Patent Application
20140278796
The disclosed implementations relate generally to identifying target audience for a product or service marketed on the Internet and/or TV channels, and in particular, to systems and methods for identifying potential customers for a product/service from analyzing data relating to information consumption activities by a group of panelists.
People are spending more and more time on the Internet, e.g., browsing news, entertainment and social media web sites; conducting business transactions; and purchasing or selling products/services. As a result, companies are increasing their efforts to reach potential customers through on-line advertising. However, due to different demographic sectors of the public having unique preferences regarding where to spend their time and money on the Internet, it is a challenge for advertisers to know where to focus their online advertising dollars. For example, college students may be more interested in visiting a sports related website like www.ncaa.org, but young mothers would probably like to spend more time on websites that provide infant related information. Therefore, it is not the most efficient way for a company to promote its products or services by merely placing its advertisements on a website based on its popularity without considering the demographic nature of the visitors of the website.
In accordance with some implementations described below, a method for selecting potential customers for a product/service is performed at a computer server having memory and one or more processors. The computer server collects information consumption activity data, conversion data, and demographic data from a plurality of panelists and identifies a set of product/service keywords for each panelist from the information consumption activity data associated with the panelist. For each product/service keyword, the computer server then aggregates the demographic data of those panelists associated with the product/service keyword using the conversion data and generates a set of demographic attributes from the aggregated demographic data in order to characterize potential customers of the product/service.
In accordance with some implementations described below, a method for generating a demographic characterization for a product/service is performed at a computer server having memory and one or more processors. In response to receiving from a client device a request to identify potential customers of a product/service, the computer server determines one or more categories for the product/service. For each category, the computer server identifies a set of product/service keywords, each product/service keyword having an associated set of demographic attributes characterizing potential customers of the product/service. The computer server then generates a demographic characterization for the product/service by aggregating the sets of demographic attributes associated with the respective sets of product/service keywords and returns information about the demographic characterization for the product/service for display at the client device.
In accordance with some implementations described below, a computer system for generating a demographic characterization for a product/service is provided. The computer system includes one or more processors and memory for storing one or more programs. The programs, when executed by the one or more processors, cause the computer system to perform the following instructions: receiving from a client device a request for identify potential customers of a product/service; determining one or more categories for the product/service; identifying a set of product/service keywords for each category, each product/service keyword having an associated set of demographic attributes characterizing potential customers of the product/service; generating a demographic characterization for the product/service by aggregating the sets of demographic attributes associated with the respective sets of product/service keywords; and returning information about the demographic characterization for the product/service for display at the client device.
In accordance with some implementations described below, a computer system for selecting potential customers for a product/service is provided. The computer system includes one or more processors and memory for storing one or more programs. The programs, when executed by the one or more processors, cause the computer system to perform the following instructions: collecting one or more of information consumption activity data, conversion data, and demographic data from a plurality of panelists; identifying a set of product/service keywords for each panelist from the information consumption activity data associated with the panelist; for each of the set of product/service keywords: aggregating the demographic data of the plurality of panelists who are associated with the product/service keyword using the conversion data; and generating a set of demographic attributes from the aggregated demographic data in order to characterize potential customers of the product/service.
The aforementioned implementation of the invention as well as additional implementations will be more clearly understood as a result of the following detailed description of the various aspects of the invention when taken in conjunction with the drawings. Like reference numerals refer to corresponding parts throughout the several views of the drawings.
In some cases, a panelist refers to an individual and associated terminal devices used by the individual for accessing the Internet. For example, a data collection agency may invite a group of individuals to participate in a program wherein the individuals (or “panelists”) voluntarily agree to allow the agency to collect information relating to their web browsing and TV viewing activities, e.g., at home with/without compensation. In addition, the panelists also agree to provide their demographic information to the data collection agency so that it is possible to associate their respective web browsing and TV viewing activities with different demographic sectors. This allows the agencies to derive information useful for associating a product/service with a set of demographic attributes.
As shown in
The conversion data 12 indicates the success of a marketing campaign. For example, the click-through rate for a particular advertisement is one type of conversion data 12 that measures the likelihood of a panelist clicking on a product/service promotion message on a web page (e.g., in some implementations, the click-through rate is the ratio of clicks to presentations for a particular advertisement). The conversion data 12 may also include information indicating whether a panelist has purchased a product/service after viewing the product/service's promotion message on the Internet or on TV. As described below, the conversion data 12 is useful when the survey system 40 determines a set of demographic attributes associated with preferred customers for a product/service. For example, if there is a high conversion rate (whether it is measured by the click-through rate or the number of actual commercial transactions) for a product/service among a particular demographic sector of the public, the demographic attributes unique to this sector can be given more weight as well when it comes to online advertising. Accordingly, when a company tries to promote a product/service of similar nature, the company can also target the demographic sector as the main source of potential customers and launch campaigns at venues (e.g., websites or TV channels/programs) popular among visitors/viewers from the same demographic sector.
In sum, the survey system 40 collects information consumption activity data and conversion data from panelists 10-1, 10-2 and stores that data in the panelist information consumption activity database 107. The data in the panelist information consumption activity database 107 serves as raw data to be processed by the survey system 40 (more specifically, the analytics module 110). From such data, the analytics module 110 derives a set of product/service keywords for each panelist. The set of product/service keywords indicates what type of products or services in which the panelist might be interested. Typically, a product/service can be characterized using one or multiple (e.g., 5) keywords and similar products/services may share some keywords in common. For example, if the information consumption activity data includes many occurrences of the website www.nba.com, then the analytics module 110 may associate the panelist with the keyword “basketball.” If the information consumption activity data includes many occurrences of the website www.cnbc.com, the analytics module 110 may associate the panelist with keywords like “stock” and “investment.”
In some implementations, the survey system 40 includes a website-keyword model 101, a web search-keyword model 103, and a TV program-keyword model 105 for associating a panelist with an appropriate set of product/service keywords based on the panelist's information consumption activity data. The three models may be generated by conducting a market survey among a group of users/viewers, e.g., by providing a list of candidate keywords and letting the users/viewers pick those that most accurately characterize a website or a TV program based on their opinions. Alternatively, some models may be generated and provided to the survey system 40 by a third-party entity by aggregating a sufficient number of data samples from a group of users/viewers. For example, it is possible to associate a web search query with a set of keywords based on their occurrence frequencies in the search results corresponding to the search query.
Based on one or more of these models, the analytics module 110 analyzes the information consumption activity data associated with each individual panelist such as websites visited by the panelist, web searches submitted by the panelist, and TV programs watched by the panelist, and derives a set of keywords for characterizing products and/or services that the panelist may be interested in purchasing. For example, for a website (including a web page), the analytics module 110 identifies one or more keywords associated with the website in the website-keyword model. It is possible that a panelist may visit many similar websites that share some keywords in common. In some implementations, the analytics module 110 assigns a weight to a keyword. In some implementations, the weight may be dependent upon the popularity of the website on the Internet, the amount of time that the panelist spends on the website, how well the keyword weight characterizes the website, etc. Therefore, if a particular keyword is associated with multiple websites visited by the panelist, the analytics module 110 aggregates their weights together to indicate the relevance between the panelist and this particular keyword. Similar approaches can be applied to the web search history and the TV viewing data. In some implementations, the analytics module 110 only identifies a predefined number of keywords for a panelist and stores this relationship in the panelist-keyword database 109. For example, the analytics module 110 may choose a keyword for a panelist only if the weight associated with the keyword is higher than a certain level. Alternatively, the analytics module 110 may choose the top-N (e.g., 5) keywords ranked by their weights for each panelist and stores them in the panelist-keyword database 109. In other words, the analytics module 110 converts the information consumption activity data that represents the specific events associated with a panelist into a more abstractive representation in the form of a set of keywords. As will be described below, a keyword may be associated with a particular type of product/service. It is possible to define a relationship between a panelist and a product/service that the panelist may be interested in using the keywords.
Multiple issues have to be resolved before the information in the panelist-keyword database 109 can be used for predicting or identifying potential customers for a product or service. First, the information in the panelist-keyword database 109 is keyed by different panelists such that each panelist in the panelist-keyword database 109 has an associated set of keywords. But it is often more useful for a company to find out which demographic sector of the public is interested in its product/service and then promote the product/server to the targeted demographic sector by launching a campaign at venues (such as websites or TV programs) that are appealing to the same demographic sector. The aggregate module 130 is responsible for aggregating the demographic data of the panelists and identifying the demographic information for different keywords. As noted above, a panelist who participates in the survey program has agreed to provide his or her personal information such as age, gender, education level, incoming level, geographical location, ethnicity, etc., to the survey system 40, which is stored in the panelist demographic database 113. In some implementations, the aggregate module 130 uses the conversion data associated with the panelists to adjust the aggregation of the demographic data of the panelists. For example, if a panelist purchases a particular product/service after visiting a website promoting the product/service or clicks a promotion link to the website promoting the product/service, the demographic data associated with this panelist is given more weight when aggregating the demographic data for a particular keyword that may be related to the product/service relative to other panelists that have no conversion data associated with the product/service.
Moreover, when a company (or its representative) sends a request to the survey system 40 for identifying potential customers for a product or service, it has no or little information about the demographic information of the potential customers. Typically, the company can only provide some information about the product/service it tries to promote (such as one or more keywords associated with the product/service), it is the responsibility of the survey system 40 to determine the demographic nature of the potential customers based on the information derived from the surveying results of the panelists. In other words, besides aggregating the demographic data of different panelists in the panelist-keyword database 109, the aggregate module 130 is responsible for inverting the relationship in the panelist-keyword database 109, generating a new relationship between the keyword and demographic attributes, and storing the relationship in the keyword-demographic attribute database 111. Unlike the panelist-keyword database 109, the new relationship in the keyword-demographic attribute database 111 is indexed by keywords. Using the keyword-demographic attribute database 111, the frontend module 120 can answer a query from a client for identifying potential customers for a product/service by identifying a set of demographic attributes for the product/service. As explained below, in some implementations the demographic attributes have a broad scope and they may include websites and TV programs that are popular among users/viewers who may be potential customers of the product/service. Based on the query results returned by the survey system 40, a company can develop an effective marketing strategy by targeting product/service campaigns at those potential customers.
In some implementations, the survey system 40 includes a product/service classifier 121 for identifying one or more categories for a product/service submitted by a company from a client. Using a category-keyword model 123, the product/service classifier 121 converts the categories associated with the product/service into a set of keywords and returns the keywords to the frontend module 120. Upon receipt of the keywords, the frontend module 120 then queries the keyword-demographic attribute database 111 for demographic attributes corresponding to the keywords associated with the product/service. As noted above, the keyword-demographic attribute database 111 includes a set of demographic attributes characterizing potential customers of a product/service for each keyword associated with the product/service. Next, the frontend module 120 generates a demographic characterization for the product/service by aggregating the demographic attributes corresponding to different keywords and returns information about the demographic characterization for the product/service for display at the client device.
In some implementations, the memory 212 includes high-speed random access memory, such as DRAM, SRAM, or other random access solid state memory devices. In some implementations, memory 212 includes non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. In some implementations, memory 212 includes one or more storage devices remotely located from the processor(s) 202. Memory 212, or alternately one or more storage devices (e.g., one or more nonvolatile storage devices) within memory 212, includes a non-transitory computer readable storage medium. In some implementations, memory 212 or the computer readable storage medium of memory 212 stores the following programs, modules and data structures, or a subset thereof:
It should be noted that the modules, databases, and models in the survey system 40 describe above in connection with
The backend subsystem identifies (302) a set of product/service keywords for each panelist from the information consumption activity data associated with the panelist. The result mapping relationship between the panelist and the set of keywords from performing this operation are stored in the panelist-keyword database 109. In order to build the relationship between the panelists and the keywords, the backend subsystem may need to consult multiple pre-existing keyword models. As shown in
As noted above, the relationship between the panelists and the keywords is keyed by the panelists. The backend subsystem needs to converts it into a new relationship keyed by the keywords in order to characterize potential customers for a product/service. For each of the set of product/service keywords (304), the backend subsystem aggregates (306) the demographic data of the panelists who are associated with the product/service keyword using the conversion data. For example, if a panelist purchases a particular product/service that is characterized by the keyword, the conversion data associated with this commercial transaction is used for giving more weight to the demographic data of the panelist based on the assumption that another individual having similar demographic data is more likely to be interested in the product/service. Therefore, a company that promotes this type of product/service should “bias” its marketing efforts towards the demographic sector of which the panelist is a member. After the aggregation, the backend subsystem generates (308) a set of demographic attributes from the aggregated demographic data to be associated with the keyword.
Next, the frontend subsystem generates (406) a demographic characterization for the product/service by aggregating the sets of demographic attributes associated with the respective sets of product/service keywords and returns (408) information about the demographic characterization for the product/service for display at the client device. In some implementations, at least some sets of demographic attributes (e.g., the most commonly researched ones) associated with particular product/service keywords can be aggregated in advance of a customer request (e.g., once or twice per day). In some implementations, the demographic characterization includes an age distribution of customers of the product/service, a gender distribution of customers of the product/service, an education distribution of customers of the product/service, an income distribution of customers of the product/service, an ethnicity distribution of customers of the product/service, and a geographical distribution of customers of the product/service.
In this example, the survey system 40 returns a demographic characterization of the potential customers for the product, which is then rendered on the display of the client like the one shown in
Reference has been made in detail to implementations, examples of which are illustrated in the accompanying drawings. While particular implementations are described, it will be understood it is not intended to limit the invention to these particular implementations. On the contrary, the invention includes alternatives, modifications and equivalents that are within the spirit and scope of the appended claims. Numerous specific details are set forth in order to provide a thorough understanding of the subject matter presented herein. But it will be apparent to one of ordinary skill in the art that the subject matter may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the implementations.
Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, first ranking criteria could be termed second ranking criteria, and, similarly, second ranking criteria could be termed first ranking criteria, without departing from the scope of the present invention. First ranking criteria and second ranking criteria are both ranking criteria, but they are not the same ranking criteria.
The terminology used in the description of the invention herein is for the purpose of describing particular implementations only and is not intended to be limiting of the invention. As used in the description of the invention and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and/or “comprising,” when used in this specification, specify the presence of stated features, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, operations, elements, components, and/or groups thereof.
As used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in accordance with a determination” or “in response to detecting,” that a stated condition precedent is true, depending on the context. Similarly, the phrase “if it is determined [that a stated condition precedent is true]” or “if [a stated condition precedent is true]” or “when [a stated condition precedent is true]” may be construed to mean “upon determining” or “in response to determining” or “in accordance with a determination” or “upon detecting” or “in response to detecting” that the stated condition precedent is true, depending on the context.
Although some of the various drawings illustrate a number of logical stages in a particular order, stages that are not order dependent may be reordered and other stages may be combined or broken out. While some reordering or other groupings are specifically mentioned, others will be obvious to those of ordinary skill in the art and so do not present an exhaustive list of alternatives. Moreover, it should be recognized that the stages could be implemented in hardware, firmware, software or any combination thereof.
The foregoing description, for purpose of explanation, has been described with reference to specific implementations. However, the illustrative discussions above are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The implementations were chosen and described in order to best explain principles of the invention and its practical applications, to thereby enable others skilled in the art to best utilize the invention and various implementations with various modifications as are suited to the particular use contemplated. Implementations include alternatives, modifications and equivalents that are within the spirit and scope of the appended claims. Numerous specific details are set forth in order to provide a thorough understanding of the subject matter presented herein. But it will be apparent to one of ordinary skill in the art that the subject matter may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the implementations.
