CN114463040A - Advertisement plan generating method, device, computer equipment and storage medium - Google Patents
Advertisement plan generating method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114463040A CN114463040A CN202111675668.2A CN202111675668A CN114463040A CN 114463040 A CN114463040 A CN 114463040A CN 202111675668 A CN202111675668 A CN 202111675668A CN 114463040 A CN114463040 A CN 114463040A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- historical
- plan
- information
- advertisement plan
- 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
Links
Images
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
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F40/295—Named entity recognition
-
- 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
- G06Q30/0276—Advertisement creation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement plan generating method, an advertisement plan generating device, computer equipment and a storage medium, wherein the method comprises the steps of establishing demand information by acquiring advertisements; detecting whether an advertisement plan to be selected exists in the historical advertisement plan data set or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data; when an advertisement plan to be selected exists in a historical advertisement plan data set, acquiring real-time information, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected; and recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as an advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced. The invention improves the efficiency and the accuracy of generating the advertisement plan.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a method and an apparatus for generating an advertisement plan, a computer device, and a storage medium.
Background
With the development of science and technology, more and more new media are generated and developed, so that advertisements can be put on different media to achieve the effect of information exposure, and the popularization efficiency of products, activities and the like is improved. Before advertisement placement, the advertisement plan needs to be customized, such as advertisement design form, advertisement placement object, and the like.
In the advertisement plan in the prior art, generally, the advertisement design requirements of a client are sent to an advertisement company, and the advertisement company decodes the advertisement design requirements and then performs advertisement design and delivery strategy design, but the method for customizing the advertisement plan has low efficiency, and the advertisement design and the delivery strategy design are both decoded manually, so that design errors are easy to occur, and further the effectiveness of making the advertisement plan is low.
Disclosure of Invention
The embodiment of the invention provides an advertisement plan generating method, an advertisement plan generating device, computer equipment and a storage medium, and aims to solve the problems of low advertisement plan customizing efficiency and low effectiveness in the prior art.
An advertisement plan generating method, comprising:
acquiring advertisement formulation demand information; the advertisement formulation demand information is associated with target index data;
acquiring a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; associating a historical indicator data with a historical advertising program;
detecting whether the historical advertisement plan data set has an advertisement plan to be selected or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data;
when the historical advertisement plan data set has an advertisement plan to be selected, acquiring real-time information, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected;
and recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as an advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
An advertisement plan generating apparatus comprising:
the advertisement information acquisition module is used for acquiring advertisement formulation demand information; the advertisement formulation demand information is associated with target index data;
the advertisement plan acquisition module is used for acquiring a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; associating a historical indicator data with a historical advertising program;
the advertisement plan detection module is used for detecting whether an advertisement plan to be selected exists in the historical advertisement plan data set or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data;
the index prediction module is used for acquiring real-time information when an advertisement plan to be selected exists in the historical advertisement plan data set, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected;
and the first advertisement plan generating module is used for recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as the advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the above advertisement plan generating method when executing the computer program.
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described advertisement plan generating method.
According to the method, the advertisement plan with higher profitability (namely the advertisement plan to be selected) in the historical advertisement plans is used as a basis, the future profitability of the advertisement plan to be selected is predicted through the acquired real-time information, so that the advertisement plan to be replaced is finally determined, the advertisement plan with higher profitability in the historical is referred, the advertisement plan with higher profitability is subjected to local plan replacement through the advertisement formulation demand information, the generation efficiency of the target advertisement plan is improved, the expected profitability of the generated target advertisement plan is higher, and the advertisement putting profit of a target user is improved; furthermore, in the embodiment, the advertisement formulation requirement information sent by the user does not need to be manually interpreted, so that the labor is saved, the advertisement plan generation time is reduced, and the effectiveness of advertisement plan generation is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a diagram of an application environment of a method for generating an advertisement plan according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of generating an advertising plan in accordance with an embodiment of the present invention;
FIG. 3 is a schematic block diagram of an advertisement plan generating apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The advertisement plan generating method provided by the embodiment of the invention can be applied to the application environment shown in fig. 1. Specifically, the advertisement plan generating method is applied to an advertisement plan generating system, the advertisement plan generating system comprises a client and a server shown in fig. 1, and the client and the server are in communication through a network and are used for solving the problems of low advertisement plan customizing efficiency and low effectiveness in the prior art. The client is also called a user side, and refers to a program corresponding to the server and providing local services for the client. The client may be installed on, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
In an embodiment, as shown in fig. 2, an advertisement plan generating method is provided, which is described by taking the server in fig. 1 as an example, and includes the following steps:
s10: acquiring advertisement formulation demand information; the advertisement formulation demand information is associated with target index data.
It can be understood that the advertisement formulation requirement information represents the requirement of the user for formulating the advertisement plan, and the advertisement formulation requirement information may include, for example, advertisement title information (e.g., title content, title font format, title background, etc.), advertisement targeting information (e.g., promotion crowd information, promotion area information, etc. that the advertisement needs to be pushed), advertisement promotion material (representing the type of advertisement pushing, such as pictures, videos, etc.), and advertisement promotion plan (representing the platform of advertisement pushing, such as different video playing platforms, music playing platforms, etc.). The target index data represents the expected revenue of the user after the advertisement plan is implemented, the target index data can be any index or combination of multiple indexes of click rate (representing the percentage of the user clicking the advertisement), download conversion rate (generally aiming at the advertisement containing the advertisement that the user can click to download the attachment), or consumption conversion rate (representing the value of the advertisement browsed by the user), and the target index data can be preset by the user.
S20: acquiring a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; one of the historical advertising programs is associated with one of the historical index data.
As can be appreciated, a historical advertising plan is an advertising plan that has been implemented prior to the targeted user sending the advertising formulation requirement information. The historical indicator data refers to a real profit value brought by the historical advertisement plan after the historical advertisement plan is implemented, and may also include one or more of click rate, download conversion rate and consumption conversion rate. Further, the historical index data may be obtained by collecting data such as advertisement putting times, click times, downloading times, browsing data and the like after the implementation of the historical advertisement plan, and performing conversion, for example, determining click rate according to the advertisement putting times and click times, determining downloading conversion rate according to the advertisement putting times and download times, and determining consumption conversion rate according to flow values required for putting different advertisements once and flow consumption values of advertisements browsed by the user.
S30: detecting whether the historical advertisement plan data set has an advertisement plan to be selected or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data.
Specifically, after a historical advertisement plan data set is obtained, target index data associated with advertisement formulation demand information is compared with historical index data associated with all historical advertisement plans, and the target index data is supposed to only comprise click rate data, so that a historical advertisement plan corresponding to the historical index data containing click rate data can be screened out before the target index data is compared with the historical index data, the click rate data of the historical advertisement plan is further compared with the click rate data of the advertisement formulation demand information, and if the click rate data of the historical index data is larger than or equal to the click rate data set by the target index data, the historical advertisement plan is considered as a plan to be selected; and if the click rate data of the historical index data is smaller than the click rate data set by the target index data, the historical advertisement plan is determined not to be the plan to be selected.
For example, when the target index data includes multiple types of index data (for example, the click rate, the download conversion rate, the consumption conversion rate, and the like described above), the target index data may be compared with the same type of data in the historical index data, for example, the click rate, the download conversion rate, and the like are compared, the number of multiple types of index data in the historical index data that are greater than or equal to the target index data is determined, for example, the click rate data and the download conversion rate in one historical index data are greater than the click rate data and the download conversion rate set in the target index data, the number of index data that are greater than the target index data in the historical index data is considered to be two, if three types of index data are included in the target index data, and more than two types of index data are set to be greater than or equal to the data in the target index data (it may also be set that all types of index data are greater than or equal to the target index data (it is also possible to set that all types of index data are greater than or equal to the target index data The data in (2) can be set by self), the historical advertisement plan is determined as the advertisement plan to be selected.
S40: and when the historical advertisement plan data set has the advertisement plan to be selected, acquiring real-time information, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected.
Specifically, after detecting whether the historical advertisement plan data set has the advertisement plan to be selected, if the historical advertisement plan data set has the advertisement plan to be selected, the profit representing the advertisement plan to be selected is expected, but the profit (i.e., the historical index data) of the advertisement plan to be selected is historically collected, and therefore the profit of the advertisement plan to be selected needs to be estimated, so that the real-time information is introduced in the embodiment, and after the real-time information is subjected to entity identification and intention feature extraction, index prediction can be performed on the advertisement plan to be selected according to the entity and the intention in the real-time information, so that the prediction index data corresponding to the advertisement to be selected is obtained.
The real-time information refers to policy information, activity information, and the like. The real-time dynamic information can be obtained through a crawler technology, namely, a technology for obtaining information from a webpage or other media through a program or a script. The time for acquiring the real-time information may be determined according to the time of the historical index data corresponding to the advertisement plan to be selected, and for example, assuming that the statistical time of the historical index data is 2021 year, 8 month and 23 days, the time for acquiring the real-time information may be any time after 8 month and 23 days. The prediction index data is the future yield rate of the advertisement plan to be selected according to the real-time information, and the prediction index data can be obtained by adjusting the historical index data of the advertisement plan to be selected according to the real-time information.
S50: and recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as an advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
Specifically, after index prediction is performed on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected, the prediction index data of the advertisement plan to be selected is compared with target index data, if the prediction index data is greater than or equal to the target index data, the advertisement plan to be selected corresponding to the prediction index data greater than or equal to the target index data is recorded as an advertisement plan to be replaced, specific contents in the advertisement plan to be replaced are adaptively replaced according to advertisement formulation demand information, such as replacement promotion area information, promotion crowd information and the like, and the replaced advertisement plan to be replaced is determined as the target advertisement plan. If the prediction index data is smaller than the target index data, the future yield rate of the advertisement plan to be replaced after implementation is possibly not met with the set requirement of the target index data, and the advertisement plan to be replaced corresponding to the highest prediction index data can be sent to the target user so that the target user can use the advertisement plan to be replaced as a template, and therefore the generation efficiency of the advertisement plan can be improved.
In this embodiment, firstly, an advertisement plan with a higher profitability in a historical advertisement plan (that is, the advertisement plan to be selected) is used as a basis, and the future profitability of the advertisement plan to be selected is predicted through the acquired real-time information, so that the advertisement plan to be replaced is finally determined, so that the generation efficiency of a target advertisement plan is improved by taking the advertisement plan with the higher profitability in the historical history as a reference and performing local plan replacement on the advertisement plan to be replaced through advertisement formulation demand information, and the expected profitability of the generated target advertisement plan is higher, so that the advertisement income of a target user is improved; furthermore, in the embodiment, the advertisement formulation requirement information sent by the user does not need to be manually interpreted, so that the labor is saved, the advertisement plan generation time is reduced, and the effectiveness of advertisement plan generation is improved.
In an embodiment, after step S30, that is, after detecting whether there is an advertisement plan to be selected in the historical advertisement plan database, the method further includes:
and when no advertisement plan to be selected exists in the historical advertisement plan data set, carrying out data analysis on the advertisement formulation demand information to obtain promotion crowd information, promotion area information and promotion content information in the advertisement formulation demand information.
It can be understood that after detecting whether the historical advertisement plan data set has the advertisement plan to be selected, if the historical advertisement plan data set does not have the advertisement plan to be selected, and the historical advertisement plan data set is characterized by not having the plan meeting the requirement of the target index data, the advertisement plan corresponding to the advertisement formulation requirement information can be generated intelligently, and then the advertisement formulation requirement information needs to be subjected to data analysis first, so that the promotion crowd information, the promotion area information and the promotion content information in the advertisement formulation requirement information are obtained. The popularization crowd information represents a user portrait of a target crowd needing to push advertisements, and the popularization crowd information can include basic information such as age, gender, behavior interest and the like of the user; the promotion area information represents an area needing to push the advertisement, and the promotion area information can be divided and selected on a map mapped in a real scene or can be divided and selected by adopting real coordinate information. The promotion content information represents advertisement content to be pushed, such as promoted text data, industry associated with the promoted content, and the like.
And generating advertisement targeting information according to the popularization crowd information and the popularization area information, and determining a popularization content label corresponding to the advertisement formulation demand information according to the popularization content information.
In an understandable way, the advertisement targeting information represents the pushing direction of the advertisement, that is, the advertisement is pushed to the user portrait in the area corresponding to the promotion area information and the user corresponding to the promotion crowd information. The promotion content label is an industry to which the advertisement content representing the advertisement formulation demand information belongs, such as a sports industry, an education industry, a medical industry and the like.
Specifically, after data analysis is performed on advertisement formulation demand information to obtain promotion crowd information, promotion area information and promotion content information in the advertisement formulation demand information, the promotion crowd information and the promotion area information can be integrated to obtain advertisement targeting information; and performing entity identification on the promotion content information so as to identify key words related to any industry in the promotion content information, and determining an industry label to which the promotion content information belongs according to the identified key words, namely the promotion content label.
And determining an advertisement putting label corresponding to the promotion content label from a preset platform recommendation database, and determining an advertisement promotion material corresponding to the promotion content label from a preset creative material database.
It can be understood that the preset platform recommendation database is used for storing different advertisement platforms and combinations of different advertisement slots in the platforms, that is, sample delivery triples. The sample release triples comprise sample promotion labels, sample release labels and release index data, wherein the sample release labels are used for representing industry information corresponding to the sample release triples, and the sample promotion labels can be game industry labels, education industry labels, e-commerce industry labels and the like. The sample putting label is platform information and position information representing advertisement putting. The platform information is a media platform for advertisement delivery, for example, an application platform, such as a wechat platform, an app platform, or a website platform, such as a search engine of hundredths, dog search, and the like. The slot information is a position where the advertisement is placed on the media platform, for example, the advertisement may be placed on the top, bottom, side, etc. of the media platform, and the slot information further includes a size of the advertisement slot when the advertisement is placed, for example, 240 × 100 single pictures or videos are placed on the top of the media platform. The method comprises the steps that delivery index data represent profits obtained by delivering advertisements in platforms and layout positions represented by sample delivery labels, and the delivery index data comprise platform index data and layout position index data; the platform index data refers to the number of times an advertisement is clicked or downloaded by a user or the duration of browsing after the advertisement is delivered on the media platform, and can be characterized by the average number of index data collected each day after the advertisement is delivered for a period of time. The position index data refers to the number of times that the advertisement is clicked or downloaded by a user or the browsing duration after the advertisement is placed on the position of the platform, and can be represented by the average number of index data collected every day after the advertisement is placed for a period of time.
Further, the preset creative material database is used to store different types of creative materials, such as picture-type materials and video-type materials. The advertisement promotion material is a material matched with the industry corresponding to the promotion content label, and the advertisement promotion material can be a picture material or a video material with the highest utilization rate in the industry corresponding to the promotion content label, or a picture material or a video material with the highest income corresponding to an advertisement plan after being used in other advertisement plans.
And generating a target advertisement plan according to the advertisement targeting information, the advertisement putting label and the advertisement promotion material.
Specifically, after the advertisement targeting information, the advertisement putting label and the advertisement promotion material corresponding to the advertisement formulation demand information are determined, the target advertisement plan can be generated according to the advertisement targeting information, the advertisement putting label and the advertisement promotion material. In addition, the advertisement title information can be selected according to the promotion content information, for example, the content information used as the label is selected according to the promotion content information, and then different advertisement title information is generated through different title styles, so that the target advertisement plan is generated according to the advertisement target information, the advertisement release label and the advertisement promotion material.
In this embodiment, when there is no advertisement plan to be selected, can be through analyzing out the popularization crowd information in the advertisement formulation demand information, promote regional information and popularization content information, and then according to promoting crowd information, promote regional information and popularization content information, with the help of presetting platform recommendation database and presetting creative materials database, confirm advertisement directional information, advertisement putting label and advertisement promotion material, thereby generate the target advertisement plan, so can carry out the generation of advertisement plan intelligently, need not artifically read advertisement formulation demand information, the efficiency of advertisement plan formulation has been improved, manpower and materials have been saved.
In an embodiment, the determining, in the self-provisioning platform recommendation database, an advertisement placement tag corresponding to the promoted content tag includes:
obtaining a sample putting triple corresponding to a sample promotion label which is the same as the promotion content label from a preset platform recommendation database; the sample release triples are composed of sample promotion labels, sample release labels and release index data.
The sample release tag is used for representing industry information corresponding to the sample release triplet, and illustratively, the sample promotion tag may be a game industry tag, an education industry tag, an e-commerce industry tag, and the like. The sample putting label is platform information and position information representing advertisement putting. The platform information is a media platform for advertisement delivery, for example, an application platform, such as a wechat platform, an app platform, or a website platform, such as a search engine of hundredths, dog search, and the like. The slot information is a position where the advertisement is placed on the media platform, for example, the advertisement may be placed on the top, bottom, side, etc. of the platform, and the slot information further includes a size of the advertisement slot when the advertisement is placed, for example, a single picture or a video of 500 × 100 is placed on the front page of the platform. The method comprises the steps that delivery index data represent profits obtained by delivering advertisements in platforms and layout positions represented by sample delivery labels, and the delivery index data comprise platform index data and layout position index data; the platform index data refers to the number of times an advertisement is clicked or downloaded by a user or the duration of browsing after the advertisement is delivered on the media platform, and can be characterized by the average number of index data collected each day after the advertisement is delivered for a period of time. The position index data refers to the number of times that the advertisement is clicked or downloaded by a user or the browsing duration after the advertisement is placed on the position of the platform, and can be represented by the average number of index data collected every day after the advertisement is placed for a period of time.
Specifically, after determining a promotion content tag corresponding to the advertisement formulation demand information according to the promotion content information, querying whether a sample promotion tag identical to the promotion content tag exists in a preset platform recommendation database, namely comparing the promotion content tag with the sample promotion tag in the preset platform recommendation database; it can be understood that each sample release triplet may be stored in the preset platform recommendation database in a decision tree manner, that is, each sample promotion tag is used as one of the tree nodes, and after comparing the promotion content tag with all sample promotion tags, all sample release triplets under the tree nodes of the sample promotion tag identical to the promotion content tag are extracted.
And extracting the sample putting label and the putting index data from all the obtained sample putting triples.
Specifically, after a sample release triplet corresponding to a sample promotion tag identical to the promotion content tag is obtained from a preset platform recommendation database, the sample release tag and release index data in the obtained sample release triplet can be extracted.
And determining advertisement putting labels from all the sample putting labels according to the target index data and all the extracted putting index data.
Specifically, after the sample delivery labels and the delivery index data are extracted from all the obtained sample delivery triples, sample delivery labels corresponding to the delivery index data larger than or equal to the target index data can be selected and determined as delivery labels to be compared, and if the number of the delivery labels to be compared is one and only one, the delivery labels to be compared are recorded as advertisement delivery labels; and if the number of the release labels to be compared is more than one, recording the release labels to be compared with the maximum release index data as advertisement release labels. Therefore, the delivery platform and the delivery positions are screened through the index data, so that the accuracy of making the delivery platform and the delivery positions in the advertisement plan is higher, and the effectiveness and the income of making the advertisement plan are improved.
In one embodiment, before determining the advertisement promotional material corresponding to the promotional content tag, the method further comprises:
acquiring a historical creative material group; the historical creative material group comprises historical video materials and historical picture materials.
It is to be understood that the historical video assets are video-type creative assets, the historical picture assets are picture-type creative assets, and the historical video assets and the historical picture assets can be extracted from the historical advertising campaign.
And extracting theme characteristics of the historical picture materials to obtain historical picture themes corresponding to the historical picture materials, and generating picture material labels according to the historical picture themes.
As can be understood, the theme feature extraction is to extract features in the historical picture material, and when the advertisement is delivered in the form of a picture, the picture often contains some text or graphic features, so that the picture theme of the historical picture material can be identified by extracting the text or graphic features in the historical picture material.
Specifically, for example, an LDA (text Dirichlet Allocation) Model may be used to perform image-text recognition on the historical picture material, and a feature recognition Model such as a convolutional neural network is used to perform graphic feature recognition on the historical picture material, so as to obtain a text feature sentence and a graphic feature category of the historical picture material, and then a Gaussian Mixture Model (GMM) may be used as a preset text subject Model to perform subject extraction on the text feature sentence, so as to determine a text subject of the historical picture material, and further, according to the text subject and the graphic feature category, a historical picture subject corresponding to the historical picture material may be determined, so as to generate a picture material tag according to the historical picture subject.
And identifying key materials of the historical video materials to obtain historical key materials corresponding to the historical video materials, and generating video material labels according to the historical key materials.
As can be appreciated, the key material identification refers to identifying a specific image frame in the historical video material, for example, identifying an image frame with a person in the historical video material, or having other objects (e.g., an animal, a sporting event, etc.), so as to determine the content included in the historical key material in the historical video material, and thus determine a video material label corresponding to the historical key material, where the video material label represents the key content included in the historical video material, for example, the video material label may indicate the industry to which the historical video material is applied, or the scene to which the historical video material is applied (e.g., a christmas event, a yearly celebration event, etc.).
Specifically, after the historical video material in the historical creative material group is obtained, the key material identification may be performed on the historical video material, for example, a frame difference method is used to screen a plurality of image frames in the historical video material, that is, by comparing the difference degree between two adjacent image frames, if the difference degree between two image frames is greater, it is represented that the image content between the subsequent image frame and the previous image frame has a greater difference, so that the subsequent image frame may be subjected to image identification, which may be, for example, face identification, basic pattern identification, or character identification, so as to obtain the image content included in the subsequent image frame, and thus the image content in the subsequent image frame is determined as the historical key material. After all image frames in the historical video material are identified, video material labels corresponding to the historical video material are determined according to all historical key materials obtained from the historical video material.
And generating a video material group by using the historical video material and the video material label corresponding to the historical video material, and generating a picture material group by using the historical picture material and the picture material label corresponding to the historical picture material.
And storing all the video material groups and all the picture material groups into the preset creative material database.
Specifically, after video material tags corresponding to historical video materials and picture material tags corresponding to the historical picture materials are determined, the historical video materials and the video material tags corresponding to the historical video materials can be generated into video material groups, the historical picture materials and the picture material tags corresponding to the historical picture materials can be generated into picture material groups, and then all the video material groups and all the picture material groups are stored in the preset creative material database.
In an embodiment, in step S40, that is, the performing the index prediction on the advertisement plan to be selected according to the real-time information to obtain the prediction index data corresponding to the advertisement to be selected includes:
and carrying out entity identification and intention characteristic extraction on the real-time information to obtain an entity identification result and an intention extraction result corresponding to the real-time information.
It can be understood that the entity identification is a process of extracting the entity in the real-time information, so as to determine the industry to which the real-time information belongs according to the entity identification result. The intention feature extraction is a process of extracting action intentions in the real-time information, so as to perform emotion analysis according to intention extraction results and entity recognition results.
Specifically, after the real-time information is obtained, word segmentation processing is carried out on the real-time information to obtain a plurality of information words in the real-time information, and further entity recognition can be carried out on each information word through a neural network model obtained in advance based on supervised or semi-supervised or unsupervised form training to obtain an entity recognition result; and determining information words belonging to the entity of the execution department (such as a sports bureau, an education department and the like) according to the entity recognition result, so that intention recognition is carried out on the real-time information according to the information words belonging to the entity of the execution department, namely, the action entity corresponding to the entity of the execution department in the real-time information is recognized, and the information words corresponding to the action entity are taken as intention extraction results. For example, if a real-time information is "xx department considers that the electronic contest industry is well developed", the execution department entity is "xx department", and the corresponding action entity is "keep".
And determining information industry labels according to the entity identification result, and acquiring advertisement industry labels corresponding to the advertisements to be selected.
It is understood that the entity recognition result indicates the entity meaning of the information word having the entity meaning in the real-time information, such as the industry entity, the execution department entity, the action entity, etc. Therefore, after the real-time information is subjected to entity identification, the industry entity in the real-time information can be determined, and the information industry label is determined according to the industry entity. The advertisement industry label represents the industry corresponding to the advertisement plan to be selected.
Determining whether the information industry label is the same as the advertising industry label.
And when the information industry label is the same as the advertisement industry label, determining prediction index data corresponding to the advertisement plan to be selected according to the intention extraction result and the historical index data.
Specifically, after the information industry label is determined according to the entity identification result and the advertisement industry label corresponding to each advertisement to be selected is obtained, the information industry label is compared with the advertisement industry label to determine whether the information industry label is the same as the advertisement industry label, if the information industry label is the same as the advertisement industry label, index prediction is performed on historical index data according to the intention extraction result, and therefore prediction index data corresponding to the advertisement plan to be selected is determined.
Furthermore, the emotion corresponding to the real-time information can be determined according to the information words and phrases respectively corresponding to the entity recognition result and the intention extraction result, and in this embodiment, the emotion of the real-time information is divided into: positive emotion (for example, words such as propagation, promotion and expansion are obtained as the result of the intention feature extraction), negative emotion (for example, words such as attack and weakening are obtained as the result of the intention feature extraction), and normal emotion (for example, words such as retention and stability are obtained as the result of the intention feature extraction); if the emotion of the real-time information is positive, the revenue representing the delivery of the advertisement plan to be selected may be promoted in a future period of time, and further the historical index data corresponding to the advertisement plan to be selected may be promoted, for example, the click rate, the download rate or the browsing consumption value in the historical index data is promoted, that is, the real-time information brings forward revenue for the advertisement plan to be selected; if the emotion of the real-time information is a negative emotion, the revenue representing the delivery of the to-be-selected advertisement plan may be reduced in a future period of time, and further reduction processing may be performed on historical index data corresponding to the to-be-selected advertisement plan, for example, the click rate, the download rate, or the browsing consumption value in the historical index data is reduced, that is, the real-time information brings negative revenue to the to-be-selected advertisement plan. The emotion of the real-time information is assumed to be normal emotion, that is, the real-time information has no great influence on the benefit of the delivery of the to-be-selected advertisement plan, and then the historical index data corresponding to the to-be-selected advertisement plan can be directly recorded as the prediction index data.
In an embodiment, the step S50, namely, the generating the target advertisement plan according to the advertisement formulation requirement information and the advertisement plan to be replaced includes:
acquiring advertisement plan information of the advertisement plan to be replaced; the advertisement plan information comprises at least one configuration item to be replaced.
It can be understood that before the advertisement plan information of the advertisement plan to be replaced is obtained, the formulated demand industry label of the advertisement formulated demand information can be obtained, the formulated demand industry label is compared with the advertisement industry label of the advertisement plan to be replaced, the advertisement plan to be replaced corresponding to the advertisement industry label which is the same as the formulated demand industry label is screened out and recorded as the screening advertisement plan, and therefore the advertisement plan information of the screening advertisement plan is obtained. The advertisement plan information includes at least one to-be-replaced configuration item, and as indicated in the above description, the to-be-replaced configuration item may be, for example, advertisement title information, advertisement targeting information (advertisement crowd information and advertisement area information), advertisement promotion material, and advertisement promotion plan.
And carrying out data analysis on the advertisement formulation demand information to obtain at least one advertisement plan configuration item in the advertisement formulation demand information.
It can be understood that, in the above description, after the data analysis is performed on the advertisement formulation demand information, the promotion crowd information, the promotion area information, and the promotion content information in the advertisement formulation demand information can be obtained, so that the promotion crowd information, the promotion area information, and the promotion content information are the advertisement plan configuration items in the advertisement formulation demand information, and in addition, the advertisement plan configuration items may also include promotion title information, and the like.
And carrying out configuration adjustment on at least one configuration item to be replaced according to all the advertisement plan configuration items, and recording the adjusted advertisement plan to be replaced as the target advertisement plan.
Specifically, after the to-be-replaced configuration item in the advertisement plan information of the to-be-replaced advertisement plan and the advertisement plan configuration item in the advertisement formulation requirement information are obtained, configuration adjustment can be performed on one or more to-be-replaced configuration items according to the advertisement plan configuration items, that is, one of the to-be-replaced configuration items can be changed according to the advertisement plan configuration items, for example, advertisement crowd information in the advertisement plan configuration item is replaced by promotion crowd information in the to-be-replaced configuration item, and the adjusted to-be-replaced advertisement plan is recorded as a target advertisement plan; all the configuration items to be replaced can be replaced by the advertisement plan configuration items, so that the target advertisement plans can be generated in batch by flexibly replacing the configuration items, and the generation efficiency of the advertisement plans is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not limit the implementation process of the embodiments of the present invention in any way.
In one embodiment, an advertisement plan generating apparatus is provided, which corresponds to the advertisement plan generating method in the above embodiments one to one. As shown in fig. 3, the advertisement plan generating apparatus includes an advertisement information acquiring module 10, an advertisement plan acquiring module 20, an advertisement plan detecting module 30, an index predicting module 40, and a first advertisement plan generating module 50. The functional modules are explained in detail as follows:
an advertisement information obtaining module 10, configured to obtain advertisement formulation requirement information; the advertisement formulation demand information is associated with target index data;
an advertisement plan acquisition module 20, configured to acquire a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; associating a historical indicator data with a historical advertising program;
an advertisement plan detection module 30, configured to detect whether there is an advertisement plan to be selected in the historical advertisement plan data set; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data;
the index prediction module 40 is configured to obtain real-time information when an advertisement plan to be selected exists in the historical advertisement plan data set, and perform index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected;
and the first advertisement plan generating module 50 is configured to record the advertisement plan to be selected corresponding to the prediction index data greater than or equal to the target index data as an advertisement plan to be replaced, and generate a target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
Preferably, the advertisement plan generating apparatus further includes:
the data analysis module is used for carrying out data analysis on the advertisement formulation demand information when no advertisement plan to be selected exists in the historical advertisement plan data set so as to obtain promotion crowd information, promotion area information and promotion content information in the advertisement formulation demand information;
the tag generation module is used for generating advertisement targeting information according to the popularization crowd information and the popularization area information and determining a popularization content tag corresponding to the advertisement formulation demand information according to the popularization content information;
the data matching module is used for determining an advertisement putting label corresponding to the promotion content label from a preset platform recommendation database and determining an advertisement promotion material corresponding to the promotion content label from a preset creative material database;
and the second advertisement plan generating module is used for generating a target advertisement plan according to the advertisement targeting information, the advertisement putting label and the advertisement promotion material.
Preferably, the data matching module comprises:
the data acquisition unit is used for acquiring a sample release triple corresponding to a sample promotion label which is the same as the promotion content label from a preset platform recommendation database; the sample putting triplet consists of a sample promotion label, a sample putting label and putting index data;
the data extraction unit is used for extracting the sample putting labels and putting index data from all the obtained sample putting triples;
and the label generating unit is used for determining advertisement putting labels from all the sample putting labels according to the target index data and all the extracted putting index data.
Preferably, the advertisement plan generating apparatus further includes:
the creative material acquisition module is used for acquiring a historical creative material group; the historical creative material group comprises historical video materials and historical picture materials;
the theme feature extraction module is used for extracting theme features of the historical picture materials to obtain historical picture themes corresponding to the historical picture materials and generating picture material labels according to the historical picture themes;
the key material identification module is used for identifying key materials of the historical video materials to obtain historical key materials corresponding to the historical video materials and generating video material labels according to the historical key materials;
the material integration module is used for generating a video material group from the historical video material and the video material label corresponding to the historical video material, and generating a picture material group from the historical picture material and the picture material label corresponding to the historical picture material;
and the material storage module is used for storing all the video material groups and all the picture material groups into the preset creative material database.
Preferably, the index prediction module 40 includes:
the entity intention identification unit is used for carrying out entity identification and intention characteristic extraction on the real-time information to obtain an entity identification result and an intention extraction result corresponding to the real-time information;
the label determining unit is used for determining information industry labels according to the entity identification result and acquiring advertisement industry labels corresponding to the advertisement plans to be selected;
a tag comparison unit for determining whether the information industry tag is the same as the advertisement industry tag;
and the index prediction unit is used for determining prediction index data corresponding to the advertisement plan to be selected according to the intention extraction result and the historical index data when the information industry label is the same as the advertisement industry label.
Preferably, the first advertisement plan generating module 50 includes:
the information acquisition unit is used for acquiring the advertisement plan information of the advertisement plan to be replaced; the advertisement plan information comprises at least one configuration item to be replaced;
the data analysis unit is used for carrying out data analysis on the advertisement formulation demand information to obtain at least one advertisement plan configuration item in the advertisement formulation demand information;
and the configuration adjusting unit is used for performing configuration adjustment on at least one to-be-replaced configuration item according to all the advertisement plan configuration items and recording the adjusted to-be-replaced advertisement plan as the target advertisement plan.
For the specific definition of the advertisement plan generating device, reference may be made to the above definition of the advertisement plan generating method, which is not described herein again. The modules in the advertisement plan generating device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the advertisement plan generating method in the above-described embodiment. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an advertisement plan generation method.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the advertisement plan generating method in the above embodiments is implemented.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the advertisement plan generation method in the above-described embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An advertisement plan generating method, comprising:
acquiring advertisement formulation demand information; the advertisement formulation demand information is associated with target index data;
acquiring a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; associating a historical indicator data with a historical advertising program;
detecting whether the historical advertisement plan data set has an advertisement plan to be selected or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data;
when the historical advertisement plan data set has an advertisement plan to be selected, acquiring real-time information, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected;
and recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as an advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
2. The method of generating an advertisement plan according to claim 1, wherein after detecting whether there is an advertisement plan to be selected in the historical advertisement plan database, the method further comprises:
when no advertisement plan to be selected exists in the historical advertisement plan data set, performing data analysis on the advertisement formulation demand information to obtain promotion crowd information, promotion area information and promotion content information in the advertisement formulation demand information;
generating advertisement targeting information according to the promotion crowd information and the promotion area information, and determining a promotion content label corresponding to the advertisement formulation demand information according to the promotion content information;
determining an advertisement putting label corresponding to the promotion content label from a preset platform recommendation database, and determining an advertisement promotion material corresponding to the promotion content label from a preset creative material database;
and generating a target advertisement plan according to the advertisement targeting information, the advertisement putting label and the advertisement promotion material.
3. The method of generating an advertisement plan according to claim 2, wherein determining the advertisement placement label corresponding to the promotion content label in the self-provisioning platform recommendation database includes:
obtaining a sample putting triple corresponding to a sample promotion label which is the same as the promotion content label from a preset platform recommendation database; the sample putting triplet consists of a sample promotion label, a sample putting label and putting index data;
extracting the sample putting labels and the putting index data from all the obtained sample putting triples;
and determining advertisement putting labels from all the sample putting labels according to the target index data and all the extracted putting index data.
4. The advertisement plan generating method of claim 2, wherein prior to determining the advertisement promotional material corresponding to the promotional content tag, comprising:
acquiring a historical creative material group; the historical creative material group comprises historical video materials and historical picture materials;
extracting theme characteristics of the historical picture materials to obtain historical picture themes corresponding to the historical picture materials, and generating picture material labels according to the historical picture themes;
performing key material identification on the historical video material to obtain historical key material corresponding to the historical video material, and generating a video material label according to the historical key material;
generating a video material group by using the historical video material and the video material label corresponding to the historical video material, and generating a picture material group by using the historical picture material and the picture material label corresponding to the historical picture material;
and storing all the video material groups and all the picture material groups into the preset creative material database.
5. The method of claim 1, wherein the performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected comprises:
carrying out entity identification and intention feature extraction on the real-time information to obtain an entity identification result and an intention extraction result corresponding to the real-time information;
determining information industry labels according to the entity identification result, and acquiring advertisement industry labels corresponding to the advertisement plans to be selected;
determining whether the information industry label is the same as the advertisement industry label;
and when the information industry label is the same as the advertisement industry label, determining prediction index data corresponding to the advertisement plan to be selected according to the intention extraction result and the historical index data.
6. The method of generating an advertising plan according to claim 1, wherein the generating a target advertising plan based on the advertisement formulation requirement information and the advertisement plan to be replaced comprises:
acquiring advertisement plan information of the advertisement plan to be replaced; the advertisement plan information comprises at least one configuration item to be replaced;
performing data analysis on the advertisement formulation demand information to obtain at least one advertisement plan configuration item in the advertisement formulation demand information;
and carrying out configuration adjustment on at least one configuration item to be replaced according to all the advertisement plan configuration items, and recording the adjusted advertisement plan to be replaced as the target advertisement plan.
7. An advertisement plan generating apparatus, comprising:
the advertisement information acquisition module is used for acquiring advertisement formulation demand information; the advertisement formulation demand information is associated with target index data;
the advertisement plan acquisition module is used for acquiring a historical advertisement plan data set; the historical advertising campaign dataset comprises at least one historical advertising campaign; associating a historical target data with one of said historical advertising programs;
the advertisement plan detection module is used for detecting whether an advertisement plan to be selected exists in the historical advertisement plan data set or not; the advertisement plan to be selected refers to a historical advertisement plan corresponding to historical index data which is greater than or equal to the target index data;
the index prediction module is used for acquiring real-time information when an advertisement plan to be selected exists in the historical advertisement plan data set, and performing index prediction on the advertisement plan to be selected according to the real-time information to obtain prediction index data corresponding to the advertisement to be selected;
and the first advertisement plan generating module is used for recording the advertisement plan to be selected corresponding to the prediction index data which is greater than or equal to the target index data as the advertisement plan to be replaced, and generating the target advertisement plan according to the advertisement formulation demand information and the advertisement plan to be replaced.
8. The advertising plan generating apparatus of claim 7, wherein the advertising plan generating apparatus further comprises:
the data analysis module is used for carrying out data analysis on the advertisement formulation demand information when no advertisement plan to be selected exists in the historical advertisement plan data set so as to obtain promotion crowd information, promotion area information and promotion content information in the advertisement formulation demand information;
the tag generation module is used for generating advertisement targeting information according to the popularization crowd information and the popularization area information and determining a popularization content tag corresponding to the advertisement formulation demand information according to the popularization content information;
the data matching module is used for determining an advertisement putting label corresponding to the promotion content label from a preset platform recommendation database and determining an advertisement promotion material corresponding to the promotion content label from a preset creative material database;
and the second advertisement plan generating module is used for generating a target advertisement plan according to the advertisement targeting information, the advertisement putting label and the advertisement promotion material.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the advertisement plan generating method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the advertisement plan generating method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675668.2A CN114463040A (en) | 2021-12-31 | 2021-12-31 | Advertisement plan generating method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675668.2A CN114463040A (en) | 2021-12-31 | 2021-12-31 | Advertisement plan generating method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114463040A true CN114463040A (en) | 2022-05-10 |
Family
ID=81408311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111675668.2A Pending CN114463040A (en) | 2021-12-31 | 2021-12-31 | Advertisement plan generating method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114463040A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114757720A (en) * | 2022-05-23 | 2022-07-15 | 一点灵犀信息技术(广州)有限公司 | Advertisement plan distribution method and device, electronic equipment and storage medium |
| CN116955613A (en) * | 2023-06-12 | 2023-10-27 | 广州数说故事信息科技有限公司 | Method for generating product concept based on research report data and large language model |
-
2021
- 2021-12-31 CN CN202111675668.2A patent/CN114463040A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114757720A (en) * | 2022-05-23 | 2022-07-15 | 一点灵犀信息技术(广州)有限公司 | Advertisement plan distribution method and device, electronic equipment and storage medium |
| CN116955613A (en) * | 2023-06-12 | 2023-10-27 | 广州数说故事信息科技有限公司 | Method for generating product concept based on research report data and large language model |
| CN116955613B (en) * | 2023-06-12 | 2024-02-27 | 广州数说故事信息科技有限公司 | Method for generating product concept based on research report data and large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107864301B (en) | Client label management method, system, computer equipment and storage medium | |
| CN114463040A (en) | Advertisement plan generating method, device, computer equipment and storage medium | |
| CN109829629A (en) | Generation method, device, computer equipment and the storage medium of risk analysis reports | |
| CN108804133B (en) | Method, system, computer device and storage medium for acquiring virtual resources | |
| CN113204660B (en) | Multimedia data processing method, tag identification device and electronic equipment | |
| CN109949089B (en) | Method, device and terminal for determining display rate | |
| CN111881901A (en) | Screenshot content detection method and device and computer-readable storage medium | |
| CA3143808A1 (en) | Event promoting method, device, computer apparatus, and storage medium | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN113420018A (en) | User behavior data analysis method, device, equipment and storage medium | |
| CN113918738B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN114371946B (en) | Information push method and information push server based on cloud computing and big data | |
| CN111581600A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN114756669A (en) | Intelligent analysis method and device for problem intention, electronic equipment and storage medium | |
| CN114223012A (en) | Push object determination method and device, terminal equipment and storage medium | |
| CN112396079A (en) | Number recognition model training method, number recognition method and device | |
| US20210042582A1 (en) | System and method for monitoring health of crop to validate crop insurance claim | |
| CN114463673B (en) | Material recommendation method, device, equipment and storage medium | |
| CN115809889A (en) | Intelligent passenger group screening method, system, medium and equipment based on marketing effect | |
| CN110598090A (en) | Interest tag generation method and device, computer equipment and storage medium | |
| CN111127057A (en) | Multi-dimensional user portrait restoration method | |
| CN111178934B (en) | Method and device for acquiring target object | |
| CN113901265A (en) | Video tag extraction method and device, computer equipment and storage medium | |
| CN111914199B (en) | Page element filtering method, device, equipment and storage medium | |
| CN114463044A (en) | Advertisement plan adjusting method, device, computer equipment and 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 |