CN112734504B - Intelligent traffic routing method, device and system - Google Patents
Intelligent traffic routing method, device and system Download PDFInfo
- Publication number
- CN112734504B CN112734504B CN202110359494.2A CN202110359494A CN112734504B CN 112734504 B CN112734504 B CN 112734504B CN 202110359494 A CN202110359494 A CN 202110359494A CN 112734504 B CN112734504 B CN 112734504B
- Authority
- CN
- China
- Prior art keywords
- flow
- advertisement
- engine
- module
- information
- 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
- G06Q30/0273—Determination of fees for advertising
- G06Q30/0275—Auctions
-
- 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
- G06Q30/0252—Targeted advertisements based on events or environment, e.g. weather or festivals
-
- 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
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (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)
- Environmental & Geological Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and a system for intelligently routing traffic, which belong to the technical field of Internet change, in particular to an intelligent traffic routing system, comprising the following steps: the intelligent routing algorithm engine is used for acquiring environment information to be analyzed in real time, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid and the click rate, the conversion rate and the life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow; a bidding engine for purchasing traffic in a bidding manner; and the price inquiry engine is used for outputting and selling the residual flow. The invention adopts an artificial intelligence mode to dynamically distribute and route the flow, thereby greatly improving the working efficiency, saving the time cost and improving the reaction mechanism.
Description
Technical Field
The invention belongs to the technical field of Internet change, and particularly relates to a method, a device and a system for intelligently routing traffic.
Background
With the development of internet digital advertisements, an advertisement Network alliance (Ad-Network) is connected with a plurality of traffic providers and can serve a plurality of traffic consumers, so that the development becomes a very successful mode.
The programmed buying and selling market in China is unprecedented, and as programmed buying is a bidding mode, an Internet advertisement trading platform (Ad Exchange) is connected with buyers and sellers of advertisement trading, namely an advertiser party and an advertisement slot owner, like a stock trading platform. Unlike the stock exchange, the bidding mechanism of the internet advertisement exchange is not first come and first come but bid acquisition, i.e., RTB (real time bidding) mode. The internet advertisement trading platform is a large market, and the problem of balance between flow supply and flow demand is solved to a great extent. Especially for a traditional advertisement network alliance, the method can be completely adjusted by an internet advertisement trading platform, and the balance problem of a supplier and a demander is perfectly solved.
The inventor finds that the traffic routing problem comes along after the advertising network alliance integrates the traffic and the advertising inventory into the large market of the internet advertising trading platform. The traditional method can only rely on an optimizer to manually and rigidly cut the flow, so that the problem of flow imbalance caused by high frequency in a small range is caused.
Disclosure of Invention
In order to at least solve the technical problem, the invention provides a traffic intelligent routing method, device and system.
According to a first aspect of the present invention, there is provided a traffic intelligent routing system, comprising:
the intelligent routing algorithm engine is used for acquiring environment information to be analyzed in real time, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid and the click rate, the conversion rate and the life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow;
the bidding engine is used for purchasing the flow in a bidding mode when the intelligent routing algorithm engine judges that the advertising network alliance needs to configure the flow;
and the price inquiry engine is used for outputting and selling the residual flow under the condition that the intelligent routing algorithm engine judges that the advertising network alliance does not need to configure the flow.
Further, the intelligent routing algorithm engine comprises an information intake module, a strategy configuration module, an AI module and a decision module.
Further, the information intake module is used for acquiring weather information of each city, major holidays at home and abroad, commercial holidays, contents and recent hotspots of released media, keywords of each major search list, and release situation information of advertisement creativity of each industry in real time, and the information is used as information to be analyzed of the environment.
Further, the policy configuration module is configured to configure weight and industry policy, including media and point locations sold with limited traffic, advertisement industry priority, industry information policy inclusion factor, and basic pairing policy during cold start period.
Further, the AI module is configured to use a machine learning manner to obtain a click rate, a conversion rate and a life cycle value by using the traffic feature data of each traffic request and the environment information to be analyzed as feature vectors through modeling calculation, and calculate the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid, the click rate, the conversion rate and the life cycle value.
Further, the judgment module is used for judging an operation mode according to the basic pairing strategy, the advertisement value and the flow of the advertisement network alliance, and triggering a bidding engine when the operation mode is judged to be the flow which needs to be configured by the advertisement network alliance; and triggering the price inquiry engine under the condition that the operation mode is judged to be the advertising network alliance and the flow does not need to be configured.
According to a second aspect of the present invention, a traffic intelligent routing method includes:
accessing a bidding engine, a price inquiring engine and an intelligent routing algorithm engine;
the method comprises the steps of acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid and click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, advertisement value and advertisement network alliance flow;
when the situation that the advertising network alliance needs to configure the flow is judged, purchasing the flow in a bidding mode by adopting a bidding engine;
and outputting and selling the residual flow by adopting an inquiry engine under the condition of judging that the advertisement network alliance does not need to configure the flow.
According to a third aspect of the present invention, an intelligent traffic routing device comprises:
the system comprises a setting module, a price inquiring engine and an intelligent routing algorithm engine, wherein the setting module is used for accessing the price bidding engine, the price inquiring engine and the intelligent routing algorithm engine;
the judging module is used for acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid, click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow;
the flow purchasing module is used for purchasing the flow in a bidding mode by adopting a bidding engine when the flow needs to be configured in the advertising network alliance is judged;
and the output module is used for outputting and selling the residual flow by adopting an inquiry engine under the condition that the flow does not need to be configured by the advertising network alliance.
According to a fourth aspect of the invention, a computer device comprises a memory, a processor and a computer program stored on the memory and executable on the processor,
the processor, when executing the program, performs the steps of the method as described above.
According to a fifth aspect of the present invention, a computer-readable storage medium stores a program which, when executed, is capable of implementing the method as described above.
The invention has the beneficial effects that: let the computer solve the dynamic distribution and the route of flow through big data and artificial intelligence, balanced flow supplier and flow demand side, solved the flow and supplied with and be greater than the demand, appear the problem of not filling enough, can in time carry out the flow for the developer and become present. The invention can also avoid the condition that the flow supply is less than the demand and the demand of the advertiser putting amount can not be met. In addition, the flow is dynamically distributed and routed in an artificial intelligence mode, so that the working efficiency can be greatly improved, the time cost is saved, and the reaction mechanism is improved.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which,
fig. 1 is a flow chart of an intelligent traffic routing method according to the present invention;
fig. 2 is a schematic structural diagram of an intelligent traffic routing system provided in the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of illustrating the present invention and are not to be construed as limiting the present invention.
In order to more clearly illustrate the invention, the invention is further described below with reference to preferred embodiments and the accompanying drawings. Similar parts in the figures are denoted by the same reference numerals. It is to be understood by persons skilled in the art that the following detailed description is illustrative and not restrictive, and is not to be taken as limiting the scope of the invention.
In a first aspect of the present invention, there is provided a traffic intelligent routing method, as shown in fig. 1, including:
step 201: accessing a bidding engine, a price inquiring engine and an intelligent routing algorithm engine;
in the invention, a bidding engine which can be accessed to the traffic of an Internet advertisement trading platform (Ad Exchange) is added on the basis of an advertisement network alliance system. An inquiry engine capable of solving the advertisement filling is added, and an intelligent routing algorithm engine for coordinating and commanding the self consumption of the flow, the flow supplement purchase or the operation of the advertisement filling is added.
Step 202: the method comprises the steps of acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid and click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, advertisement value and advertisement network alliance flow;
in the system with various flow sources and outputs, namely under the condition that a plurality of internet advertisement trading platforms and a DSP (digital signal processor) are connected to the upstream and downstream of flow supply and demand of an advertisement network alliance system, a supplier is formed to be composed of a plurality of media and a plurality of internet advertisement trading platforms, and a demand supplier is formed to be composed of an advertiser system, a plurality of internet advertisement trading platforms and a plurality of demand supplier platforms.
And acquiring contents including weather information of each city, major holidays of China and abroad, commercial holidays, contents of delivered media, recent hotspots, keywords of each major search list, advertisement creative delivery condition information of each industry and the like in real time by adopting an intelligent routing algorithm engine to serve as the information to be analyzed of the environment.
Further, the intelligent routing algorithm engine obtains an API, a crawler, a word segmentation and a semantic analysis algorithm according to a series of information related to the advertisement delivery environment, and obtains the following steps: weather information of each city, major holidays at home and abroad, commercial holidays, contents and recent hotspots of released media, keywords of each major search list, advertisement creative release condition information of each industry and the like are taken as environment information to be analyzed.
And according to the flow characteristic data of each flow request, combining the captured environment information to be analyzed as a characteristic vector, and performing modeling calculation by adopting a DeepFM algorithm to obtain the click rate, the conversion rate and the life cycle value.
In the invention, advertisement value (advale) = exposure price (cpmpice) + click value (clickvale) + conversion value (convertvale) + back-end conversion value (postvalue);
click value (ClickValue, hereinafter abbreviated as CV) = click value coefficient (α) × click rate (CTR);
conversion value (ConvertValue, hereinafter abbreviated as CvV) = conversion value coefficient (β) × conversion rate (CVR);
a back-end transformation value (hereinafter referred to as BV) = a back-end transformation coefficient (γ) × life cycle value (LTV);
this gives:
AdValue=CPMPrice+α×CTR+β×CvV+γ×LTV。
and according to the advertisement property and the advertisement owner appeal, the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient of different advertisements are different, and after the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient corresponding to the advertisement are obtained, the advertisement value is calculated according to the exposure bid of the advertisement owner, the click value coefficient, the conversion value coefficient, the rear-end conversion coefficient, the click rate, the conversion rate and the life cycle value.
Configuring weight and industry strategy, including media and point of sale with limited flow, advertisement industry priority, industry information strategy containing factor, and basic pairing strategy in cold starting period.
Step 203: when the situation that the advertising network alliance needs to configure the flow is judged, purchasing the flow in a bidding mode by adopting a bidding engine;
in the invention, a flow supplier is accessed, the flow of the internet advertisement trading platform can be accessed into the system, the flow of the advertisement network alliance is monitored in real time, and when the flow of the advertisement network alliance is monitored to be insufficient, a bidding engine is utilized to purchase the flow from the internet advertisement trading platform or SSP (Sell-Side platform, supplier platform) in a bidding mode.
In the invention, a bidding engine which can access the flow of an internet advertisement transaction platform is added on the basis of the advertisement network alliance which is easy to have wisdom. After the internet advertisement trading platform is accessed to the traffic, when the alliance traffic is insufficient, the traffic can be purchased from the internet advertisement trading platform or the supplier platform through bidding at any time.
In the invention, when the sufficient flow supply of the advertising network alliance is judged and the flow needs to be configured based on the basic pairing strategy and the advertising value, a bidding engine is adopted to acquire the flow suitable for the current advertisement. That is to say, even when the self traffic is sufficient, whether to adopt the traffic more suitable for the current advertisement can be judged according to the intelligent routing algorithm engine, so as to save the cost.
Step 204: and outputting and selling the residual flow by adopting an inquiry engine under the condition of judging that the advertisement network alliance does not need to configure the flow.
In the invention, a query engine is added on the basis of the advertisement network alliance system. When monitoring that the flow supply of the advertisement network alliance is excessive, namely the advertisement is not filled enough, the rest flow can be output to an internet advertisement trading platform or a DSP (demand-side platform) for selling, so that the benefit of a developer is ensured, and the economic income of the developer is increased.
According to a second aspect of the present invention, there is provided an intelligent traffic routing device, comprising:
the system comprises a setting module, a price inquiring engine and an intelligent routing algorithm engine, wherein the setting module is used for accessing the price bidding engine, the price inquiring engine and the intelligent routing algorithm engine;
in the invention, a bidding engine which can be accessed to the traffic of an Internet advertisement trading platform (Ad Exchange) is added on the basis of an advertisement network alliance system. An inquiry engine capable of solving the advertisement filling is added, and an intelligent routing algorithm engine for coordinating and commanding the self consumption of the flow, the flow supplement purchase or the operation of the advertisement filling is added.
The judging module is used for acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid, click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow;
in the system with various flow sources and outputs, namely under the condition that a plurality of internet advertisement trading platforms and a DSP (digital signal processor) are connected to the upstream and downstream of flow supply and demand of an advertisement network alliance system, a supplier is formed to be composed of a plurality of media and a plurality of internet advertisement trading platforms, and a demand supplier is formed to be composed of an advertiser system, a plurality of internet advertisement trading platforms and a plurality of demand supplier platforms.
And the judging module is used for acquiring the contents including weather information of each city, major holidays at home and abroad, commercial holidays, media delivery, recent hotspots, keywords of each major search list, advertisement creative delivery condition information of each industry and the like in real time by adopting an intelligent routing algorithm engine as the information to be analyzed of the environment.
And the judging module is also used for performing modeling calculation by adopting a DeepFM algorithm according to the flow characteristic data of each flow request and the taken environment information to be analyzed as characteristic vectors to obtain the click rate, the conversion rate and the life cycle value.
In the invention, advertisement value (advale) = exposure price (cpmpice) + click value (clickvale) + conversion value (convertvale) + back-end conversion value (postvalue);
click value (ClickValue, hereinafter abbreviated as CV) = click value coefficient (α) × click rate (CTR);
conversion value (ConvertValue, hereinafter abbreviated as CvV) = conversion value coefficient (β) × conversion rate (CVR);
a back-end transformation value (hereinafter referred to as BV) = a back-end transformation coefficient (γ) × life cycle value (LTV);
this gives:
AdValue=CPMPrice+α×CTR+β×CvV+γ×LTV。
and the judging module is also used for calculating the advertisement value according to the advertisement property and the advertiser appeal, the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient of different advertisements, and the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient corresponding to the advertisement, and the exposure bid of the advertiser, the click value coefficient, the conversion value coefficient, the rear-end conversion coefficient, the click rate, the conversion rate and the life cycle value.
The judgment module is also used for configuring the weight and the industry strategy, including the media and the point locations sold with limited flow, the advertisement industry priority, the industry information strategy containing factors and the basic pairing strategy in the cold start period.
The flow purchasing module is used for purchasing the flow in a bidding mode by adopting a bidding engine when the flow needs to be configured in the advertising network alliance is judged;
in the invention, a flow supplier is accessed, the flow of the internet advertisement trading platform can be accessed into the system, the flow of the advertisement network alliance is monitored in real time, and when the flow of the advertisement network alliance is monitored to be insufficient, a bidding engine is utilized to purchase the flow from the internet advertisement trading platform or SSP (Sell-Side platform, supplier platform) in a bidding mode.
In the invention, a bidding engine which can access the flow of an internet advertisement transaction platform is added on the basis of the advertisement network alliance which is easy to have wisdom. After the internet advertisement trading platform is accessed to the traffic, when the alliance traffic is insufficient, the traffic can be purchased from the internet advertisement trading platform or the supplier platform through bidding at any time.
In the invention, when the sufficient flow supply of the advertising network alliance is judged and the flow needs to be configured based on the basic pairing strategy and the advertising value, a bidding engine is adopted to acquire the flow suitable for the current advertisement. That is to say, even when the self traffic is sufficient, whether to adopt the traffic more suitable for the current advertisement can be judged according to the intelligent routing algorithm engine, so as to save the cost.
The output module is used for outputting and selling the residual flow by adopting an inquiry engine under the condition that the flow does not need to be configured by the advertising network alliance;
in the invention, a query engine is added on the basis of the advertisement network alliance system. When monitoring that the flow supply of the advertisement network alliance is excessive, namely the advertisement is not filled enough, the rest flow can be output to an internet advertisement trading platform or a DSP (demand-side platform) for selling, so that the benefit of a developer is ensured, and the economic income of the developer is increased.
According to a third aspect of the present invention, there is provided a traffic intelligent routing system, as shown in fig. 2, including:
the intelligent routing algorithm engine 401 is used for acquiring environment information to be analyzed in real time, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, performing modeling calculation to obtain click rate, conversion rate and life cycle value, calculating advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid, click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, advertisement value and advertisement network alliance flow;
in the system with various flow sources and outputs, namely under the condition that a plurality of Ad Exchange (Internet advertisement trading platforms) and DSPs (digital signal processors) are connected to the upstream and downstream of flow supply and demand of an advertisement network alliance system, a supplier is formed to be composed of a plurality of media and a plurality of Internet advertisement trading platforms, and a demand supplier is formed to be composed of an advertiser system, a plurality of Internet advertisement trading platforms and a plurality of demand supplier platforms. The invention reasonably allocates the flow by adopting the intelligent routing algorithm engine, so that the flow distribution is kept balanced and the maximum change efficiency is obtained.
The intelligent routing algorithm engine 401 includes an information ingestion module, a policy configuration module, and an AI module.
And the information intake module is used for acquiring the contents including the weather information of each city, major holidays of China and abroad, commercial holidays, contents of released media, recent hotspots, keywords of each hot search list, advertisement creative release condition information of each industry and the like in real time to serve as the information to be analyzed of the environment.
Further, the information intake module comprises a series of information acquisition APIs, crawlers, word segmentation and semantic analysis algorithms related to the advertisement delivery environment, and the acquisition is as follows according to the series of information acquisition APIs, crawlers, word segmentation and semantic analysis algorithms related to the advertisement delivery environment: and the weather information of each city, the major holidays at home and abroad, the commercial holidays, the contents of the released media, the recent hotspots, the keywords of each major search list, the information of the release situation of the advertisement creativity of each industry and the like are used as the information to be analyzed of the environment.
And the strategy configuration module is used for configuring weight and industry strategies, including media and point locations sold with limited flow, advertisement industry priority, industry information strategy inclusion factors and basic pairing strategies in a cold start period.
The AI module is used for modeling and calculating flow characteristic data and environment information to be analyzed of each flow request as characteristic vectors in a machine learning mode to obtain click rate, conversion rate and life cycle value, and calculating the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid and the click rate, the conversion rate and the life cycle value; in the invention, the AI module takes the flow characteristic data of each flow request and the information to be analyzed of the environment as characteristic vectors by adopting a machine learning mode, models and calculates the relevance between the flow and the advertisement, and then calculates the advertisement value. The accuracy of calculating the advertising value can be improved.
And further, the AI module is used for performing modeling calculation by adopting a DeepFM algorithm according to the flow characteristic data of each flow request and the taken environment information to be analyzed as characteristic vectors to obtain the click rate, the conversion rate and the life cycle value.
In the invention, advertisement value (advale) = exposure price (cpmpice) + click value (clickvale) + conversion value (convertvale) + back-end conversion value (postvalue);
click value (ClickValue, hereinafter abbreviated as CV) = click value coefficient (α) × click rate (CTR);
conversion value (ConvertValue, hereinafter abbreviated as CvV) = conversion value coefficient (β) × conversion rate (CVR);
a back-end transformation value (hereinafter referred to as BV) = a back-end transformation coefficient (γ) × life cycle value (LTV);
this gives:
AdValue=CPMPrice+α×CTR+β×CvV+γ×LTV。
and according to the advertisement property and the advertisement owner appeal, the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient of different advertisements are different, and after the click value coefficient, the conversion value coefficient and the rear-end conversion coefficient corresponding to the advertisement are obtained, the advertisement value is calculated according to the exposure bid of the advertisement owner, the click value coefficient, the conversion value coefficient, the rear-end conversion coefficient, the click rate, the conversion rate and the life cycle value.
And the judging module is used for judging the operation mode according to the basic pairing strategy, the advertisement value and the flow of the advertisement network alliance, and triggering the bidding engine when the operation mode is judged to be the flow which needs to be configured by the advertisement network alliance. And triggering the price inquiry engine under the condition that the operation mode is judged to be the advertising network alliance and the flow does not need to be configured.
A bidding engine 402, configured to purchase traffic in a bidding manner when the intelligent routing algorithm engine 401 determines that the advertisement network alliance needs to configure traffic;
in the invention, a flow supplier is accessed, the flow of an internet advertisement trading platform can be accessed into a system, the flow of an advertisement network alliance is monitored in real time, and when the flow of the advertisement network alliance is monitored to be insufficient, a bidding engine buys the flow from the internet advertisement trading platform or SSP (Sell-Side platform, supplier platform) in a bidding mode.
In the invention, a bidding engine which can access the flow of an internet advertisement transaction platform is added on the basis of the advertisement network alliance which is easy to have wisdom. After the internet advertisement trading platform is accessed to the traffic, when the alliance traffic is insufficient, the traffic can be purchased from the internet advertisement trading platform or the supplier platform through bidding at any time.
In the invention, when the sufficient flow supply of the advertising network alliance is judged and the flow needs to be configured based on the basic pairing strategy and the advertising value, a bidding engine is adopted to acquire the flow suitable for the current advertisement. That is to say, even when the self traffic is sufficient, whether to adopt the traffic more suitable for the current advertisement can be judged according to the intelligent routing algorithm engine, so as to save the cost.
The price inquiry engine 403 is configured to output and sell remaining traffic under the condition that the intelligent routing algorithm engine 401 determines that the advertisement network alliance does not need to configure traffic;
in the invention, a query engine is added on the basis of the advertisement network alliance system. When monitoring that the flow supply of the advertisement network alliance is excessive, namely the advertisement is not filled enough, the rest flow can be output to an internet advertisement trading platform or a DSP (demand-side platform) for selling, so that the benefit of a developer is ensured, and the economic income of the developer is increased.
In the invention, a bidding engine which can be accessed to the traffic of an Internet advertisement trading platform (Ad Exchange) is added on the basis of an advertisement network alliance system. An inquiry engine capable of solving the advertisement filling is added, and an intelligent routing algorithm engine for coordinating and commanding the self consumption of the flow, the flow supplement purchase or the operation of the advertisement filling is added. Let the computer solve the dynamic allocation and the route of flow through big data and artificial intelligence, fundamentally has solved, and balanced flow supplier and flow demand side avoid the flow to supply with and be greater than the demand, appear filling inadequately, can't be fine carry out the flow for the developer and become present, also can avoid the flow to supply with and be less than the demand, the condition that can't satisfy the demand of advertiser's input volume appears. In addition, the flow is dynamically distributed and routed in an artificial intelligence mode, so that the working efficiency can be greatly improved, the time cost is saved, and the reaction mechanism is improved.
As used herein, the singular forms "a", "an", "the" and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
It should be understood that the above detailed description of the technical solution of the present invention with the help of preferred embodiments is illustrative and not restrictive. On the basis of reading the description of the invention, a person skilled in the art can modify the technical solutions described in the embodiments, or make equivalent substitutions for some technical features; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. An intelligent traffic routing system, comprising:
the intelligent routing algorithm engine is used for acquiring environment information to be analyzed in real time, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid and the click rate, the conversion rate and the life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow;
the bidding engine is used for purchasing the flow in a bidding mode when the intelligent routing algorithm engine judges that the advertising network alliance needs to configure the flow;
the price inquiring engine is used for outputting and selling the residual flow under the condition that the intelligent routing algorithm engine judges that the advertising network alliance does not need to configure the flow;
the intelligent routing algorithm engine comprises an information intake module, a strategy configuration module, an AI module and a judgment module;
the information intake module is used for acquiring weather information of each city, holidays of domestic and foreign festivals, contents and hot spots of delivered media, keywords of each hot search list and advertisement creative delivery condition information of each industry in real time as environment information to be analyzed;
the strategy configuration module is used for configuring weight and industry strategies, including media and point locations sold with limited flow, advertisement industry priority, industry information strategy containing factors and basic pairing strategies in a cold start period.
2. The system of claim 1,
the AI module is used for modeling and calculating flow characteristic data of each flow request and the environment information to be analyzed serving as characteristic vectors in a machine learning mode to obtain click rate, conversion rate and life cycle value, and calculating the advertisement value according to the advertisement property, the advertiser appeal, the advertiser exposure bid and the click rate, the conversion rate and the life cycle value.
3. The system of any one of claims 1-2,
the decision module is used for judging an operation mode according to a basic pairing strategy, an advertisement value and the flow of the advertisement network alliance, and triggering a bidding engine when the decision operation mode is that the flow needs to be configured for the advertisement network alliance; and triggering the price inquiry engine under the condition that the operation mode is judged to be the advertising network alliance and the flow does not need to be configured.
4. An intelligent traffic routing method, comprising:
accessing a bidding engine, a price inquiring engine and an intelligent routing algorithm engine;
the method comprises the steps of acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating the advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid and click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, advertisement value and advertisement network alliance flow;
the intelligent routing algorithm engine is adopted, and comprises an information intake step, a strategy configuration step, an AI operation step and a judgment step;
the information intake step is used for acquiring weather information of each city, holidays of domestic and foreign festivals, contents and hot spots of delivered media, keywords of each hot search list and advertisement creative delivery condition information of each industry in real time as environment information to be analyzed;
the strategy configuration step is used for configuring weight and industry strategies, including media and point locations sold with limited flow, advertisement industry priority, industry information strategy containing factors and basic pairing strategies in a cold start period;
when the situation that the advertising network alliance needs to configure the flow is judged, purchasing the flow in a bidding mode by adopting a bidding engine;
and outputting and selling the residual flow by adopting an inquiry engine under the condition of judging that the advertisement network alliance does not need to configure the flow.
5. An intelligent traffic routing device, comprising:
the system comprises a setting module, a price inquiring engine and an intelligent routing algorithm engine, wherein the setting module is used for accessing the price bidding engine, the price inquiring engine and the intelligent routing algorithm engine;
the judging module is used for acquiring environment information to be analyzed in real time by adopting an intelligent routing algorithm engine, taking flow characteristic data of each flow request and the environment information to be analyzed as characteristic vectors, carrying out modeling calculation to obtain click rate, conversion rate and life cycle value, calculating advertisement value according to advertisement properties, advertiser appeal, advertiser exposure bid, click rate, conversion rate and life cycle value, configuring a basic pairing strategy, and judging an operation mode according to the basic pairing strategy, the advertisement value and the advertisement network alliance flow;
the intelligent routing algorithm engine comprises an information intake module, a strategy configuration module, an AI module and a judgment module;
the information intake module is used for acquiring weather information of each city, holidays of domestic and foreign festivals, contents and hot spots of delivered media, keywords of each hot search list and advertisement creative delivery condition information of each industry in real time as environment information to be analyzed;
the strategy configuration module is used for configuring weight and industry strategies, including media and point locations sold with limited flow, advertisement industry priority, industry information strategy containing factors and basic pairing strategies in a cold start period;
the flow purchasing module is used for purchasing the flow in a bidding mode by adopting a bidding engine when the flow needs to be configured in the advertising network alliance is judged;
and the output module is used for outputting and selling the residual flow by adopting an inquiry engine under the condition that the flow does not need to be configured by the advertising network alliance.
6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor,
the steps of the method of claim 4 are implemented when the program is executed by the processor.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program which, when executed, is capable of implementing the method of claim 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110359494.2A CN112734504B (en) | 2021-04-02 | 2021-04-02 | Intelligent traffic routing method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110359494.2A CN112734504B (en) | 2021-04-02 | 2021-04-02 | Intelligent traffic routing method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734504A CN112734504A (en) | 2021-04-30 |
| CN112734504B true CN112734504B (en) | 2021-07-16 |
Family
ID=75596423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110359494.2A Active CN112734504B (en) | 2021-04-02 | 2021-04-02 | Intelligent traffic routing method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734504B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379461B (en) * | 2021-06-25 | 2023-12-01 | 中国科学技术大学 | Advertisement exposure prediction method based on deep learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105246046A (en) * | 2015-11-13 | 2016-01-13 | Tcl集团股份有限公司 | Method and device for sharing flow of mobile terminal |
| CN106960359A (en) * | 2017-02-10 | 2017-07-18 | 上海智子信息科技股份有限公司 | A kind of full-automatic bid optimization method and system calculated based on streaming |
| CN108197968A (en) * | 2017-11-27 | 2018-06-22 | 浙江美哇广告股份有限公司 | Advertising renewal method and system based on integration metering |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012012342A2 (en) * | 2010-07-19 | 2012-01-26 | Mediamath, Inc. | Systems and methods for determining competitive market values of an ad impression |
| CN104636945B (en) * | 2013-11-11 | 2018-03-27 | 秒针信息技术有限公司 | A kind of method and device for realizing DSP advertisement puttings |
| CN109003126A (en) * | 2018-06-29 | 2018-12-14 | 北京三快在线科技有限公司 | Bidding data processing method, device, electronic equipment and computer-readable medium |
-
2021
- 2021-04-02 CN CN202110359494.2A patent/CN112734504B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105246046A (en) * | 2015-11-13 | 2016-01-13 | Tcl集团股份有限公司 | Method and device for sharing flow of mobile terminal |
| CN106960359A (en) * | 2017-02-10 | 2017-07-18 | 上海智子信息科技股份有限公司 | A kind of full-automatic bid optimization method and system calculated based on streaming |
| CN108197968A (en) * | 2017-11-27 | 2018-06-22 | 浙江美哇广告股份有限公司 | Advertising renewal method and system based on integration metering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734504A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4724443B2 (en) | Systems and methods for optimizing paid list revenue | |
| US20130238398A1 (en) | System and method for dynamic product pricing | |
| CN107679904A (en) | A kind of method and device of Recommendations | |
| CN109919719A (en) | Information-pushing method calculates equipment and computer storage medium | |
| CN102841906A (en) | Integrated transaction processing system and transaction processing method | |
| CN112734504B (en) | Intelligent traffic routing method, device and system | |
| CN102129631A (en) | Method, equipment and system for SPU attribute aggregation | |
| CN112215611B (en) | Block chain-based offer method, seller node equipment, terminal equipment and storage medium | |
| CN108932636A (en) | A kind of commodity retail prediction technique and equipment | |
| CN104615721A (en) | Method and system for recommending communities based on returned goods related information | |
| CN115775163A (en) | Programmed advertisement putting method, device and medium based on big data | |
| CN108876020A (en) | A kind of supply chain optimization method based on stochastic demand and Restriction of Service Level | |
| CN106156971B (en) | Logistics resource collaborative relationship information processing method and device | |
| CN109509012A (en) | Ad traffic predictor method and device | |
| CN108429260A (en) | Sale of electricity company Multiple Time Scales transaction electricity decision-making technique and system | |
| Grossman et al. | Money balances, commodity inventories, and inflationary expectations | |
| CN110020135B (en) | Demand determination method, resource recommendation method and related device | |
| CN115860786A (en) | Big data based sales management method and device | |
| CN114971794A (en) | Time period-based high-utility sequence mode analysis method and system in group purchase | |
| CN110210885A (en) | Excavate method, apparatus, equipment and the readable storage medium storing program for executing of potential customers | |
| CN114626921A (en) | E-commerce platform online shopping mall commodity sales promotion management method, system and computer storage medium | |
| CN110363558A (en) | A kind of method and apparatus generating commodity association message | |
| CN112102042A (en) | Electric power transaction cloud platform and cloud platform-based market transaction intelligent matching method | |
| JP2020144952A (en) | Presentation device, presentation method and presentation program | |
| CN111178963A (en) | Member life cycle management method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |