CN116503115B - Advertisement resource recommendation method and system based on Internet game platform - Google Patents
Advertisement resource recommendation method and system based on Internet game platform Download PDFInfo
- Publication number
- CN116503115B CN116503115B CN202310767432.4A CN202310767432A CN116503115B CN 116503115 B CN116503115 B CN 116503115B CN 202310767432 A CN202310767432 A CN 202310767432A CN 116503115 B CN116503115 B CN 116503115B
- Authority
- CN
- China
- Prior art keywords
- information
- advertisement
- sequence
- node
- recommended
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 72
- 239000013598 vector Substances 0.000 claims description 58
- 238000000605 extraction Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000012015 optical character recognition Methods 0.000 claims 3
- 238000012163 sequencing technique Methods 0.000 claims 2
- 238000004891 communication Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/131—Protocols for games, networked simulations or virtual reality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
- H04L67/306—User profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of computer Internet, and provides an advertisement resource recommendation method and system based on an Internet game platform, wherein the method comprises the steps of obtaining first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by the game platform watched by the user; screening the first information according to the threshold information to obtain second information, wherein the second information comprises the first information of which the viewing time length of the user is longer than that of the threshold information; constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period; extracting features of the advertisement sequence to obtain feature information of each node in the sequence; according to the method, the first advertisement list to be recommended is generated according to the characteristic information of each node in the sequence, and the first advertisement list to be recommended comprises advertisement information to be recommended to the game platform user.
Description
Technical Field
The invention relates to the technical field of computer Internet, in particular to an advertisement resource recommendation method and system based on an Internet game platform.
Background
With the popularization of personal computers and mobile handheld devices, game platforms have become one of the most commonly used network services, so that internet advertisements are placed through game platforms to become an increasingly popular choice for businesses, but internet advertisements are aimed at attracting truly interesting users and reducing interference to uninteresting users, and in the prior art, the advertisements of the businesses are generally recommended for platform users according to the funds placed by the businesses, but the method cannot achieve personalized recommendation of the advertisements, and cannot accurately push the advertisements according to the demands of customers, but the contradiction of the users to the advertisements is increased, so that an advertisement resource recommendation method based on the internet game platforms is needed, personalized recommendation of the advertisements can be achieved, and the probability of ineffective popularization is reduced.
Disclosure of Invention
The invention aims to provide an advertisement resource recommendation method and system based on an Internet game platform, so as to solve the problems.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
In one aspect, an embodiment of the present application provides an advertisement resource recommendation method based on an internet game platform, where the method includes:
acquiring first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by a game platform watched by the user, and the advertisement information is video information;
screening the first information according to the threshold information to obtain second information, wherein the second information comprises first information of which the viewing time length of a user is longer than that of the threshold information;
constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period;
Extracting features of the advertisement sequence to obtain feature information of each node in the sequence;
And generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, wherein the first advertisement list to be recommended comprises advertisement information to be recommended to a game platform user.
In a second aspect, an embodiment of the present application provides an advertisement resource recommendation system based on an internet game platform, where the system includes:
The first acquisition module is used for acquiring first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by a game platform watched by the user, and the advertisement information is video information;
The first processing module is used for screening the first information according to the threshold information to obtain second information, wherein the second information comprises first information of which the viewing time length is longer than that of the threshold information;
the second processing module is used for constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period;
the third processing module is used for extracting the characteristics of the advertisement sequence to obtain the characteristic information of each node in the sequence;
And the fourth processing module is used for generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, wherein the first advertisement list to be recommended comprises advertisement information to be recommended to the game platform user.
In a third aspect, an embodiment of the present application provides an advertisement resource recommendation device based on an internet game platform, where the device includes a memory and a processor. The memory is used for storing a computer program; the processor is used for realizing the advertisement resource recommending method based on the Internet game platform when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the advertisement resource recommendation method based on an internet game platform.
The beneficial effects of the invention are as follows:
According to the invention, the first information is screened through the threshold information to obtain the second information, and the advertisement sequence is constructed according to the second information, so that the interest of the user in any period of time can be effectively reflected, the response rate of the user to the recommended advertisements is improved, and then the advertisement sequence is subjected to feature extraction, so that the features of the user to the interested advertisements can be effectively analyzed, the first advertisement list to be recommended is generated to recommend personalized advertisements to the user, and the problem that the accurate advertisement pushing is difficult to realize in the prior art is effectively solved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an advertisement resource recommendation method based on an internet game platform according to an embodiment of the invention.
Fig. 2 is a schematic structural diagram of an advertisement resource recommendation system based on an internet game platform according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an advertisement resource recommendation device based on an internet game platform according to an embodiment of the present invention.
The drawing is marked: 901. a first acquisition module; 902. a first processing module; 903. a second processing module; 904. a third processing module; 905. a fourth processing module; 906. a second acquisition module; 907. an identification module; 908. a fifth processing module; 909. a sixth processing module; 9031. an acquisition unit; 9032. a first processing unit; 9033. a second processing unit; 9041. a third processing unit; 9042. a fourth processing unit; 9043. a fifth processing unit; 9081. a sixth processing unit; 9082. a seventh processing unit; 9083. an eighth processing unit; 800. advertisement resource recommending equipment based on an Internet game platform; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
The embodiment provides an advertisement resource recommendation method based on an internet game platform, and it can be appreciated that a scene, for example, a scene of personalized advertisement recommendation for a game platform user, can be paved in the embodiment.
Referring to fig. 1, the method includes a step S1, a step S2, a step S3, a step S4, and a step S5, where the method specifically includes:
Step S1, acquiring first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by a game platform watched by the user, and the advertisement information is video information;
It can be appreciated that, as one of the commonly used network services, the game platform through which internet advertisements are delivered is also becoming an increasingly popular choice for businesses, and thus, obtaining historical advertisement information viewed by a user through a database in the game platform can effectively provide a data base for content of interest to the user.
Step S2, screening the first information according to the threshold information to obtain second information, wherein the second information comprises first information of which the viewing time length is longer than that of the threshold information;
It can be understood that the problem of mispoint advertisement may exist in the game platform of the user, so that the mispoint situation of the user is filtered by using the set threshold information to determine the advertisement information really interested by the user, thereby improving the accuracy of recommending advertisement resources to the user.
S3, constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period;
It can be appreciated that the advertisements clicked by the user within a period of time can reflect the interests and hobbies of the user within the period of time, and more direct and accurate information can be provided for advertisement recommendation compared with the original user characteristics and advertisement characteristics.
It can be understood that the step S3 further includes a step S31, a step S32, and a step S33, where specific details are:
Step S31, acquiring a preset sequence length;
Step S32, ordering the second information in a preset time period according to the watching duration to obtain the sequence information of the advertisements;
And step S33, constructing an advertisement sequence according to the preset sequence length and the sequence information of the advertisements.
In this embodiment, if the span of the advertisement sequence data is too long, it is difficult to reflect the needs and hobbies of the user in a certain period of time, and the advertisements in the sequence are difficult to form related information, and the trained node vector is difficult to represent the true meaning of the advertisements, so that further sampling of the sequence is required, the length of the preset sampled sequence is 5, the preset period of time is one week, the advertisements which are watched by the user in the point of one week are ordered according to the watching time length from long to short, so as to obtain the sequence information of the advertisements, and the advertisement sequences of the first 5 advertisement information components are selected as the needs and hobbies of the user in the preset period of time.
S4, extracting features of the advertisement sequence to obtain feature information of each node in the sequence;
it may be understood that the step S4 further includes a step S41, a step S42, and a step S43, where specific details are:
step S41, obtaining video information, text information and audio information corresponding to each advertisement in the advertisement sequence according to each node in the advertisement sequence;
It can be understood that the text information and the audio information corresponding to the video information obtained according to the advertisement information are well known to those skilled in the art, and thus are not described herein.
Step S42, performing feature extraction on the video information in one node to obtain a first feature vector, performing feature extraction on the text information in one node to obtain a second feature vector, and performing feature extraction on the audio information in one node to obtain a third feature vector;
It can be understood that the video information is sent to the three-dimensional convolutional neural network model to obtain a first feature vector, the first feature vector is a representation of space-time features, feature extraction of text information and audio information is a technical scheme well known to those skilled in the art, so that details are not repeated herein, the second feature vector is used for representing features of advertisement text information, the third feature vector is used for representing features of an advertisement audio information screen, it is to be noted that in the prior art, feature information in the video is extracted by adopting a two-dimensional convolutional neural network and a convolutional neural-long-short-time memory network, but the calculation cost is high and the correlation between space and time information cannot be modeled, and the calculation mode of the latter excessively depends on the space features to cause a large amount of useful time information to be lost.
And step S43, fusing the first feature vector, the second feature vector and the third feature vector in one node to obtain feature information of one node.
It may be appreciated that fusing the first feature vector, the second feature vector, and the third feature vector in one node is specifically:
In the above formula, F is the feature vector after fusion, namely the feature information of a node, A, B, C is the first feature vector, the second feature vector and the third feature vector respectively, 、/>、/>The weight coefficients corresponding to the first feature vector, the second feature vector and the third feature vector are used for representing that the feature in the dimension is more interested, and the/>, which needs to be described, are shown as follows、、/>The determination may be performed by using an attention mechanism, and the determination of the feature weights by using an attention mechanism is a technical solution well known to those skilled in the art, and is not described herein.
And S5, generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, wherein the first advertisement list to be recommended comprises advertisement information to be recommended to a game platform user.
It can be understood that the characteristic information of each node in the sequence comprises characteristic information of advertisements most interested by the user in a preset time period, the similarity matching is carried out on the basis of the characteristic information and all advertisement information in the game platform to generate a first advertisement list to be recommended, and the advertisement recommendation is carried out on the user of the game platform on the basis of the advertisements in the first advertisement list to be recommended, so that personalized advertisement recommendation of the user is realized, and the problem that accurate advertisement pushing is difficult to realize in the prior art is effectively solved.
It may be understood that step S5 further includes step S6, step S7, step S8 and step S9, where specific steps are:
s6, acquiring key frame information, wherein the key frame information comprises video frames corresponding to clicking operations performed by watching game advertisements by a user;
It can be understood that when the user performs a click operation after watching the game advertisement, it indicates that the user responds to the advertisement, that is, the user is interested in knowing the advertisement, so that the video frame corresponding to the click operation of the user on the advertisement is used as key frame information, which indicates that the user is most sensitive to the key frame.
S7, recognizing the key frame information by utilizing an OCR recognition technology to obtain text information corresponding to the key frame;
it will be appreciated that the key frame information needs to be preprocessed before being identified by using OCR recognition technology to improve the quality of the image, so as to ensure the accuracy of text information identification, so as to improve the accuracy of advertisement recommendation for users, where preprocessing includes binarizing, laplace sharpening, filtering, etc. the image.
Step S8, extracting keywords from the text information corresponding to the key frames to obtain first keyword information;
It may be understood that step S8 further includes step S81, step S82 and step S83, where specific details are:
Step S81, performing word segmentation on the text information corresponding to the key frames to obtain text information subjected to word segmentation;
Step S82, calculating the text information after word segmentation by using a word vector algorithm to obtain a word vector corresponding to each word segment;
and step S83, sending the word vector corresponding to each word to the trained keyword extraction model to obtain first keyword information.
In this embodiment, the prior art generally adopts a TF-IDF keyword extraction method to extract keywords of a text, but the method has the disadvantage of ignoring semantic links among words, so in this embodiment, word vector algorithm is used to convert words into word vectors for calculation through word vector processing on text information, and then neural network is used to find keywords of the text information.
And S9, screening the first game advertisement list to be recommended by utilizing the first keyword information to obtain a second game advertisement list to be recommended.
It can be understood that the text information of each advertisement information in the first game advertisement list to be recommended is extracted by keywords to obtain second keyword information; calculating the similarity between the first keyword information and the second keyword information to obtain similarity information; judging whether the similarity information is larger than a similarity threshold value, wherein if the similarity information is smaller than the similarity threshold value, deleting the corresponding advertisement information in a first game advertisement list to be recommended until the first game advertisement list to be recommended is screened out to obtain a second game advertisement list to be recommended, and calculating the similarity between the first keyword information and the second keyword information to obtain the similarity information specifically comprises the following steps:
in the above, COS Representing cosine values between the first keyword information and the second keyword information, i.e. similarity information,/>And/>The first keyword information and the second keyword information are respectively represented.
Example 2:
as shown in fig. 2, the present embodiment provides an advertisement resource recommendation system based on an internet game platform, where the system includes a first acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904, and a fourth processing module 905, and specifically includes:
the first obtaining module 901 is configured to obtain first information and threshold information, where the first information includes historical advertisement information recommended to a user by a game platform that the user has watched, and the advertisement information is video information;
The first processing module 902 is configured to filter the first information according to the threshold information to obtain second information, where the second information includes first information that is longer than the threshold information when viewed by a user;
A second processing module 903, configured to construct an advertisement sequence according to the second information, where the advertisement sequence includes historical advertisement information that is viewed sequentially in a preset time period;
a third processing module 904, configured to perform feature extraction on the advertisement sequence to obtain feature information of each node in the sequence;
the fourth processing module 905 is configured to generate a first advertisement to be recommended list according to the feature information of each node in the sequence, where the first advertisement to be recommended list includes advertisement information to be recommended to the game platform user.
In a specific embodiment of the disclosure, the second processing module 903 further includes an obtaining unit 9031, a first processing unit 9032, and a second processing unit 9033, where specific details are:
An acquiring unit 9031, configured to acquire a preset sequence length;
the first processing unit 9032 is configured to sort the second information in a preset time period according to the viewing duration, so as to obtain sequence information of the advertisement;
and a second processing unit 9033, configured to construct an advertisement sequence according to the preset sequence length and the sequence information of the advertisement.
In a specific embodiment of the disclosure, the third processing module 904 further includes a third processing unit 9041, a fourth processing unit 9042, and a fifth processing unit 9043, where specific details are:
A third processing unit 9041, configured to obtain, according to each node in the advertisement sequence, video information, text information, and audio information corresponding to each advertisement in the advertisement sequence;
a fourth processing unit 9042, configured to perform feature extraction on the video information in one node to obtain a first feature vector, perform feature extraction on the text information in one node to obtain a second feature vector, and perform feature extraction on the audio information in one node to obtain a third feature vector;
and a fifth processing unit 9043, configured to fuse the first feature vector, the second feature vector, and the third feature vector in one node to obtain feature information of one node.
In a specific embodiment of the present disclosure, the fourth processing module 905 further includes a second obtaining module 906, an identifying module 907, a fifth processing module 908, and a sixth processing module 909, where specific details are:
a second obtaining module 906, configured to obtain key frame information, where the key frame information includes video frames corresponding to clicking operations performed by a user watching a game advertisement;
the recognition module 907 is configured to recognize the key frame information by using an OCR recognition technology, so as to obtain text information corresponding to the key frame;
a fifth processing module 908, configured to extract a keyword from the text information corresponding to the key frame, so as to obtain first keyword information;
And a sixth processing module 909, configured to screen the first to-be-recommended game advertisement list by using the first keyword information, so as to obtain a second to-be-recommended game advertisement list.
In a specific embodiment of the disclosure, the fifth processing module 908 further includes a sixth processing unit 9081, a seventh processing unit 9082, and an eighth processing unit 9083, where specific details are:
A sixth processing unit 9081, configured to perform word segmentation on the text information corresponding to the key frame, to obtain text information after word segmentation;
A seventh processing unit 9082, configured to calculate the text information after the word segmentation by using a Li Yongci vector algorithm, to obtain a word vector corresponding to each word segment;
And an eighth processing unit 9083, configured to send the word vector corresponding to each word segment to the trained keyword extraction model, to obtain first keyword information.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3:
Corresponding to the above method embodiment, an advertisement resource recommendation device based on an internet game platform is further provided in this embodiment, and an advertisement resource recommendation device based on an internet game platform described below and an advertisement resource recommendation method based on an internet game platform described above may be referred to correspondingly.
FIG. 3 is a block diagram illustrating an advertising asset recommendation device 800 based on an Internet gaming platform, according to an exemplary embodiment. As shown in fig. 3, the internet game platform-based advertising asset recommendation device 800 may include: a processor 801, a memory 802. The internet game platform based advertising asset recommendation device 800 may also include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the internet game platform-based advertisement resource recommendation device 800, so as to complete all or part of the steps in the internet game platform-based advertisement resource recommendation method. The memory 802 is used to store various types of data to support the operation of the internet game platform based advertising asset recommendation device 800, which may include, for example, instructions for any application or method operating on the internet game platform based advertising asset recommendation device 800, as well as application related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the internet game platform-based advertising asset recommendation device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, the corresponding communication component 805 may therefore include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the internet game platform based advertising asset recommendation device 800 may be implemented by one or more Application Specific Integrated Circuits (ASIC), digital signal processors (DIGITALSIGNAL PROCESSOR DSP), digital signal processing devices (DIGITAL SIGNAL Processing Device DSPD), programmable logic devices (Programmable Logic Device PLD), field programmable gate arrays (Field Programmable GATE ARRAY FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the internet game platform based advertising asset recommendation method described above.
In another exemplary embodiment, there is also provided a computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the above-described internet game platform-based advertising resource recommendation method. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the internet game platform based advertising asset recommendation device 800 to perform the internet game platform based advertising asset recommendation method described above.
Example 4:
Corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and an advertisement resource recommendation method based on an internet game platform described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the advertisement resource recommendation method based on the internet game platform of the above method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, which may store various program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (6)
1. An advertisement resource recommendation method based on an internet game platform is characterized by comprising the following steps:
Acquiring first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by a game platform watched by the user, and the historical advertisement information is video information;
screening the first information according to the threshold information to obtain second information, wherein the second information comprises first information of which the viewing time length of a user is longer than that of the threshold information;
constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period;
Extracting features of the advertisement sequence to obtain feature information of each node in the sequence;
generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, wherein the first advertisement list to be recommended comprises advertisement information to be recommended to a game platform user;
after generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, the method further comprises the following steps:
obtaining key frame information, wherein the key frame information comprises video frames corresponding to clicking operations performed by a user watching game advertisements;
identifying the key frame information by utilizing an OCR (optical character recognition) technology to obtain text information corresponding to the key frame;
Extracting keywords from the text information corresponding to the key frames to obtain first keyword information;
screening the first advertisement list to be recommended by using the first keyword information to obtain a second advertisement list to be recommended;
The feature extraction is performed on the advertisement sequence to obtain feature information of each node in the sequence, and the feature extraction comprises the following steps:
According to each node in the advertisement sequence, video information, text information and audio information corresponding to each advertisement in the advertisement sequence are obtained;
Extracting features of the video information in one node to obtain a first feature vector, extracting features of the text information in one node to obtain a second feature vector, and extracting features of the audio information in one node to obtain a third feature vector;
Fusing the first feature vector, the second feature vector and the third feature vector in one node to obtain feature information of one node;
and sending the video information to a three-dimensional convolutional neural network model to obtain a first feature vector, wherein the first feature vector is a representation of space-time features.
2. The internet game platform-based advertising resource recommendation method of claim 1, wherein constructing an advertising sequence based on the second information comprises:
acquiring a preset sequence length;
sequencing the second information in a preset time period according to the watching duration to obtain the sequence information of the advertisements;
And constructing an advertisement sequence according to the preset sequence length and the sequence information of the advertisements.
3. The internet game platform-based advertisement resource recommendation method of claim 1, wherein extracting keywords from text information corresponding to the key frames to obtain first keyword information comprises:
word segmentation is carried out on the text information corresponding to the key frames, and text information after word segmentation is obtained;
The Li Yongci vector algorithm calculates the text information after word segmentation processing to obtain word vectors corresponding to each word segment;
and sending the word vector corresponding to each word to the trained keyword extraction model to obtain first keyword information.
4. An advertisement resource recommendation system based on an internet game platform, which is characterized by comprising:
the first acquisition module is used for acquiring first information and threshold information, wherein the first information comprises historical advertisement information recommended to a user by a game platform watched by the user, and the historical advertisement information is video information;
The first processing module is used for screening the first information according to the threshold information to obtain second information, wherein the second information comprises first information of which the viewing time length is longer than that of the threshold information;
the second processing module is used for constructing an advertisement sequence according to the second information, wherein the advertisement sequence comprises historical advertisement information watched in sequence in a preset time period;
the third processing module is used for extracting the characteristics of the advertisement sequence to obtain the characteristic information of each node in the sequence;
the fourth processing module is used for generating a first advertisement list to be recommended according to the characteristic information of each node in the sequence, wherein the first advertisement list to be recommended comprises advertisement information to be recommended to a game platform user;
wherein, after the fourth processing module, the method further comprises:
The second acquisition module is used for acquiring key frame information, wherein the key frame information comprises video frames corresponding to clicking operations performed by watching game advertisements by a user;
The recognition module is used for recognizing the key frame information by utilizing an OCR recognition technology to obtain text information corresponding to the key frame;
the fifth processing module is used for extracting keywords from the text information corresponding to the key frames to obtain first keyword information;
The sixth processing module is used for screening the first advertisement list to be recommended by using the first keyword information to obtain a second advertisement list to be recommended;
Wherein the third processing module comprises:
the third processing unit is used for obtaining video information, text information and audio information corresponding to each advertisement in the advertisement sequence according to each node in the advertisement sequence;
The fourth processing unit is used for carrying out feature extraction on the video information in one node to obtain a first feature vector, carrying out feature extraction on the text information in one node to obtain a second feature vector and carrying out feature extraction on the audio information in one node to obtain a third feature vector;
A fifth processing unit, configured to fuse the first feature vector, the second feature vector, and the third feature vector in a node, to obtain feature information of the node;
and sending the video information to a three-dimensional convolutional neural network model to obtain a first feature vector, wherein the first feature vector is a representation of space-time features.
5. The internet game platform-based advertising resource recommendation system of claim 4, wherein the second processing module comprises:
The acquisition unit is used for acquiring a preset sequence length;
The first processing unit is used for sequencing the second information in a preset time period according to the watching duration to obtain the sequence information of the advertisements;
And the second processing unit is used for constructing an advertisement sequence according to the preset sequence length and the sequence information of the advertisements.
6. The internet game platform-based advertising resource recommendation system of claim 4, wherein the fifth processing module comprises:
The sixth processing unit is used for performing word segmentation on the text information corresponding to the key frames to obtain text information subjected to word segmentation;
the seventh processing unit is used for calculating the text information after word segmentation by using a word vector algorithm to obtain a word vector corresponding to each word segmentation;
and the eighth processing unit is used for sending the word vector corresponding to each word to the trained keyword extraction model to obtain first keyword information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310767432.4A CN116503115B (en) | 2023-06-27 | 2023-06-27 | Advertisement resource recommendation method and system based on Internet game platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310767432.4A CN116503115B (en) | 2023-06-27 | 2023-06-27 | Advertisement resource recommendation method and system based on Internet game platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116503115A CN116503115A (en) | 2023-07-28 |
| CN116503115B true CN116503115B (en) | 2024-05-03 |
Family
ID=87325223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310767432.4A Active CN116503115B (en) | 2023-06-27 | 2023-06-27 | Advertisement resource recommendation method and system based on Internet game platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503115B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109525866A (en) * | 2018-12-06 | 2019-03-26 | 安徽海豚新媒体产业发展有限公司 | A kind of advertisement sending method based on viewing duration |
| CN109831684A (en) * | 2019-03-11 | 2019-05-31 | 深圳前海微众银行股份有限公司 | Video optimized recommended method, device and readable storage medium storing program for executing |
| CN111582913A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | Advertisement recommendation method and device |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN115858815A (en) * | 2022-12-23 | 2023-03-28 | 百度(中国)有限公司 | Method for determining mapping information, advertisement recommendation method, device, equipment and medium |
-
2023
- 2023-06-27 CN CN202310767432.4A patent/CN116503115B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109525866A (en) * | 2018-12-06 | 2019-03-26 | 安徽海豚新媒体产业发展有限公司 | A kind of advertisement sending method based on viewing duration |
| CN109831684A (en) * | 2019-03-11 | 2019-05-31 | 深圳前海微众银行股份有限公司 | Video optimized recommended method, device and readable storage medium storing program for executing |
| CN111582913A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | Advertisement recommendation method and device |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN115858815A (en) * | 2022-12-23 | 2023-03-28 | 百度(中国)有限公司 | Method for determining mapping information, advertisement recommendation method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 郑小发.《人工智能背景下社会网络治理建设与实践探索》.延边大学出版社,2022,第244-249页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116503115A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11256739B2 (en) | Data access based on con lent of image recorded by a mobile device | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN108399180B (en) | Knowledge graph construction method and device and server | |
| CN105488154A (en) | Theme application recommendation method and device | |
| CN112364204B (en) | Video searching method, device, computer equipment and storage medium | |
| CN112801719A (en) | User behavior prediction method, user behavior prediction device, storage medium, and apparatus | |
| CN112507153B (en) | Method, computing device, and computer storage medium for image retrieval | |
| CN113469298B (en) | Model training method and resource recommendation method | |
| CN110209921B (en) | Method and device for pushing media resource, storage medium and electronic device | |
| CN115909127A (en) | Training method of abnormal video recognition model, abnormal video recognition method and device | |
| CN115147130A (en) | Problem prediction method, apparatus, storage medium, and program product | |
| CN113704509B (en) | Multimedia recommendation method and device, electronic equipment and storage medium | |
| CN116503115B (en) | Advertisement resource recommendation method and system based on Internet game platform | |
| CN114282119B (en) | Scientific and technological information resource retrieval method and system based on heterogeneous information network | |
| CN113780318B (en) | Method, device, server and medium for generating prompt information | |
| CN110879863B (en) | Cross-domain search method and cross-domain search device | |
| CN113256379A (en) | Method for correlating shopping demands for commodities | |
| CN112115300A (en) | Text processing method and device, electronic equipment and readable storage medium | |
| CN113297417A (en) | Video pushing method and device, electronic equipment and storage medium | |
| CN116304146B (en) | Image processing method and related device | |
| CN114880572B (en) | Intelligent news client recommendation system | |
| CN112287184B (en) | Migration labeling method, device, equipment and storage medium based on neural network | |
| CN116911912B (en) | Method and device for predicting interaction objects and interaction results | |
| CN113836326A (en) | User preference intelligent extraction method based on self-media platform | |
| CN117633363A (en) | News personalized recommendation method, device and computer 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 | ||
| GR01 | Patent grant |