CN117575702A - Multi-mode advertisement putting system - Google Patents

Multi-mode advertisement putting system Download PDF

Info

Publication number
CN117575702A
CN117575702A CN202311532485.4A CN202311532485A CN117575702A CN 117575702 A CN117575702 A CN 117575702A CN 202311532485 A CN202311532485 A CN 202311532485A CN 117575702 A CN117575702 A CN 117575702A
Authority
CN
China
Prior art keywords
advertisement
data
mode
modal
picture
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.)
Pending
Application number
CN202311532485.4A
Other languages
Chinese (zh)
Inventor
高洁
张峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Hongtu Xinda Technology Co ltd
Original Assignee
Beijing Hongtu Xinda Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Hongtu Xinda Technology Co ltd filed Critical Beijing Hongtu Xinda Technology Co ltd
Priority to CN202311532485.4A priority Critical patent/CN117575702A/en
Publication of CN117575702A publication Critical patent/CN117575702A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
    • G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

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

Abstract

The invention discloses a multi-mode advertisement putting system, which relates to the technical field of advertisement putting and comprises a multi-mode data acquisition module, a multi-mode data characteristic identification module, a multi-mode data analysis module and a multi-mode advertisement putting module; the multi-mode data acquisition module acquires multi-mode advertisement data in a network through a data acquisition tool to obtain a multi-mode data set; the multi-mode data feature recognition module is used for carrying out feature recognition on the multi-mode data set and acquiring multi-mode data features; the multi-mode data analysis module is used for analyzing the multi-mode data characteristics to obtain advertisement pre-delivery results; the multi-mode advertisement putting module is used for putting advertisements according to the advertisement pre-putting results to obtain advertisement putting results; the invention can solve the problem of information deviation caused by the single-mode condition, and improves the advertisement putting accuracy aiming at users through analyzing the online multi-mode advertisement data.

