CN114881685A - Advertisement delivery method, device, electronic device and storage medium - Google Patents
Advertisement delivery method, device, electronic device and storage medium Download PDFInfo
- Publication number
- CN114881685A CN114881685A CN202210420416.3A CN202210420416A CN114881685A CN 114881685 A CN114881685 A CN 114881685A CN 202210420416 A CN202210420416 A CN 202210420416A CN 114881685 A CN114881685 A CN 114881685A
- Authority
- CN
- China
- Prior art keywords
- entity
- user
- advertisement
- target
- coefficient
- 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
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Animal Behavior & Ethology (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application relates to an advertisement delivery method, an advertisement delivery device, an electronic device and a storage medium, wherein the method comprises the following steps: receiving an advertisement to be delivered, and determining advertisement element information corresponding to the advertisement, wherein the advertisement element information comprises a plurality of element entities; acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data; determining a target user according to the relevance of the multiple element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing the name of the user; and determining a delivery strategy according to the user behavior information of the target user, and delivering the advertisement to the target user based on the delivery strategy. Through the method and the device, the problems that the advertising effect is poor and the advertising cost is high when the advertising mode is put in a large-range fixed-time mode in the correlation technique are solved, the advertising cost of an advertiser can be reduced through accurate putting, and the advertising effect is improved are achieved.
Description
Technical Field
The present application relates to the field of internet advertisement technologies, and in particular, to an advertisement delivery method, an advertisement delivery device, an electronic device, and a storage medium.
Background
With the rapid development of the internet and the mobile internet, the network has become an essential part of people's life, and various information is acquired through the internet. The Internet is used as an important information medium, and massive advertisement information can be uploaded every day; various types of advertisements are delivered through various internet advertisement platforms, such as pop-up windows and floating windows in web pages, and front advertisements at the beginning of videos and spot advertisements in the middle of videos.
In the related art, internet advertisements are usually delivered in a large-scale and fixed-time manner, for example, within one week, before the video of a video website begins, a specific advertisement is delivered. The method for releasing the advertisements in a large-range and fixed-time mode cannot meet the requirements of performing targeting and releasing the advertisements of specific target personnel in a specific small range, reduces the releasing effect of the advertisements, and has high releasing cost.
Aiming at the problems of poor advertising effect and high advertising cost in the prior art that advertising is delivered in a large-range and fixed-time delivery mode, an effective solution is not available.
Disclosure of Invention
The application provides an advertisement delivery method, an advertisement delivery device, an electronic device and a storage medium, which are used for at least solving the problems of poor delivery effect and high delivery cost of delivering advertisements in a large-range fixed-time delivery mode in the related art.
In a first aspect, the present application provides an advertisement delivery method, including: receiving an advertisement to be delivered, and determining advertisement element information corresponding to the advertisement, wherein the advertisement element information comprises a plurality of element entities; acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data; determining a target user according to the relevance of the element entities and all entities related to the target entity in the graph data, wherein the target entity is a named entity for representing a user name; and determining a delivery strategy according to the user behavior information of the target user, and delivering the advertisement to the target user based on the delivery strategy.
In a second aspect, the present application provides an intent recognition apparatus comprising:
the advertisement delivery system comprises a receiving module, a delivering module and a delivering module, wherein the receiving module is used for receiving an advertisement to be delivered and determining advertisement element information corresponding to the advertisement, and the advertisement element information comprises a plurality of element entities;
the acquisition module is used for acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data;
the determining module is used for determining a target user according to the relevance of the element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing a user name;
and the processing module is used for determining a delivery strategy according to the user behavior information of the target user and delivering the advertisement to the target user based on the delivery strategy.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor, configured to implement the steps of the advertisement delivery method according to any one of the embodiments of the first aspect when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the advertising method as set forth in any one of the embodiments of the first aspect.
The method and the device can be applied to the field of internet advertisements to carry out directional identification of the delivered object and accurate delivery of the advertisements. According to the advertisement delivery method, the device, the electronic device and the storage medium, advertisement element information corresponding to an advertisement is determined by receiving the advertisement to be delivered, wherein the advertisement element information comprises a plurality of element entities; acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data; determining a target user according to the relevance of the multiple element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing the name of the user; the method and the device for releasing the advertisement determine a releasing strategy according to the user behavior information of the target user, and release the advertisement to the target user based on the releasing strategy, so that the problems of poor releasing effect and high releasing cost of releasing the advertisement in a large-range fixed-time releasing mode in the related technology are solved, the advertisement cost of an advertiser can be reduced through accurate releasing, and the beneficial effect of improving the advertisement releasing effect is achieved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of an advertisement delivery method according to an embodiment of the present application;
fig. 2 is a schematic diagram of NLP entity extraction according to the preferred embodiment of the present application;
FIG. 3 is a first illustration of profile data for a preferred embodiment of the present application;
FIG. 4 is a second illustration of profile data for a preferred embodiment of the present application;
fig. 5 is a schematic structural diagram of an advertisement delivery device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. 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 application.
Before describing the embodiments of the present application, the following description will be made of the related art means used in the advertisement delivery method of the embodiments of the present application and the problems in the related art.
Natural Language Processing (NLP) is a technology for performing various types of Processing and Processing on Natural Language information in written form and spoken form specific to humans using a computer as a tool. NLP is applied to machine translation, automatic question answering, speech processing, information retrieval, information extraction, and the like.
The knowledge extraction is to extract the knowledge contained in the information source through the processes of identification, understanding, screening, induction and the like, and store the extracted knowledge to form a knowledge meta base; the method comprises the steps of extracting knowledge from data of different sources and different structures to form knowledge, storing the knowledge into a knowledge graph, wherein the knowledge graph comprises entities and weights, the weights are relationship coefficients between the entities, and the knowledge graph can be obtained through calculation of different keyword algorithms (such as TF-IDF and Text-Rank) in NLP technology.
The knowledge graph is a semantic network, describes objective things in the form of a graph, and the graph is composed of nodes and edges. Nodes in the knowledge graph represent concepts and entities, the concepts are abstracted things, the entities are concrete things, the edges represent the relationship and the attribute of the things, the internal features of the things are represented by the attribute, and the external contact is represented by the relationship; the knowledge graph is stored by the triple of 'entity relation entity' or 'entity attribute value' to form a graph-shaped knowledge base.
Various techniques described herein may be used for named entity recognition, keyword extraction, information extraction, etc. of text.
Fig. 1 is a schematic flowchart of an advertisement delivery method according to an embodiment of the present application. As shown in fig. 1, an embodiment of the present application provides an advertisement delivery method, which includes the following steps:
step S101, receiving an advertisement to be delivered, and determining advertisement element information corresponding to the advertisement, wherein the advertisement element information comprises a plurality of element entities.
In this embodiment, a main body executing the advertisement delivery method of the present application is an advertisement delivery platform, and may also be an advertisement delivery terminal; in this embodiment, after an advertisement provider (advertiser) provides an advertisement to a corresponding delivery end (delivery platform, terminal), the delivery end performs data processing on advertisement content to obtain advertisement element information including a plurality of element entities; in the present embodiment, the advertisement includes at least an advertisement attribute and an advertisement element, wherein the advertisement attribute includes a type, an applicable group (age), and the like; the advertising elements include speakers, brands, product categories, and the like.
In some optional embodiments, the means for obtaining the advertisement element information may employ manual extraction, that is, when providing the advertisement, providing the corresponding advertisement element describing the advertisement, for example: keywords of the advertisement; the NLP technology can be adopted to obtain advertisement element information and element entities; for example: the advertisement is as follows: star a stands for product XX, and the available element entities are star a and product XX.
Step S102, acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data.
In this embodiment, the user portrait data is obtained by integrating the user according to the static information data and the dynamic information data of the user, wherein the static information data of the user includes data of demographic attributes, business attributes and the like, such as age, gender, income, occupation and region, and the static information data can be a user tag; the dynamic information data of the user is behavior information of the user which changes constantly, and when the user behavior is presented on the internet, the behavior is represented as browsing a webpage or a product single page, searching a product, issuing a microblog message and the like related to the product; in this embodiment, after the static information data and the dynamic information data of the user are collected, a data model of the user portrait is constructed by performing data modeling, and the following formula may be adopted: user identification + time + behavior type + contact point (website address + content) constructs user portrait data, namely describes when, where and what a user does, and therefore an MM label is marked.
In this embodiment, NLP is used to perform entity extraction on dynamic information data in user portrait data, fig. 2 is a schematic diagram of NLP entity extraction according to a preferred embodiment of the present application, referring to fig. 2, in some optional embodiments, entity extraction, that is, named entity identification, is performed by collecting historical search records, historical browsing records, current search content, and the like of a user, and includes entity detection and classification, for example: and identifying a person name and a place name.
In some optional embodiment modes of the embodiment, entity extraction can also be performed by collecting search records (such as "star B tv drama") of users, browsed video information (such as "character a turns around to character B, and the reaction of character C is too real"), advertisement information (such as "star C stands for makeup brand a"), live broadcast information ("character C makeup brand B live broadcast meal video", "makeup brand C-star D burst makeup room"), and taking the above data as analysis objects, and performing the following steps: performing word segmentation on text corpora needing to be extracted; obtaining a field label to be identified, and labeling the segmentation result; extracting the labeled participles of the labels; the extracted participles are combined into a named entity of a required field; thus, the entities that can be extracted are: character a, character B, character C, make-up brand a, brand, make-up booth.
In this embodiment, the extraction of the entity is completed by using an NLP technology, the retrieved content is accurately analyzed by using the NLP, and the knowledge graph is constructed based on the entity, relationship, attribute and other knowledge elements extracted from the relevant data (including structured data and semi-structured data) acquired from the corresponding public platform, so that the preference direction of the user can be more accurately obtained, when the advertisement to be delivered matches the preference of the corresponding user, at this time, the advertisement is delivered to the user, and the accurate delivery of the advertisement can be realized and the effective delivery of the advertisement can be improved.
In this embodiment, to improve the delivery efficiency of the precise advertisement delivery, the map data (refer to the map data shown in fig. 3 and 4) obtained from the preset map database is map data preliminarily screened from a plurality of map data in the map database according to a plurality of element entities, that is, the selected map data is map data having a certain correlation with the advertisement to be delivered, for example: the advertisement to be launched is a dialect about a certain star, the corresponding map data is that a certain user searches the star in the historical network using process, and the search records of the corresponding user contain video products, advertisement information, live broadcast information and microblog information related to the star; through the primarily screened map data, the data can be more matched when the relation between a plurality of element entities and the user is calculated, and the determined target user is more accurate.
Step S103, determining a target user according to the relevance of the multiple element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing the name of the user.
In this embodiment, after obtaining the graph data, by calculating the relationship between the element entity and the user corresponding to the graph data, and according to the degree of correlation between the element entity and the corresponding user, it is determined whether the preference of the user matches with the advertisement to be delivered, for example: and matching the element entities with the corresponding map general data to screen out a user with high matching degree, wherein the user has stronger willingness or preference for receiving the delivered advertisements, and the delivered advertisements have high possibility of being responded by the user, so that the advertisement delivery efficiency is improved.
In this embodiment, each element entity is used to calculate the relationship with the user, so as to determine whether the correlation between the advertisement to be delivered and the user is high, and the calculation of the relationship between the element entities and the user is to calculate the product of the relationship coefficient between each element entity and the entity associated with the user; it should be noted that, when calculating the correlation between the element entity and the entity associated with the user, the product of the relationship coefficients between the element entity and the named entity in the entity corresponding to the user needs to be calculated, and the product is multiplied by the relationship coefficient between the named entity representing the user name and the corresponding entity, so as to obtain the relationship coefficient between the element entity and the corresponding entity, and if the corresponding entity is also associated with the entity of the next level, the relationship coefficient between the element entity and the entity of the next level needs to be calculated, so that the requirement for calculating the relationship between each element entity and the user is satisfied; for example: when the representation user name is entity A, the entity A associates the entity B to the entity M, and at least one of the entity B to the entity M is associated with the corresponding next-level entity a, namely the corresponding entity a is associated with the entity A through one of the entity B to the entity M; for example: in the process of calculating the relationship between each element entity and the user, when calculating the relationship coefficient between the element entity and the entity a, the relationship coefficient between the entity a and the element entity, the relationship coefficient between the entity a and the corresponding one of the associated entities B to M, and the relationship coefficient between the corresponding one of the entity B to M and the entity a need to be calculated, and the product of all the relationship coefficients corresponds to the relationship coefficient between the element entity and the entity a.
In this embodiment, when the matching degree of the target user corresponding to the map data calculated based on the element entity is high, the confirmation of the corresponding delivery target is completed.
And step S104, determining a delivery strategy according to the user behavior information of the target user, and delivering the advertisement to the target user based on the delivery strategy.
In this embodiment, after the corresponding user target is determined, a delivery policy is further generated based on an operation corresponding to the user, where the corresponding delivery policy includes determining a delivery object and/or a delivery time of the advertisement for a device/platform and a user time used for delivering historical habits of the corresponding user, so as to more accurately implement delivery of the advertisement.
Through the steps from S101 to S104, advertisement element information corresponding to the advertisement is determined by receiving the advertisement to be delivered, wherein the advertisement element information comprises a plurality of element entities; acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data; determining a target user according to the relevance of the multiple element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing the name of the user; the method and the device for releasing the advertisement determine a releasing strategy according to the user behavior information of the target user, and release the advertisement to the target user based on the releasing strategy, so that the problems of poor releasing effect and high releasing cost of releasing the advertisement in a large-range fixed-time releasing mode in the related technology are solved, the advertisement cost of an advertiser can be reduced through accurate releasing, and the beneficial effect of improving the advertisement releasing effect is achieved.
In some embodiments, the determining the target user according to the correlation degree of the plurality of element entities and all entities associated with the target entity in the map data in step S103 may be implemented by:
and step 21, extracting target entities corresponding to the map data and all entities related to the target entities.
In this embodiment, the map data is displayed at least according to the relationship and attribute between the entities, and the corresponding entities can be directly extracted from the map data.
And step 22, sequentially calculating the relationship coefficients of each element entity and all entities related to the target entity and the target entity, and determining the relationship coefficient sum of each element entity and all entities related to the target entity and the target entity, wherein the relationship coefficients are used for representing the correlation degree of the corresponding entity and the element entity.
In this embodiment, the NLP technique is adopted to calculate the relationship coefficients between the element entities and the target entities and the entities associated with the target entities, that is, to determine the corresponding word weights or relationship weights.
