌曝光区域效果图包括曲线图或柱状图。如图5所示，指示出三条曲线，分别表示品牌曝光面积在20％以下，20％～50％以及50％以上的趋势变化。
上述步骤S101至步骤S104为对一个预设时间段内集合的待识别图像集合进行分析的过程。
本申请实施例公开的一种品牌曝光效果分析方法，通过集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；对所述计算结果进行汇总和统计，得到品牌曝光趋势。本申请通过对待识别图像集合中各个待识别图像上与目标品牌相关的元素进行识别，并计算确定该元素在待识别图像集合中曝光时的有效数据，基于该有效数据进行统计和分析，得到该元素对应品牌的曝光趋势，实现对现有社交网络中的品牌曝光效果进行量化评估和分析的目的。进一步，使得企业能够了解到自己的企业品牌在社交网路中显示时所能够带来的效果，从而确定在那段时间，采用哪种方式进行推广。
基于上述本申请实施例公开的品牌曝光效果分析方法，本申请实施例还对应公开了一种品牌曝光效果分析装置，如图6所示，该品牌曝光效果分析装置600主要包括：
集合单元601，用于集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块。
标注单元602，用于基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成。
计算单元603，用于计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果。
可选的，该有效数据包括品牌曝光数和/或品牌曝光率时，该计算单元603，具体包括：计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
分析单元604，用于对所述计算结果进行汇总和统计，得到品牌曝光趋势。
进一步的，该品牌曝光效果分析装置中还包括：预设单元605。该预设单元605包括：
搜索单元，用于基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站。
批量批注单元，用于批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合。
可选的，批量批注单元可以利用多人标注的平台或labelimg工具对所述目标品牌素材中包含的元素进行批量标注，生成对应各个元素的训练集。
可选的，批量批注单元也可以利用机器经由学习生成的自动标注工具对目标品牌素材中包含的各个元素进行自动的批量标注，生成对应各个元素的训练集。
训练单元，用于对所述训练集进行训练，得到对应的预设模型。
可选的，训练单元可以基于tensorflow和Faster-RCNN架构对对应各个元素的所述训练集进行训练，得到对应的预设模型。
上述本申请实施例公开的品牌曝光效果分析装置中的各个单元具体的原 理和执行过程，与上述本申请实施例公开的品牌效果分析方法相同，可参见上述本申请实施例公开的品牌曝光效果分析方法中相应的部分，这里不再进行赘述。
基于上述本申请实施例公开的品牌曝光效果分析装置，上述各个单元可以通过一种由处理器和存储器构成的硬件设备实现。具体为：上述各个单元和模块作为程序单元存储于存储器中，由处理器执行存储在存储器中的上述程序单元来实现品牌曝光效果的分析。
其中，处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来实现对品牌曝光效果的分析。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
进一步的，本申请实施例提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行所述品牌曝光效果分析方法。
进一步的，本申请实施例提供了一种设备，设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序，处理器执行程序时实现以下步骤：集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；对所述计算结果进行汇总和统计，得到品牌曝光趋势。
其中，所述有效数据包括：品牌曝光数和/或品牌曝光率。相应地，计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果，包括：计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
其中，所述对所述计算结果进行汇总和统计，得到品牌曝光趋势，包括： 对所述计算结果进行汇总和统计，生成所述品牌曝光趋势效果图，所述品牌曝光区域效果图包括曲线图或柱状图。
其中，所述预设模型由所述目标品牌素材训练生成的过程包括：基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；对所述训练集进行训练，得到对应的预设模型。
可选的，可以利用多人标注的平台或labelimg工具对所述目标品牌素材中包含的元素进行批量标注，生成对应各个元素的训练集。
可选的，也可以利用机器经由学习生成的自动标注工具对目标品牌素材中包含的各个元素进行自动的批量标注，生成对应各个元素的训练集。
可选的，可以基于tensorflow和Faster-RCNN架构对对应各个元素的所述训练集进行训练，得到对应的预设模型。
本申请实施例中公开的设备可以是服务器、PC、PAD、手机等。
进一步的，本申请实施例还提供了一种存储介质，其上存储有程序，该程序被处理器执行时实现所述品牌曝光效果分析方法。
本申请还提供了一种计算机程序产品，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序：集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；对所述计算结果进行汇总和统计，得到品牌曝光趋势。
其中，所述有效数据包括：品牌曝光数和/或品牌曝光率。相应地，计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果，包括：计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；将得到的所述品牌曝光数和/或所述品牌曝光率 作为计算结果。
其中，所述对所述计算结果进行汇总和统计，得到品牌曝光趋势，包括：对所述计算结果进行汇总和统计，生成所述品牌曝光趋势效果图，所述品牌曝光区域效果图包括曲线图或柱状图。
其中，所述预设模型由所述目标品牌素材训练生成的过程包括：基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；对所述训练集进行训练，得到对应的预设模型。
可选的，可以利用多人标注的平台或labelimg工具对所述目标品牌素材中包含的元素进行批量标注，生成对应各个元素的训练集。
可选的，也可以利用机器经由学习生成的自动标注工具对目标品牌素材中包含的各个元素进行自动的批量标注，生成对应各个元素的训练集。
可选的，可以基于tensorflow和Faster-RCNN架构对对应各个元素的所述训练集进行训练，得到对应的预设模型。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中 的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和 硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种品牌曝光效果分析方法，其特征在于，包括：
    集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；
    基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；
    计算标注的各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；
    对所述计算结果进行汇总和统计，得到品牌曝光趋势。
  2. 根据权利要求1所述的方法，其特征在于，所述预设模型由所述目标品牌素材训练生成，包括：
    基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；
    批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；
    对所述训练集进行训练，得到对应的预设模型。
  3. 根据权利要求2所述的方法，其特征在于，所述对所述训练集进行训练，得到对应的预设模型，包括：
    基于tensorflow和Faster-RCNN架构对对应各个元素的所述训练集进行训练，得到对应的预设模型。
  4. 根据权利要求1-3中任一项所述的方法，其特征在于，所述有效数据包括：品牌曝光数和/或品牌曝光率，计算各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果，包括：
    计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面 积之积；
    将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
  5. 根据权利要求1-3中任一项所述的方法，其特征在于，所述对所述计算结果进行汇总和统计，得到品牌曝光趋势，包括：
    对所述计算结果进行汇总和统计，生成所述品牌曝光趋势效果图，所述品牌曝光区域效果图包括曲线图或柱状图。
  6. 一种品牌曝光效果分析装置，其特征在于，包括：
    集合单元，用于集合预设时间段内从社交网络上获取的待识别图像，生成待识别图像集合，所述待识别图像来自所述社交网络的主版块和/或子版块；
    标注单元，用于基于预先确定的预设模型对所述待识别图像集合中的所述待识别图像进行识别，确定所述待识别图像上与目标品牌相关的元素，并标注，所述预设模型由目标品牌素材训练生成；
    计算单元，用于计算标注的各个所述元素在所述待识别图像集合中曝光时的有效数据，得到对应各个所述元素的计算结果；
    分析单元，用于对所述计算结果进行汇总和统计，得到品牌曝光趋势。
  7. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    搜索单元，用于基于爬虫技术，从目标平台获取目标品牌素材，所述目标平台包括搜索平台和/或素材网站；
    批量批注单元，用于批量标注所述目标品牌素材，生成相应的训练集，所述目标品牌素材包括品牌产品图片，品牌标志logo，品牌广告物料中的任一一个元素或任意元素的组合；
    训练单元，用于对所述训练集进行训练，得到对应的预设模型。
  8. 根据权利要求6所述的装置其特征在于，所述有效数据包括：品牌曝光数和/或品牌曝光率，所述计算单元，具体包括：计算各个所述元素在所述待识别图像集合中的所述品牌曝光数和/或所述品牌曝光率，所述品牌曝光率为品牌在待识别图像中的面积与待识别图像总面积之积；将得到的所述品牌曝光数和/或所述品牌曝光率作为计算结果。
  9. 一种存储介质，其特征在于，所述存储介质包括存储的程序，其中， 在所述程序运行时控制所述存储介质所在设备执行如权利要求1-5中任一项所述的品牌曝光效果分析方法。
  10. 一种处理器，其特征在于，所述处理器用于运行程序，其中，所述程序运行时执行如权利要求1-5中任一项所述的品牌曝光效果分析方法。
PCT/CN2018/108292 2017-09-30 2018-09-28 品牌曝光效果分析方法及装置 WO2019062841A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710915100.0 2017-09-30
CN201710915100.0A CN109598524A (zh) 2017-09-30 2017-09-30 品牌曝光效果分析方法及装置

Publications (1)

Publication Number Publication Date
WO2019062841A1 true WO2019062841A1 (zh) 2019-04-04

Family

ID=65900697

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/108292 WO2019062841A1 (zh) 2017-09-30 2018-09-28 品牌曝光效果分析方法及装置

Country Status (2)

Country Link
CN (1) CN109598524A (zh)
WO (1) WO2019062841A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113743281A (zh) * 2021-08-30 2021-12-03 上海明略人工智能(集团)有限公司 节目广告素材识别方法、系统、计算机设备和存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112445892B (zh) * 2019-09-02 2023-09-29 百度在线网络技术（北京）有限公司 确定品牌提及率的方法、装置、电子设备及存储介质
CN111260402A (zh) * 2020-01-16 2020-06-09 精硕科技（北京）股份有限公司 一种品牌竞争力分析方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978665A (zh) * 2015-06-16 2015-10-14 北京畅游天下网络技术有限公司 一种品牌评估方法和装置
CN105184611A (zh) * 2015-09-08 2015-12-23 精硕世纪科技（北京）有限公司 广告效果量化方法和展示系统
US20160189206A1 (en) * 2013-08-13 2016-06-30 Beijing Gridsum Technology Co., Ltd. Monitoring method and device for display number of pictures
CN107016344A (zh) * 2017-03-08 2017-08-04 上海极链网络科技有限公司 视频中品牌识别系统及其实现方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2360581A (en) * 2000-03-15 2001-09-26 Television Monitoring Services Quantification of brand exposure on screen
KR100892847B1 (ko) * 2007-05-29 2009-04-10 엔에이치엔(주) 광고 집행에 따른 반응정보 제공 방법 및 시스템
US20090106087A1 (en) * 2007-10-17 2009-04-23 Google Inc. Contextual auction bidding
US20140019264A1 (en) * 2012-05-07 2014-01-16 Ditto Labs, Inc. Framework for product promotion and advertising using social networking services
US20170109785A1 (en) * 2013-01-30 2017-04-20 Google Inc. Providing content with branding labels

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160189206A1 (en) * 2013-08-13 2016-06-30 Beijing Gridsum Technology Co., Ltd. Monitoring method and device for display number of pictures
CN104978665A (zh) * 2015-06-16 2015-10-14 北京畅游天下网络技术有限公司 一种品牌评估方法和装置
CN105184611A (zh) * 2015-09-08 2015-12-23 精硕世纪科技（北京）有限公司 广告效果量化方法和展示系统
CN107016344A (zh) * 2017-03-08 2017-08-04 上海极链网络科技有限公司 视频中品牌识别系统及其实现方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113743281A (zh) * 2021-08-30 2021-12-03 上海明略人工智能(集团)有限公司 节目广告素材识别方法、系统、计算机设备和存储介质

Also Published As

Publication number Publication date
CN109598524A (zh) 2019-04-09

Similar Documents

Publication Publication Date Title
WO2019062388A1 (zh) 广告效果分析方法及装置
TWI753044B (zh) 影片資料的推薦方法和裝置
US9785719B2 (en) Generating synthetic data
US8374454B2 (en) Detection of objects using range information
CN109561052B (zh) 网站异常流量的检测方法及装置
CN107358247B (zh) 一种确定流失用户的方法及装置
CN110532833A (zh) 一种视频分析方法及装置
WO2019062841A1 (zh) 品牌曝光效果分析方法及装置
EP2899671A1 (en) Identification method and device for target object in image
US20180075066A1 (en) Method and apparatus for displaying electronic photo, and mobile device
CN109325996B (zh) 用于生成信息的方法和装置
CN111553729A (zh) 一种电商用户画像数据生成方法、装置和计算设备
CN111507332A (zh) 车辆vin码检测方法与设备
Lu et al. Multi-scale feature progressive fusion network for remote sensing image change detection
CN112446361A (zh) 一种训练数据的清洗方法及设备
CN105809488B (zh) 一种信息处理方法及电子设备
CN109726670B (zh) 一种从视频中提取目标检测样本集的方法
CN108154377B (zh) 广告作弊预测方法及装置
WO2022241987A1 (zh) 图像检索方法及装置
Mohsin et al. Convolutional neural networks for real-time wood plank detection and defect segmentation
Thomas et al. Computer vision supported pedestrian tracking: A demonstration on trail bridges in rural Rwanda
CN108875770B (zh) 行人检测误报数据的标注方法、装置、系统和存储介质
CN110740231A (zh) 视频数据标注方法、装置、电子设备及介质
CN116071375B (zh) 图像分割方法和装置、存储介质及电子设备
CN110910362A (zh) 一种影像序列的标注方法、装置、处理器及存储介质

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: 18860695

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: 18860695

Country of ref document: EP

Kind code of ref document: A1