Description

Multi-mode advertisement putting system
Technical Field
The invention relates to the technical field of advertisement delivery, in particular to a multi-mode advertisement delivery system.
Background
The prior art (patent publication No. CN 109146565A) discloses an advertisement putting method and an advertisement putting system. The advertisement putting method comprises the following steps: the mobile power lease server receives advertisement information sent by the mobile terminal; the mobile power lease server receives and audits the advertisement information; and if the auditing result is passed, the advertising information is sent to the mobile power supply, so that the display screen of the mobile power supply can play the advertising information. It has the following advantages: the method is convenient for timely putting advertisements, is convenient for updating and maintaining advertisement information, and can effectively put customized advertisements aiming at different target groups and application scenes. The information deviation problem caused by the single-mode condition can not be solved in the prior art, so that the advertisement putting accuracy rate for users can not be improved.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art; therefore, the invention provides the multi-mode advertisement delivery system, which can solve the problem of information deviation caused by single-mode conditions, and improves the advertisement delivery accuracy aiming at users through analyzing the online multi-mode advertisement data.
In order to achieve the above object, a first aspect of the present invention provides a multi-modal advertisement delivery system, including a multi-modal data acquisition module, a multi-modal data feature recognition module, a multi-modal data analysis module, and a multi-modal advertisement delivery module;
the multi-mode data acquisition module acquires multi-mode advertisement data in a network through a data acquisition tool to obtain a multi-mode data set;
the multi-mode data feature recognition module is used for carrying out feature recognition on the multi-mode data set and acquiring multi-mode data features;
the multi-mode data analysis module is used for analyzing the multi-mode data characteristics to obtain advertisement pre-delivery results;
and the multi-mode advertisement putting module is used for putting advertisements according to the advertisement pre-putting results to obtain advertisement putting results.
Preferably, the acquiring, by the data acquisition tool, the multi-mode advertisement data in the network to obtain a multi-mode data set includes:
searching the advertisement theme keywords through a search engine, and extracting websites of each search result;
performing intersection operation on the website of the search result to obtain an advertisement website result, and taking the advertisement website result as an advertisement basic information source library;
acquiring the website in the advertisement basic information source library according to a preset advertisement information number threshold value by pre-acquiring the website in the advertisement basic information source library, and acquiring data according to the acquired website;
acquiring multi-modal data from the acquired website through a data acquisition tool, filtering keywords of titles and contents of the multi-modal data, and distributing the multi-modal data to a multi-modal data set D= { (I) according to categories 1 ，T 1 )，...，(I m ，T m ) }, wherein I m ，T m Respectively denoted as mth picture data and text data in the multimodal dataset.
Preferably, the feature identifying the multi-mode data set and acquiring multi-mode data features includes:
marking the first segment of the sequence of the text data in the multi-mode dataset;
extracting characters on the picture data in the multi-mode dataset through a picture character recognition technology to obtain a picture text;
splicing the picture text and the text data, and marking the sequence tail end of the picture text;
extracting feature vectors of a sequence first segment of the text data and a sequence tail end of the picture text as joint features R= { R of the picture text and the text data 1 ，R 2 ，...，R r (wherein R is r Representing the characteristics of the text data and the r-th word in the picture text;
inputting the picture data in the multi-modal dataset into a pre-trained deep learning model, and extracting the input of the penultimate hidden layer of the pre-trained deep learning model as the image feature P= { P of the picture data 1 ，P 2 ，...，P r }，P r Image features represented as the r-th region in the picture data;
enhancing the combined feature and the image feature to obtain an enhanced combined feature and an enhanced image feature;
according to the enhancementThe relevance between the joint features and the enhanced image features is subjected to multi-modal fusion to obtain multi-modal data featuresWherein W is r Denoted as the r-th multi-modal data feature.
Preferably, the analyzing the multi-mode data features to obtain the advertisement pre-delivery result includes:
classifying advertisement categories according to the multi-mode data characteristics, calculating the distribution condition of each advertisement category, and obtaining advertisement pre-delivery results, wherein the expression is as follows:
wherein W is i The feature vector denoted as the ith multi-modal data feature, r is denoted as the total number of categories of multi-modal data features.
Preferably, the advertising according to the advertising pre-placement result, to obtain an advertising result, includes:
when the advertisement pre-putting result y=1, the advertisement putting result is the corresponding advertisement category;
when the advertisement is pre-putWhen the advertisement is put in, the result of the advertisement is that the advertisement is put in randomly +.>A corresponding advertisement category;
when the advertisement is pre-putAnd if so, the advertisement putting result is that the corresponding advertisement category is not put.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the website with advertisements on the network is acquired through the multi-mode data acquisition module, the multi-mode data in the website is further acquired, the multi-mode data is subjected to characteristic recognition through the multi-mode data characteristic recognition module, the characteristics of text data and picture data in the multi-mode data are acquired, the distribution category of the advertisements is determined through analyzing the characteristics of the text data and the picture data, and the advertisement delivery is implemented according to the distribution condition of the advertisements of each category, so that the problem of information deviation caused by the single-mode condition can be solved, and the advertisement delivery precision rate for users is improved through analyzing the online multi-mode advertisement data.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system structure according to the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of a first aspect of the present application provides a multi-mode advertisement delivery system, including a multi-mode data acquisition module, a multi-mode data feature identification module, a multi-mode data analysis module, and a multi-mode advertisement delivery module;
the multi-mode data acquisition module acquires multi-mode advertisement data in a network through a data acquisition tool to obtain a multi-mode data set;
further, the acquiring the multi-mode advertisement data in the network by the data acquisition tool to obtain a multi-mode data set includes:
searching the advertisement theme keywords through a search engine, and extracting websites of each search result;
performing intersection operation on the website of the search result to obtain an advertisement website result, and taking the advertisement website result as an advertisement basic information source library;
acquiring the website in the advertisement basic information source library according to a preset advertisement information number threshold value by pre-acquiring the website in the advertisement basic information source library, and acquiring data according to the acquired website;
it should be explained that, in the embodiment of the present invention, when the preset advertisement information number threshold is 100, in the process of pre-collecting the websites in the advertisement base information source library, the websites with collected advertisements smaller than 100 websites are removed, and the websites with collected advertisements larger than 100 websites are reserved.
Acquiring multi-modal data from the acquired website through a data acquisition tool, filtering keywords of titles and contents of the multi-modal data, and distributing the multi-modal data to a multi-modal data set D= { (I) according to categories 1 ，T 1 )，...，(I m ，T m ) }, wherein I m ，T m Respectively denoted as mth picture data and text data in the multimodal dataset.
It should be explained that in the embodiment of the invention, the main sources (hundred degrees, microblogs, headlines, etc.) of the advertisement basic information are firstly determined, the representative websites with large influence are selected and manually screened to obtain the prior information sources, and the prior information sources are obtained by manual experience, so that some advertisement basic information sources may be omitted, and therefore, the deficiency of manual experience needs to be made up by a search engine, and the advertisement basic information source websites which are not included in the prior information sources are found out.
The multi-mode data feature recognition module is used for carrying out feature recognition on the multi-mode data set and acquiring multi-mode data features;
further, the performing feature recognition on the multi-mode data set and obtaining multi-mode data features includes:
marking the first segment of the sequence of the text data in the multi-mode dataset;
extracting characters on the picture data in the multi-mode dataset through a picture character recognition technology to obtain a picture text;
it should be explained that, in the embodiment of the present invention, the image and text recognition technology uses the image and text recognition library EasyOCR, easyOCR as an open-source OCR (Optical Character Recognition) library, so that it can be used normally, and it can read the text in the image and convert it into editable text;
the method for using the image character recognition library EasyOCR comprises the following steps: the easycr library is installed first, then OCR objects are created, and the language to be recognized is specified. The image or video stream is then loaded and identified using the OCR object. And finally, processing and analyzing the identification result according to the need.
Splicing the picture text and the text data, and marking the sequence tail end of the picture text;
extracting feature vectors of a sequence first segment of the text data and a sequence tail end of the picture text as joint features R= { R of the picture text and the text data 1 ，R 2 ，...，R r (wherein R is r Representing the characteristics of the text data and the r-th word in the picture text;
it should be explained that, in the embodiment of the present invention, the text and text data of the picture are converted into the feature vector by the bidirectional encoder based on the transducer.
Inputting the picture data in the multi-modal dataset into a pre-trained deep learning model, and extracting the input of the penultimate hidden layer of the pre-trained deep learning model as the image feature P= { P of the picture data 1 ，P 2 ，...，P r }，P r Image features represented as the r-th region in the picture data;
it should be explained that in the embodiment of the present invention, it is enough that only one layer or even three layers of hidden elements are needed for the common hidden layer, the better the number of hidden layers is not necessarily set, the too many hidden layers may cause data to be over-fitted, but in order to better extract the characteristics of the picture data, the input of the hidden layer of the penultimate layer is used as the image characteristics of the picture data, so that the data cannot be over-fitted, and the accuracy of extracting the characteristics can be improved.
Enhancing the combined feature and the image feature to obtain an enhanced combined feature and an enhanced image feature;
it should be explained that, in the embodiment of the present invention, the joint feature and the image feature are enhanced by Attention mechanism Attention, and the enhanced joint feature is obtained after the joint feature passes through the a-layer Attention blockWherein a is denoted as the number of attention layers of the joint feature, < >>Respectively expressed as a parameter matrix of a layer, and the same is done to obtain enhanced image characteristics P a 。
Performing multi-mode fusion according to the correlation degree between the enhanced joint feature and the enhanced image feature to obtain multi-mode data featuresWherein W is r Denoted as the r-th multi-modal data feature.
It should be explained that, in the embodiment of the present invention, attention is paid again by the Attention mechanism Performing multi-modal fusion, using the enhanced joint feature as query and the enhanced image feature as key and value to obtain multi-modal data feature ∈>
The multi-mode data analysis module is used for analyzing the multi-mode data characteristics to obtain advertisement pre-delivery results;
further, the analyzing the multi-mode data features to obtain the advertisement pre-delivery result includes:
classifying advertisement categories according to the multi-mode data characteristics, calculating the distribution condition of each advertisement category, and obtaining advertisement pre-delivery results, wherein the expression is as follows:
wherein W is i The feature vector denoted as the ith multi-modal data feature, r is denoted as the total number of categories of multi-modal data features.
And the multi-mode advertisement putting module is used for putting advertisements according to the advertisement pre-putting results to obtain advertisement putting results.
The step of carrying out advertisement delivery according to the advertisement pre-delivery result to obtain the advertisement delivery result comprises the following steps:
when the advertisement pre-putting result y=1, the advertisement putting result is the corresponding advertisement category;
when the advertisement is pre-putWhen the advertisement is put in, the result of the advertisement is that the advertisement is put in randomly +.>A corresponding advertisement category;
when the advertisement is pre-putAnd if so, the advertisement putting result is that the corresponding advertisement category is not put.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.

Claims (5)

1. The multi-mode advertisement delivery system is characterized by comprising a multi-mode data acquisition module, a multi-mode data characteristic identification module, a multi-mode data analysis module and a multi-mode advertisement delivery module;
the multi-mode data acquisition module acquires multi-mode advertisement data in a network through a data acquisition tool to obtain a multi-mode data set;
the multi-mode data feature recognition module is used for carrying out feature recognition on the multi-mode data set and acquiring multi-mode data features;
the multi-mode data analysis module is used for analyzing the multi-mode data characteristics to obtain advertisement pre-delivery results;
and the multi-mode advertisement putting module is used for putting advertisements according to the advertisement pre-putting results to obtain advertisement putting results.
2. The multi-modal advertising system of claim 1 wherein the acquiring, by the data acquisition tool, multi-modal advertising data in the network to obtain the multi-modal dataset comprises:
searching the advertisement theme keywords through a search engine, and extracting websites of each search result;
performing intersection operation on the website of the search result to obtain an advertisement website result, and taking the advertisement website result as an advertisement basic information source library;
acquiring the website in the advertisement basic information source library according to a preset advertisement information number threshold value by pre-acquiring the website in the advertisement basic information source library, and acquiring data according to the acquired website;
acquiring multi-mode data from the acquired website through a data acquisition tool, filtering keywords of titles and contents of the multi-mode data, and classifying the multi-mode data according to categoriesAssigning the multimodal data to a multimodal data set d= { (I) 1 ，T 1 )，...，(I m ，T m ) }, wherein I m ，T m Respectively denoted as mth picture data and text data in the multimodal dataset.
3. The multi-modal advertising system of claim 1 wherein the feature recognition of the multi-modal dataset and the acquisition of multi-modal data features comprises:
marking the first segment of the sequence of the text data in the multi-mode dataset;
extracting characters on the picture data in the multi-mode dataset through a picture character recognition technology to obtain a picture text;
splicing the picture text and the text data, and marking the sequence tail end of the picture text;
extracting feature vectors of a sequence first segment of the text data and a sequence tail end of the picture text as joint features R= { R of the picture text and the text data 1 ，R 2 ，...，R r (wherein R is r Representing the characteristics of the text data and the r-th word in the picture text;
inputting the picture data in the multi-modal dataset into a pre-trained deep learning model, and extracting the input of the penultimate hidden layer of the pre-trained deep learning model as the image feature P= { P of the picture data 1 ，P 2 ，...，P r }，P r Image features represented as the r-th region in the picture data;
enhancing the combined feature and the image feature to obtain an enhanced combined feature and an enhanced image feature;
multimode fusion is carried out according to the correlation degree between the enhanced joint feature and the enhanced image feature, so as to obtain multimode data featuresWherein W is r Expressed as the r-th multimodeState data characteristics.
4. The multi-modal advertising system of claim 1 wherein the analyzing the multi-modal data features to obtain advertising pre-placement results comprises:
classifying advertisement categories according to the multi-mode data characteristics, calculating the distribution condition of each advertisement category, and obtaining advertisement pre-delivery results, wherein the expression is as follows:
wherein W is i The feature vector denoted as the ith multi-modal data feature, r is denoted as the total number of categories of multi-modal data features.
5. The multi-modal advertisement delivery system according to claim 1, wherein the performing advertisement delivery according to the advertisement pre-delivery result to obtain an advertisement delivery result comprises:
when the advertisement pre-putting result y=1, the advertisement putting result is the corresponding advertisement category;
when the advertisement is pre-putWhen the advertisement is put in, the result of the advertisement is that the advertisement is put in randomly +.>A corresponding advertisement category;
when the advertisement is pre-putAnd if so, the advertisement putting result is that the corresponding advertisement category is not put.
CN202311532485.4A 2023-11-16 2023-11-16 Multi-mode advertisement putting system Pending CN117575702A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311532485.4A CN117575702A (en) 2023-11-16 2023-11-16 Multi-mode advertisement putting system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311532485.4A CN117575702A (en) 2023-11-16 2023-11-16 Multi-mode advertisement putting system

Publications (1)

Publication Number Publication Date
CN117575702A true CN117575702A (en) 2024-02-20

Family

ID=89885621

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311532485.4A Pending CN117575702A (en) 2023-11-16 2023-11-16 Multi-mode advertisement putting system

Country Status (1)

Country Link
CN (1) CN117575702A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113947436A (en) * 2021-10-22 2022-01-18 合肥工业大学 Multi-mode advertisement popularity prediction method based on text supervision attention
CN115330423A (en) * 2021-04-25 2022-11-11 福州果集信息科技有限公司 Advertisement analysis method and system for webpage image-text data
CN115830610A (en) * 2022-11-07 2023-03-21 武汉理工大学 Multi-mode advertisement recognition method and system, electronic equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115330423A (en) * 2021-04-25 2022-11-11 福州果集信息科技有限公司 Advertisement analysis method and system for webpage image-text data
CN113947436A (en) * 2021-10-22 2022-01-18 合肥工业大学 Multi-mode advertisement popularity prediction method based on text supervision attention
CN115830610A (en) * 2022-11-07 2023-03-21 武汉理工大学 Multi-mode advertisement recognition method and system, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吕学强，等: "多模态语言舆情数据集构建与识别方法", 《北京信息科技大学学报( 自然科学版)》, vol. 38, no. 5, 31 October 2023 (2023-10-31), pages 1 - 9 *

Similar Documents

Publication Publication Date Title
CN109117777B (en) Method and device for generating information
US9218364B1 (en) Monitoring an any-image labeling engine
US7853582B2 (en) Method and system for providing information services related to multimodal inputs
US9037600B1 (en) Any-image labeling engine
CN112818906A (en) Intelligent full-media news cataloging method based on multi-mode information fusion understanding
CN110929125B (en) Search recall method, device, equipment and storage medium thereof
US8370323B2 (en) Providing information services related to multimodal inputs
US10915756B2 (en) Method and apparatus for determining (raw) video materials for news
CN109492168B (en) Visual tourism interest recommendation information generation method based on tourism photos
CN111506794A (en) Rumor management method and device based on machine learning
CN113688951B (en) Video data processing method and device
CN112257452B (en) Training method, training device, training equipment and training storage medium for emotion recognition model
CN113806588B (en) Method and device for searching video
CN113469152B (en) Similar video detection method and device
CN112784078A (en) Video automatic editing method based on semantic recognition
CN115269913A (en) Video retrieval method based on attention fragment prompt
US20190215579A1 (en) Derivative media content systems and methods
CN116975340A (en) Information retrieval method, apparatus, device, program product, and storage medium
CN113868419B (en) Text classification method, device, equipment and medium based on artificial intelligence
CN113407775B (en) Video searching method and device and electronic equipment
CN116977701A (en) Video classification model training method, video classification method and device
CN114528851B (en) Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium
CN117575702A (en) Multi-mode advertisement putting system
CN113220843A (en) Method, device, storage medium and equipment for determining information association relation
CN114547435A (en) Content quality identification method, device, equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination