CN112446743A - Block chain-based advertisement recommendation method and terminal - Google Patents
Block chain-based advertisement recommendation method and terminal Download PDFInfo
- Publication number
- CN112446743A CN112446743A CN202011470195.8A CN202011470195A CN112446743A CN 112446743 A CN112446743 A CN 112446743A CN 202011470195 A CN202011470195 A CN 202011470195A CN 112446743 A CN112446743 A CN 112446743A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- recommended
- block
- tag
- block chain
- 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.)
- Granted
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses an advertisement recommendation method and a terminal based on a block chain, wherein a first advertisement is obtained, and an advertisement label and an advertisement weight value are obtained according to an advertisement brand; storing the first advertisement into a main information block chain, taking a block identifier of the main information block in the main information block chain as block content to generate a tag block, and storing the tag block; when pushing is needed, obtaining a user information tag of a user to be recommended, obtaining a corresponding tag block chain, and then obtaining a probability value to be recommended of each block identifier in a block chain set to be recommended according to a user information weight value and an advertisement weight value; and finally, selecting advertisements to be recommended with preset recommendation number according to the probability value to be recommended, and pushing the advertisements to be recommended to the users to be recommended according to preset pushing requirements. The advertisement recommendation method and the advertisement recommendation system can reduce the advertisement recommendation cost and improve the advertisement recommendation effect.
Description
Technical Field
The invention relates to the technical field of information disclosure, in particular to an advertisement recommendation method and terminal based on a block chain.
Background
The advertisement, as the name implies, is an advertisement that informs the general public of the society of something. Economic advertising refers to advertising for profit purposes, typically commercial advertising, which is a means of disseminating information of goods or services to consumers or users through advertising media in a paid manner for the purpose of promoting the goods or providing the services. Commercial advertisements are such economic advertisements.
The nature of the economic advertising is still to obtain more money, which on the one hand needs to reduce the expenditure of economic advertising and on the other hand needs to have a better promotional effect to make the product more marketable. Therefore, if the cost of the economic advertisement is low, the promotion effect may be affected, and if the cost of the economic advertisement is increased to improve the promotion effect, the promotion effect may not be compensated.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the advertisement recommendation method and the terminal based on the block chain are provided to reduce advertisement recommendation cost and improve advertisement recommendation effect.
In order to solve the technical problems, the invention adopts the technical scheme that:
an advertisement recommendation method based on a block chain comprises the following steps:
s1, acquiring a first advertisement, obtaining an advertisement brand of the first advertisement, and collecting a plurality of advertisement labels corresponding to the advertisement brand and an advertisement weight value of each advertisement label;
s2, generating a main information block from the first advertisement and storing the main information block into a main information block chain, and acquiring a block identifier of the main information block in the main information block chain;
s3, using the block identifier of the main information block in the main information block chain as the block content to generate tag blocks, storing the tag blocks into the tag block chain corresponding to each first advertisement tag, and using the advertisement weight value of the advertisement tag as the advertisement weight value of the block identifier corresponding to the first advertisement, where each tag block chain corresponds to an advertisement tag;
s4, obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are information of interest of the users obtained according to historical access data of the users;
s5, selecting a block identification to be recommended with a preset number of recommendations according to the probability value to be recommended, acquiring a corresponding advertisement to be recommended from the main information block chain according to the block identification to be recommended, and pushing the advertisement to be recommended to the user to be recommended according to a preset pushing requirement.
Further, the step S5 specifically includes the following steps:
s51, marking the block identification mark with the probability value to be recommended greater than or equal to a first preset value in all the tag block chains to be recommended as recommended, marking the block identification mark with the probability value to be recommended smaller than the first preset value and greater than or equal to a second preset value in all the tag block chains to be recommended as recommended waiting, marking the block identification mark with the probability value to be recommended smaller than the second preset value in all the tag block chains to be recommended as not recommended, wherein the first preset value is (0.6P)max，0.9Pmax) The second predetermined value is (0.2P)max，0.4Pmax) Said P ismaxThe value is the maximum value in the probability value to be recommended;
s52, judging whether the number of the block identifications marked as recommendation meets the preset recommendation number, if so, randomly selecting the block identifications with the preset recommendation number from the block identifications marked as recommendation as block identifications to be recommended, and then executing a step S54, if not, executing a step S53;
s53, taking the block identifications marked as recommendation as block identifications to be recommended, obtaining the residual recommendation number according to the preset recommendation number and the block identifications to be recommended, selecting the block identifications with the residual recommendation number from the block identifications marked as recommendation waiting as the block identifications to be recommended, and then executing the step S54;
s54, acquiring a corresponding advertisement to be recommended from the main information block chain according to the block identification to be recommended, and pushing the advertisement to be recommended to the user to be recommended according to a preset pushing requirement.
