(12) United States Patent (10) Patent No.: US 7.689,548 B2 Li Et Al .

US 7,689,548 B2 1. 2 FIG. 4 is a flow diagram showing a method for determining keyword bid patterns based upon one or more bid upon key words, in accordance with an embodiment of the present RECOMMENDING KEYWORDS BASED ON BIDDING PATTERNS invention; BACKGROUND In the paid search advertising industry, content and context are the primary criteria utilized to measure similarity between keywords. As such, these two measures are commonly used in keyword Suggestion tools, that is, tools that Suggest to an entity (e.g., an advertiser) upon receipt of a first keyword, one or more additional keywords upon which it may want to consider placing a bid as well. For example, if an advertiser places a bid on the keyword “vehicle', a keyword Suggestion tool may also Suggest Words having similar meaning, e.g., “automobile”, “motorcycle”, “bus', and the like. While additional keyword suggestion is beneficial to advertisers seeking to place keywords, content and/or context similarity keyword Suggestions provide an advertiser with fairly limited information from which to evaluate their key word bidding strategies. Additionally, referring back to the above examples the Suggested keywords are often words or terms that the advertiser likely could have formulated on their own, simply by being intimately involved in their specific industry. 10 15 invention; 25 BRIEF SUMMARY This Summary is provided to introduce a selection of con cepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed sub ject matter, nor is it intended to be used as an aid in determin ing the scope of the claimed Subject matter. Embodiments of the present invention relate to techniques for cross-selling keywords among keyword bidding entities (e.g., advertisers) based upon bidding patterns. For instance, a keyword Suggestion tool inaccordance with an embodiment of the present invention, upon receipt of a first keyword, may examine all additional keywords that have been paired with the first keyword in the bidding patterns of other advertising entities and recommend one or more of the paired keywords to the bidding entity for consideration. In other embodiments, a keyword Suggestion tool in accordance with the present invention, upon receipt of a keyword/keywords from a first advertisingentity, may examine the bidding pattern of the first advertising entity in comparison to the bidding patterns of other advertising entities to identify advertising entities that are similar to the bidding entity. Recommendations may then be made to the first advertising entity based upon keywords that the identified similar advertising entities have bid. 30 FIG. 8 is a flow diagram showing a method for determining bidding entity similarity, in accordance with an embodiment of the present invention; FIG.9 is an illustrative screen display of an exemplary user interface for accepting keywords forbid and Suggesting addi tional keywords for consideration based upon bidding entity similarity and keyword significance, wherein a single key word has been input by a user, in accordance with an embodi ment of the present invention; and FIG. 10 is an illustrative screen display of an exemplary user interface for accepting keywords for bid and suggesting additional keywords for consideration based upon bidding entity similarity and keyword significance, wherein multiple keywords have been input by a user, in accordance with an embodiment of the present invention. 35 DETAILED DESCRIPTION 40 45 50 BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS The present invention is described in detail below with reference to the attached drawing figures, wherein: FIG. 1 is a block diagram of an exemplary computing environment suitable for use in implementing embodiments of the present invention; FIG. 2 is a block diagram of an exemplary computing system Suitable for use in implementing embodiments of the present invention; FIG. 3 is flow diagram showing a method for recommend ing keywords based on keyword bid patterns determined rela tive to one or more bid upon keywords, in accordance with an embodiment of the present invention; FIG.5 is an illustrative screen display of an exemplary user interface for accepting keywords forbid and, based upon that keyword, Suggesting additional keywords for consideration, wherein a single keyword has been input by a user, in accor dance with an embodiment of the present invention; FIG. 6 is an illustrative screen display of an exemplary user interface for accepting keywords forbid and, based upon that keyword, Suggesting additional keywords for consideration, wherein multiple keywords have been input by a user, in accordance with an embodiment of the present invention; FIG. 7 is a flow diagram showing a method for recom mending keywords based on keyword bid patterns deter mined based upon bidding entity similarity and keyword sig nificance, in accordance with an embodiment of the present 55 60 65 The subject matter of the present invention is described with specificity herein to meet statutory requirements. How ever, the description itself is not intended to limit the scope of this patent. Rather, the inventors have contemplated that the claimed Subject matter might also be embodied in other ways, to include different steps or combinations of steps similar to the ones described in this document, in conjunction with other present or future technologies. Moreover, although the terms “step’ and/or “block” may be used hereinto connote different elements of methods employed, the terms should not be inter preted as implying any particular order among or between various steps herein disclosed unless and except when the order of individual steps is explicitly described. Embodiments the present invention provides techniques for cross-selling keywords among keyword bidding entities (e.g., advertisers) based upon bidding patterns. In one aspect, a keyword Suggestion tool inaccordance with an embodiment of the present invention, upon receipt of a keyword from a first advertising entity, examines all additional keywords that any single advertising entity that has bid upon the first keyword has also bid upon, and recommends one or more of the paired keywords to the first advertising entity for consideration. In another aspect, a keyword Suggestion tool in accordance with an embodiment of the present invention, upon receipt of a keyword from a first advertising entity, examines the bidding pattern of the first advertising entity in comparison to the bidding patterns of other advertising entities to identify advertising entities that are similar to the bidding entity. Rec ommendations may then be made to the first advertising entity based upon keywords that the identified similar adver

US 7,689,548 B2 3 tisingentities have bid, even if the similar advertising entities have not bid upon the keyword upon which the first advertis ing entity is presently bidding. Accordingly, in one embodiment, the present invention relates to a method for recommending keywords based upon keyword bid patterns. The method includes receiving a first keyword bid upon by a first entity; retrieving at least one bid pattern associated with a plurality of entities, the at least one bid pattern including at least one second keyword paired with the first keyword; determining if the first entity has bid upon the at least one second keyword; and, if it is determined that the first entity has not bid upon the at least one second key word, presenting the second keyword to the first entity. In another embodiment, the present invention relates to a method for recommending keywords based on bidding entity similarity. The method includes receiving a first keyword bid upon by a first entity; identifying at least one of a plurality of other entities that is similar to the first entity; determining at least one significant keyword bid upon by the at least one of the plurality of other entities that is similar to the first entity: and presenting the at least one significant keyword to the first entity. Embodiments of the present invention further relate to computer-readable media having computer-executable instructions embodied thereon for performing the methods 10 15 25 described herein. In yet another embodiment, the present invention relates to a computerized system for recommending keywords. The system includes a keyword receiving component configured to receive at least one keyword bid upon by a first entity; a bidding history determining component configured to deter mine abidding history associated with the first entity and each of the plurality of other entities; and a Suggested keyword presentation component configured to present at least one Suggested keyword to the first entity based upon the bidding history associated with the first entity and the bidding history associated with the at least one of the plurality of other enti 30 other medium that can be used to encode desired information 35 ties. Having briefly described an overview of embodiments of the present invention, an exemplary operating environment Suitable for use in implementing embodiments of the present 40 invention is described below. Referring initially to FIG. 1 in particular, an exemplary operating environment for implementing the present inven tion is shown and designated generally as computing device 100. Computing device 100 is but one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the inven tion. Neither should the computing-environment 100 beinter preted as having any dependency or requirement relating to any one or combination of components illustrated. The invention may be described in the general context of computer code or machine-useable instructions, including computer-executable instructions such as program compo nents, being executed by a computer or other machine. Such as a personal data assistant or other handheld device. Gener ally, program components including routines, programs, objects, components, data structures, and the like, refer to code that perform particular tasks or implement particular abstract data types. The invention may be practiced in a vari ety of system configurations, including hand-held devices, consumer electronics, general-purpose computers, more spe cialty computing devices, etc. The invention may also be practiced in distributed computing environments where tasks are performed by remote-processing devices that are linked through a communications network. 4 With continued reference to FIG. 1, computing device 100 includes a bus 110 that directly or indirectly couples the following devices: memory 112, one or more processors 114, one or more presentation components 116, input/output (I/O) ports 118, I/O components 120, and an illustrative power supply 122. Bus 110 represents what may be one or more busses (such as an address bus, data bus, or combination thereof). Although the various blocks of FIG. 1 are shown with lines for the sake of clarity, in reality, delineating various components is not so clear, and metaphorically, the lines would more accurately be grey and fuZZy. For example, one may consider a presentation component Such as a display device to be an I/O component. Also, processors have memory. We recognize that such is the nature of the art, and reiterate that the diagram of FIG. 1 is merely illustrative of an exemplary computing device that can be used in connection with one or more embodiments of the present invention. Distinction is not made between Such categories as “worksta tion.” “server.” “laptop,” “hand-held device.” etc., as all are contemplated within the scope of FIG. 1 and reference to “computing device.” Computing device 100 typically includes a variety of com puter-readable media. By way of example, and not limitation, computer-readable media may comprises Random Access Memory (RAM); Read Only Memory (ROM); Electronically Erasable Programmable Read Only Memory (EEPROM); flash memory or other memory technologies; CDROM, digi tal versatile disks (DVD) or other optical or holographic media; magnetic cassettes, magnetic tape, magnetic disk Stor age or other magnetic storage devices, carrier wave or any and be accessed by computing device 100. Memory 112 includes computer-storage media in the form of volatile and/or nonvolatile memory. The memory may be removable, nonremovable, or a combination thereof. Exem plary hardware devices include Solid-state memory, hard drives, optical-disc drives, etc. Computing device 100 includes one or more processors that read data from various entities such as memory 112 or I/O components 120. Presen tation component(s) 116 present data indications to a user or other device. Exemplary presentation components include a display device, speaker, printing component, vibrating com ponent, etc. 45 50 55 60 65 I/O ports 118 allow computing device 100 to be logically coupled to other devices including I/O components 120, some of which may be built in. Illustrative components include a microphone, joystick, game pad, satellite dish, Scanner, printer, wireless device, etc. As previously mentioned, in one embodiment, the present invention relates to techniques for cross-selling keywords among keyword bidding entities (e.g., advertisers) based upon bidding patterns. For instance, a keyword Suggestion tool in accordance with an embodiment of the present inven tion, upon receipt of a first keyword, may examine all addi tional keywords that have been paired with the first keyword in the bidding patterns of other advertising entities and rec ommend one or more of the paired keywords to the bidding entity for consideration. In other embodiments, a keyword Suggestion tool in accordance with the present invention, upon receipt of a keyword from a first advertising entity, may examine the bidding pattern of the first advertising entity in comparison to the bidding patterns of other advertising enti ties to identify advertising entities that are similar to the bidding entity. Recommendations may then be made to the first advertising entity based upon keywords that the identi fied similar advertising entities have bid.

US 7,689,548 B2 5 Referring now to FIG. 2, a block diagram is illustrated that shows an overall system architecture 200 for recommending keywords in accordance with embodiments of the present invention. It will be understood and appreciated by those of ordinary skill in the art that the overall system architecture 200 shown in FIG. 2 is merely an example of one suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the present invention. Neither should the overall system architecture 200 be interpreted as having any dependency or requirement related to any single component or combination of compo 6 associated with the bidding entity, as well as a bidding pattern associated with one or more additional entities that have 5 10 nents illustrated therein. System 200 includes a user device 202 connected to a server 206 and a database 208 via a network 206. Each of the user device 202 and the server 206 shown in FIG. 2 may be any type of computing device, such as, for example, comput ing device 100 described above with reference to FIG. 1. By way of example only and not limitation, the user device 202 and/or the server 206 may be a personal computer, desktop computer, laptop computer, handheld device, consumer elec 15 tronic device, and the like. It should be noted, however, that the invention is not limited to implementation on Such com puting devices, but may be implemented on any of a variety of different types of computing devices within the scope of embodiments of the present invention. As shown in FIG. 2, the user device 202 includes keyword (s) receiving component 210, a bid pattern determining com ponent 212, a Suggested keyword(s) presentation component 214, a confidence value determining component 216, a bid ding entity similarity determining component 218, and a key word significance determining component 220 for imple menting embodiments of the present invention. In some embodiments, the components 210, 212, 214, 216, 218, and 220 may be implemented as stand-alone applications. In other embodiments, the components 210, 212, 214, 216, 218, and 220 may be integrated directly into the operating system for the user device 202. It will be understood by those skilled in the art that the components 210, 212, 214, 216, 218, and 220 illustrated in FIG. 2 are exemplary in nature and in number and should not be construed as limiting. Any number of components may be employed to achieve the desired func tionality within the scope of embodiments of the present 25 30 described below. 35 hereof. The bid pattern determining component 212 of the user device 202 is configured for determining a bidding pattern Bid pattern data associated with each of the bidding entity and one or more additional bidding entities may be stored in association with database 208 and/or server 206 and accessed 40 invention. The keyword(s) receiving component 210 is configured for receiving one or more keywords input by a user at the user device 202, each keyword received being a keyword upon which the user desires to place a bid. By way of example only, a keyword input by the user may be a single term, a phrase including a plurality of terms, a product name, a brand name, or the like. Typically, the user will be an individual authorized to place bids on keywords on behalf of a bidding entity, for instance, an advertising entity. In one embodiment, the key word(s) receiving component 210 is further configured for transmitting received keywords (in addition to an identifier associated with the bidding entity, if desired) to a database 208 for storage (via network 204). It will be understood and appreciated by those of ordinary skill in the art that database 208 may be a single database as shown or a database cluster (not shown) and may be a stand alone component or inte grated with either server 206 or user device 202, or any combination thereof. Additionally, in some embodiments, the server 206 may be a plurality of servers (not shown) or may not be present in the system at all. Any and all Such variations are contemplated to be within the scope of embodiments placed bids on one or more keywords at Some previous point in time. In one embodiment, the bid pattern determining component is configured for determining the bidding pattern of the bidding entity and one or more additional entities relative to a particular keyword the bidding entity has input into the keyword(s) receiving component 210. For instance, if the bidding entity inputs the keyword “aromatherapy' and Such keyword is received by the keyword(s) receiving com ponent 210, the bid pattern determining component 212 may be configured for determining the bid patterns of one or more other bidding entities who have placed bids on keyword “aro matherapy' at Some point in time. In this instance, the bidding pattern(s) of the one or more other bidding entities may include additional keywords on which those same bidding entities have placed bids. In another embodiment, the bid pattern determining com ponent 212 is configured for determining the bidding pattern of the bidding entity and one or more additional entities relative to the bidding pattern of the bidding entity. That is, the bid pattern determining component 212 may be configured for determining all keywords on which the bidding entity currently bidding upon a particular keyword has placed bids during a predefined prior time period. Additionally, the bid pattern determining component 212 may be configured for determining all keywords on which any bidding entities simi lar to the bidding entity currently bidding upon a particular keyword have placed bids during a predefined prior time period. Bidding entities that may be considered “similar to the bidding entity currently bidding upon a particular key word may be determined by the bidding entity similarity determining component 218 of user device 202, as more fully by the bid pattern determining component 212 via network 204. Such bid pattern data may include, by way of example only, the keywords on which an entity has placed bids, an identifier associating the entity with the bid upon keyword, a time during which any keyword bids were placed, and the like. 45 50 The Suggested keyword(s) presentation component 214 is configured to present at least one suggested keyword to the user inputting the bid upon keyword based upon the bid pattern associated with the first entity and the bid pattern associated with at least one of a plurality of other entities. Typically, presentation of the Suggested keyword(s) com prises displaying the Suggested keyword(s) on a display device associated with the user device 202. However, other 55 60 65 types of presentation, Such as an audible presentation, may also be provided within the scope of embodiments of the present invention. In one embodiment, the Suggested keyword(s) presentation component 214 may be configured to present one or more Suggested keywords determined relative to a particular key word the bidding entity has input into the keyword(s) receiv ing component

US 7.689,548 B2 Page 2 2005/0O862O6 2005/0091111 2005.0102270 2005/O137939 2005, 014.4065 2005/0171932 2005/0222901 2005/0228797 2005/0262428