HK1212480B - Systems and methods for search results targeting - Google Patents

Abstract

The invention discloses the systems and methods for search results targeting. The system includes a first database configured to store advertiser bidding information and a second database configured to store websites statistics generated by a search engine. The system includes one or more modules configured to: receive an input from an advertiser; obtain a plurality of advertiser keywords from the first database based on the input from the advertiser; rank the plurality of advertiser keywords; obtain a plurality of website identifiers for each top ranked advertiser keywords from a second database; rank the obtained website identifiers based on history statistics of the obtained website identifiers; and select the top ranked website identifiers as retargeting candidates for the advertiser.

Description

System and method for search result targeting

Technical Field

The present disclosure relates to the field of internet searching, and more particularly to systems and methods for search result targeting.

Background

Advertisers use online advertising to increase brand awareness or drive revenue for them. Common ad campaigns have a particular targeting. There are two main methods of orientation: 1. content targeting-site content-based targeting; 2. behavioral targeting-targeting based on the use of online behavior or derived behavior using online behavior.

Site content is categorized according to a common taxonomy, like the interactive advertising agency (IAB) taxonomy, common content targeting or context targeting. The ads are then targeted according to the taxonomy.

Redirection is a form of behavior-targeted advertising, which is also referred to as behavior reselling or behavior redirection. After people leave the advertiser's website, the redirect may provide people with online advertisements more frequently. Redirection helps companies advertise to web site visitors that leave without conversion, which may include any results other than sales.

Redirection is accomplished by displaying advertisements to the user via various advertising networks from which agents purchase media on behalf of advertisers as the user browses the internet. Typically, redirection marks or labels users who access a particular brand's web site with data called pixels or cookies. When a user accesses a website having a cookie function for the first time, a cookie is transmitted from the server computer system to the browser and stored to the local terminal device through the browser. Later when the user returns to the same website, the website will recognize the user because of the stored cookie with the user information. The computer server system would only provide banner advertisements to people whose pixels or cookies indicate the original brand's participation.

However, conventional redirection requires user behavior data from cookies, which are not always available. Moreover, cookies may provide inaccurate information and cause other problems. Cookies pose potential privacy issues, for example, because they are used to compile long-term records of a person's browsing history. The cookie also stores the previously entered password, address, and credit card number. The hacker may use the data of the cookie to gain access to the user data, or even to the website to which the cookie belongs.

Thus, conventional online advertising systems do not provide an effective targeting solution for advertisers without user behavior data. There is a need to develop new systems and methods for orientation and redirection.

Disclosure of Invention

In the disclosed method, data from the advertiser database and the web search database is used to identify the correct internet candidate domain and/or subdomain for the advertiser. Thus, when a user accesses any of the candidates, the computer system may display the targeted advertisement to the user and also mark the user for targeting and/or redirection without further user information.

In one aspect, a computer system for orientation is provided. The computer system includes a processor and a non-transitory storage medium accessible to the hardware processor. The system includes a first database including advertiser bid information and a second database including website statistics generated by a search engine. The system includes input from an advertiser, and a plurality of advertiser keywords obtained from a first database system based on the input from the advertiser. The system includes one or more modules configured to: ranking the plurality of advertiser keywords; obtaining a plurality of website identifiers for respective highest ranked advertiser keywords from a second database; ranking the obtained website identifiers based on historical statistics of the obtained website identifiers; and selecting the highest ranked website identifier as a targeting candidate for the advertiser.

In a second aspect, a method or program for targeting implemented in a computer system is provided. In a computer-implemented method, the system obtains a plurality of advertiser keywords from a first database system based on input from an advertiser. The system ranks a plurality of advertiser keywords. The system obtains a plurality of website identifiers for respective highest ranked advertiser keywords from a second database. The system ranks the obtained website identifiers based on historical statistics of the obtained website identifiers. The system selects the highest ranked website identifier for the advertiser as the targeting candidate.

Drawings

FIG. 1 is an example computer system according to one embodiment of this disclosure;

FIG. 2A illustrates an example apparatus for orienting;

FIG. 2B illustrates an example system for orienting;

FIG. 3 is an example block diagram illustrating an embodiment of the present disclosure; and

fig. 4 is an example block diagram illustrating an embodiment of the present disclosure.

Detailed Description

Throughout the specification and claims, terms may have a subtle meaning, implicit or implied from the context, in addition to the meaning specifically recited. Likewise, the phrase "in one embodiment" as used herein does not necessarily refer to the same embodiment, and the phrase "in another embodiment" as used herein does not necessarily refer to a different embodiment. For example, claimed subject matter is intended to include combinations of example embodiments in whole or in part.

In general terms may be at least partially understood from the context of use. For example, as used herein, terms such as "and," "or," or "and/or" may include a wide variety of meanings that depend at least in part on their use in context. Generally, "or" if used in association lists such as A, B or C is intended to refer to A, B and C (used herein in an inclusive sense), and A, B or C (used herein in an exclusive sense). In addition, the term "one or more" as used herein, at least in part in the context of context, may be used to describe any feature, structure, or characteristic in the singular or in the plural. Likewise, the terms "a," "an," or "the" may be read to mean either the singular or the plural, such as at least in part according to the context. Additionally, the term "based on" may be understood to not necessarily be intended to represent an exclusive set of factors, but instead to allow for the presence of other factors not necessarily explicitly described, also depending at least in part on the context.

The term "social network" generally refers to a network of individuals (e.g., acquaintances, friends, family, colleagues, or collaborators) coupled through a communication network or through various sub-networks. Potentially, other relationships may then be formed as a result of social interaction via a communication network or sub-network. For example, the social network may be used to identify other connections for various activities (including, but not limited to, dating, job exchange, receiving or providing transit services, content sharing, creating new associations, maintaining existing associations, identifying potential activity partners, performing or supporting business transactions, and so forth).

Social networks may include individuals with similar experiences, opinions, educational levels, or backgrounds. Subgroups may exist or be created according to individual user profiles, for example where members of a subgroup may belong to multiple subgroups. An individual may also have multiple "1: few (minority) "associations, such as associations about family, college classmates, or collaborators.

An individual's social network may refer to a set of direct human relationships or a set of indirect human relationships. Direct personal relationships refer to the relationship of an individual with whom the individual may communicate, such as with family members, friends, colleagues, collaborators, or the like. An indirect personal relationship refers to a relationship that, while not on an individual-to-individual basis, may be used for an individual to communicate with another individual (e.g., a friend of a friend or the like). Different rights or permissions may be associated with a relationship in a social network. Social networks may also generate relationships or connections with entities other than individuals, such as companies, brands, or so-called "avatars". The social network of an individual may be represented in various forms (e.g., visually, electronically, or functionally). For example, a "social graph" or "social relationship graph" represents entities in a social network with nodes and relationships with edges or links.

For web portals like Yahoo, advertisements may be displayed on web pages that originate from a user-defined search based at least in part on one or more search terms. An advertisement may be beneficial to a user, advertiser, or web portal if the displayed advertisement is relevant to one or more user interests. Accordingly, various techniques have been developed to infer user interests, user intent, or to subsequently target relevant advertisements to users. One method of presenting targeted advertisements includes using demographic characteristics (e.g., age, income, gender, occupation, etc.) to predict user behavior, such as by grouping. The advertisement may be presented to the user in the target audience based at least in part on the predicted user behavior(s).

Another approach includes profile type ad targeting. In this approach, a user profile for a user may be generated to model user behavior, for example, by tracking the user's path between web sites or networks of sites, and compiling the profile based at least in part on the pages or advertisements ultimately delivered. For example, correlations are identified for user purchases. The identified correlations may be targeted to potential purchasers by targeting content or advertisements to specific users.

FIG. 1 is a block diagram of one embodiment of an environment 100 in which a system for targeting may operate. The system may implement methods for search result targeting and search result redirection. However, it should be understood that the systems and methods described below are not limited to use in the particular example environment 100 shown in FIG. 1, but may be extended to a wide variety of implementations.

The environment 100 may include a cloud computing environment 110 and a connected server system 120, the connected server system 120 including a content server 122, a search engine 124, and an advertisement server 126. Server system 120 may include additional servers for additional computing or service purposes. For example, the server system 120 may include servers of social networks, online shopping sites, and any other online services.

Content server 122 may be a computer, a server, or any other computing device known in the art, or content server 122 may be a computer program, instructions, and/or software code stored on a computer-readable storage medium that is executable on a single server, processors of multiple servers, or any other type of computing device known in the art. Content server 122 delivers content (e.g., web pages) using the hypertext transfer protocol and/or other protocols. Content server 122 may also be a virtual machine running a program that delivers content.

The search engine 124 may be a computer system, one or more servers, or any other computing device known in the art, or the search engine 124 may be a computer program, instructions, and/or software code stored on a computer-readable storage medium that is executable on a processor of a single server, multiple servers, or any other type of computing device known in the art. Search engine 124 is designed to assist users in locating information on the internet or an intranet.

The ad server 126 may be a computer system, one or more servers, or any other computing device known in the art, or the ad server 126 may be a computer program, instructions, and/or software code stored on a computer-readable storage medium that is executable on a processor of a single server, multiple servers, or any other type of computing device known in the art. The ad server 126 is designed to provide digital ads to web users according to display conditions requested by advertisers.

The cloud computing environment 110 and the connected server system 120 may access the database system 150. Database system 150 may include one or more databases. At least one database in the database system may be an advertiser database in which information about advertiser keywords bid on by different advertisers is stored. The advertiser database may also include the costs and revenues generated by advertisers for each keyword. For example, advertiser data may include keywords on an advertiser's website, product information related to the advertiser, and bid information for the advertiser.

The database system may also include a web search database. The web search database may record search history data from the search engine 124. The web search database may further include: keywords of the website, product information in the website, and product categories in the website. For each keyword, the web search database may include search volume, click-through rate, cost-per-click, and revenue-per-search. The web search database also includes other statistics for each web site.

The environment 100 may also include a plurality of computing devices 132, 134, and 136. The computing device may be a computer, smart phone, personal digital assistant, digital reader, Global Positioning System (GPS) receiver, or any other device that may be used to access the internet.

An advertiser or any other user may use a computing device (e.g., computing devices 132, 134, 136) to access information on server system 120. The advertiser sends an input identifying the products or services he can offer. The input may also identify a plurality of keywords related to the product or service. The server system 120 may use the input to look up other relevant advertiser keywords from the database system 150. The server system 120 may also rank the advertiser keywords and receive websites from the database system for the highest ranked advertiser keywords. These website identifiers may include the highest level domain name and sub-domain names. The website identifier may also include any identifier that identifies at least one web page.

Fig. 2A illustrates an example device 200 for orientation. Device 200 may be a computer, smartphone, server, terminal device, or any other computing device that includes a hardware processor 210, a non-transitory storage medium 220, and a network interface 230. Hardware processor 210 accesses programs and data stored in non-transitory storage medium 220. The device 200 may also include at least one sensor 240. The sensor 240 may include a transducer that measures and converts a physical quantity into a signal that can be understood by the device 200. For example, the sensor 240 may include a light sensor, a sound sensor, a gyroscope, an accelerometer, a barometer, a proximity sensor, a temperature sensor, or any other sensor.

The device 200 may communicate with other devices 200a, 200b, and 200c through a network interface 230. The device 200 may be in communication with a first database 250 and a second database 252. Databases 250 and 252 may be located remotely or locally. In either case, device 200 may access databases 250 and 252 via a network that may perform wired and wireless communications. The network may include a computer network, a telephone network, a wireless network, or any network that may be used to access a database. The first database 250 may store data related to advertiser bids and the second database 252 may store data related to user activity on different websites. The second database 252 may receive input from a search engine system.

Fig. 2B illustrates an example system 500 for selecting orientation candidates. System 500 may include one or more devices such as device 200 shown in fig. 2A. For example, the system 500 includes a processor 510 and a storage medium 520 accessible to the processor 510. Storage media 520 may include non-transitory storage media and transitory storage media. Storage media 520 may include a number of data modules and program modules. The data module may include input 522 from the advertiser, keywords 526 obtained from the database, and an identifier 528 identified by the program module 524. Program modules 524 may be executed by processor 510. Input 522 may include information of a product or service, information of a competitor, a category of a product or service, or any other information that an advertiser would like system 500 to use. Keywords 526 may include advertiser keywords, search keywords, bid keywords, or any other keywords stored in a database related to a product or service. The identifier 528 may include a domain name, a website address, an IP address, or any other web identifier that may be used to identify a website.

For example, based on input from an advertiser, the system 500 may obtain a plurality of advertiser keywords from the first database 542. The program module 524 then ranks the plurality of advertiser keywords. The ranking may be based on various metrics in the search marketplace. The program module 524 may obtain a plurality of website identifiers from the second database 544 for each of the highest ranked advertiser keywords. A plurality of web site identifiers may be stored in a search engine database. Alternatively or additionally, the plurality of website identifiers may be stored in a social networking database or any other database that includes keywords and website identifiers. Program module 524 may rank the obtained website identifiers according to historical statistics of the obtained website identifiers. The program module 524 may select the highest ranked website identifier for the advertiser as the targeting candidate 530. Program module 524 may present targeted advertisements to users who access the selected targeting candidates. After the user leaves the targeting candidate, program module 524 may also present the redirected advertisement to the user who left without conversion.

Fig. 3 shows an example block diagram 300 illustrating an embodiment of the disclosure. The corresponding method may be implemented by the apparatus or computer system described above. Other steps may be added or substituted.

In step 310, the device obtains a plurality of advertiser keywords based on input from an advertiser, wherein the plurality of advertiser keywords are stored in a first database. The first database is related to the Yahoo operated search market. The first database may include information relating to advertiser keyword bid information and an amount of spending on each advertiser keyword.

The input from the advertiser may include only a very brief summary of the product or service. In this case, the device may first analyze the input to receive an initial set of keywords, as shown in step 312 of FIG. 4. For example, the device may use pattern recognition, natural language processing, or other signal processing methods to analyze the input and identify an initial set of keywords from the analysis.

The input from the advertiser may include several keywords, detailed information, images, past advertisements, advertisements to be displayed, and any additional information from the advertiser. The device may use all of the above information from the advertiser to identify more keywords related to the advertiser.

Once the initial set of keywords is identified, the device may expand the initial set of keywords according to the semantics of the initial set of keywords to obtain a plurality of advertiser keywords, step 314 of FIG. 4. The device may expand the initial set of keywords by words that include products or services with similar meanings, similar brands, competitors, or other terms related to the initial keywords. For example, a keyword set including "running shoes" may be extended to include "walking shoes, athletic shoes, cross-training shoes, marathon shoes" and brand names associated with running.

The device may also expand the initial set of keywords to introduce words with typographical or common misspellings, words in a different order, or non-semantic terms related to the advertiser. The non-semantic terms may include at least one of: the geographic location of the advertiser, a colloquial name associated with the product or service, and age information associated with the product or service.

In step 320, the device ranks keywords for multiple advertisers based on information from different advertisers. This information includes past spending on each advertiser's keywords, the number of bids made by different advertisers, cost per click information, revenue generated by each keyword, and other information available. For example, the device may rank the plurality of advertiser keywords according to at least one of: search volume, click-through rate, cost-per-click, and revenue-per-search. Keywords with greater search volume, higher click-through rate, higher cost per click, or higher revenue per search may be ranked higher.

At step 330, the device obtains a plurality of website identifiers from the second database for each of the highest ranked advertiser keywords. The second database may be a database associated with a search engine, social networking server, and other computer servers. For example, the second database may store domain-level page rankings, spam scores, and past visitors' commercial intentions to the website. The page rank may be calculated by the search engine to measure the importance of the web page at the highest domain level or subdomain level. The spam score can be computed by the device to determine a likelihood of receiving spam from a website identified by the website identifier. Websites with higher page rank and lower spam score may be ranked higher. In other words, page rank is a positive factor and spam score is a negative factor.

By tracking the user's transformed pixels or cookies of online purchasing behavior in the displayed activity, the commercial intent of a web visitor in the past can be tracked. pixels or cookies may track the types of products that web visitors purchase or add to a shopping cart. The tracking information may also include the number of views each visitor spends on a particular sub-domain name or a particular product.

The website identifier includes at least one of a domain name of a highest level and a sub-domain name. For large web sites that include thousands of different products, sub-domain names are necessary to match a particular product of an advertiser. For example, when the advertiser's product is "sports shoes," a sub-domain name that is used to identify shoe sales departments in large online stores is necessary. It is not easy for a general web site to identify the commercial intention of a user/advertiser for a particular advertiser because the field includes a wide variety of products. It is necessary for the device to collapse and scroll the results to the domain and subdomain levels.

In step 340, the device ranks the obtained website identifiers according to historical statistics of the obtained website identifiers. The historical statistics may include at least one of: click-through rates for keywords in a web page, domain-level page rankings, spam scores, commercial intentions of past visitors to a website, or other statistical or commercial information that may be obtained by a device.

In step 350, the device selects the highest ranked website identifier as the targeting candidate for the advertiser. The device provides a list of website names as targeting candidates to the advertiser. The device may also automatically target users who visit any of these websites to the advertiser's products or services. Advertisers may purchase other targeted and/or redirected advertisements, or bid on banner advertisements, on these targeted websites.

In step 360, the device annotates users who access the candidates according to the arbitrary orientation entered. When the user accesses any of the targeting candidates, cookies may be used to tag the user so that another device or computer system may redirect the user to other products and services from the advertiser. This may also be combined with an email system or other system. For example, when a user reads an email from a targeted candidate website, the user may also be tagged for future redirection. The device may annotate the user by other methods, such as a server log or tag.

In step 370, the device presents the annotated user with a redirected advertisement related to the advertiser. The device may analyze user behavior from cookies or pixels and present online advertisements to the annotated user.

The disclosed systems and methods may be used for search result targeting and/or search result redirection. The disclosed system has the following advantages. The system provides targeting and/or redirection without any user behavior from cookies. Also, the system uses both advertiser bid information from the advertising system and website statistics from the search engine system to identify highly relevant websites.

It is therefore intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that it is the following claims, including all equivalents, that are intended to define the spirit and scope of this invention.

Claims (20)

1. A system for search result targeting comprising a processor and a non-transitory storage medium accessible to the processor, the system comprising:

a first database comprising advertiser bid information;

a second database comprising website statistics generated by a search engine;

input from an advertiser;

a plurality of advertiser keywords obtained from the first database based on the input from the advertiser; and

one or more modules configured to:

ranking the plurality of advertiser keywords;

obtaining, from the second database, a plurality of website identifiers for respective highest-ranked advertiser keywords;

ranking the obtained website identifiers based on historical statistics of the obtained website identifiers; and

selecting the highest ranked website identifier as a targeting candidate for the advertiser.

2. The system of claim 1, wherein the system is further configured to annotate users accessing arbitrary orientation candidates according to the input.

3. The system of claim 2, wherein the system is configured to present the annotated user with a redirected advertisement that is relevant to the advertiser.

4. The system of claim 1, wherein the first database is configured to store at least one of:

the keywords on the advertiser's web site,

product information relating to the advertiser, an

Bid information for advertisers.

5. The system of claim 1, wherein the system is configured to rank the plurality of advertiser keywords based on at least one of:

the amount of searching is determined by the search volume,

the rate of the click-through is increased,

cost per click, and

revenue per search.

6. The system of claim 1, wherein the plurality of website identifiers comprises at least one of:

the highest level domain name, an

A sub-domain name.

7. The system of claim 1, wherein the second database is configured to store at least one of:

the domain-level page rank is set to,

spam score, and

the web site's past visitor's commercial intention.

8. The system of claim 1, wherein obtaining the plurality of advertiser keywords based on the input comprises:

analyzing the input to receive an initial set of keywords; and

extending the initial set of keywords based on semantics of the initial set of keywords to obtain the plurality of advertiser keywords.

9. A method for search result targeting, comprising:

obtaining, by one or more computing devices, a plurality of advertiser keywords from a first database based on input from an advertiser;

ranking, by the one or more computing devices, the plurality of advertiser keywords;

obtaining, by the one or more computing devices, a plurality of website identifiers for respective highest-ranked advertiser keywords from a second database;

ranking, by the one or more computing devices, the obtained website identifiers based on historical statistics of the obtained website identifiers;

selecting, by the one or more computing devices, a highest ranked website identifier for the advertiser as a targeting candidate.

10. The method of claim 9, further comprising:

annotating, by the one or more computing devices, a user that accesses any orientation candidate according to the input.

11. The method of claim 10, further comprising:

the annotated user is presented with a redirected advertisement that is relevant to the advertiser.

12. The method of claim 9, wherein the first database is configured to store at least one of:

the keywords on the advertiser's web site,

product information relating to the advertiser, an

Bid information for advertisers.

13. The method of claim 9, wherein ranking the plurality of advertiser keywords comprises ranking the plurality of advertiser keywords based on at least one of:

the amount of searching is determined by the search volume,

the rate of the click-through is increased,

cost per click, and

revenue per search.

14. The method of claim 9, wherein the plurality of website identifiers comprises at least one of:

the highest level domain name, an

A sub-domain name.

15. The method of claim 9, wherein the second database is configured to store at least one of:

the domain-level page rank is set to,

spam score, and

the web site's past visitor's commercial intention.

16. The method of claim 9, wherein obtaining the plurality of advertiser keywords based on the input comprises:

analyzing the input to receive an initial set of keywords; and

extending the initial set of keywords based on semantics of the initial set of keywords to obtain the plurality of advertiser keywords.

17. A non-transitory storage medium configured to store a set of instructions that direct a computer system to perform acts for search result targeting, the acts comprising:

obtaining a plurality of advertiser keywords from a first database based on input from an advertiser;

ranking the plurality of advertiser keywords;

obtaining a plurality of website identifiers for respective highest ranked advertiser keywords from a second database;

ranking the obtained website identifiers based on historical statistics of the obtained website identifiers;

selecting the highest ranked website identifier as a targeting candidate for the advertiser.

18. The non-transitory storage medium of claim 17, wherein the set of instructions directs the computer system to perform:

the annotation accesses users that are candidates for arbitrary orientation according to the input.

19. The non-transitory storage medium of claim 17, wherein the set of instructions directs the computer system to perform:

the annotated user is presented with a redirected advertisement that is relevant to the advertiser.

20. The non-transitory storage medium of claim 17, wherein obtaining the plurality of advertiser keywords based on the input comprises:

analyzing the input to receive an initial set of keywords; and

extending the initial set of keywords based on semantics of the initial set of keywords to obtain the plurality of advertiser keywords.