CN109272360B - Intelligent advertisement recommendation method, system and device - Google Patents
Intelligent advertisement recommendation method, system and device Download PDFInfo
- Publication number
- CN109272360B CN109272360B CN201811139588.3A CN201811139588A CN109272360B CN 109272360 B CN109272360 B CN 109272360B CN 201811139588 A CN201811139588 A CN 201811139588A CN 109272360 B CN109272360 B CN 109272360B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- recommendation set
- user
- rule
- advertisement recommendation
- 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
- 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
- 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
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses an advertisement recommendation method and system, which comprises the following steps: receiving HTTP request information of a user; screening advertisements according to a preset rule to obtain a first recommendation set; screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set; and pushing the ordered second advertisement recommendation set to the user. Therefore, when the advertisement is recommended to the user, the advertisement putting effect is considered, and the maximization of the benefit is ensured.
Description
Technical Field
The invention relates to the field of advertisement recommendation, in particular to an advertisement recommendation method, system and device.
Background
With the development of internet technology, the proportion of advertisers selecting advertisement delivery on the internet gradually increases, and when users click on the information, the users jump to a specific advertisement page.
At present, in order to push advertisements to users more specifically, advertisement recommendation technologies are rapidly developed, but advertisement recommendation technologies in the prior art generally push advertisements to users according to user history records, but do not consider advertisement delivery effects, and cannot guarantee maximization of advertisement benefits.
Disclosure of Invention
In view of this, the embodiment of the invention discloses an advertisement recommendation method and system, which solve the problem that advertisement benefit maximization cannot be ensured because the advertisement delivery effect is not considered in the advertisement recommendation process in the prior art.
The invention discloses an intelligent advertisement recommendation method, which comprises the following steps:
receiving HTTP request information of a user;
screening advertisements according to a preset rule to obtain a first recommendation set;
screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set;
and pushing the ordered second advertisement recommendation set to the user.
Optionally, the screening and sorting the advertisements in the advertisement recommendation set according to the advertisement delivery effects in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, including:
determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
determining a sequencing rule of the user according to a preset flow distribution rule;
if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set.
Optionally, the sorting the advertisement effect according to the user characteristic and the advertisement characteristic includes:
determining weights of the user features and advertisement features included in the fourth advertisement recommendation set;
and sequencing the fourth advertisement recommendation set according to the weight of each user characteristic and the weight of each advertisement characteristic.
Optionally, the method further includes:
acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
Optionally, the method further includes:
and determining the delivery effect of the target advertisement according to the response behavior of the user to the target advertisement.
Optionally, the method further includes:
generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
The embodiment of the invention also discloses an intelligent advertisement recommendation system, which comprises:
the advertisement clicking server is used for receiving HTTP request information of a user and sending an ordered advertisement recommendation set request to the dynamic advertisement pool;
the dynamic advertisement pool is used for screening advertisements according to a preset rule to obtain a first recommendation set;
and the advertisement sorting server is used for screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, and sending the ordered second advertisement recommendation set to the advertisement click server through the dynamic advertisement pool.
Optionally, the advertisement ranking server is specifically configured to:
determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
determining a sequencing rule of the user according to a preset flow distribution rule;
if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set.
Optionally, the dynamic advertisement pool is further used for updating advertisements and off-shelf advertisements.
Optionally, the method further includes:
the smart advertisement generating server is used for generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
Optionally, the method further includes:
an advertisement settlement server and an effect database;
the advertisement settlement server is used for acquiring the response behavior of the user to the advertisement and sending the response behavior to the effect database;
the effectiveness database stores the response behavior of the user to the advertisement.
The embodiment of the invention also discloses an intelligent advertisement recommending device, which comprises:
a receiving user request unit for receiving HTTP request information of a user;
the advertisement screening unit is used for screening advertisements according to a preset rule to obtain a first recommendation set;
the advertisement sorting unit is used for screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set;
and the advertisement recommending unit is used for pushing the ordered second advertisement recommendation set to the user.
Optionally, the sorting unit includes:
a first advertisement putting effect determining subunit, configured to determine an advertisement putting effect of each advertisement in the first advertisement recommendation set;
the classification unit is used for classifying the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
a sorting rule determining unit, configured to determine a sorting rule of the user according to a preset traffic distribution rule;
the first sequencing subunit is configured to, if the determined user sequencing rule is a first rule, sequence the third advertisement recommendation set based on an advertisement delivery effect to obtain an ordered fifth advertisement recommendation set;
and the second sorting subunit is used for sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set if the determined sorting rule of the user is the second rule.
Optionally, the method further includes:
the storage unit is used for acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
Optionally, the method further includes:
and the second advertisement putting effect determining unit is used for determining the putting effect of the target advertisement according to the response behavior of the user to the target advertisement.
The invention also discloses a computer-readable storage medium, on which a computer program is stored, which computer program controls, when running, an apparatus on which the storage medium is located to perform the steps of the advertisement recommendation method according to any one of claims 1-6.
The invention also discloses computer equipment, which comprises a memory and a processor; the memory stores a computer program which, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.
The embodiment of the invention discloses an intelligent advertisement recommendation method, a system and a device, comprising the following steps: receiving HTTP request information of a user; screening advertisements according to a preset rule to obtain a first recommendation set; screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set; and pushing the ordered second advertisement recommendation set to the user. Therefore, when the advertisement is recommended to the user, the advertisement putting effect is considered, and the maximization of the benefit is ensured.
In addition, by sequencing the advertisements by adopting the feature matching rules, the preset weight and the advertisement putting effect, the benefit maximization is ensured, and the dynamic update of the advertisements is also ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart illustrating an advertisement recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for ordering advertisements according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram illustrating an advertisement recommendation system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating another structure of an advertisement recommendation system according to an embodiment of the present invention;
FIG. 5 is an interaction diagram of an advertisement recommendation system according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an advertisement recommendation apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram illustrating an advertisement recommendation device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart of an advertisement recommendation method provided in an embodiment of the present invention is shown, where the method includes:
s101: receiving HTTP request information of a user;
in this embodiment, when the user clicks a web page, the user terminal device sends an HTTP request to the server, and the server receives the HTTP request sent by the device terminal.
The received HTTP request of the user may be an HTTP request sent by one user or multiple users.
In this embodiment, after receiving the HTTP request information of the user, the feature information of the user may also be acquired. The user characteristic information includes: device information, geographic location information, source media, historical behavior, and the like.
S102: screening advertisements according to a preset rule to obtain a first recommendation set;
in this embodiment, the rules for screening advertisements may include multiple types, and a technician may set the rules according to actual situations, which is not limited in this embodiment. For example, it may include: user-advertisement feature matching based screening, manual rule based screening and risk control based screening, target region law and regulation based screening, and the like.
The specific process of screening advertisements through the user-advertisement feature matching rule may include:
and matching the acquired user characteristics with the advertisement characteristics to determine the advertisement according with the user characteristics.
For example, the following steps are carried out: assume that the ad features of ad 1 include: the applicable area is as follows: china, applicable people: age 18 or older, category: a game class; the advertising features of advertisement 2 include: the applicable area is as follows: china, applicable people: age, category: a tool class; the advertising features of advertisement 3 include: the applicable area is as follows: uk, applicable age below 10 years, category: tools. The features of user a include: device location: china and age: visited historical advertising categories over 18 years old: and (6) playing the game. Therefore, by matching the user characteristics of the user a with the advertisement characteristics of the 3 advertisements, the advertisement 1 can be screened out as the recommended advertisement of the user a.
The advertisement characteristics are determined by the description information of the advertisement, and therefore, the embodiment further includes generating advertisement description information, where the description information includes a plurality of characteristics of the advertisement. The advertisement characteristics are applied when performing characteristic matching on the advertisement. Reference is made in particular to the above description.
For example, the following steps are carried out: the description information of a certain advertisement is only suitable for the advertisement of game class above 18 years old, and the game class is the characteristic of the advertisement if the advertisement is suitable above 18 years old.
Through the screening of S102, an unordered advertisement set can be obtained, and the advertisement set comprises advertisements which accord with preset rules.
S103: and screening and sorting the advertisements in the first advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set.
In this embodiment, after the screening in S102, an advertisement set that can be recommended to the user is obtained, but the advertisement set does not consider the advertisement delivery effect, and the advertisements fed back to the user are not always advertisement with good delivery effect.
The advertisement delivery effect may include a plurality of impact indicators, including: click-through rate, dwell time, and payment case, etc. The advertisement putting effect value can be calculated according to the putting indexes of the advertisement putting effect, and the advertisement putting effect value can be used for sequencing the advertisements recommended to the user.
However, the advertisements are continuously updated and off-shelf, and for the newly on-line advertisements, the advertisement putting effect is not verified, and the advertisements cannot be sequenced according to the advertisement putting effect.
Therefore, in order to cope with frequent advertisement updating and off-shelf under the condition of ensuring that the delivery effect is maximized, the advertisements are sorted by the following two implementation modes:
the first implementation mode comprises the following steps:
and for the advertisements which accord with the advertisement putting effect rules, sequencing the advertisements based on the putting effect of each advertisement.
The preset advertisement putting effect rule may be set by a technician according to an actual situation, and is not limited herein.
For example, the following steps are carried out: in the case that the advertisement delivery effect includes an expected advertisement delivery effect value (eCPM), an advertisement with the expected advertisement delivery effect value greater than a preset threshold may be specified as an advertisement that meets a preset advertisement delivery effect rule, and otherwise, an advertisement that does not meet the advertisement delivery effect rule.
In this embodiment, different advertisements have different advertisement delivery effects, and the advertisements are sorted according to the different advertisement delivery effects.
The advertisement putting effect according to which the advertisements are sequenced is obtained by sending the advertisements to the users and analyzing or calculating the response behaviors of the users to the advertisements.
The second embodiment:
ordering the advertisements which do not accord with the preset advertisement putting effect rule based on the characteristic matching rule;
in this embodiment, the feature matching rule used here is basically the same as the matching method of the user-advertisement features mentioned in S102, except that the feature matching rule in the second embodiment considers the weight of each feature, that is, each user feature and advertisement feature in the user-advertisement features used in the second embodiment has a corresponding weight value, and the specific second embodiment includes:
determining weights of the user features and advertisement features included in the fourth advertisement recommendation set;
and sequencing the fourth advertisement recommendation set according to the weight of each user characteristic and the weight of each advertisement characteristic.
The determination method of the weight value may include two of the following:
the first way is that before the advertisement is on line, the weights of different user characteristics and different advertisement characteristics are estimated through the verification of the advertisement effect;
the second method comprises the following steps: after the advertisement is on line, determining the advertisement putting effect through the response behavior of the user to the target advertisement, and determining the weights of different user characteristics and advertisement characteristics according to the advertisement putting effect.
Specifically, the method includes the following steps S201 to S205, that is, determining, according to a preset traffic distribution rule, which of the second embodiment and the first embodiment is applied to order the advertisement recommendation set for an HTTP request of a certain user:
s201: determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
s202: dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
s203: determining a sequencing rule of the user according to a preset flow distribution rule;
for example, the following steps are carried out: assuming a traffic ratio of 9:1, each user has a 90% chance to use the embodiment pair advertisement recommendation sets for ranking, and each user also has a 10% chance to use the embodiment pair advertisement recommendation sets for ranking.
S204: if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
s205: and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the characteristic matching rule to obtain an ordered sixth advertisement recommendation set.
The first rule corresponds to the first embodiment, and the second rule corresponds to the second embodiment.
In this embodiment, the advertisements can be sorted according to the known advertisement putting effect by the first embodiment, that is, the advertisement with the better advertisement putting effect is arranged at the front position and preferentially recommended to the client, so that the maximization of the advertisement putting effect is ensured.
However, for newly online advertisements, since there is no advertisement putting effect and sequencing according to the advertisement putting effect cannot be performed, the advertisement putting effect needs to be verified first, and this part of advertisements can be divided into the fourth advertisement recommendation set, and is pushed to the user after being sequenced in a feature matching manner. Therefore, the advertisement effect can be pushed to the user under the condition that the new online advertisement with the advertisement effect does not exist, and the advertisement effect of the advertisement can be determined according to the response information of the client to the advertisement after the advertisement effect is pushed to the client.
Therefore, the ranking method of the second embodiment can search or verify the advertisement placement effect. After the advertisement putting effect is obtained, the advertisements are sequenced according to the advertisement putting effect, namely the advertisements which are allocated to the third advertisement set before are allocated to the fourth advertisement set after the advertisement putting effect is determined, and under the condition that the advertisement putting effect meets the preset condition, if the advertisements are recommended later, the advertisements are allocated to the fourth advertisement set.
In this embodiment, after the advertisement is pushed to the user, the response behavior of the user to the advertisement is recorded, the advertisement delivery effect can be determined according to the response behavior of the user to the advertisement, and the advertisement delivery effect is applied to the subsequent advertisement ranking. Wherein the response action of the user to the advertisement comprises: click information, conversion information, subscription information, and the like, which may specifically include: advertisement subscription, application download, registration, recharge, etc.
The embodiment of the invention discloses an advertisement recommendation method, which comprises the following steps: receiving HTTP request information of a user; screening advertisements according to a preset rule to obtain a first recommendation set; screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set; and pushing the ordered second advertisement recommendation set to the user. Therefore, when the advertisement is recommended to the user, the advertisement putting effect is considered, and the maximization of the benefit is ensured.
In addition, the advertisements are sequenced simultaneously in a mode based on the characteristic matching rules and the advertisement putting effect, so that the benefit maximization is ensured, and the support for the dynamic updating of the advertisements is also ensured.
Referring to fig. 3 to fig. 4, schematic structural diagrams of an advertisement recommendation system according to an embodiment of the present invention are shown, in this embodiment, the system includes:
an advertisement click server 301 for receiving HTTP request information of a user;
the dynamic advertisement pool 302 is used for screening advertisements according to a preset rule to obtain a first recommendation set;
and the advertisement sorting server 303 is configured to screen and sort the advertisements in the advertisement recommendation set according to the advertisement delivery effects in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, and send the ordered second advertisement recommendation set to the advertisement click server.
Optionally, the dynamic advertisement pool is further used for updating advertisements and off-shelf advertisements.
Optionally, smartlink advertisement generating server 304 is configured to generate advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
Optionally, the method further includes:
an advertisement settlement server 305 and an effect database 306;
the advertisement settlement server is used for acquiring the response behavior of the user to the advertisement and sending the response behavior information to the effect database;
the effectiveness database stores the response behavior of the user to the advertisement.
Through the system of the embodiment, the advertisement click server receives HTTP request information of a user and sends an ordered advertisement recommendation set request to the dynamic advertisement pool; the method comprises the steps that a dynamic advertisement pool screens advertisements according to preset rules to obtain a first recommendation set, and sends a request to an advertisement sequencing server; the advertisement sorting server screens and sorts the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set; and pushing the ordered second advertisement recommendation set to the user. Therefore, when the advertisement is recommended to the user, the advertisement putting effect is considered, and the maximization of the benefit is ensured.
And the advertisement sequencing server sequences the advertisements simultaneously by means of a characteristic matching rule-based mode and an advertisement putting effect-based mode, thereby ensuring the maximum benefit and simultaneously ensuring the dynamic update of the advertisements.
In this embodiment, in order to more clearly introduce the functions that can be implemented by each server in the advertisement recommendation system, each server is described in detail, specifically, referring to fig. 5, the functions of each server of the advertisement recommendation system and a specific process of advertisement recommendation are shown:
smartlink advertisement generation server 401: descriptive information for the advertisement is generated, the descriptive information including at least one characteristic of the advertisement.
Wherein the description information includes: required delivery regions, required delivery equipment, required delivery user population, required delivery user characteristics, price settlement rules, risk control rules, information transfer rules, and the like.
The advertisement click server 402: receiving an HTTP request of a user and collecting characteristic information of the user; after receiving the HTTP request, sending an ordered advertisement recommendation set request to the dynamic advertisement pool, namely requiring to return an ordered advertisement set (or ordered advertisement list); after receiving the ordered advertisement set, one (unit advertisement space) or a plurality of (a plurality of) advertisement jumps are carried out to guide the user to enter the advertisement page.
Wherein, the characteristic information of the user comprises: device information, geographic information, source media, historical behavior, and the like.
Also, in order to respond to speed and availability, ad click servers are typically distributed globally, providing a multi-node server.
Dynamic advertisement pool 403:
the management of the online advertisement is realized, which comprises the following steps: accessing new advertisements, namely updating advertisements, off-shelf advertisements and the like;
providing an advertisement screening function, and screening advertisements according to a preset rule after receiving an ordered advertisement recommendation set request sent by an advertisement click server to obtain a first recommendation set;
the preset rule may be preset by a technician, and is not limited in this example, and includes: user-advertisement feature matching based screening, manual rule based screening and risk control based screening, target region law and regulation based screening, and the like.
And after the unordered first advertisement recommendation set is obtained, a request is sent to the ordering server.
The advertisement ranking server 404: and screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, and sending the ordered second advertisement recommendation set to the dynamic advertisement pool so that the dynamic advertisement pool sends the second advertisement recommendation set to the advertisement click server.
The advertisement settlement server 405: and after the advertisement is pushed to the user, acquiring the response behavior of the user to the advertisement, and sending the response behavior to the effect database for storage.
The effectiveness database 406 stores the received response behavior of the user to the advertisement.
In the embodiment, the advertisement click server receives HTTP request information of a user and sends an ordered advertisement recommendation set request to the dynamic advertisement pool; the method comprises the steps that a dynamic advertisement pool screens advertisements according to preset rules to obtain a first recommendation set, and sends a request to an advertisement sequencing server; the advertisement sorting server screens and sorts the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set; and pushing the ordered second advertisement recommendation set to the user. Therefore, when the advertisements are recommended, the advertisement putting effect is considered, and the maximization of the benefit is ensured.
And the advertisement sequencing server sequences the advertisements simultaneously in a mode based on the characteristic matching rule and the advertisement putting effect, thereby ensuring the maximum benefit and simultaneously ensuring the dynamic update of the advertisements.
Referring to fig. 6, a schematic structural diagram of an advertisement recommendation apparatus according to an embodiment of the present invention is shown, in this embodiment, the apparatus includes:
a user request receiving unit 501, configured to receive HTTP request information of a user;
the advertisement screening unit 502 is configured to screen advertisements according to a preset rule to obtain a first recommendation set;
the advertisement sorting unit 503 is configured to screen and sort the advertisements in the advertisement recommendation set according to the advertisement delivery effects in the first advertisement recommendation set, so as to obtain an ordered second advertisement recommendation set;
and an advertisement recommending unit 504, configured to push the ordered second advertisement recommendation set to the user.
Optionally, the sorting unit includes:
a first advertisement putting effect determining subunit, configured to determine an advertisement putting effect of each advertisement in the first advertisement recommendation set;
the classification unit is used for classifying the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
a sorting rule determining unit, configured to determine a sorting rule of the user according to a preset traffic distribution rule;
the first sequencing subunit is configured to, if the determined user sequencing rule is a first rule, sequence the third advertisement recommendation set based on an advertisement delivery effect to obtain an ordered fifth advertisement recommendation set;
and the second sorting subunit is used for sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set if the determined sorting rule of the user is the second rule.
Optionally, the second sorting subunit includes:
a weight determining subunit, configured to determine weights of the user features and advertisement features included in the fourth advertisement recommendation set;
and the third sorting subunit is used for sorting the fourth advertisement recommendation set according to the weight of each user characteristic and the weight of each advertisement characteristic.
Optionally, the method further includes:
the storage unit is used for acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
Optionally, the method further includes:
and the second advertisement putting effect determining unit is used for determining the putting effect of the target advertisement according to the response behavior of the user to the target advertisement.
Optionally, the method further includes:
an advertisement description information generating unit for generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
Through the device of the embodiment, when the advertisement is recommended to the user, the advertisement putting effect is considered, and the maximization of the benefit is ensured. In addition, by sequencing the advertisements by adopting the feature matching rules, the preset weight and the advertisement putting effect, the benefit maximization is ensured, and the dynamic update of the advertisements is also ensured.
The advertisement recommending device comprises a processor and a memory, wherein the user request receiving unit, the advertisement sequencing unit, the advertisement recommending unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and advertisement recommendation is realized by adjusting kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The embodiment of the invention provides a computer-readable storage medium, wherein a program is stored on the storage medium, and the computer program controls equipment where the storage medium is located to execute the steps of the advertisement recommendation method when running.
The embodiment of the invention provides a processor, which is used for running a program, wherein the advertisement recommendation method is executed when the program runs.
Referring to fig. 7, a schematic structural diagram of a computer device disclosed in the embodiment of the present invention is shown, including a memory 601 and a processor 602; the memory stores a computer program, wherein the processor 602 executes the computer program to perform the following steps:
receiving HTTP request information of a user;
screening advertisements according to a preset rule to obtain a first recommendation set;
screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set;
and pushing the ordered second advertisement recommendation set to the user.
Optionally, the screening and sorting the advertisements in the advertisement recommendation set according to the advertisement delivery effects in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, including:
determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the delivery effect of each advertisement in the third advertisement recommendation set meets a preset condition;
determining a sequencing rule of the user according to a preset flow distribution rule;
if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set.
Optionally, the sorting the advertisement effect according to the user characteristic and the advertisement characteristic includes:
determining weights of the user features and advertisement features included in the fourth advertisement recommendation set;
and sequencing the fourth advertisement recommendation set according to the weight of each user characteristic and the weight of each advertisement characteristic.
Optionally, the method further includes:
acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
Optionally, the method further includes:
and determining the delivery effect of the target advertisement according to the response behavior of the user to the target advertisement.
Optionally, the method further includes:
generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (14)
1. An intelligent advertisement recommendation method is characterized by comprising the following steps:
receiving HTTP request information of a user;
screening advertisements according to a preset rule to obtain a first advertisement recommendation set;
screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set;
pushing the ordered second advertisement recommendation set to the user;
wherein, the screening and sorting of the advertisements in the advertisement recommendation set according to the advertisement delivery effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set includes:
determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the advertisement putting effect value of each advertisement in the third advertisement recommendation set is greater than a preset threshold, and the advertisements in the third advertisement recommendation set have influence indexes used for calculating the advertisement putting effect, wherein the influence indexes comprise click rate, stay time and payment condition;
determining a sequencing rule of the user according to a preset flow distribution rule;
if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set.
2. The method of claim 1, wherein the ranking the fourth set of advertisement recommendations according to feature matching rules and preset weights comprises:
determining weights of the user features and advertisement features included in the fourth advertisement recommendation set;
and sequencing the fourth advertisement recommendation set according to the weight of each user characteristic and the weight of each advertisement characteristic.
3. The method of claim 1, further comprising:
acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
4. The method of claim 3, further comprising:
and determining the delivery effect of the target advertisement according to the response behavior of the user to the target advertisement.
5. The method of claim 1, further comprising:
generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
6. An intelligent advertisement recommendation system, comprising:
the advertisement clicking server is used for receiving HTTP request information of a user and sending an ordered advertisement recommendation set request to the dynamic advertisement pool;
the dynamic advertisement pool is used for screening advertisements according to a preset rule to obtain a first advertisement recommendation set;
the advertisement sorting server is used for screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set, and sending the ordered second advertisement recommendation set to the advertisement clicking server through the dynamic advertisement pool;
wherein the advertisement ranking server is specifically configured to:
determining the advertisement putting effect of each advertisement in the first advertisement recommendation set;
dividing the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the advertisement putting effect value of each advertisement in the third advertisement recommendation set is greater than a preset threshold, and the advertisements in the third advertisement recommendation set have influence indexes used for calculating the advertisement putting effect, wherein the influence indexes comprise click rate, stay time and payment condition;
determining a sequencing rule of the user according to a preset flow distribution rule;
if the determined ordering rule of the user is a first rule, ordering the third advertisement recommendation set based on advertisement putting effect to obtain an ordered fifth advertisement recommendation set;
and if the determined sorting rule of the user is a second rule, sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set.
7. The system of claim 6, wherein the dynamic advertisement pool is further configured to update advertisements and off-shelf advertisements.
8. The system of claim 6, further comprising:
the smart advertisement generating server is used for generating advertisement description information; the advertisement description information includes a plurality of characteristics of the advertisement.
9. The system of claim 6, further comprising:
an advertisement settlement server and an effect database;
the advertisement settlement server is used for acquiring the response behavior of the user to the advertisement and sending the response behavior to the effect database;
the effectiveness database stores the response behavior of the user to the advertisement.
10. An intelligent advertisement recommendation device, comprising:
a receiving user request unit for receiving HTTP request information of a user;
the advertisement screening unit is used for screening advertisements according to a preset rule to obtain a first advertisement recommendation set;
the advertisement sorting unit is used for screening and sorting the advertisements in the advertisement recommendation set according to the advertisement putting effect in the first advertisement recommendation set to obtain an ordered second advertisement recommendation set;
the advertisement recommending unit is used for pushing the ordered second advertisement recommending set to the user;
wherein the sorting unit includes:
a first advertisement putting effect determining subunit, configured to determine an advertisement putting effect of each advertisement in the first advertisement recommendation set;
the classification unit is used for classifying the first advertisement recommendation set into two types according to the advertisement putting effect to obtain a third advertisement recommendation set and a fourth advertisement recommendation set; the advertisement putting effect value of each advertisement in the third advertisement recommendation set is greater than a preset threshold, and the advertisements in the third advertisement recommendation set have influence indexes used for calculating the advertisement putting effect, wherein the influence indexes comprise click rate, stay time and payment condition;
a sorting rule determining unit, configured to determine a sorting rule of the user according to a preset traffic distribution rule;
the first sequencing subunit is configured to, if the determined user sequencing rule is a first rule, sequence the third advertisement recommendation set based on an advertisement delivery effect to obtain an ordered fifth advertisement recommendation set;
and the second sorting subunit is used for sorting the fourth advertisement recommendation set according to the feature matching rule and a preset weight to obtain an ordered sixth advertisement recommendation set if the determined sorting rule of the user is the second rule.
11. The apparatus of claim 10, further comprising:
the storage unit is used for acquiring and storing the response behavior of the user to the target advertisement; the target advertisement is any one advertisement.
12. The apparatus of claim 11, further comprising:
and the second advertisement putting effect determining unit is used for determining the putting effect of the target advertisement according to the response behavior of the user to the target advertisement.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed, controls an apparatus in which the storage medium is located to carry out the steps of the method according to any one of claims 1-5.
14. A computer device comprising a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811139588.3A CN109272360B (en) | 2018-09-28 | 2018-09-28 | Intelligent advertisement recommendation method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811139588.3A CN109272360B (en) | 2018-09-28 | 2018-09-28 | Intelligent advertisement recommendation method, system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109272360A CN109272360A (en) | 2019-01-25 |
| CN109272360B true CN109272360B (en) | 2021-09-10 |
Family
ID=65198239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811139588.3A Active CN109272360B (en) | 2018-09-28 | 2018-09-28 | Intelligent advertisement recommendation method, system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109272360B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298625A (en) * | 2019-05-22 | 2019-10-01 | 菜鸟智能物流控股有限公司 | Logistics data processing method, device, equipment and storage medium |
| CN110223110A (en) * | 2019-05-27 | 2019-09-10 | 浙江华坤道威数据科技有限公司 | A kind of DSP advertisement analysis system based on big data |
| CN110473026A (en) * | 2019-08-22 | 2019-11-19 | 中山职业技术学院 | A kind of Combined advertisement method for pushing |
| CN110796477A (en) * | 2019-09-23 | 2020-02-14 | 北京三快在线科技有限公司 | Advertisement display method and device, electronic equipment and readable storage medium |
| CN111079000B (en) * | 2019-11-25 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Content processing method, device, equipment and storage medium |
| CN111949527A (en) * | 2020-08-05 | 2020-11-17 | 北京字节跳动网络技术有限公司 | Game video testing method, device, equipment and storage medium |
| CN114334073A (en) * | 2020-09-28 | 2022-04-12 | 卫宁健康科技集团股份有限公司 | Medicine distribution mode recommendation method and device |
| CN118246987B (en) * | 2024-05-29 | 2024-08-02 | 泉州市丰泽区三旭网络科技有限公司 | Advertisement delivery position management system based on delivery effect analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
| CN102521767A (en) * | 2011-12-13 | 2012-06-27 | 亿赞普(北京)科技有限公司 | Method and system for publishing network advertising information |
| WO2013017307A1 (en) * | 2011-08-02 | 2013-02-07 | Qatar Foundation | Advertising matching |
| CN104112210A (en) * | 2013-04-17 | 2014-10-22 | 华为技术有限公司 | Advertisement pushing method and device |
| CN106952112A (en) * | 2017-03-01 | 2017-07-14 | 心触动（武汉）文化传媒有限公司 | A kind of method for delivering advertisement accurately and system |
| CN107679883A (en) * | 2017-05-05 | 2018-02-09 | 平安科技（深圳）有限公司 | The method and system of advertisement generation |
| CN108230026A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7840438B2 (en) * | 2005-07-29 | 2010-11-23 | Yahoo! Inc. | System and method for discounting of historical click through data for multiple versions of an advertisement |
| CN101146260A (en) * | 2007-10-19 | 2008-03-19 | 吕利勇 | Mobile phone advertisement distribution system and method |
| CN102592235A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertisement serving system |
| US20160188734A1 (en) * | 2014-12-30 | 2016-06-30 | Socialtopias, Llc | Method and apparatus for programmatically synthesizing multiple sources of data for providing a recommendation |
| CN105678587B (en) * | 2016-01-12 | 2020-11-24 | 腾讯科技（深圳）有限公司 | Recommendation feature determination method, information recommendation method and device |
| CN105956161B (en) * | 2016-05-17 | 2019-07-02 | 北京奇虎科技有限公司 | A kind of information recommendation method and device |
-
2018
- 2018-09-28 CN CN201811139588.3A patent/CN109272360B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013017307A1 (en) * | 2011-08-02 | 2013-02-07 | Qatar Foundation | Advertising matching |
| CN102346899A (en) * | 2011-10-08 | 2012-02-08 | 亿赞普(北京)科技有限公司 | Method and device for predicting advertisement click rate based on user behaviors |
| CN102521767A (en) * | 2011-12-13 | 2012-06-27 | 亿赞普(北京)科技有限公司 | Method and system for publishing network advertising information |
| CN104112210A (en) * | 2013-04-17 | 2014-10-22 | 华为技术有限公司 | Advertisement pushing method and device |
| CN106952112A (en) * | 2017-03-01 | 2017-07-14 | 心触动（武汉）文化传媒有限公司 | A kind of method for delivering advertisement accurately and system |
| CN107679883A (en) * | 2017-05-05 | 2018-02-09 | 平安科技（深圳）有限公司 | The method and system of advertisement generation |
| CN108230026A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
Non-Patent Citations (2)
| Title |
|---|
| Multimodal Content Analysis for Effective Advertisements on YouTube;Nikhita Vedula;《https://arxiv.org/pdf/1709.03946.pdf》;20170912;全文 * |
| 美团点评联盟广告场景化定向排序机制;马莹 一凡;《https://tech.meituan.com/2017/12/04/targeting-agentscore.html》;20171204;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109272360A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272360B (en) | Intelligent advertisement recommendation method, system and device | |
| US10348550B2 (en) | Method and system for processing network media information | |
| CN105550903B (en) | Target user determination method and device | |
| US20210049622A1 (en) | Marketing method and apparatus based on deep reinforcement learning | |
| JP5904766B2 (en) | System and method for providing recommended keywords | |
| US8666809B2 (en) | Advertisement campaign simulator | |
| US20070198937A1 (en) | Method for determining a profile of a user of a communication network | |
| US20090216620A1 (en) | Method and system for providing targeting advertisement service in social network | |
| CN103295147A (en) | Method, device and system for advertising | |
| US20140358694A1 (en) | Social media pricing engine | |
| CN101071437A (en) | User classifying method, directional advertising launching method, device and system | |
| CN112148992B (en) | Content pushing method, device, computer equipment and storage medium | |
| US20110196690A1 (en) | Method and system of selecting landing pages and optimizing routing efficiency | |
| US20170032430A1 (en) | List-based advertisement serving | |
| CN109903076A (en) | A kind of ad data generation method, system, electronic equipment and storage medium | |
| US20150227963A1 (en) | Systems, methods, and apparatus for budget allocation | |
| CN114357292B (en) | Model training method, device and storage medium | |
| US20240177184A1 (en) | Self-learning valuation and access to digital content | |
| CN111460301A (en) | Object pushing method and device, electronic equipment and storage medium | |
| CN113139826A (en) | Method and device for determining distribution authority of advertisement space and computer equipment | |
| CN104025086A (en) | Triggering social pages | |
| CN114266592A (en) | Distribution method, distribution device, equipment and medium of advertisement materials | |
| CN111260416B (en) | Method and device for determining associated user of object | |
| CN111652471A (en) | List distribution control method and device, electronic equipment and storage medium | |
| CN114925261A (en) | Keyword determination method, apparatus, device, storage medium and program product |
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 |