In this embodiment, when calculating the relationship coefficients between the element entities and all entities, and when the current entity is also associated with a next-level entity, it is necessary to determine a corresponding relationship coefficient based on the relationship coefficient between the current entity element entity and the relationship coefficient between the current element entity and the associated next-level entity, for example: when the target entity is entity 1, the entity 1 associates entity 2 to entity N, and one of entity 2 to entity N is associated with the next-level entity N, so that entity N is associated with entity 1 through one of entity 2 to entity N; for example: in the process of calculating the relationship coefficient between each element entity and all entities, when calculating the relationship weight between an element entity and an entity N, the relationship coefficient between the entity 1 and the element entity, the relationship coefficient between the entity 1 and the corresponding one of the associated entities 2 to N, and the relationship coefficient between the corresponding one of the entity 2 to the entity N and the entity N need to be calculated, and the product of all the relationship coefficients corresponds to the relationship coefficient between the element entity and the entity N.
In this embodiment, when calculating the relationship between the element entity and the user corresponding to the target entity, that is, determining the correlation between the element entity and the user, it is necessary to sum the relationship coefficients of all entities associated with the element entity and the target entity, and when the sum of the relationship coefficients is greater than a set threshold, it indicates that the matching degree between the user, the element entity, and the corresponding advertisement is high.
And step 23, judging whether the sum of the relation coefficients is larger than a preset threshold value.
And 24, under the condition that the sum of the relation coefficients is judged to be larger than the preset threshold value, determining the user corresponding to the target entity as the target user.
Extracting a target entity corresponding to the map data and all entities related to the target entity in the steps; sequentially calculating the relationship coefficients of each element entity and all entities related to the target entity and the target entity, and determining the relationship coefficient sum of each element entity and all entities related to the target entity and the target entity; judging whether the sum of the relation coefficients is larger than a preset threshold value or not; and under the condition that the relation coefficient sum is larger than the preset threshold value, determining the user corresponding to the target entity as the target user, and realizing the matching of the correlation degree of the element entity corresponding to the advertisement content and the map data corresponding to the target user, so that the advertisement to be delivered is the content preferred by the target user, thereby accurately delivering the advertisement and improving the effective delivery rate of the advertisement.
In some embodiments, the step 21 of sequentially calculating the relationship coefficient between each element entity and the target entity and all entities associated with the target entity may be implemented by the following steps:
step 31, determining a first entity and a second entity associated with the first entity in all entities associated with the target entity, wherein the first entity is an entity directly associated with the target entity.
In this embodiment, the first entity is an entity that generates a direct relationship with the target entity, that is, in the graph data, the target entity and the first entity are respectively located on two nodes that are directly connected, and the second entity may be an entity that generates a direct connection with the first entity, that is, the first entity and the second entity are located on two nodes that are directly connected, or may be an indirectly connected entity, that is, an intermediate entity that is associated with the two entities exists between the first entity and the second entity, of course, the second entity is located on a boundary of the graph data, and meanwhile, the first entity may not be associated with the corresponding second entity, and at this time, the first entity is located on a boundary of the graph data; in some alternative embodiments of the present application, the atlas data is hierarchically arranged in the following format: the target entity-the first entity-the second entity corresponding to the user, that is, the second entity is not set with the first entity, and the second entity is also the boundary corresponding to the map data.
Step 32, using the natural language to process the NLP, calculating a first relation coefficient between the element entity and the target entity, a second relation coefficient between the target entity and the first entity, and a third relation coefficient between the first entity and the second entity.
In this embodiment, the NLP is processed by natural language, and the calculation of the corresponding relationship coefficient should be understood as a known means, and the existing algorithm and means for determining the corresponding relationship coefficient are applicable to the present application.
And step 33, determining the relationship coefficients of the element entity and all entities related to the target entity and the target entity based on the first relationship coefficient, the second relationship coefficient and the third relationship coefficient.
In this embodiment, the first relation coefficient corresponds to a relation coefficient between the target entity and the element entity, the relation coefficient between the element entity and the first entity is determined according to the first relation coefficient and the second relation coefficient, and the relation coefficient between the element entity and the second entity is determined according to the first relation coefficient, the second relation coefficient, and the third relation coefficient; when an intermediate entity exists between the first entity and the second entity, the corresponding third relation coefficient is the product of the relation coefficient of the first entity and the intermediate entity and the relation coefficient of the intermediate entity and the second entity.
Determining a first entity and a second entity associated with the first entity in all entities associated with the target entity through the determination in the step; processing NLP by using natural language, and calculating a first relation coefficient between the element entity and the target entity, a second relation coefficient between the target entity and the first entity and a third relation coefficient between the first entity and the second entity; and determining the relationship coefficients of the element entities and all entities associated with the target entities and the target entities based on the first relationship coefficient, the second relationship coefficient and the third relationship coefficient, so that the calculation of the relationship coefficients of the element entities and the entities associated with the corresponding users is realized, and the determination of the relationship coefficients between the two entities associated through the common entities is determined by adopting the product of the relationship coefficients, thereby ensuring the effectiveness of the determination of the correlation between the entities, and ensuring that the matching degree of the matched users is high when the advertisement elements are matched with the map data.
In some embodiments, the determining, in step 33, the relationship coefficients of the element entity and all entities associated with the target entity and the target entity based on the first relationship coefficient, the second relationship coefficient and the third relationship coefficient is implemented by:
and step 41, determining the first relation coefficient as a relation coefficient corresponding to the element entity and the target entity.
Step 42, multiplying the first relation coefficient and the second relation coefficient to obtain a second coefficient, wherein the relation coefficient corresponding to the element entity and the first entity comprises the second coefficient;
and 43, multiplying the first relation coefficient, the second relation coefficient and the third relation coefficient to obtain a third coefficient, and determining that the relation coefficient corresponding to the element entity and the second entity comprises the third coefficient.
Determining the first relation coefficient as the corresponding relation coefficient of the element entity and the target entity through the first relation coefficient in the step; multiplying the first relation coefficient and the second relation coefficient to obtain a second coefficient serving as a relation coefficient corresponding to the element entity and the first entity; and multiplying the first relation coefficient, the second relation coefficient and the third relation coefficient to obtain a third coefficient serving as a corresponding relation coefficient of the element entity and the second entity, thereby realizing the assignment of the corresponding relation coefficient between the entities.
In some embodiments, the determining the sum of the relationship coefficients of each element entity and all entities associated with the target entity and the target entity in step 22 on the basis of determining the relationship coefficients between the corresponding entities and entities may be implemented by:
and step 51, acquiring a first relation coefficient, a second coefficient and a third coefficient.
And step 52, accumulating the first relation coefficient, the second coefficient and the third coefficient to obtain a relation weight sum, wherein the relation coefficient sum of all entities related to each element entity, the target entity and the target entity comprises the relation weight sum.
In this embodiment, after the sum of the relationship weights is obtained by accumulation, when the sum of the relationship weights is greater than the preset threshold, it is determined that the user correlation degree corresponding to the target entity is high, and the target entity is locked as the target user.
Through the steps 51 to 52, the determination of the correlation degree between the element entity and the user is realized, so that the subsequent locking of the target user is facilitated, and the accurate advertisement delivery is realized.
In some embodiments, the step S104 determines the delivery policy according to the user behavior information of the target user, and is implemented by the following steps:
and step 61, determining action tag information corresponding to the user according to the acquired user behavior information, wherein the action tag information comprises preference information used for representing historical operation of the user.
In this embodiment, after the target user is determined, the target user may be accurately delivered according to the network usage habit corresponding to the user, where the network usage habit corresponding to the user includes devices and platforms commonly used by the user, for example: the common media platform and the user are used to log in at the PC end or the mobile end, and are used to the network time period, for example: the habitual online or online time; after the habits corresponding to the target users are obtained through analysis, the advertisements are delivered under the condition of meeting the habits of the users, so that the effective delivery of the advertisements is improved, namely the delivered advertisements are preferred by the users, and the corresponding users can pay attention to and/or respond to the delivered advertisements.
In this embodiment, in the user behavior information, the preference of the user historical operation, that is, the network usage habit, is represented by the action tag information, and the action tag information may also be stored in a preset map database by map data corresponding to the user and retained in a form in which a plurality of named entities are combined into the map data, so that the data consistency of the database system is ensured.
In this embodiment, for the habit of the user, the corresponding parameters include two types: time type parameter, soft or hard equipment such as equipment/subassembly/platform specifically include: a media platform and a habit network using period which are commonly used by a user; by determining the type of the acquired preference information of the historical operation of the user, the receiving end after the advertisement is put and the time when the advertisement is put are further determined, and if the corresponding user puts the advertisement based on the own network using habit when receiving the advertisement, the acceptance of the user on the advertisement can be improved, and the rejection and the resistance to the advertisement putting are reduced.
And 63, determining a delivery strategy based on the classification information, wherein the delivery strategy comprises delivery equipment and/or delivery time for delivering the advertisement.
Determining action label information corresponding to the user according to the acquired user behavior information in the steps, wherein the action label information comprises preference information used for representing the historical operation of the user and is based on the preference information of the historical operation of the user, and determining classification information corresponding to the historical operation of the user; and determining a delivery strategy based on the classification information, wherein the delivery strategy comprises delivery equipment and/or delivery time for delivering the advertisement, and the corresponding delivery object and/or delivery time are determined based on the network using habit of the user, so that the acceptance of the user to the advertisement is further improved, the rejection and rejection of the delivered advertisement are reduced, the accurate delivery is met, the advertisement delivery cost is reduced, and the advertisement delivery effect is improved.
In some of these embodiments, the construction of the atlas data includes the steps of:
step 71, user portrait data corresponding to a preset user and text data corresponding to a preset scene are obtained, wherein the user portrait data are generated according to user tag information and user behavior data, and the text data comprise structured data and partial structured data.
In this embodiment, by collecting user image data and text data, corresponding data preparation is provided for subsequent knowledge extraction and knowledge fusion, so that the corresponding map data is matched with the corresponding preset scene.
And 72, respectively identifying and extracting entities and entity attributes of the user portrait data and the text data to obtain at least two entities and attribute information of each entity.
In this embodiment, the identification and extraction of the entity and the entity attribute of the text data are performed after the entity extraction of the user portrait data by the NLP, that is, after the text data corresponding to the preset scene is acquired, data related to the entity extracted by the NLP is detected in the text data, and then, the knowledge extraction of the detected related data is performed, specifically, the method includes the following processing: named entity recognition, term extraction, relationship extraction, event extraction, coreference resolution, for example: detecting an entity "Beijing" and a corresponding classification category entity "place name" from the corpus "city where Beijing is busy", for example: finding multiple related terms of single composition from corpus to accomplish term extraction, for example: the relation extraction is carried out on the corpus that the character W and the character X are good friends, and the following can be obtained: [ person W ] < friend > [ person X ], for example: extracting information such as trigger words, time, place and the like of event occurrence from a news report, for example: determining the object of pronouns "he", "she" and "it" in the corpus, and further completing coreference resolution.
In the embodiment, knowledge extraction is performed on user portrait data and text data, so that corresponding entities and relationships and attributes between the entities are obtained.
And 73, carrying out knowledge fusion processing on the relationship between any two entities and the attribute information of each entity to generate at least one entity pair relationship template, wherein the map data comprises the entity pair relationship template, and the knowledge fusion processing comprises similarity calculation, duplication removal and disambiguation of the entities.
In this embodiment, generating the entity-to-relationship template is also a process of knowledge extraction.
Acquiring user portrait data corresponding to a preset user and text data corresponding to a preset scene in the steps; respectively identifying and extracting entity attributes and entity attributes of user portrait data and text data to obtain attribute information of at least two entities and each entity; the method comprises the steps of carrying out knowledge fusion processing on the relationship between any two entities and attribute information of each entity to generate at least one entity-to-relationship template, enabling atlas data to comprise the entity-to-relationship template, enabling the knowledge fusion processing to comprise similarity calculation, duplication removal and disambiguation of the entities, adopting user image data acquisition, NLP entity extraction, knowledge extraction and knowledge fusion to achieve generation of the atlas data, accurately analyzing retrieval data contents through NLP, combining text data corresponding to a preset scene to construct the knowledge atlas data, and obtaining preference directions of users more accurately, so that advertisement delivery is accurate and matched with target users and advertisement delivery is accurate.
It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here.
The embodiment further provides an advertisement delivery device, which is used for implementing the above embodiments and preferred embodiments, and the description of the device is omitted. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 4 is a block diagram of an advertisement delivery apparatus according to an embodiment of the present application, and as shown in fig. 4, the apparatus includes:
a receiving module 51, configured to receive an advertisement to be delivered, and determine advertisement element information corresponding to the advertisement, where the advertisement element information includes multiple element entities;
an obtaining module 52, coupled to the receiving module 51, for obtaining atlas data from a preset atlas database, where the atlas data is formed by entity extraction and knowledge fusion corresponding to user portrait data;
a determining module 53, coupled to the obtaining module 52, configured to determine a target user according to the correlation degrees of the multiple element entities and all entities associated with the target entity in the graph data, where the target entity is a named entity for representing a user name;
and the processing module 54 is coupled to the determining module 53, and is configured to determine an advertisement delivery policy according to the user behavior information of the target user, and deliver the advertisement to the target user based on the advertisement delivery policy.
By the device of the embodiment of the application, the advertisement to be delivered is received, and the advertisement element information corresponding to the advertisement is determined, wherein the advertisement element information comprises a plurality of element entities; acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data; determining a target user according to the relevance of the multiple element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing the name of the user; the method and the device for releasing the advertisement determine a releasing strategy according to the user behavior information of the target user, and release the advertisement to the target user based on the releasing strategy, so that the problems of poor releasing effect and high releasing cost of releasing the advertisement in a large-range fixed-time releasing mode in the related technology are solved, the advertisement cost of an advertiser can be reduced through accurate releasing, and the beneficial effect of improving the advertisement releasing effect is achieved.
In some of these embodiments, the determining module 32 further comprises:
the first extraction unit is used for extracting a target entity corresponding to the map data and all entities related to the target entity;
the first calculation unit is coupled with the first extraction unit and used for calculating the relationship coefficients of all entities related to each element entity, the target entity and the target entity in sequence and determining the relationship coefficient sum of all entities related to each element entity, the target entity and the target entity, wherein the relationship coefficients are used for representing the correlation degree of the corresponding entities and the element entities;
the first judgment unit is coupled with the first calculation unit and used for judging whether the relation coefficient sum is larger than a preset threshold value or not;
and the first determining unit is coupled with the first judging unit and used for determining the user corresponding to the target entity as the target user under the condition that the sum of the relation coefficients is judged to be larger than the preset threshold value.
In some embodiments, the first extracting unit is further configured to determine a first entity and a second entity associated with the first entity from all entities associated with the target entity, where the first entity is an entity directly associated with the target entity; processing NLP by using natural language, and calculating a first relation coefficient between the element entity and the target entity, a second relation coefficient between the target entity and the first entity and a third relation coefficient between the first entity and the second entity; and determining the relationship coefficients of the element entity and all entities related to the target entity and the target entity based on the first relationship coefficient, the second relationship coefficient and the third relationship coefficient.
In some embodiments, the first extracting unit is further configured to determine the first relationship coefficient as a relationship coefficient corresponding to the element entity and the target entity; multiplying the first relation coefficient and the second relation coefficient to obtain a second coefficient, wherein the relation coefficient corresponding to the element entity and the first entity comprises the second coefficient; and multiplying the first relation coefficient, the second relation coefficient and the third relation coefficient to obtain a third coefficient, and determining that the relation coefficient corresponding to the element entity and the second entity comprises the third coefficient.
In some embodiments, the first computing unit is further configured to obtain a first relation coefficient, a second coefficient, and a third coefficient; and accumulating the first relation coefficient, the second coefficient and the third coefficient to obtain a relation weight sum, wherein the relation coefficient sum of each element entity and all entities related to the target entity and the target entity comprises the relation weight sum.
In some of these embodiments, the processing unit 54 further includes:
the second determining unit is used for determining action tag information corresponding to the user according to the acquired user behavior information, wherein the action tag information comprises preference information used for representing historical operation of the user;
the third determining unit is coupled with the second determining unit and used for determining the classification information corresponding to the historical user operation based on the preference information of the historical user operation, wherein the classification information corresponding to the historical user operation at least comprises one of the following types: operating equipment object information and operating time information;
and the fourth determining unit is coupled with the third determining unit and is used for determining a delivery strategy based on the classification information, wherein the delivery strategy comprises delivery equipment and/or delivery time for delivering the advertisement.
In some embodiments, the obtaining module 52 is further configured to obtain user portrait data corresponding to a preset user and text data corresponding to a preset scene, where the user portrait data is generated according to user tag information and user behavior data, and the text data includes structured data and partially structured data; respectively identifying and extracting entities and entity attributes of user portrait data and text data to obtain at least two entities and attribute information of each entity; and carrying out knowledge fusion processing on the relationship between any two entities and the attribute information of each entity to generate at least one entity pair relationship template, wherein the map data comprises the entity pair relationship template, and the knowledge fusion processing comprises similarity calculation, duplicate removal and disambiguation of the entities.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 6, an embodiment of the present application provides an electronic device including a processor 61, a communication interface 62, a memory 63, and a communication bus 64, where the processor 61, the communication interface 62, and the memory 63 complete mutual communication through the communication bus 64,
a memory 63 for storing a computer program;
the processor 61 is adapted to implement the method steps of fig. 1 when executing the program stored in the memory 63.
The processing in the server implements the method steps in fig. 1, and the technical effect brought by the method steps is consistent with the technical effect of the advertisement delivery method in fig. 1 executed in the foregoing embodiment, and is not described again here.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the advertisement delivery method provided in any of the foregoing method embodiments.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform the advertising method of any of the above embodiments.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An advertisement delivery method, comprising:
receiving an advertisement to be delivered, and determining advertisement element information corresponding to the advertisement, wherein the advertisement element information comprises a plurality of element entities;
acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data;
determining a target user according to the relevance of the element entities and all entities related to the target entity in the graph data, wherein the target entity is a named entity for representing a user name;
and determining a delivery strategy according to the user behavior information of the target user, and delivering the advertisement to the target user based on the delivery strategy.
2. The method of claim 1, wherein determining a target user based on the relevance of the plurality of element entities to all entities associated with the target entity in the graph data comprises:
extracting the target entity corresponding to the map data and all entities related to the target entity;
sequentially calculating the relationship coefficients of each element entity and all entities related to the target entity and the target entity, and determining the relationship coefficient sum of each element entity and all entities related to the target entity and the target entity, wherein the relationship coefficients are used for representing the association degree of the corresponding entity and the element entity;
judging whether the relation coefficient sum is larger than a preset threshold value or not;
and under the condition that the relation coefficient sum is judged to be larger than a preset threshold value, determining the user corresponding to the target entity as a target user.
3. The method of claim 2, wherein calculating the relationship coefficients of each of the constituent entities with all entities associated with the target entity and the target entity in turn comprises:
determining a first entity and a second entity associated with the first entity in all entities associated with the target entity, wherein the first entity is an entity directly associated with the target entity;
calculating a first relation coefficient of the element entity and the target entity, a second relation coefficient of the target entity and the first entity and a third relation coefficient between the first entity and the second entity by using Natural Language Processing (NLP);
determining relationship coefficients of the element entity with the target entity and all entities associated with the target entity based on the first relationship coefficient, the second relationship coefficient and the third relationship coefficient.
4. The method of claim 3, wherein determining the relationship coefficients of the element entity and all entities associated with the target entity and the target entity based on the first relationship coefficient, the second relationship coefficient, and the third relationship coefficient comprises:
determining the first relation coefficient as a relation coefficient corresponding to the element entity and the target entity;
multiplying the first relation coefficient and the second relation coefficient to obtain a second coefficient, wherein the relation coefficient corresponding to the element entity and the first entity comprises the second coefficient;
and multiplying the first relation coefficient, the second relation coefficient and the third relation coefficient to obtain a third coefficient, and determining that the relation coefficient corresponding to the element entity and the second entity comprises the third coefficient.
5. The method of claim 4, wherein determining a sum of relationship coefficients for each of the constituent entities with all entities associated with the target entity and the target entity comprises:
acquiring the first relation coefficient, the second coefficient and the third coefficient;
and accumulating the first relation coefficient, the second coefficient and the third coefficient to obtain a relation weight sum, wherein the relation coefficient sum of all entities related to the target entity and the relation weight sum of each element entity comprise the relation weight sum.
6. The method of claim 1, wherein determining a placement strategy based on the user behavior information of the target user comprises:
determining action tag information corresponding to the user according to the acquired user behavior information, wherein the action tag information comprises preference information used for representing the historical operation of the user;
based on the preference information of the user historical operation, determining classification information corresponding to the user historical operation, wherein the classification information corresponding to the user historical operation at least comprises one of the following types: operating equipment object information and operating time information;
and determining the delivery strategy based on the classification information, wherein the delivery strategy comprises delivery equipment and/or delivery time of advertisement delivery.
7. The method of claim 1, wherein the construction of the atlas data comprises:
acquiring user portrait data corresponding to a preset user and text data corresponding to a preset scene, wherein the user portrait data is generated according to user tag information and user behavior data, and the text data comprises structured data and partial structured data;
respectively identifying and extracting entity attributes and entity attributes of the user portrait data and the text data to obtain attribute information of at least two entities and each entity;
and carrying out knowledge fusion processing on the relationship between any two entities and the attribute information of each entity to generate at least one entity pair relationship template, wherein the map data comprises the entity pair relationship template, and the knowledge fusion processing comprises similarity calculation, duplication removal and disambiguation of the entities.
8. An advertisement delivery device, comprising:
the system comprises a receiving module, a display module and a display module, wherein the receiving module is used for receiving an advertisement to be launched and determining advertisement element information corresponding to the advertisement, and the advertisement element information comprises a plurality of element entities;
the acquisition module is used for acquiring atlas data from a preset atlas database, wherein the atlas data is formed by performing entity extraction and knowledge fusion on user portrait data;
the determining module is used for determining a target user according to the relevance of the element entities and all entities related to the target entity in the map data, wherein the target entity is a named entity for representing a user name;
and the processing module is used for determining a delivery strategy according to the user behavior information of the target user and delivering the advertisement to the target user based on the delivery strategy.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the steps of the advertisement delivery method of any one of claims 1 to 7 when executing the program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the advertising method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420416.3A CN114881685A (en) | 2022-04-20 | 2022-04-20 | Advertisement delivery method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420416.3A CN114881685A (en) | 2022-04-20 | 2022-04-20 | Advertisement delivery method, device, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881685A true CN114881685A (en) | 2022-08-09 |
Family
ID=82670821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210420416.3A Pending CN114881685A (en) | 2022-04-20 | 2022-04-20 | Advertisement delivery method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881685A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115687790A (en) * | 2022-12-01 | 2023-02-03 | 松原市逐贵网络科技有限公司 | Advertisement pushing method and system based on big data and cloud platform |
| CN115689648A (en) * | 2022-10-28 | 2023-02-03 | 广东柏烨互动网络科技有限公司 | User information processing method and system applied to directional delivery |
-
2022
- 2022-04-20 CN CN202210420416.3A patent/CN114881685A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689648A (en) * | 2022-10-28 | 2023-02-03 | 广东柏烨互动网络科技有限公司 | User information processing method and system applied to directional delivery |
| CN115687790A (en) * | 2022-12-01 | 2023-02-03 | 松原市逐贵网络科技有限公司 | Advertisement pushing method and system based on big data and cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN106547908B (en) | Information pushing method and system | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| CN106682169B (en) | Application label mining method and device, application searching method and server | |
| US10180979B2 (en) | System and method for generating suggestions by a search engine in response to search queries | |
| CN109325179B (en) | Content promotion method and device | |
| EP3564828A1 (en) | Method of data query based on evaluation and device | |
| CN106970991B (en) | Similar application identification method and device, application search recommendation method and server | |
| CN107544988B (en) | Method and device for acquiring public opinion data | |
| CN106682170B (en) | Application search method and device | |
| US20220172247A1 (en) | Method, apparatus and program for classifying subject matter of content in a webpage | |
| CN112989038B (en) | Sentence-level user portrait generation method and device and storage medium | |
| CN107679070B (en) | Intelligent reading recommendation method and device and electronic equipment | |
| CN110597987A (en) | Search recommendation method and device | |
| CN114881685A (en) | Advertisement delivery method, device, electronic device and storage medium | |
| CN109947903B (en) | Idiom query method and device | |
| US10216989B1 (en) | Providing additional information for text in an image | |
| CN111400464B (en) | Text generation method, device, server and storage medium | |
| CN110851560B (en) | Information retrieval method, device and equipment | |
| JP6341899B2 (en) | Advertisement system and advertisement delivery method | |
| CN110825954A (en) | Keyword recommendation method and device and electronic equipment | |
| CN109145261B (en) | Method and device for generating label | |
| CN118250516A (en) | Hierarchical processing method for users | |
| CN110827063A (en) | Multi-strategy fused commodity recommendation method, device, terminal and storage medium | |
| CN111209488B (en) | Information sharing method and device |
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 |