Further, the step S3 specifically includes the following steps:
s31, using the advertisement brand of the first advertisement and the block identification of the main information block in the main information block chain as block content to generate tag blocks, respectively storing the tag blocks into the tag block chain corresponding to each first advertisement tag, and using the advertisement weight value of the advertisement tag as the advertisement weight value of the block identification corresponding to the first advertisement, wherein each tag block chain corresponds to one advertisement tag;
s32, determining whether the advertisement brand of the previous tag tile in the tag tile chain is the same as the advertisement brand of the newly generated tag tile, if so, modifying a position symbol corresponding to the previous tag tile on the tag sequence corresponding to the tag tile chain to be an invalid tag, and then executing step S33, otherwise, directly executing step S33, where each tag tile chain corresponds to a tag sequence sequentially corresponding to the arrangement order of each tag tile;
s33, newly adding a position symbol of a valid tag to a position corresponding to the newly generated tag tile on the tag sequence corresponding to the tag tile chain;
the step S4 specifically includes the following steps:
s41, obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, wherein the user information labels are user interest information obtained according to historical access data of the users;
s42, obtaining a pre-recommendation probability value of each effective block identifier in the block chain set to be recommended according to the user information weight value of each user information tag and the advertisement weight value of each effective block identifier of each effective tag in each block chain of the to-be-recommended tags in the block chain set to be recommended, and adding the pre-recommendation probability values of the same effective block identifier in the block chain set to be recommended to obtain the to-be-recommended probability value of each effective block identifier in the block chain set to be recommended.
Further, the first preset value is 0.8PmaxThe second preset value is 0.2Pmax。
Further, the step S1 specifically includes the following steps:
the method comprises the steps of obtaining a first advertisement, obtaining an advertisement brand of the first advertisement, and collecting the first N advertisement labels corresponding to the advertisement brand and an advertisement weight value of each advertisement label, wherein N is (2, 10).
Further, the N is 5.
Further, the step S5 specifically includes the following steps:
sequentially selecting a preset recommendation number of block identifications to be recommended according to the probability value to be recommended from large to small, acquiring corresponding advertisements to be recommended from the main information block chain according to the block identifications to be recommended, and pushing the advertisements to be recommended to the user to be recommended according to a preset pushing requirement.
Further, the step S4 specifically includes the following steps:
the method comprises the steps of obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value and an advertisement score value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are information of interest of the users obtained according to historical access data of the users, and the advertisement score value of each block label is a score average value received by an advertisement corresponding to the block label.
Further, the step S4 further includes the following steps:
if the advertisement score value of the block identifier is lower than a lowest threshold value, marking the block identifier of which the advertisement score value is lower than the lowest threshold value as not recommended.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a block chain based advertisement recommendation terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of a block chain based advertisement recommendation method as described above when executing the computer program.
The invention has the beneficial effects that: when storing a first advertisement, extracting a label and acquiring a corresponding weight value according to an advertisement brand, then storing the label and the corresponding weight value into a main information block chain, and storing a block identifier in the main information block chain into a label block chain corresponding to each first advertisement label. At the moment, if advertisement recommendation of a user is needed, a user information tag of the user to be recommended is obtained, the corresponding tag block chain is obtained through quick traversal of the user information tag, then, a probability value to be recommended of each block mark in the block chain set to be recommended can be obtained only by calculation according to a pre-generated weight value, and advertisement recommendation is carried out according to the probability value to be recommended, so that the user can receive advertisements which are more interesting, and the advertisement recommendation of the invention can improve the advertisement recommendation effect while reducing the advertisement recommendation cost.
Drawings
Fig. 1 is a schematic flowchart of an advertisement recommendation method based on a block chain according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an advertisement recommendation terminal based on a block chain according to an embodiment of the present invention.
Description of reference numerals:
1. an advertisement recommendation terminal based on a block chain; 2. a processor; 3. a memory.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Example one
Referring to fig. 1 to fig. 2, a block chain-based advertisement recommendation method provided in this embodiment includes the steps of:
s1, obtaining the first advertisement, obtaining the advertisement brand of the first advertisement, and collecting a plurality of advertisement labels corresponding to the advertisement brand and the advertisement weight value of each advertisement label;
the number of the advertisement tags is N, where N is (2, 10), and in this embodiment, N is 5.
That is, in this embodiment, the label extraction and the weight value extraction for the first advertisement may be implemented by using an existing algorithm, for example, 5 advertisement labels with relatively representative advertisement brands may be obtained by obtaining the advertisement information and the user rating information from the public website, and then an advertisement weight value is attached to the 5 advertisement labels according to the frequency of occurrence.
S2, generating a main information block from the first advertisement and storing the main information block into a main information block chain, and acquiring a block identifier of the main information block in the main information block chain;
s3, taking block identifications of the main information block in the main information block chain as block contents to generate label blocks, respectively storing the label blocks into label block chains corresponding to each first advertisement label, taking advertisement weight values of the advertisement labels as advertisement weight values of the block identifications corresponding to the first advertisements, and enabling each label block chain to correspond to one advertisement label;
thus, in this embodiment, assuming that the advertisement tags of the first advertisement are A, B and C, and the tile identifier corresponding to the first advertisement is a in step S2, tile identifiers a are stored in the a tile chain, the B tile chain, and the C tile chain, and each tile identifier a has an advertisement weight value corresponding to advertisement tags A, B and C.
It should be understood that if there is no corresponding tag block chain, a new tag block chain may be automatically generated.
S4, obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are user interest information obtained according to historical access data of the users;
in this embodiment, step S4 specifically includes the following steps:
the method comprises the steps of obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label, obtaining a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value and an advertisement score value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are information of interest of the users obtained according to historical access data of the users, and the advertisement score value of each block label is a score average value received by an advertisement corresponding to the block label;
and if the advertisement score value of the block identifier is lower than the lowest threshold value, marking the block identifier with the advertisement score value lower than the lowest threshold value as not recommended.
In this embodiment, there are many tag block chains corresponding to the advertisement, such as an a block chain, a B block chain, a C block chain, a D block chain, and the like, and assuming that the user information tags are B and D, it is only necessary to determine the block identifiers of the B block chain and the D block chain, and the user information tags are B and D, which may be calculated in advance when the user information weight values of the user are the same, and the block identifiers of the B block chain and the D block chain may also be calculated in advance, so that the probability values to be recommended of all the block identifiers of the B block chain and the D block chain can be quickly obtained.
The advertisement score value of the block identifier is lower than the lowest threshold, the user rating of the advertisement corresponding to the block identifier is too low, and even if the advertisement is matched with the user to a high degree, the user experience is easily influenced due to poor advertisement quality, so that a reaction which is suitable for the user is generated.
S5, selecting the to-be-recommended block identifications with preset recommendation numbers according to the to-be-recommended probability value, acquiring the corresponding to-be-recommended advertisements from the main information block chain according to the to-be-recommended block identifications, and pushing the to-be-recommended advertisements to the to-be-recommended users according to preset pushing requirements.
In this embodiment, step S5 specifically includes the following steps:
sequentially selecting the to-be-recommended block identifications with preset recommendation numbers according to the probability value to be recommended from large to small, acquiring corresponding to-be-recommended advertisements from the main information block chain according to the to-be-recommended block identifications, and pushing the to-be-recommended advertisements to the to-be-recommended users according to preset pushing requirements.
The advertisements to be recommended corresponding to the block identifications to be recommended with the maximum probability value to be recommended are sent to the users to be recommended, so that the advertisements which are interested by the users are sent under the condition of small recommendation calculation amount.
Example two
Referring to fig. 1 to fig. 2, in the advertisement recommendation method based on a block chain according to the present embodiment, on the basis of the first embodiment, the step S5 is replaced with the following steps:
s51, marking the block identification mark with the probability value to be recommended greater than or equal to a first preset value in all the tag block chains to be recommended as recommended, marking the block identification mark with the probability value to be recommended smaller than the first preset value and greater than or equal to a second preset value in all the tag block chains to be recommended as to-be recommended, and marking the block identification mark with the probability value to be recommended smaller than the second preset value in all the tag block chains to be recommended as not-to-be-recommendedThe first predetermined value is (0.6P)max，0.9Pmax) The second predetermined value is (0.2P)max，0.4Pmax)，PmaxThe probability value is the maximum value in the probability values to be recommended;
in this embodiment, the first predetermined value is 0.8PmaxThe second predetermined value is 0.2PmaxThe block mark at the head part of the probability value to be recommended is an advertisement which is interested by the user and is listed as a recommended option, and the block mark at the tail part of the probability value to be recommended is an advertisement which is not interested by the user and is listed as a non-recommended option; and for being at 0.2Pmax-0.8PmaxThe advertisements in the middle portion of (1) are advertisements that are likely to be of interest to the user, and thus are marked as waiting for recommendation.
S52, judging whether the number of the block identifications marked as recommendation meets a preset recommendation number, if so, randomly selecting the block identifications with the preset recommendation number from the block identifications marked as recommendation as block identifications to be recommended, and then executing a step S54, and if not, executing a step S53;
s53, taking the block identifications marked as recommendation as block identifications to be recommended, obtaining the residual recommendation number according to the preset recommendation number and the block identifications to be recommended, selecting the block identifications with the residual recommendation number from the block identifications marked as recommendation waiting as the block identifications to be recommended, and then executing the step S54;
s54, acquiring the corresponding advertisement to be recommended from the main information block chain according to the block identification to be recommended, and pushing the advertisement to be recommended to the user to be recommended according to the preset pushing requirement.
For steps S52 to S54, if the number of advertisements in which the user is interested exceeds the preset number of recommendations, the block identifiers of the preset number of recommendations are randomly selected from the advertisements as the to-be-recommended block identifiers, and if the number of advertisements in which the user is interested is not enough, the block identifiers of the remaining number of recommendations are randomly selected from the advertisements in which the user is likely to be interested as the to-be-recommended block identifiers, so that compared with directly selecting the to-be-recommended advertisements of the remaining number of recommendations from large to small, the user is ensured to receive the advertisements in which the user is interested, and more advertisements are more likely to be seen by other users, and all advertisements are more likely to be recommended to the user on an average basis; when some advertisements with lower original probability are recommended to the user, if the user shows interest, the probability value corresponding to the user information label is sent to change, the situation that the user is limited to the interested field of the user is avoided, and the advertisement recommendation has more diversity and possibility.
EXAMPLE III
Referring to fig. 1 to fig. 2, in the advertisement recommendation method based on a block chain according to the present embodiment, on the basis of the first embodiment, the step S3 specifically includes the following steps:
s31, using block marks of the advertisement brand of the first advertisement and the main information block in a main information block chain as block contents to generate label blocks, respectively storing the label blocks into a label block chain corresponding to each first advertisement label, using advertisement weight values of the advertisement labels as advertisement weight values of the block marks corresponding to the first advertisement, and using each label block chain corresponding to one advertisement label;
in this embodiment, the advertising brand is also stored in the label tile.
S32, judging whether the advertisement brand of the previous label block in the label block chain is the same as the advertisement brand of the newly generated label block, if so, modifying the position symbol corresponding to the previous label block on the label sequence corresponding to the label block chain into an invalid label, and then executing the step S33, otherwise, directly executing the step S33, wherein each label block chain corresponds to a label sequence sequentially corresponding to the arrangement sequence of each label block;
s33, adding the position symbol of the valid tag to the position corresponding to the newly generated tag block in the tag sequence corresponding to the tag block chain.
Therefore, in this embodiment, for the advertisement, if there are a plurality of tag blocks of the same advertisement brand, the advertisement is an iterative advertisement, and therefore, the old advertisement needs to be deleted, so as to avoid two new and old advertisements of one advertisement brand appearing at the same time, and ensure the advertisement recommendation effect.
In this embodiment, step S4 specifically includes the following steps:
step S4 specifically includes the following steps:
s41, obtaining user information labels of the users to be recommended, obtaining each label block chain corresponding to each user information label, and obtaining a block chain set to be recommended, wherein the user information labels are user interest information obtained according to historical access data of the users;
s42, obtaining a pre-recommendation probability value of each effective block identifier in the block chain set to be recommended according to the user information weight value of each user information label and the advertisement weight value of each effective block identifier of which each position symbol in each block chain of the to-be-recommended labels in the block chain set to be recommended is an effective label, and adding the pre-recommendation probability values of the same effective block identifier in the block chain set to be recommended to obtain the to-be-recommended probability value of each effective block identifier in the block chain set to be recommended.
In this embodiment, only the B blockchain includes the chunk identifier a, and the D blockchain does not include the chunk identifier a, so that the pre-recommendation probability value of the chunk identifier a is the pre-recommendation probability value of the chunk identifier a on the B blockchain.
In other equivalent embodiments, if the blockchain set to be recommended includes a blockchain a, a blockchain B and a blockchain D, the blockchain a and the blockchain B both include a blockidentity a, and thus the pre-recommendation probability value of the blockidentity a is the sum of the pre-recommendation probability value of the blockidentity a on the blockchain a and the pre-recommendation probability value of the blockidentity a on the blockchain B.
Therefore, the advertisement is divided into the labels to be subjected to secondary association storage, the interest degree of the advertisement to the user is reflected by adding the probability values, in the process, full-text traversal and calculation of the advertisement are not needed, and therefore the calculation amount is further reduced on the basis of guaranteeing the real reflection of the interest of the user, and the advertisement recommendation effect can be improved while the advertisement recommendation cost is reduced.
Example four
Referring to fig. 4, a block chain based advertisement recommendation terminal 1 includes a memory 3, a processor 2, and a computer program stored on the memory 3 and executable on the processor 2, where the processor 2 implements the steps of the block chain based advertisement recommendation method according to any one of the first to second embodiments when executing the computer program.
In summary, according to the advertisement recommendation method and terminal based on the block chain provided by the present invention, when storing the first advertisement, tag extraction and corresponding weight value acquisition are performed according to the advertisement brand, and then the obtained tag is stored in the main information block chain, and the block identifier in the main information block chain is stored in the tag block chain corresponding to each first advertisement tag, because the storage of the advertisement is much less than the amount of the user, the calculation amount of the advertisement pre-processing is significantly less than the recommendation calculation of each subsequent user. At the moment, if advertisement recommendation of a user is needed, obtaining a user information tag of the user to be recommended, quickly traversing the user information tag to obtain a corresponding tag block chain, and then selecting and recommending advertisements according to probability values corresponding to advertisement brands, preset recommendation numbers and block identifications, so that the user can receive advertisements which are more interesting, and the advertisement recommendation of the invention can improve the advertisement recommendation effect while reducing the advertisement recommendation cost; meanwhile, random selection is added when the information to be recommended is selected according to the probability value to be recommended, so that advertisement recommendation has more diversity and possibility.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (10)
1. An advertisement recommendation method based on a block chain is characterized by comprising the following steps:
s1, acquiring a first advertisement, obtaining an advertisement brand of the first advertisement, and collecting a plurality of advertisement labels corresponding to the advertisement brand and an advertisement weight value of each advertisement label;
s2, generating a main information block from the first advertisement and storing the main information block into a main information block chain, and acquiring a block identifier of the main information block in the main information block chain;
s3, using the block identifier of the main information block in the main information block chain as the block content to generate tag blocks, storing the tag blocks into the tag block chain corresponding to each first advertisement tag, and using the advertisement weight value of the advertisement tag as the advertisement weight value of the block identifier corresponding to the first advertisement, where each tag block chain corresponds to an advertisement tag;
s4, obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are information of interest of the users obtained according to historical access data of the users;
s5, selecting a block identification to be recommended with a preset number of recommendations according to the probability value to be recommended, acquiring a corresponding advertisement to be recommended from the main information block chain according to the block identification to be recommended, and pushing the advertisement to be recommended to the user to be recommended according to a preset pushing requirement.
2. The method for recommending advertisement based on blockchain according to claim 1, wherein said step S5 specifically includes the following steps:
s51, marking the block identification mark with the probability value to be recommended being larger than or equal to a first preset value in all the tag block chains to be recommended as recommended, marking the block identification mark with the probability value to be recommended being smaller than the first preset value and larger than or equal to a second preset value in all the tag block chains to be recommended as recommended waiting, and marking all the block identification marksThe block identification mark of the block chain of the tag to be recommended, in which the probability value to be recommended is smaller than the second preset value, is not recommended, and the first preset value is (0.6P)max，0.9Pmax) The second predetermined value is (0.2P)max，0.4Pmax) Said P ismaxThe value is the maximum value in the probability value to be recommended;
s52, judging whether the number of the block identifications marked as recommendation meets the preset recommendation number, if so, randomly selecting the block identifications with the preset recommendation number from the block identifications marked as recommendation as block identifications to be recommended, and then executing a step S54, if not, executing a step S53;
s53, taking the block identifications marked as recommendation as block identifications to be recommended, obtaining the residual recommendation number according to the preset recommendation number and the block identifications to be recommended, selecting the block identifications with the residual recommendation number from the block identifications marked as recommendation waiting as the block identifications to be recommended, and then executing the step S54;
s54, acquiring a corresponding advertisement to be recommended from the main information block chain according to the block identification to be recommended, and pushing the advertisement to be recommended to the user to be recommended according to a preset pushing requirement.
3. The method of claim 2, wherein the step S3 specifically includes the following steps:
s31, using the advertisement brand of the first advertisement and the block identification of the main information block in the main information block chain as block content to generate tag blocks, respectively storing the tag blocks into the tag block chain corresponding to each first advertisement tag, and using the advertisement weight value of the advertisement tag as the advertisement weight value of the block identification corresponding to the first advertisement, wherein each tag block chain corresponds to one advertisement tag;
s32, determining whether the advertisement brand of the previous tag tile in the tag tile chain is the same as the advertisement brand of the newly generated tag tile, if so, modifying a position symbol corresponding to the previous tag tile on the tag sequence corresponding to the tag tile chain to be an invalid tag, and then executing step S33, otherwise, directly executing step S33, where each tag tile chain corresponds to a tag sequence sequentially corresponding to the arrangement order of each tag tile;
s33, newly adding a position symbol of a valid tag to a position corresponding to the newly generated tag tile on the tag sequence corresponding to the tag tile chain;
the step S4 specifically includes the following steps:
s41, obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, wherein the user information labels are user interest information obtained according to historical access data of the users;
s42, obtaining a pre-recommendation probability value of each effective block identifier in the block chain set to be recommended according to the user information weight value of each user information tag and the advertisement weight value of each effective block identifier of each effective tag in each block chain of the to-be-recommended tags in the block chain set to be recommended, and adding the pre-recommendation probability values of the same effective block identifier in the block chain set to be recommended to obtain the to-be-recommended probability value of each effective block identifier in the block chain set to be recommended.
4. The method of claim 2, wherein the first predetermined value is 0.8PmaxThe second preset value is 0.2Pmax。
5. The method for recommending advertisement based on blockchain according to claim 1, wherein said step S1 specifically includes the following steps:
the method comprises the steps of obtaining a first advertisement, obtaining an advertisement brand of the first advertisement, and collecting the first N advertisement labels corresponding to the advertisement brand and an advertisement weight value of each advertisement label, wherein N is (2, 10).
6. The method of claim 5, wherein N is 5.
7. The method for recommending advertisement based on blockchain according to claim 1, wherein said step S5 specifically includes the following steps:
sequentially selecting a preset recommendation number of block identifications to be recommended according to the probability value to be recommended from large to small, acquiring corresponding advertisements to be recommended from the main information block chain according to the block identifications to be recommended, and pushing the advertisements to be recommended to the user to be recommended according to a preset pushing requirement.
8. The method of claim 7, wherein the step S4 specifically includes the following steps:
the method comprises the steps of obtaining user information labels of users to be recommended, obtaining each label block chain corresponding to each user information label to obtain a block chain set to be recommended, obtaining a probability value to be recommended of each block label in the block chain set to be recommended according to a user information weight value of each user information label and an advertisement weight value and an advertisement score value of each block label in each block chain of the labels to be recommended under the block chain set to be recommended, wherein the user information labels are information of interest of the users obtained according to historical access data of the users, and the advertisement score value of each block label is a score average value received by an advertisement corresponding to the block label.
9. The method for recommending advertisement based on blockchain according to claim 8, wherein said step S4 further comprises the steps of:
if the advertisement score value of the block identifier is lower than a lowest threshold value, marking the block identifier of which the advertisement score value is lower than the lowest threshold value as not recommended.
10. A blockchain-based advertisement recommendation terminal comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that: the processor when executing the computer program performs the steps of a method for blockchain based advertisement recommendation according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011470195.8A CN112446743B (en) | 2020-12-14 | 2020-12-14 | Advertisement recommendation method and terminal based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011470195.8A CN112446743B (en) | 2020-12-14 | 2020-12-14 | Advertisement recommendation method and terminal based on block chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446743A true CN112446743A (en) | 2021-03-05 |
| CN112446743B CN112446743B (en) | 2023-07-25 |
Family
ID=74739868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011470195.8A Active CN112446743B (en) | 2020-12-14 | 2020-12-14 | Advertisement recommendation method and terminal based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446743B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609381A (en) * | 2021-07-13 | 2021-11-05 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090222316A1 (en) * | 2008-02-28 | 2009-09-03 | Yahoo!, Inc. | Method to tag advertiser campaigns to enable segmentation of underlying inventory |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN108764975A (en) * | 2018-05-13 | 2018-11-06 | 深圳纬目信息技术有限公司 | A kind of method of advertisement spreading and device based on block chain |
| US20200234380A1 (en) * | 2019-01-17 | 2020-07-23 | Shriniwas Dulori | System and method for smart community |
| CN111582913A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | Advertisement recommendation method and device |
| CN111667300A (en) * | 2020-05-18 | 2020-09-15 | 范国闯 | Automatic advertisement trading and putting method and system based on block chain intelligent contract |
| CN111767466A (en) * | 2020-09-01 | 2020-10-13 | 腾讯科技（深圳）有限公司 | Recommendation information recommendation method and device based on artificial intelligence and electronic equipment |
-
2020
- 2020-12-14 CN CN202011470195.8A patent/CN112446743B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090222316A1 (en) * | 2008-02-28 | 2009-09-03 | Yahoo!, Inc. | Method to tag advertiser campaigns to enable segmentation of underlying inventory |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN108764975A (en) * | 2018-05-13 | 2018-11-06 | 深圳纬目信息技术有限公司 | A kind of method of advertisement spreading and device based on block chain |
| US20200234380A1 (en) * | 2019-01-17 | 2020-07-23 | Shriniwas Dulori | System and method for smart community |
| CN111582913A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | Advertisement recommendation method and device |
| CN111667300A (en) * | 2020-05-18 | 2020-09-15 | 范国闯 | Automatic advertisement trading and putting method and system based on block chain intelligent contract |
| CN111767466A (en) * | 2020-09-01 | 2020-10-13 | 腾讯科技（深圳）有限公司 | Recommendation information recommendation method and device based on artificial intelligence and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609381A (en) * | 2021-07-13 | 2021-11-05 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
| CN113609381B (en) * | 2021-07-13 | 2023-12-12 | 杭州网易云音乐科技有限公司 | Work recommendation method, device, medium and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446743B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9710723B2 (en) | Context-based image recognition for consumer market research | |
| US8180667B1 (en) | Rewarding creative use of product placements in user-contributed videos | |
| US20130101209A1 (en) | Method and system for extraction and association of object of interest in video | |
| US10068237B2 (en) | Transmit an authentication mark | |
| CN104361503A (en) | Offline commodity sales volume information collecting method based on two-dimensional codes | |
| CN112580637B (en) | Text information identification method, text information extraction method, text information identification device, text information extraction device and text information extraction system | |
| US8972279B2 (en) | Matching audio advertisements to items on a shopping list in a mobile device | |
| CN104851028A (en) | Method and system for evaluating product on basis of tag | |
| CN112446743B (en) | Advertisement recommendation method and terminal based on block chain | |
| CN111582913B (en) | Advertisement recommendation method and device | |
| CN110347786B (en) | Semantic model tuning method and system | |
| CN111093101B (en) | Media file delivery method and device, storage medium and electronic device | |
| CN110969473B (en) | User tag generation method and device | |
| CN111831941A (en) | Two-dimensional code recognition method and device, storage medium and electronic device | |
| CN116664250A (en) | Content information recommendation method, device, server and storage medium | |
| CN116028708A (en) | Training method and device for recommendation model | |
| CN110674388A (en) | Mapping method and device for push item, storage medium and terminal equipment | |
| US20210124995A1 (en) | Selecting training symbols for symbol recognition | |
| CN107609559A (en) | A kind of recognition methods and system based on VR anti-counterfeiting technologies | |
| CN115456711A (en) | Commodity information pushing method and device based on block chain technology and readable medium | |
| CN110611848A (en) | Information processing method, system, terminal, server and readable storage medium | |
| CN111681057A (en) | Method and device for processing media resource for information delivery | |
| CN111507773A (en) | Coupon management method, device and storage medium | |
| CN110427513A (en) | Picture recommendation method and system | |
| CN111159314B (en) | Electronic tag association method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |