CN110390098B - Method, device, equipment and storage medium for selecting data delivery party based on big data - Google Patents
Method, device, equipment and storage medium for selecting data delivery party based on big data Download PDFInfo
- Publication number
- CN110390098B CN110390098B CN201910527849.7A CN201910527849A CN110390098B CN 110390098 B CN110390098 B CN 110390098B CN 201910527849 A CN201910527849 A CN 201910527849A CN 110390098 B CN110390098 B CN 110390098B
- Authority
- CN
- China
- Prior art keywords
- product
- target
- data
- user
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (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 a method, a device, equipment and a storage medium for selecting a data delivering party based on big data, wherein the method comprises the following steps: receiving user information of a plurality of first target users and product information of a plurality of first target products; sequentially selecting a second target user, obtaining a first product score according to a preset scoring rule, and acquiring page content of a data delivery party in a mode of simulating a specific behavior of the second target user; calculating first similarity between the page content and the information of the multiple products, selecting a second target product corresponding to a second similarity with the highest similarity, acquiring a second product score of the second target product from the first product scores, and acquiring an effect score of a data delivery party on a second target user by using a preset formula; accumulating the effect scores of the data delivering parties to obtain the effect score of the data delivering parties; and selecting the data delivery party with the highest effect score. The invention aims to solve the problem of finding a data delivery party which better meets the self service requirement and has better effect.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a method, a device, equipment and a storage medium for selecting a data delivery party based on big data.
Background
When product advertisement putting is carried out, advertisement data putting parties with better effects need to be found for cooperation, how to check the advertisement putting effects of the data putting parties generally depends on public praise and influence in the industry, the data are provided by third parties, certain deviation exists, and the relevance of the data and self business is not too large. Therefore, it is an urgent problem to find a data delivery party that better meets the self service requirement and has better effect.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for selecting a data delivering party based on big data, and aims to solve the problem of finding a data delivering party which better meets the service requirement of the data delivering party and has a better effect.
In order to achieve the above object, the present invention provides a method for selecting a data delivering party based on big data, including:
receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises user figures;
selecting a second target user from the plurality of first target users, obtaining the first product scores of the plurality of first target products by the second target user according to the user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behavior of the second target user, wherein the specific behavior at least comprises the behavior of the second target user related to the preset service;
calculating first similarity of the page content and product information of a plurality of first target products, acquiring second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, acquiring a second product score of a second target user on the second target product from the first product score, and acquiring an effect score of a data releasing party on the second target user according to the second similarity and the second product score by a preset formula;
accumulating the effect scores of the second target users by the data delivering party, and obtaining the effect score of the data delivering party according to the accumulated score of the effect scores, wherein the effect score is used for evaluating the delivering effect of the data delivering party;
and comparing the effect scores of the data delivering parties, and selecting the data delivering party with the highest effect score.
Further, the step of obtaining the scores of the second target user on the first products of the plurality of first target products according to a preset scoring rule according to the relationship between the user information of the second target user and the product information of the plurality of first target products, wherein the product information at least comprises product risk, product income, product sales volume and popularization strength, and the step comprises the following steps:
dividing a plurality of first target products into suitable products and unsuitable products according to the user portrait and the product risk;
respectively sorting the suitable products and the unsuitable products in a descending order according to the product income, wherein if the product income is the same, the products are sorted in a descending order according to the product sales volume, if the product sales volume is the same, the products are sorted in a descending order according to the promotion strength, and the sorting of the unsuitable products with the largest product income is lower than that of the suitable products with the smallest product income, so that the suitable degree sorting of the first target product is obtained;
and performing descending order numbering on the plurality of first target products according to the appropriateness ordering sequence of the target products, recording the product numbers as the product scores of the first target products, and obtaining the first product scores of the second target user on the plurality of first target products.
Further, the step of obtaining the page content of the data publisher in a manner of simulating the second target user specific behavior includes:
acquiring historical user behavior characteristics of a second target user from a system database;
analyzing the user behavior characteristics to obtain the specific behavior of the second target user;
and acquiring the page content of the data delivery party in a mode of simulating the specific behavior of the second target user according to the specific behavior of the second target user.
Further, before the step of calculating the first similarity between the page content and the product information of the plurality of first target products, the method further comprises the following steps:
judging whether the page content is related to a preset service or not;
if the result is not related to the preset service, recording the effect score of the data delivery party on the second target user as zero;
and if the first similarity is related to the preset service, the step of calculating the first similarity between the page content and the product information of the first target products is carried out.
Further, the step of obtaining the effect score of the data releasing party on the second target user by the preset formula according to the second similarity and the second product score includes the steps of:
converting the page content into character content;
acquiring product contents from the product information of a plurality of first target products, and calculating first similarity between the product contents and the text contents;
acquiring a second similarity with the highest similarity in the first similarities;
selecting a second target product corresponding to the second similarity from the plurality of first target products;
acquiring a second product score of a second target user for a second target product from the first product score;
and multiplying the second similarity by the second product score to obtain the effect score of the data delivery party on the second target user.
Further, the step of calculating the similarity between the product content and the text content, wherein the product content is a first product keyword, includes:
matching the first product keywords with the text content one by one to obtain the number of second product keywords which are the same as the text content;
and calculating the ratio of the number of the second product keywords to the number of the first product keywords to obtain the similarity between the product content and the text content.
Further, the step of matching the first product keywords with the text content one by one to obtain the number of second product keywords the same as the text content comprises:
performing word segmentation processing on the text content;
matching the first product keywords with each participle to obtain second product keywords which are the same as the participles;
and counting the number of the second product keywords.
The invention also provides a device for selecting a data delivery party based on big data, which comprises:
the receiving module is used for receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises a user portrait;
the first scoring module is used for selecting a second target user from the plurality of first target users, obtaining the first product scoring of the plurality of first target products by the second target user according to the user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behavior of the second target user, wherein the specific behavior at least comprises the behavior of the second target user related to the preset service;
the calculation module is used for calculating first similarity of the page content and product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user for the second target product from the first product scores, and obtaining an effect score of a data delivery party for the second target user according to the second similarity and the second product score;
the accumulation module is used for accumulating the effect scores of the second target users by the data releasing party, and obtaining the effect scores of the data releasing party according to the accumulated scores of the effect scores, wherein the effect scores are used for evaluating the releasing effect of the data releasing party;
and the selecting module is used for comparing the effect scores of the data delivering parties and selecting the data delivering party with the highest effect score.
The invention also proposes a device comprising a memory storing computer-readable instructions and a processor implementing the steps of any of the above methods when the processor executes the computer-readable instructions.
The present invention also provides a computer non-transitory readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of any of the methods described above.
The method, the device, the equipment and the storage medium for selecting the data delivering party based on the big data have the advantages that: the method comprises the steps of respectively scoring a plurality of target products by each target user, obtaining a plurality of page contents at a data delivery party in a mode of simulating user behaviors, respectively carrying out similarity calculation on the plurality of page contents and the plurality of target products to obtain effect scores of the data delivery party for each target user, accumulating the effect scores to obtain the effect scores of the data delivery party, judging whether an advertisement delivery strategy of the data delivery party better accords with expectations of the data delivery party for the target users according to the effect scores of the data delivery party, and selecting the data delivery party which better accords with self business requirements and has better effect according to the effect scores of the data delivery party.
Drawings
FIG. 1 is a schematic diagram illustrating steps of a method for selecting a data publisher based on big data according to the present invention;
FIG. 2 is a schematic flow chart of a device for selecting a data publisher based on big data according to the present invention;
fig. 3 is a block diagram schematically illustrating the structure of an embodiment of the apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, a method for selecting a data publisher based on big data includes:
s1, receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises user portrait;
s2, selecting a second target user from the multiple first target users, obtaining the first product scores of the multiple first target products by the second target users according to the user information of the second target user and the product information of the multiple first target products and the preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behaviors of the second target user, wherein the specific behaviors at least comprise the behaviors of the second target user related to the preset service;
s3, calculating first similarity of the page content and product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user for the second target product from the first product score, and obtaining an effect score of the data releasing party for the second target user according to the second similarity and the second product score and a preset formula;
s4, accumulating the effect scores of the second target users by the data releasing party, and obtaining the effect scores of the data releasing party according to the accumulated scores of the effect scores, wherein the effect scores are used for evaluating the releasing effect of the data releasing party;
and S5, comparing the effect scores of the data delivering parties, and selecting the data delivering party with the highest effect score.
In the step S1, taking the loan service as an example, first, a plurality of first target users are screened from users who have applied for the loan service, for example, an expert selects a group of representative and general first target users from a user database, the plurality of first target users may be mass users, the user information may include user images, historical behavior characteristic data of users who have passed by, and the like, and a plurality of target products are simultaneously selected, the target products may be loan financial products to be promoted, that is, loan financial products that need to be advertised and placed, or may be a plurality of representative and general loan financial products selected by the expert, and the product information of the target products may include product content, product risk, product income, product sales volume, promotion sequencing, and the like.
In the step S2, one second target user is sequentially selected from the received multiple first target users, for each selected second target user, according to the user information and the product information, the product scores of the multiple first target products by the second target user are obtained by using a preset scoring rule, that is, it is expected that the second target user sees the expected values of the multiple first target products, for example, the suitability ranking of the multiple first target products is performed according to the user information and the product information, that is, the suitability ranking of the first target products seen by the second target user is expected, and the first target product most suitable for the second target user represents the first target product most expected to be seen by the second target user, the score of the first target product is the highest, so as to obtain the first product scores of the multiple first target products by the second target user. The method comprises the steps that page content of a data putting party is obtained in a mode of simulating specific behaviors of a second target user, wherein the specific behaviors at least comprise a behavior that the second target user conducts related to a preset service, for example, the preset service is loan, the second target user easily applies for loan when buying things in the next year, users with similar qualifications to the second target user can be simulated in the data putting party, similar operations are conducted at similar time, the page content of the data putting party is obtained, whether the data putting party puts advertisements of loan products or not is judged, the put loan products are products, namely, when the second target user conducts loan operation on the data putting party, which products are put by the data putting party, and the data putting party selects an advertisement loan putting channel for putting the product advertisements.
Further, the product information at least includes product risk, product income, product sales volume, and promotion strength, and in step S2, the method includes:
s21, dividing the first target products into suitable products and unsuitable products according to the user portrait and the product risks;
s22, respectively sequencing the suitable products and the unsuitable products in a descending order according to the product income, wherein if the product income is the same, the products are sequenced in a descending order according to the product sales volume, if the product sales volume is the same, the products are sequenced in a descending order according to the promotion strength, and the sequence of the unsuitable products with the largest product income is lower than that of the suitable products with the smallest product income, so that the sequence of the suitability degree of the first target product is obtained;
and S23, performing descending order numbering on the first target products according to the proper degree sorting order, recording the product numbers as the product scores of the first target products, and obtaining the first product scores of the second target user on the first target products.
In step S21, the user representation is a tagged user model abstracted according to the information of the user social attribute, the living habit, the consumption behavior, etc., the content of the user representation may include sex, age, occupation, loan repayment ability, value view, etc., the user representation may be a user representation directly calling the established user representation related to the target user, the target product is divided into a suitable product and an unsuitable product according to the user representation and the product risk, for example, the user representation of the target user indicates that the target user has strong loan repayment ability, and then a product with high risk is suitably pushed, then a first target product with high product risk is divided into a suitable product, and a product with low relative push risk is not suitable, and then a first target product with low risk is divided into an unsuitable product, etc.
In the step S22, the target products classified as suitable products are sorted individually, and the target products classified as unsuitable products are also sorted individually, if two target products with high product risk are determined, the target products are sorted according to the product income of the target products, the target products with high income are sorted in the front, the product sales are compared if the target products with the same income are found, the product sales are sorted in the front, the product sales are sorted according to the promotion strength, the promotion strength is preset, the promotion emphasis is placed on a plurality of first target products, then the first target products classified as suitable products are sorted in the front of the first target products classified as unsuitable products, that is, the sorting of the unsuitable products with the maximum product income is lower than the suitable products with the minimum product income, so as to obtain the suitable sorting of the plurality of first target products by the second target user, i.e., the order in which the second targeted user is expected to see the first targeted products in the delivered advertisement.
In the above step S23, for the plurality of first target products that have been ranked in order, the first target product ranked at the top is most suitable for the second target user to see, and the product score is also highest, for example, there are three target products, the number of the first target product ranked at the top is three, and the product score of the second target user for the first target product is three, the product number of the first target product ranked at the last is one, and the product score of the second target user for the first target product is one, so as to obtain the first product score of the plurality of first target products by the second target user.
Further, in step S2, the method includes:
s24, acquiring historical user behavior characteristics of the second target user from the system database;
s25, analyzing the user behavior characteristics to obtain the specific behavior of the second target user;
and S26, acquiring the page content of the data delivery party in a mode of simulating the specific behavior of the second target user according to the specific behavior of the second user.
In the present embodiment, the user behavior mainly refers to a behavior of the user on the internet or the mobile internet, such as browsing a web page, searching a record, using application software, and network social behavior. The system database is used for independently collecting user behavior data of each target user aiming at different network data sources to form historical user behavior characteristics of the user, such as collecting websites visited by the user, search contents, visit time, website contents, mobile phone application program use conditions and the like. The historical user behavior feature data of the second target user is obtained in a system database, the obtained user behavior features are analyzed, the operation behavior of the second target user when applying for loan products in the past is determined, for example, the second target user applies for loan when buying a car in the past year, namely, the second target user purchases the car when the behavior related to the preset service (loan) is twenty one, namely, the car is purchased when the specific behavior of the second target user is twenty one, the car is purchased according to the obtained specific behavior of the second target user, the crawler software interacts with an interface API of a data delivery party, operation is performed in the data delivery party according to the specific behavior of the second target user in a virtual mode, and then page content of the data delivery party is obtained.
In the step S3, calculating a first similarity between the obtained page content and the product information of the multiple target products, analyzing whether the page content has a first target product that is expected to be seen by a second target user, and if the page content has a highest similarity, determining that the page content includes the product information of the target product, so as to obtain a second similarity with the highest similarity in the first similarity, selecting a corresponding second target product from the multiple first target users according to the second similarity, obtaining a second product score of the second target product from the first product score, calculating an effect score of the data publisher on the second target user by using a preset formula, and determining whether the advertisement delivery policy of the data publisher on the target user more conforms to the expectation of the user.
Further, before step S3, the method includes:
s31, judging whether the page content is related to a preset service;
s32, if the data distribution party is not related to the preset service, the effect score of the data distribution party to the second target user is zero;
s33, if the preset business is related, the step of calculating the first similarity of the page content and the product information of the first target products is carried out.
In the embodiment, considering that the page content obtained by simulating the specific behavior of the second user may not be related to the service of the user, directly calculating the similarity between the page content and the product information of the plurality of first target products is time-consuming and slow in efficiency, therefore, the method can compare with the preset service to judge whether the page content contains the content related to the self service or not, if the business is loan business, it can find out if there is a word eye of loan in the page content, if not, if the obtained page content is judged to be irrelevant to the preset loan service, the obtained current page content of the data delivery party has no information aiming at the second target user, namely no advertisement content of the loan financial products is delivered, which is not in line with the expectation of the user, the score of the effect of the data publisher on the second target user is recorded as zero for the content of the page acquired this time.
Further, the product information includes product content of the first target product, and in step S3, the method includes:
s34, converting the page content into character content;
s35, obtaining product content from the product information of a plurality of first target products, and calculating first similarity between the product content and the text content;
s36, acquiring a second similarity with the highest similarity in the first similarities;
s37, selecting a second target product with the highest second similarity from the plurality of first target products;
s38, acquiring a second product score of a second target user for a second target product from the first product score;
and S39, multiplying the second similarity by the second product score to obtain the effect score of the data delivery party on the second target user.
In this embodiment, the generally acquired page content is a page picture acquired by means of screen capture or the like, and the page picture may be subjected to Optical Character Recognition (Optical Character Recognition, abbreviated as OCR), that is, for a print Character, characters are optically converted into an image file of a black-and-white dot matrix, and characters in the image are converted into a text format by Recognition software. Character recognition is carried out on the page picture by utilizing an OCR (optical character recognition) to recognize the character content in the page picture, first similarity between the recognized character content and the product content sequentially obtained from the product information of a plurality of first target products is calculated, the similarity can be calculated by comparing the similarity of two segments of character strings of python, Java and the like or carrying out matching according to keywords to obtain the first similarity between the character content and the product content of the plurality of first target products, which is the highest second similarity can be obtained according to the first similarity comparison, then a second target product corresponding to the second similarity is selected from the plurality of first target products, the similarity with the character content is the highest, the product content of the second target product can be considered to be in the obtained page content, and the second product score of the second target product of the second target user can be obtained from the scores of the first target products of the plurality of second target users, and obtaining the effect score of the data putting party on the second target user by the product of the second similarity and the second product score, namely obtaining the expected score of the loan advertisement which is intelligently recommended by the data putting party to the second target user and meets our requirements.
Further, the step S35, where the product content is the first product key, includes:
s351, matching the keywords of the first product with the text content one by one to obtain the number of the keywords of the second product, which is the same as the text content;
and S352, calculating the ratio of the number of the second product keywords to the number of the first product keywords to obtain the similarity between the product content and the character content.
In this embodiment, considering that the content of some product information is secondary, we can set the product content of the first target product as several first product keywords, such as the category of the first target product is consumption credit, cash credit, credit, etc., and other first product keywords may also be term, amount (highest), loan time, etc., each first product keyword is matched with the text content, and it can be matched, and the ratio of the number of the same second product keywords to the total number of the first product keywords is, for example, 5 first product keywords are set and 4 second product keywords are set, and 4/5 is 0.8, that is, the similarity is 80%.
Further, in step S351, the method includes:
s3511, word segmentation processing is carried out on the character content;
s3512, matching the first product keywords with the participles to obtain second product keywords same as the participles;
s3513, counting the number of the keywords of the second product.
In this embodiment, in the present embodiment, when performing word segmentation on the converted text content, an N-gram Model (N-gram Model), a Hidden Markov Model (HMM), or a Maximum Entropy Model (Maximum Entropy Model) may be used to perform word segmentation, and the word segmentation algorithm may include: the method comprises the steps of forward maximum matching, reverse maximum matching, bidirectional maximum matching, shortest path algorithm and the like, and the segmentation of the text content is matched with product keywords.
In step S4, a plurality of different page contents of the data publisher are obtained by simulating a plurality of first target user behaviors, a plurality of effect scores of the data publisher corresponding to the plurality of first target users are obtained, the plurality of effect scores are accumulated to obtain a final effect score of the data publisher, the effect score is used for evaluating the publishing effect of the data publisher, whether the data delivering party better meets the expectation of the business requirement of the data delivering party is confirmed according to the effect score of the data delivering party, namely, whether the advertisement putting strategy of the data putting party better accords with the expectation of the data putting party to a plurality of first target users, the score of the effect score is high, the advertisement putting strategy representing the data putting party better accords with the expectation, the putting effect is better, the advertisement putting effect to a plurality of first target products is better, therefore, the data delivery party which meets the self business requirement and has a good effect can be selected to deliver the advertisements of the first target products.
In step S5, the result score of the data publisher represents that the advertisement delivery policy of the data publisher better meets the requirement, and the higher the result score is, the better meets the self service requirement and the better the effect, so according to the result score of the data publisher, the result score of the data publisher can be compared, the data publisher with the highest result score is selected, and the advertisement delivery of a plurality of first target products is performed in the selected data publisher.
Referring to fig. 2, the present invention further provides a device for selecting a data delivering party based on big data, including:
the system comprises a receiving module 1, a display module and a display module, wherein the receiving module 1 is used for receiving user information of a plurality of first target users and product information of a plurality of first target products, and the user information at least comprises user figures;
the first scoring module 2 is used for selecting a second target user from the plurality of first target users, obtaining the first product scoring of the plurality of first target products by the second target user according to the user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behavior of the second target user, wherein the specific behavior at least comprises the behavior of the second target user related to the preset service;
the calculation module 3 is used for calculating first similarity of the page content and product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user on the second target product from the first product scores, and obtaining an effect score of a data delivery party on the second target user according to the second similarity and the second product score by using a preset formula;
the accumulation module 4 is used for accumulating the effect scores of the second target users by the data delivering party, obtaining the effect scores of the data delivering party according to the accumulated scores of the effect scores, and the effect scores are used for evaluating the delivering effect of the data delivering party;
and the selecting module 5 is used for comparing the effect scores of the data delivering parties and selecting the data delivering party with the highest effect score.
In the receiving module 1, for example, the loan service is taken as an example, a plurality of first target users are screened from users who have applied for the loan service, for example, experts select a group of representative and general first target users from a user database, the plurality of first target users may be massive users, the user information may include user images, historical behavior characteristic data of the users who have passed by, and the like, and simultaneously select a plurality of target products, the target products may be loan financial products to be promoted, that is, loan financial products that need to be advertised, or a plurality of representative and general loan financial products selected by the experts, and the product information of the target products may include product content, product risk, product income, product sales volume, promotion sequencing, and the like.
In the first scoring module 2, one second target user is sequentially selected from the received multiple first target users, for each selected second target user, according to the user information and the product information, product scoring of the multiple first target products by the second target user is obtained by a preset scoring rule, that is, the second target user is expected to see expected values of the multiple first target products, for example, the multiple first target products are subjected to suitability ranking according to the user information and the product information, that is, the suitability ranking of the first target products seen by the second target user is expected, the first target product most suitable for the second target user represents the first target product most expected to be seen by the second target user, and the score of the first target product is highest, so that the first product scoring of the multiple first target products by the second target user is obtained. The method comprises the steps that page content of a data putting party is obtained in a mode of simulating specific behaviors of a second target user, wherein the specific behaviors at least comprise a behavior that the second target user conducts related to a preset service, for example, the preset service is loan, the second target user easily applies for loan when buying things in the next year, users with similar qualifications to the second target user can be simulated in the data putting party, similar operations are conducted at similar time, the page content of the data putting party is obtained, whether the data putting party puts advertisements of loan products or not is judged, the put loan products are products, namely, when the second target user conducts loan operation on the data putting party, which products are put by the data putting party, and the data putting party selects an advertisement loan putting channel for putting the product advertisements.
Further, product information includes product risk, product income, product sales volume, popularization dynamics at least, and first grade module 2 includes:
the dividing submodule is used for dividing the first target products into suitable products and unsuitable products according to the user portrait and the product risk;
the sorting submodule is used for sorting the suitable products and the unsuitable products in a descending order according to the product income, wherein if the product income is the same, the products are sorted in a descending order according to the product sales, if the product sales is the same, the products are sorted in a descending order according to the promotion strength, and the sorting of the unsuitable products with the largest product income is lower than that of the suitable products with the smallest product income, so that the suitability sorting of the first target product is obtained;
and the scoring submodule is used for performing descending numbering on the plurality of first target products according to the appropriateness sorting sequence, recording the product numbers as the product scores of the first target products, and obtaining the first product scores of the second target user on the plurality of first target products.
In the partitioning submodule, the user portrait is a tagged user model abstracted according to information such as user social attributes, living habits, consumption behaviors and the like, the content of the user portrait can comprise gender, age, occupation, repayment capability, value view and the like, the user portrait can be a user portrait which is established and related to a target user, a target product is partitioned into a proper product and an improper product according to the user portrait and product risk, for example, the user portrait of the target user shows that the target user is strong in repayment capability, the product with high risk is pushed properly, a first target product with high product risk is partitioned into a proper product, the product with low relative push risk is not proper, the first target product with low risk is partitioned into an improper product and the like.
In the sequencing submodule, the target products divided into suitable products are independently sequenced, meanwhile, the target products divided into unsuitable products are also independently sequenced, if two target products with high product risk are determined, the target products are sequenced according to the product income of the target products, the target products with high income are sequenced in the front, the target products with the same income are compared with the product sales volume, the product sales volume is sequenced in the front, the product sales volume is the same, the target products are sequenced according to the promotion strength, the promotion strength is preset and is the promotion emphasis on a plurality of first target products, then the first target products divided into suitable products are sequenced in the front of the first target products divided into unsuitable products, namely the sequencing of the unsuitable products with the maximum product income is lower than the sequencing of the suitable products with the minimum product income, so that the proper sequencing of a second target user on the plurality of first target products is obtained, i.e., the order in which the second targeted user is expected to see the first targeted products in the delivered advertisement.
In the scoring module, for the plurality of first target products that have been ranked, the first target product ranked foremost is most suitable for the second target user to see, and then the score of the product is also highest, for example, there are three target products, the number of the first target product ranked foremost is three, then the product score of the second target user for the first target product is three, the product number of the first target product ranked rearmost is one, and the product score of the second target user for the first target product is one, so as to obtain the first product score of the plurality of first target products by the second target user.
Further, the first scoring module 2 includes:
the acquisition submodule acquires the historical user behavior characteristics of a second target user from a system database;
the analysis submodule analyzes the user behavior characteristics to obtain the specific behavior of a second target user;
and the simulation sub-module is used for acquiring the page content of the data delivering party in a mode of simulating the specific behavior of the second target user according to the specific behavior of the second user.
In the present embodiment, the user behavior mainly refers to a behavior of the user on the internet or the mobile internet, such as browsing a web page, searching a record, using application software, and network social behavior. The system database is used for independently collecting user behavior data of each target user aiming at different network data sources so as to form historical user behavior characteristics of the user, such as the website accessed by the user, search content, access time, website content, mobile phone application program use condition and the like. The historical user behavior feature data of the second target user is obtained from a system database, the obtained user behavior features are analyzed, the operation behavior of the second target user when the second target user applies for loan products in the past is determined, for example, the second target user applies for loan when buying a car in the next year, namely, the second target user buys the car when the behavior related to the preset service (loan) is twenty one, namely, the car can be bought when the specific behavior of the second target user is twenty one, according to the obtained specific behavior of the second target user, the crawler software is interacted with an interface API of a data releasing party, the operation is performed in the data releasing party according to the specific behavior of the second target user virtually, and then the page content of the data releasing party is obtained.
In the calculating module 3, a first similarity between the obtained page content and the product information of the plurality of target products is calculated, whether a first target product which is expected to be seen by a second target user exists in the page content is analyzed, if the similarity between the page content and the page content is highest, the page content can be considered to contain the product information of the target product, so that a second similarity with the highest similarity in the first similarity is obtained, a corresponding second target product is selected from the plurality of first target users according to the second similarity, a second product score of the second target product by the second target user is obtained in the first product score, and an effect score of the data delivering party on the second target user is calculated by a preset formula, so that whether the advertisement delivering strategy of the data delivering party on the target user is more consistent with the expectation of the user on the target user.
Further, in some embodiments, the method further comprises:
the judging module is used for judging whether the page content is related to a preset service or not;
the second scoring module is used for scoring the effect of the data delivery party on a second target user to be zero if the second scoring module is irrelevant to the preset service;
and the entering module is used for entering a step of calculating first similarity of the page content and the product information of the first target products if the entering module is related to the preset service.
In the embodiment, considering that the page content obtained by simulating the specific behavior of the second user may not be related to the service of the user, directly calculating the similarity between the page content and the product information of the plurality of first target products directly wastes time and has low efficiency, therefore, the method can be compared with the preset service to judge whether the page content contains the content related to the self service or not, if the business is loan business, it can find out if there is a word eye of loan in the page content, if not, judging that the obtained page content is irrelevant to the preset loan service, if the obtained current page content of the data delivery party does not have information aiming at the second target user, namely the advertising content of the loan financial product is not delivered, the expectation is not met, the score of the effect of the data delivering party on the second target user is recorded as zero aiming at the acquired page content.
Further, the product information includes product content of the first target product, and the calculation module 3 includes:
the conversion submodule is used for converting the page content into character content;
the first calculation submodule is used for acquiring product contents from the product information of a plurality of first target products and calculating first similarity between the product contents and the text contents;
the first obtaining submodule is used for obtaining a second similarity with the highest similarity in the first similarities;
the selecting submodule selects a second target product with the highest second similarity from the plurality of first target products;
the second obtaining submodule is used for obtaining a second product score of a second target user on a second target product from the first product score;
and the second calculation submodule is used for multiplying the second similarity by the second product score to obtain the effect score of the data releasing party on the second target user.
In this embodiment, the generally acquired page content is a page picture acquired by means of screen capture or the like, and the page picture may be subjected to Optical Character Recognition (OCR), that is, for print characters, characters are optically converted into an image file of a black-and-white dot matrix, and characters in the image are converted into a text format by Recognition software. Character recognition is carried out on the page picture by utilizing an OCR (optical character recognition) to recognize the character content in the page picture, first similarity between the recognized character content and the product content sequentially obtained from the product information of a plurality of first target products is calculated, the calculated similarity can be obtained by comparing the similarity of two segments of character strings of python, Java and the like or carrying out matching according to keywords, the multiple similarities between the character content and the product content of the plurality of first target products are obtained, according to the comparison of the first similarity, which is the highest second similarity is obtained, then a second target product corresponding to the second similarity is selected from the plurality of first target products, the similarity with the character content is highest, the product content of the second target product is considered to be in the obtained page content, and the second product score of the second target product of the second target user is obtained from the scores of the first products of the plurality of first target products by the second target user, and obtaining the result score of the data putting party to the second target user by the product of the second similarity and the second product score, namely the expected score of the loan advertisement which is intelligently recommended by the data putting party to the second target user and meets the requirements of the loan advertisement.
Further, the product content is a first product keyword, and the first computation submodule includes:
the matching unit is used for matching the first product keywords with the text contents one by one to obtain the number of second product keywords which are the same as the text contents;
and the calculating unit is used for calculating the ratio of the number of the second product keywords to the number of the first product keywords to obtain the similarity between the product content and the character content.
In this embodiment, considering that the content of some product information is secondary, we can set the product content of the first target product as several first product keywords, such as the category of the first target product is consumption credit, cash credit, etc., and other first product keywords may also be term, amount (highest), loan time, etc., each first product keyword is matched with the page content, and it can match, and the ratio of the number of the same second product keywords to the total number of the first product keywords, such as 5 first product keywords and 4 second product keywords, 4/5 is 0.8, that is, the similarity is 80%.
Further, the matching unit includes:
the processing subunit is used for performing word segmentation processing on the text content;
the matching subunit is used for matching the first product keywords with the participles to obtain second product keywords same as the participles;
and the counting subunit is used for counting the number of the matched second product keywords.
In this embodiment, when segmenting words from the converted text, an N-gram Model, a Hidden Markov Model (HMM), or a Maximum Entropy Model (Maximum Entropy Model) may be used for segmenting words, and the segmentation algorithm may include: the method comprises the steps of forward maximum matching, reverse maximum matching, bidirectional maximum matching, shortest path algorithm and the like, and the segmentation of the text content is matched with product keywords.
In the accumulation module 4, a plurality of different page contents of the data delivering party are obtained by simulating a plurality of first target user behaviors, a plurality of corresponding effect scores of the data delivering party on a plurality of first target users are obtained, the plurality of effect scores are accumulated to obtain a final effect score of the data delivering party, the effect score is used for evaluating the delivering effect of the data delivering party, whether the data delivering party better meets the expectation of the business requirement of the data delivering party is confirmed according to the effect score of the data delivering party, namely, whether the advertisement putting strategy of the data putting party better accords with the expectation of the data putting party to a plurality of first target users, the score of the effect score is high, the advertisement putting strategy representing the data putting party better accords with the expectation, the putting effect is better, the advertisement putting effect to a plurality of first target products is better, therefore, the data delivery party which meets the self business requirement and has a good effect can be selected to deliver the advertisements of the first target products.
In the selecting module 5, the effect score of the data delivering party represents that the advertisement delivering strategy of the data delivering party better meets the requirements, the higher the effect score is, the better the self service requirements are met, the effect is good, so that according to the effect score of the data delivering party, the effect score of the data delivering party can be compared, the data delivering party with the highest effect score is selected, and the advertisement delivering of a plurality of first target products is carried out in the selected data delivering party.
Referring to fig. 3, an apparatus, which may be a computer or a server, and an internal structure of the apparatus may be as shown in fig. 3, is also provided in the embodiment of the present application. The apparatus includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational 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, computer readable instructions, and a database. The memory provides an environment for the operating system and the execution of computer-readable instructions in the non-volatile storage medium. The database of the device is used for storing data such as configuration item information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed, perform the processes of the embodiments of the methods described above. Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application further provides a computer non-transitory readable storage medium, on which computer readable instructions are stored, and when executed, the computer readable instructions perform the processes of the embodiments of the methods as described above, including: receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises user figures; selecting a second target user from the plurality of first target users, obtaining the first product scores of the plurality of first target products by the second target user according to the user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behavior of the second target user, wherein the specific behavior at least comprises the behavior of the second target user related to the preset service; calculating first similarity of the page content and product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user on the second target product in the first product score, and obtaining an effect score of a data delivery party on the second target user according to the second similarity and the second product score by a preset formula; accumulating the effect scores of the second target users by the data delivering party, and obtaining the effect score of the data delivering party according to the accumulated score of the effect scores, wherein the effect score is used for evaluating the delivering effect of the data delivering party; and comparing the effect scores of the data delivering parties, and selecting the data delivering party with the highest effect score.
The method comprises the steps of respectively scoring a plurality of target products by each target user, obtaining a plurality of page contents at a data delivery party in a mode of simulating user behaviors, respectively carrying out similarity calculation on the plurality of page contents and the plurality of target products to obtain effect scores of the data delivery party for each target user, accumulating the effect scores to obtain the effect scores of the data delivery party, judging whether an advertisement delivery strategy of the data delivery party better accords with expectations of the data delivery party for the target users according to the effect scores of the data delivery party, and selecting the data delivery party which better accords with self business requirements and has better effect according to the effect scores of the data delivery party.
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 provided herein and used in the examples may include non-volatile and/or volatile memory. 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-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, apparatus, article or method that comprises the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method for selecting a data delivery party based on big data is characterized by comprising the following steps:
receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises a user portrait;
selecting a second target user from the plurality of first target users, obtaining first product scores of the second target user on the plurality of first target products according to user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining page content of a data delivery party in a mode of simulating a specific behavior of the second target user, wherein the specific behavior at least comprises a behavior of the second target user related to a preset service;
calculating first similarity of the page content and the product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user on the second target product from the first product scores, and obtaining an effect score of a data delivery party on the second target user according to the second similarity and the second product score by a preset formula;
accumulating the effect scores of the second target users by the data delivering party, and obtaining the effect score of the data delivering party according to the accumulated score of the effect scores, wherein the effect score is used for evaluating the delivering effect of the data delivering party;
and comparing the effect scores of the data delivering parties, and selecting the data delivering party with the highest effect score.
2. The method for selecting a data publisher based on big data according to claim 1, wherein the product information at least comprises product risk, product income, product sales and promotion strength, and the step of obtaining the first product score of a plurality of first target products by a second target user according to a preset scoring rule based on the user information of the second target user and the product information of the plurality of first target products comprises:
dividing a plurality of first target products into suitable products and unsuitable products according to the user portrait and the product risk;
respectively sorting the suitable products and the unsuitable products in a descending order according to the product income, wherein if the product income is the same, the product sales volume is sorted in a descending order, if the product sales volume is the same, the promotion sales volume is sorted in a descending order, and the sorting of the unsuitable products with the largest product income is lower than that of the suitable products with the smallest product income, so that the suitability degree sorting of the first target product is obtained;
and performing descending order numbering on the plurality of first target products according to the proper degree sorting sequence, recording the numbers as the product scores of the first target products, and obtaining the first product scores of the plurality of first target products by a second target user.
3. The big data based data publisher selecting method as claimed in claim 1, wherein the step of obtaining the page content of the data publisher in a manner simulating a second target user specific behavior comprises:
acquiring historical user behavior characteristics of a second target user from a system database;
analyzing the user behavior characteristics to obtain the specific behavior of a second target user;
and acquiring the page content of the data delivery party in a mode of simulating the specific behavior of the second target user according to the specific behavior of the second target user.
4. The big data based data publisher selecting method according to claim 1, wherein said calculating a first similarity between said page content and said product information of a plurality of first target products is preceded by:
judging whether the page content is related to the preset service or not;
if the result is not related to the preset service, recording the effect score of the data delivery party on the second target user as zero;
and if the preset business is related, the step of calculating the first similarity of the page content and the product information of a plurality of first target products is carried out.
5. The method according to claim 1, wherein the product information includes product content of a first target product, the calculating a first similarity between the page content and the product information of a plurality of first target products, obtaining a second similarity with a highest similarity among the first similarities, selecting a second target product corresponding to the second similarity among the plurality of first target products, obtaining a second product score of a second target user for the second target product among the first product scores, and obtaining an effect score of the data publisher for the second target user according to the second similarity and the second product score by using a preset formula, the method includes:
converting the page content into text content;
acquiring the product content from the product information of a plurality of first target products, and calculating the first similarity between the product content and the text content;
acquiring the second similarity with the highest similarity in the first similarities;
selecting a second target product corresponding to the second similarity from the plurality of first target products;
acquiring a second product score of a second target user for a second target product from the first product score;
and multiplying the second similarity by the second product score to obtain the effect score of the data delivery party on a second target user.
6. The method for selecting data publishers based on big data according to claim 5, wherein the product content is a first product keyword, and the step of calculating the similarity between the product content and the text content comprises:
matching the first product keywords with the text content one by one to obtain the number of second product keywords which are the same as the text content;
and calculating the ratio of the number of the second product keywords to the number of the first product keywords to obtain the similarity between the product content and the text content.
7. The big data-based data publisher selecting method according to claim 6, wherein the step of matching the first product keywords with the text content one by one to obtain a second product keyword amount same as the text content comprises:
performing word segmentation processing on the text content;
matching the first product keywords with each participle to obtain second product keywords which are the same as the participles;
and counting the number of the second product keywords.
8. A device for selecting a data delivery party based on big data is characterized by comprising:
the receiving module is used for receiving user information of a plurality of first target users and product information of a plurality of first target products, wherein the user information at least comprises a user portrait;
the first scoring module is used for selecting a second target user from the plurality of first target users, obtaining the first product scores of the second target user on the plurality of first target products according to the user information of the second target user and the product information of the plurality of first target products and a preset scoring rule, and obtaining the page content of the data delivery party in a mode of simulating the specific behavior of the second target user, wherein the specific behavior at least comprises the behavior of the second target user related to a preset service;
the calculation module is used for calculating first similarity of the page content and the product information of a plurality of first target products, obtaining second similarity with the highest similarity in the first similarity, selecting a second target product corresponding to the second similarity from the plurality of first target products, obtaining a second product score of a second target user for the second target product from the first product scores, and obtaining an effect score of a data releasing party for the second target user according to the second similarity and the second product score;
the accumulation module is used for accumulating the effect scores of the second target users by the data delivering party and obtaining the effect scores of the data delivering party according to the accumulated scores of the effect scores, wherein the effect scores are used for evaluating the delivering effect of the data delivering party;
and the selecting module is used for comparing the effect scores of the data releasing parties and selecting the data releasing party with the highest effect score.
9. A computer device comprising a memory and a processor, the memory storing computer readable instructions, wherein the processor when executing the computer readable instructions implements the steps of the method of any one of claims 1 to 7.
10. A computer non-transitory storage medium having computer readable instructions stored thereon, wherein the computer readable instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910527849.7A CN110390098B (en) | 2019-06-18 | 2019-06-18 | Method, device, equipment and storage medium for selecting data delivery party based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910527849.7A CN110390098B (en) | 2019-06-18 | 2019-06-18 | Method, device, equipment and storage medium for selecting data delivery party based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110390098A CN110390098A (en) | 2019-10-29 |
| CN110390098B true CN110390098B (en) | 2022-08-19 |
Family
ID=68285730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910527849.7A Active CN110390098B (en) | 2019-06-18 | 2019-06-18 | Method, device, equipment and storage medium for selecting data delivery party based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110390098B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930452A (en) * | 2012-09-24 | 2013-02-13 | 曹欢欢 | Method and device for releasing home decoration advertisements accurately |
| CN104794631A (en) * | 2015-03-31 | 2015-07-22 | 北京奇艺世纪科技有限公司 | Verification method and device for advertisement putting effect |
| CN107563808A (en) * | 2017-08-29 | 2018-01-09 | 天脉聚源（北京）科技有限公司 | A kind of advertisement putting data statistical approach and device |
| CN108960899A (en) * | 2018-06-11 | 2018-12-07 | 广东因特利信息科技股份有限公司 | The user information exchange method and system launched for advertisement |
| CN109583970A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Advertisement placement method, device, computer equipment and storage medium |
-
2019
- 2019-06-18 CN CN201910527849.7A patent/CN110390098B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110390098A (en) | 2019-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509482B (en) | Question classification method and device, computer equipment and storage medium | |
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN111080398B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| CN111784455A (en) | Article recommendation method and recommendation equipment | |
| US20080103886A1 (en) | Determining relevance of a term to content using a combined model | |
| US8793252B2 (en) | Systems and methods for contextual analysis and segmentation using dynamically-derived topics | |
| CN109819015B (en) | Information pushing method, device and equipment based on user portrait and storage medium | |
| US20090271228A1 (en) | Construction of predictive user profiles for advertising | |
| CN106445963B (en) | Advertisement index keyword automatic generation method and device of APP platform | |
| US20100100443A1 (en) | User classification apparatus, advertisement distribution apparatus, user classification method, advertisement distribution method, and program used thereby | |
| CN106970991B (en) | Similar application identification method and device, application search recommendation method and server | |
| CN111552870A (en) | Object recommendation method, electronic device and storage medium | |
| US11354349B1 (en) | Identifying content related to a visual search query | |
| CN108446295B (en) | Information retrieval method, information retrieval device, computer equipment and storage medium | |
| US20180285748A1 (en) | Performance metric prediction for delivery of electronic media content items | |
| CN110389963B (en) | Channel effect identification method, device, equipment and storage medium based on big data | |
| CN112395410A (en) | Entity extraction-based industry public opinion recommendation method and device and electronic equipment | |
| KR101441164B1 (en) | Object customization and management system | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN105677838A (en) | User profile creating and personalized search ranking method and system based on user requirements | |
| CN114881685A (en) | Advertisement delivery method, device, electronic device and storage medium | |
| US9613135B2 (en) | Systems and methods for contextual analysis and segmentation of information objects | |
| CN113434763A (en) | Method, device, equipment and storage medium for generating recommendation reason of search result | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| JP5559750B2 (en) | Advertisement processing apparatus, information processing system, and advertisement processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |