Methods, systems, articles of manufacture, and apparatus for determining component promotion based on overlapping stimuli

Abstract

Methods, devices, systems, and articles of manufacture are disclosed for determining component lift and synergy based on overlapping stimuli. An example disclosed device for allocating advertising campaign resources includes: a vehicle classifier that classifies impression counts of an advertising campaign into vehicle types and classifies measured lift values ​​associated with the impression counts into corresponding vehicle types in the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed advertisements corresponding to one of the corresponding vehicle types in the vehicle types. The example device also includes: a correlation engine that establishes a correlation between measured lift values ​​and component lift values, the correlation being based on a weighted average between the component lift values ​​and the classified impression counts, the component lift values ​​corresponding to respondents who viewed advertisements corresponding to one of the corresponding vehicle types in the vehicle types; a lift calculator that determines the component lift values ​​based on the correlation; and an activity selector that modifies the allocation of computing resources for at least one of the vehicle types in the advertising campaign based on a comparison of the determined component lift values.

Description

Technical Field

[0001] The present disclosure relates generally to advertising data science and, more particularly, to methods, systems, articles of manufacture, and apparatus for determining component lift and synergy based on overlapping stimuli. Background Art

[0002] In recent years, advertising campaigns for products have begun to use a variety of media vehicles to present information about the product to potential consumers. The use of vehicles allows consumers to be exposed to different advertising stimulus vehicles (e.g., radio, television, online devices, etc.). Advertising companies and / or other entities (e.g., audience measurement entities (AMEs), etc.) are often concerned with determining the effectiveness of different vehicles for advertising campaigns. Summary of the invention

[0003] According to one aspect of the present invention, a device for allocating advertising campaign resources is provided, the device comprising:

[0004] A vehicle classifier, the vehicle classifier:

[0005] Categorize campaign impression counts into vehicle types;

[0006] classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types;

[0007] a correlation engine that establishes a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and categorized impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types;

[0008] a boost calculator that determines the component boost value based on the correlation; and

[0009] A campaign selector is provided to modify an allocation of computing resources to at least one of the vehicle types of the advertising campaign based on the comparison of the determined component boost values.

[0010] According to another aspect of the present invention, a method for allocating advertising campaign resources is provided, the method comprising the following steps:

[0011] By executing instructions with at least one processor, classifying impression counts of the advertising campaign into vehicle types;

[0012] executing instructions with at least one processor to classify measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types;

[0013] establishing, by executing instructions with at least one processor, a correlation between the measured lift value and a component lift value based on a weighted average of the component lift value and classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types;

[0014] Determining the component boost value based on the dependency by executing instructions with at least one processor; and

[0015] An allocation of computing resources to at least one of the vehicle types of the advertising campaign is modified based on the comparison of the determined component boost values ​​by executing instructions with at least one processor.

[0016] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium comprising instructions, which when executed cause a processor to at least:

[0017] Categorize campaign impression counts into vehicle types;

[0018] classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types;

[0019] establishing a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and the classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types;

[0020] determining the component boost value based on the correlation; and

[0021] Based on the comparison of the determined component boost values, an allocation of computing resources to at least one of the vehicle types of the advertising campaign is modified.

[0022] According to another aspect of the present invention, a device for allocating advertising campaign resources is provided, the device comprising:

[0023] A classification device, wherein:

[0024] Classify the impression counts of the campaigns into vehicle types; and

[0025] classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types;

[0026] establishing means for establishing a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types;

[0027] a component promotion determining device, the component promotion determining device determining the component promotion value based on the correlation; and

[0028] A modification device is configured to modify an allocation of computing resources to at least one of the vehicle types of the advertising campaign based on the comparison of the determined component boost values. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic illustration of an example system for computing component promotion according to the teachings of the present disclosure.

[0030] Figure 2 yes Figure 1 An example implementation of the example boost engine.

[0031] Figure 3 It means that it can be executed to achieve Figure 1 A flowchart of machine readable instructions for an example boost engine.

[0032] Figure 4 is constructed to execute Figure 3 Example instructions to implement Figure 1 Block diagram of an example processing platform for an example boost engine.

[0033] These figures are not drawn to scale. Generally, the same reference numbers are used throughout the drawings and accompanying written description to refer to the same or like parts. DETAILED DESCRIPTION

[0034] Product and service promotion activities can occur on one or more different types of media vehicles. As used herein, "media vehicle" or more simply "vehicle" refers to a specific type of vehicle used to deliver advertisements (e.g., advertising ideas or stimulations delivered to or otherwise exposed to a target audience). Example vehicles include radio, newspapers, television, etc. Vehicles can also be defined as groups of other vehicle subsets. For example, "digital" vehicles can refer to any combination of online advertisements that can be viewed on mobile devices, desktop computers, and / or any other suitable digital devices. Advertising campaigns can use one or more vehicles to convey advertisements to consumers. As used herein, "advertising", "advertisement" and / or its variants refer to marketing work types, wherein the products and / or services of interest are delivered through one or more media vehicles. Advertisements can include product and / or service information, audio and / or visual information (e.g., songs, product pictures, commercials, etc.) to disclose such product and / or service information to the audience. As used herein, "consumer," "consumers," "audience," "audience member," refers to a survey subject (e.g., a survey participant), a panelist, and / or more generally, a human being that exhibits behaviors observed in the market research art field.

[0035] One metric used to measure the effectiveness of an advertising campaign and / or vehicle is lift. As used herein, lift refers to a change in product sales associated with an advertising campaign. For example, a positive lift value may be associated with an increase in product sales (e.g., an increase in sales compared to a baseline sales metric, etc.), and a negative lift value may be associated with a decrease in product sales (e.g., someone may be deterred from purchasing a product after seeing an unpleasant advertisement, etc.). In some examples, lift may be expressed as a relative increase (e.g., as a percentage, etc.) relative to a baseline value (e.g., sales as if there were no advertising campaign, etc.). In other examples, lift may be expressed as an absolute value (e.g., a dollar amount, a number of products, etc.). In some examples, interested parties (e.g., advertisers, product manufacturers, etc.) may use lift to determine the effectiveness of advertising campaigns, vehicles, etc.

[0036] In an advertising campaign that uses more than one vehicle (e.g., TV and digital, etc.), it can be difficult to determine the lift corresponding to an individual vehicle. As used herein, "component lift" refers to the lift associated with a single vehicle of an advertising campaign. Component lift is different from "measured lift". As used herein, "measured lift" of a vehicle refers to the lift associated with consumers who are exposed to one or more advertisements via that vehicle. For example, in an advertising campaign that utilizes two vehicles (e.g., TV and radio), each vehicle has an associated component lift and measured lift. In this example, the TV measured lift is associated with any consumer exposed to the TV ad, and can include consumers exposed to both TV and radio ads. On the other hand, the TV component lift is a lift corresponding to those consumers who are exposed to the ad only via the TV vehicle. Similarly, the radio measured lift is associated with any consumer exposed to the radio ad, and can include consumers exposed to both radio and TV ads.

[0037] In many examples, an entity of interest may only have measured lift available because it may be difficult and / or costly to measure component lift directly. Also, in some examples, measured lift may be difficult to interpret. For example, in a two-vehicle advertising campaign where both vehicles have positive measured lift, one of the two vehicles may have negative component lift (e.g., a campaign utilizing both radio and television may have an overall positive lift, but the television vehicle alone may have a negative impact on the campaign, etc.).

[0038] Determining component lift for an advertising campaign is important to an advertising entity, as such information helps determine the effectiveness of advertisements associated with particular vehicles. Knowing the effectiveness of particular vehicles allows the advertising entity to more efficiently allocate campaign resources and / or otherwise prevent wasted resource allocations (e.g., financial resources associated with airtime purchases, computing resources to render ineffective media, etc.). For example, an advertising entity may determine that a particular vehicle is associated with a decrease in lift, and may reallocate budget resources (e.g., money, computing resources) to other, more successful vehicles. Additionally or alternatively, an advertising entity may modify advertisements associated with vehicles having low or negative component lift to increase the effectiveness of those advertisements (e.g., changing graphics associated with online advertisements, etc.).

[0039] The methods and apparatus disclosed herein improve the technical field of advertising research by enabling the calculation of component lift separately from measured lift. The example disclosed method includes the steps of classifying measured impression counts of an advertising campaign into vehicles; determining measured lift associated with respective ones of the vehicles; and establishing a correlation between component lift and measured lift, the correlation being based on a weighted average of the component lift. The example method also includes the steps of determining component lift; and modifying campaign resource allocation based on component lift.

[0040] Figure 1 is a schematic illustration of an example system 100 for computing component boost in accordance with the teachings of the present disclosure. The example system 100 includes: an example provider database 102, an example network 104, and an example boost engine 106. The example boost engine 106 can cause a change in resource allocation for at least one of the example first advertising campaign 108A and / or the example second advertising campaign 108B. In some examples, the boost engine 106 selects and / or otherwise identifies one or more vehicles and / or campaigns 108A, 108B that exhibit the highest relative metrics indicative of boost. In this way, the example boost engine 106 improves the technical field of data science advertising analysis and / or advertising research by preventing waste of resources. In other words, the example boost engine 106 facilitates the identification and corresponding selection of the best advertising vehicles and / or campaigns 108A, 108B.

[0041] The example provider database 102 is a database containing data corresponding to ad impressions and measured lift associated with the corresponding vehicles. As used herein, an "impression count" is the number of people who viewed an ad at least once on an associated vehicle. In some examples, the lift engine 106 may request measured impression counts and measured lift from the example provider database 102 via the network 104, and in some examples, the provider database 102 may be associated with a particular ad vehicle. For example, the provider database 102 may be associated with a television provider, and the measured impression counts and measured lift may be provided to the lift engine 106 via the network 104. In some examples, the provider database 102 may be associated with the presentation medium of the ad (e.g., a database of a social media website). In other examples, the provider database 102 is associated with a point of sale of a product (e.g., an online retailer, etc.). In some examples, if a respondent is a subscriber to the services of a provider of the provider database 102, the provider has the opportunity to record the respondent's impression of the ad and provide the information to the lift engine 106.

[0042] Despite Figure 1Only a single provider database 102 is depicted in the illustrated example of , but the boost engine 106 can retrieve information from any number of database providers (e.g., any number of databases, etc.). In some examples, multiple providers are associated with a single vehicle (e.g., multiple social media website databases can be associated with a digital vehicle, etc.). In some examples, the provider database 102 provides the joint distribution of measured impression counts and measured lift to the boost engine 106. Additionally or alternatively, the boost engine 106 uses the transmitted data to calculate the joint distribution of measured lift and measured impression counts.

[0043] Figure 1 The example network 104 facilitates communication between the provider database 102 and the promotion engine 106. As used herein, "communication", including its variations, encompasses direct communication and / or indirect communication through one or more intermediate components. In some examples, constant communication is not required, so that selective communication can be performed at periodic intervals, non-periodic intervals, and / or scheduled intervals, as well as one-time events. The example network 104 can be implemented by any suitable type of network (e.g., a cellular network, a wired network, the Internet, etc.). In some examples, the example network 104 may not exist (e.g., communication can occur via one or more buses, etc.). In these examples, the measured promotion and measured impression counts can be transmitted to the promotion engine 106 by any other suitable method (e.g., physical mail, email, etc.).

[0044] The example boost engine 106 processes the retrieved measured boosts and measured impression counts to determine component boosts associated with each advertising vehicle. In some examples, the boost engine 106 classifies the impression counts by vehicle type. In some examples, the boost engine 106 establishes a correlation between the classified measured boosts and the expected component boosts. In some examples, the boost engine 106 determines a weighted average correlation between the measured boost and the component boost. In other examples, any other appropriate correlation may be determined. The example boost engine 106 outputs an example component boost and / or a selection of one or more vehicles that exhibit the highest relative boost values. In some examples, the transmission of the component boost may cause a modification and / or selection of an advertising campaign resource allocation.

[0045] The output of the example boost engine 106 may cause a change in resource allocation to at least one of the first advertising campaign 108A and / or the second advertising campaign 108B. For example, the boost engine 106 may cause budget and / or computing resources to be reallocated from one or more vehicles of the first advertising campaign 108A to one or more vehicles of the second advertising campaign 108B. In some examples, the output of the boost engine may cause resources to be reallocated within the first advertising campaign 108A and / or the second advertising campaign (e.g., reallocating resources from inefficient vehicles of the first advertising campaign 108A to highly efficient vehicles of the first advertising campaign 108A, etc.). In some examples, the output of the boost engine 106 may cause modifications to advertisements associated with at least one of the first advertising campaign 108A and / or the second advertising campaign 108B (e.g., changes to graphics of online advertisements, etc.).

[0046] Figure 2 yes Figure 1 The example implementation of the boost engine 106 of FIG. 1 includes an example network interface 202, an example vehicle segregator 204, an example correlation engine 206, an example boost calculator 208, and an example activity selector 210. Figure 2 In the illustrated example, the example network interface 202 is a device for communication or a communication device. Figure 2 In the illustrated example, the example vehicle classifier 204 is a device for classifying, a device for vehicle classification, a vehicle classification device, or a classification device. Figure 2 In the illustrated example of , the example correlation engine 206 is a means for establishing or establishing means. Figure 2 In the illustrated example of , the example lift calculator 208 is a means or a determining means for component lift determination. Figure 2 In the illustrated example of , the example activity selector 210 is a means for modifying or a modifying means. As used herein, the example means for communicating, the example means for classifying, the example means for establishing, the example means for component promotion determination, and the example means for modifying are hardware.

[0047] Figure 2 The example network interface 202 facilitates Figure 1 The network interface 202 may communicate with the provider database 102. For example, the network interface 202 may send a request to retrieve a measurement boost and / or a measurement impression count from the provider database 102. For example, Figure 2The network interface 202 may request and / or otherwise retrieve measured impression counts and measured lift associated with a first vehicle (e.g., television, etc.) of an advertising campaign and a second vehicle (e.g., digital device, etc.) of the advertising campaign. Table 1 below depicts an example summary of the requested data:

[0048] platform Measuring impressions Determination of improvement all <![CDATA[n S ]]> <![CDATA[L S ]]> Vehicle 1 <![CDATA[n 1A ]]> <![CDATA[L 1A ]]> Vehicle 2 <![CDATA[n 2A ]]> <![CDATA[L 2A ]]>

[0049] Table 1: Retrieved example boost information

[0050] Among them, n s represents the total measured impression count associated with all vehicles of interest (e.g., the first vehicle and the second vehicle), n 1A represents the measured impression count associated with any person who generated an impression via the first vehicle, n 2A represents the measured impression count associated with any person who generated an impression via the second vehicle, L S is the total lift of the activity, L 1A represents the measured improvement associated with the first vehicle, and L 2A Represents a measured lift associated with a second vehicle. In some examples, the network interface 202 retrieves data from the provider database 102 (e.g., via the network 104). In some examples, the network interface 202 processes the retrieved data into a format readable by the example vehicle classifier 204. In some examples, in an advertising campaign utilizing more than two vehicles, the network interface 202 retrieves information about the joint distribution of measured impression counts and measured lifts for each vehicle. In some examples, the known measured lifts and known measured impression counts of Table (1) can be used to determine the component lifts associated with each vehicle. In some examples, the measured lift data received by the example network interface 202 can be classified into vehicle types by the vehicle classifier 204.

[0051] The example vehicle classifier 204 classifies the retrieved measured impression counts into component impression counts. An example matrix of component impression counts is depicted in example Table (2):

[0052]

[0053] Table 2: Component enhancement vehicle relationship matrix

[0054] Among them, n 00 Represents the count of component impressions that are not associated with either the first or second vehicle, n 10 Represents the component impression count associated with respondents who had impressions only on the first vehicle, n 01 Represents the component impression count associated with respondents who had impressions only on the second vehicle, n 11represents a component impression count associated with both the first vehicle and the second vehicle. In some examples, the component impression count n 00 、n 10 、n 01 and n 11 are mutually exclusive (e.g., component impression counts do not overlap, etc.). Component impression counts may be calculated from measured impression counts in a manner consistent with example equations (1), (2), and (3):

[0055] n 10 =n s -n 1A (1)

[0056] n 01 =n s -n 2A (2)

[0057] n 11 =n 2A +n 1A -n S (3)

[0058] In other examples, vehicle classifier 204 may use any other suitable equation or technique to classify measured impression counts into component impression counts.

[0059] The example correlation engine 206 establishes correlations between measured improvements and expected component improvements. An example matrix of component improvements is depicted in Table (3):

[0060]

[0061] Table 3: Component enhancement vehicle relationship matrix

[0062] Among them, L 00 is a component lift that is not associated with either the first vehicle (e.g., V1) or the second vehicle (e.g., V2), L 10 is the component lift associated with respondents who only had impressions via the first vehicle, L 01 is the component boost associated with subjects that only generate impressions via the second vehicle, and L 11 is the component lift associated with both the first carrier and the second carrier. The example component lifts of Table (3) are related to the measured lift table (1). For example, the total measured lift (L S ) and all components upgraded (L 00 , L 10 , L 01 , L 11 ) is associated with the first vehicle. 1A ) and the component upgrade associated with the first vehicle (L10 , L 11 ) is associated with the second vehicle. Raise the measurement associated with the second vehicle by (L 2A ) and the component upgrade associated with the second vehicle (L 01 , L 11 ) is associated with.

[0063] The example correlation engine 206 determines that the correlation (e.g., mathematical relationship, etc.) between the measured lift and the component lift is the average of the component lifts weighted (e.g., weighted average, etc.) by the corresponding impression counts. In this example, the correlation engine 206 determines the measured total lift (L) based on the ratio of (A) the sum of the impression counts multiplied by the corresponding component lifts and (B) the sum of those impression counts in a manner consistent with example equation (4). S ) and component upgrade (L 00 , L 01 , L 10 , L 11 ) are related to:

[0064]

[0065] The example correlation engine 206 raises the first carrier measurement (L 1A ) and component upgrade (L 00 , L 10 , L 11 ) is determined as:

[0066]

[0067] Similarly, the example correlation engine 206 raises the second carrier measurement by (L 2A ) and the associated component promotion (L 00 , L 01 , L 11 ) is determined as:

[0068]

[0069] In example equations (4), (5), and (6), each component lift (e.g., L 01 , L 10 , L 11 ) is obtained by counting the corresponding component impressions (e.g., n 01 、n 10 、n 11). In other examples, the correlation engine 206 determines any other suitable correlation between the component lift and the measured lift (e.g., a weighted geometric mean, etc.). In some examples, the correlation determined by the correlation engine 206 is an approximation and / or derived estimate. Additionally or alternatively, the correlation determined by the correlation engine 206 can be derived based on empirical data.

[0070] The example lift calculator 208 determines the component lifts based on the determined correlations. For example, in equations (4), (5), and (6), there are four unknown component lifts (e.g., L 00 , L 10 , L 01 , L 11 ). In some examples, the boost calculator 208 may calculate L 00 Set equal to zero, thus modifying equations (4), (5) and (6) to:

[0071]

[0072] In some examples, L 00 Assumed to be zero, this is because interested parties (e.g., advertisers, product manufacturers, etc.) do not expect the promotion associated with an ad-free vehicle. Additionally or alternatively, L 00 Associating with a zero value allows other components to be promoted (e.g., L 10 , L 01 , L 11 ) relative to the baseline improvement (e.g., L 00 ) is determined. In this example, the lift calculator 208 can use equations (7), (8), and (9) to determine the three remaining component lifts (e.g., L 10 , L 01 , L 11 In other examples, boost calculator 208 utilizes any suitable numerical method to determine component boost (eg, entropy optimization, least squares, etc.).

[0073] Although the operation of the example network interface 202, the example vehicle classifier 204, the correlation engine 206, and the example boost calculator 208 are described with reference to an advertising campaign using two vehicles, advertising campaigns that include any number of vehicles may be analyzed. For example, where a given advertising campaign includes three vehicles (e.g., television, radio, digital devices, etc.), the network interface 202 requests four measured boosts (e.g., any one vehicle, any two vehicles, any three vehicles, and the overall campaign) from the provider database 102. In this example, the vehicle classifier 204 classifies the retrieved impression counts into component impression counts associated with each of the three vehicles. In this example, the correlation engine 206 determines the correlation between the four retrieved measured boosts (e.g., any one vehicle, any two vehicles, any three vehicles, and the overall campaign) and the expected component boost (e.g., only one vehicle, only two vehicles, only three vehicles, the overall campaign, etc.). In some examples, lift calculator 208 solves for component lift using a numerical method (eg, entropy optimization, orthogonal decomposition, any numerical method suitable for solving constrained least squares problems, etc.).

[0074] The example campaign selector 210 uses the determined component boost to modify the allocation of campaign resources (e.g., budgetary resources, computing resources, etc.). For example, the campaign selector 210 reallocates resources from less productive vehicles to more productive vehicles. In some examples, the campaign selector 210 changes the budget associated with one or more vehicle types of the advertising campaign. In other examples, the campaign selector 210 issues a notification to an analyst indicating that a particular vehicle is ineffective so that the analyst and / or the campaign selector 210 can change the content of the advertisements on that vehicle. In other examples, the campaign selector 210 can take any suitable action to modify the allocation of resources for the advertising campaign.

[0075] Although in Figure 2 The implementation is illustrated in Figure 1 and Figure 2 The example boost engine 106 example method, but Figure 2 One or more of the illustrated elements, processes, and / or devices may be combined, divided, rearranged, omitted, eliminated, and / or implemented in any other manner. In addition, the example network interface 202, the example vehicle classifier 204, the example correlation engine 206, the example boost calculator 208, the example activity selector 210, and / or more generally Figure 2The example promotion engine 106 of can be implemented by hardware, software, firmware and / or any combination of hardware, software and / or firmware. Thus, for example, any of the example network interface 202, the example vehicle classifier 204, the example correlation engine 206, the example promotion calculator 208, the example activity selector 210 and / or more generally the example promotion engine 106 can be implemented by one or more analog or digital circuits, logic circuits, programmable processors, programmable controllers, graphics processing units (GPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), programmable logic devices (PLDs) and / or field programmable logic devices (FPLDs). When the apparatus or system of the present patent is understood to cover pure software and / or firmware implementations, at least one of the example network interface 202, the example vehicle classifier 204, the example correlation engine 206, the example promotion calculator 208, the example activity selector 210 is thereby explicitly defined as including: a non-transitory computer-readable storage device or storage disk including software and / or firmware, such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. Furthermore, in addition to or instead of Figure 2 The illustrated elements, processes and / or devices, Figure 1 and Figure 2 The example boost engine 106 may include one or more elements, processes and / or devices, and / or may include more than one of any or all of the illustrated elements, processes and devices. As used herein, the phrase "communication" (including variations thereof) encompasses direct communication and / or indirect communication through one or more intermediate components, and does not require direct physical (e.g., wired) communication and / or continuous communication, but rather includes selective communication at periodic intervals, scheduled intervals, non-periodic intervals, and / or one-time events.

[0076] Figure 3 Shown is the implementation Figure 1 and / or Figure 2 106 of the boost engine 106, a flowchart of example hardware logic, machine readable instructions, a hardware implemented state machine, and / or any combination thereof. The machine readable instructions may be a flowchart for executing a boost engine 106 by a computer processor (such as, for example, the following in conjunction with Figure 4 The program may be embodied in software stored on a non-transitory computer-readable storage medium (such as a CD-ROM, floppy disk, hard drive, DVD, Blu-ray disk, or memory associated with the processor 412), but the entire program and / or its portion may alternatively be executed by other means besides the processor 412, and / or embodied in firmware or dedicated hardware. In addition, although reference is made to Figure 3The example program is described by the flowchart illustrated in , but many other methods of implementing the example promotion engine 106 may alternatively be used. For example, the order of execution of the blocks may be changed, and / or some of the blocks may be changed, eliminated, or combined. Additionally or alternatively, any or all of the blocks may be implemented by one or more hardware circuits (e.g., discrete and / or integrated analog and / or digital circuits, FPGAs, ASICs, comparators, operational amplifiers (op-amps), logic circuits, etc.) that are configured to perform corresponding operations without executing software or firmware.

[0077] As mentioned above, Figure 3 The example processing of can be implemented using executable instructions (e.g., computer and / or machine readable instructions) stored on a non-transitory computer and / or machine readable medium (such as a hard drive, flash memory, read-only memory, compact disk, digital versatile disk, cache memory, random access memory, and / or any other storage device or storage disk, where information is stored for any duration (e.g., for extended periods of time, permanently, for simple examples, for temporary buffering, and / or for caching information). As used herein, the term non-transitory computer readable medium is expressly defined to include any type of computer readable storage device and / or storage disk, and to exclude propagating signals and to exclude transmission media.

[0078] "Include" and "comprising" (and all their forms and tenses) are used herein as open-ended terms. Thus, whenever a claim employs any form of "include" or "comprising" (e.g., includes, comprises, having, etc.) as a preamble or in any type of claim statement, it will be understood that additional elements, terms, etc. may be present without falling outside the scope of the corresponding claim or statement. As used herein, when the phrase "at least" is used as a transitional term, such as in the preamble of a claim, it is open in the same manner as the terms "include" and "comprising" are open. The term "and / or" when used, for example, in a form such as A, B, and / or C, refers to any combination or subset of A, B, C, such as (1) only A, (2) only B, (3) only C, (4) A and B, (5) A and C, (6) B and C, and (7) A and B and C. As used herein in the context of describing structures, components, items, objects, and / or things, the phrase “at least one of A and B” is intended to refer to implementations that include any of (1) at least one A, (2) at least one B, and (3) at least one A and at least one B. Similarly, as used herein in the context of describing structures, components, items, objects, and / or things, the phrase “at least one of A or B” is intended to refer to implementations that include any of (1) at least one A, (2) at least one B, and (3) at least one A and at least one B. As used herein in the context of describing the execution or performance of processes, instructions, actions, activities, and / or steps, the phrase “at least one of A and B” is intended to refer to implementations that include any of (1) at least one A, (2) at least one B, and (3) at least one A and at least one B. Similarly, as used herein in the context of describing the execution or performance of a process, instruction, action, activity, and / or step, the phrase "at least one of A or B" is intended to refer to an implementation that includes any of (1) at least one A, (2) at least one B, and (3) at least one A and at least one B.

[0079] Figure 3 The process 300 of FIG. 1 begins at block 302. At block 302, the network interface 202 retrieves the measured lift and measured impression count. For example, the network interface 202 sends a query to one or more databases (e.g., Figure 1 In some examples, network interface 202 converts the retrieved information into a format readable by boost engine 106. In some examples, the requested data is retrieved as a joint distribution. Alternatively, the data is retrieved through network interface 202 by any other suitable means (e.g., manually entered by a survey subject and / or analyst, retrieved from a local storage (e.g., Figure 4 storage device 428, etc.) for access).

[0080] At box 304, the vehicle classifier 204 classifies the impression counts into component impression counts. For example, in a two-vehicle advertising campaign, the vehicle classifier 204 classifies the retrieved impression counts into the values ​​described in example table (2). In some examples, the vehicle classifier 204 employs example equations (1) through (3) to classify the measured impression counts into component impression counts. In other examples, the vehicle classifier 204 uses any other suitable method to classify the retrieved impression meter data into vehicle types. In some examples, the vehicle classifier 204 may classify the measured lift value associated with the impression count into the vehicle type.

[0081] At block 306, the correlation engine 206 establishes the component boost correlation. For example, the correlation engine 206 determines (e.g., calculates, derives, etc.) the correlation between the measured boost and the component boost as a weighted average. In this example, the correlation engine 206 establishes the correlation in a manner consistent with equations (4) to (6). In other examples, the correlation engine 206 uses any other suitable correlation between the measured boost and the component boost. In some examples, the boost calculator 208 uses a numerical method to calculate the component boost.

[0082] At block 308, the lift calculator 208 determines the component lift. For example, in a two-vehicle advertising campaign, the lift calculator 208 uses example equations (7) to (9) to determine the component lift. In some examples, the lift calculator 208 makes any suitable assumptions to determine the component lift. For example, the lift calculator assumes a baseline lift (e.g., L 00 etc.) is equal to zero.

[0083] At block 310, the campaign selector 210 modifies campaign resource allocations based on the determined boost. For example, the campaign selector 210 allocates resources (e.g., funds, processing resources, bandwidth, etc.) from less productive vehicles (e.g., vehicles with relatively low component boosts) to more productive vehicles (e.g., vehicles with relatively high component boosts). In some examples, the campaign selector 210 issues a notification to an analyst indicating that a particular vehicle is not productive so that the analyst changes the content of an advertisement associated with the vehicle. The process 300 then ends.

[0084] Figure 4 is constructed to execute Figure 3 Instructions to achieve Figure 1 and Figure 2 106. The processor platform 400 may be, for example, a server, a personal computer, a workstation, a self-learning machine (e.g., a neural network), a mobile device (e.g., a cellular phone, a smart phone, an iPad, etc.). TMtablet computer), personal digital assistant (PDA), Internet appliance, DVD player, CD player, digital video recorder, Blu-ray player, game console, personal video recorder, set-top box, headset or other wearable device, or any other type of computing device.

[0085] The processor platform 400 of the illustrated example includes a processor 412. The processor 412 of the illustrated example is hardware. For example, the processor 412 can be implemented by one or more integrated circuits, logic circuits, microprocessors, GPUs, DSPs, or controllers from any desired series or manufacturer. The hardware processor can be a semiconductor-based (e.g., silicon-based) device. In this example, the processor implements the network interface 202, the example vehicle classifier 204, the example correlation engine 206, the example promotion calculator 208, and the example activity selector 210.

[0086] The processor 412 of the illustrated example includes a local memory 413 (e.g., a cache memory). The processor 412 of the illustrated example communicates with a main memory including a volatile memory 414 and a non-volatile memory 416 via a bus 418. The volatile memory 414 may be comprised of a synchronous dynamic random access memory (SDRAM), a dynamic random access memory (DRAM), Dynamic Random Access Memory The non-volatile memory 416 may be implemented by a flash memory and / or any other desired type of storage device. Access to the volatile memory 414 and the non-volatile memory 416 is controlled by a memory controller.

[0087] The processor platform 400 of the illustrated example also includes an interface circuit 420. The interface circuit 420 may be implemented by any type of interface standard, such as an Ethernet interface, a universal serial bus (USB), interface, near field communication (NFC) interface, and / or PCI express interface.

[0088] In the illustrated example, one or more input devices 422 are connected to the interface circuit 420. The input devices 422 permit a user to enter data and / or commands into the processor 412. The input devices may be implemented, for example, by an audio sensor, a microphone, a camera (still or video), a keyboard, buttons, a mouse, a touch screen, a trackpad, a trackball, isopoint, and / or a voice recognition system.

[0089] One or more output devices 424 are also connected to the interface circuit 420 of the illustrated example. The output device 424 can be implemented, for example, by a display device (e.g., a light emitting diode (LED), an organic light emitting diode (OLED), a liquid crystal display (LCD), a cathode ray tube display (CRT), an in-place switching (IPS) display, a touch screen, etc.), a tactile output device, a printer, and / or a speaker. The interface circuit 420 of the illustrated example thus typically includes a graphics driver card, a graphics driver chip, and / or a graphics driver processor.

[0090] The interface circuitry 420 of the illustrated example also includes a communication device (such as a transmitter, a receiver, a transceiver, a modem, a residential gateway, a wireless access point, and / or a network interface) to facilitate data exchange with an external machine (e.g., any kind of computing device) via a network 426. The communication may be, for example, via an Ethernet connection, a digital subscriber line (DSL) connection, a telephone line connection, a coaxial cable system, a satellite system, a direct-line wireless system, a cellular telephone system, etc.

[0091] The processor platform 400 of the illustrated example also includes one or more mass storage devices 428 for storing software and / or data. Examples of such mass storage devices 428 include floppy disk drives, hard disk drives, optical disk drives, Blu-ray disk drives, redundant array of independent disks (RAID) systems, and digital versatile disk (DVD) drives.

[0092] Figure 3 The machine-executable instructions 300 may be stored in the mass storage device 428, in the volatile memory 414, in the non-volatile memory 416, and / or on a removable non-transitory computer-readable storage medium such as a CD or DVD.

[0093] Based on the foregoing, it should be appreciated that example methods, apparatus, and articles of manufacture have been disclosed for determining component promotion and synergy based on overlapping effects. The disclosed methods and apparatus improve the efficiency of using computing devices by allowing resources (e.g., processing power, user time, money, etc.) of advertising campaigns to be more efficiently allocated and / or otherwise allocated in a manner that reduces waste (e.g., computational waste of presenting advertising vehicles with relatively poor performance, reducing monetary waste of such advertising vehicles, etc.). In addition, the disclosed methods and apparatus allow for the determination of the productivity of individual vehicles. Therefore, the disclosed methods and apparatus are directed to one or more improvements in the functionality of computers.

[0094] Although certain example methods, apparatus, and articles of manufacture are disclosed herein, the scope of coverage of this patent is not limited thereto. On the contrary, this patent covers all methods, apparatus, and articles of manufacture fairly falling within the scope of the claims of this patent.

Claims

1. A device for allocating advertising campaign resources, the device comprising: A vehicle classifier, the vehicle classifier: Categorize campaign impression counts into vehicle types; classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types; a correlation engine that establishes a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and categorized impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types; a boost calculator that determines the component boost value based on the correlation; as well as A campaign selector is provided to modify an allocation of computing resources to at least one of the vehicle types of the advertising campaign based on the comparison of the determined component boost values.

2. The device according to claim 1, wherein The corresponding carrier type includes at least one of a digital carrier, a television carrier, a newspaper carrier, or a radio carrier.

3. The device according to claim 1, wherein: The boost calculator calculates the component boost value relative to a baseline boost value.

4. The device according to claim 1, wherein: The activity selector also modifies a budget associated with at least one of the vehicle types.

5. The device according to claim 1, wherein: The campaign selector also redesigns an advertisement associated with a vehicle type of the vehicle types based on the determined component boost value.

6. The device according to claim 1, wherein: The lift calculator utilizes a least squares numerical method to determine the component lift value.

7. The device according to claim 1, wherein: The lift calculator evaluates a ratio of a sum of the component lift values ​​multiplied by the component lift values ​​to a sum of corresponding impression counts to determine the component lift value based on the correlation.

8. A method for allocating advertising campaign resources, the method comprising the following steps: By executing instructions with at least one processor, classifying impression counts of the advertising campaign into vehicle types; executing instructions with at least one processor to classify measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types; establishing, by executing instructions with at least one processor, a correlation between the measured lift value and a component lift value based on a weighted average of the component lift value and classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types; determining the component boost value based on the dependency by executing instructions with at least one processor; as well as An allocation of computing resources to at least one of the vehicle types of the advertising campaign is modified based on the comparison of the determined component boost values ​​by executing instructions with at least one processor.

9. The method according to claim 8, wherein: The corresponding carrier type includes at least one of a digital carrier, a television carrier, a newspaper carrier, or a radio carrier.

10. The method according to claim 8, wherein: The component lift values ​​are calculated relative to a baseline lift value.

11. The method according to claim 8, further comprising the steps of: A budget associated with at least one of the vehicle types is changed.

12. The method according to claim 8, further comprising the steps of: An advertisement associated with a vehicle type of the vehicle types is redesigned based on the determined component boost value.

13. The method according to claim 8, wherein: The step of determining the component improvement value includes: utilizing a least squares numerical method.

14. The method according to claim 8, wherein: Determining the component lift values ​​based on the correlations includes evaluating a ratio of a sum of the component lift values ​​multiplied by the component lift values ​​to a sum of corresponding impression counts.

15. A computer-readable storage medium comprising instructions that, when executed, cause a processor to at least: Categorize campaign impression counts into vehicle types; classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types; establishing a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and the classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types; determining the component boost value based on the correlation; and Based on the comparison of the determined component boost values, an allocation of computing resources to at least one of the vehicle types of the advertising campaign is modified.

16. The computer-readable storage medium of claim 15, wherein: The component lift values ​​are calculated relative to a baseline lift value.

17. The computer-readable storage medium of claim 15, wherein: The instructions, when executed, also cause the processor to change a budget associated with at least one of the vehicle types.

18. The computer-readable storage medium of claim 15, wherein: The instructions, when executed, further cause the processor to redesign an advertisement associated with a vehicle type of the vehicle types based on the determined component promotion value.

19. The computer-readable storage medium of claim 15, wherein: The step of determining the component improvement value includes: utilizing a least squares numerical method.

20. The computer-readable storage medium of claim 15, wherein: Determining the component lift values ​​based on the correlations includes evaluating a ratio of a sum of the component lift values ​​multiplied by the impression counts to a sum of the corresponding impression counts.

21. A device for allocating advertising campaign resources, the device comprising: A classification device, wherein: Categorize campaign impression counts into vehicle types; and classifying measured lift values ​​associated with the impression counts into respective ones of the vehicle types, the classified measured lift values ​​corresponding to respondents who viewed an advertisement corresponding to one of the respective ones of the vehicle types; establishing means for establishing a correlation between the measured lift and a component lift value based on a weighted average of the component lift value and classified impression counts, the component lift value corresponding to respondents who viewed an advertisement corresponding to one of the corresponding ones of the vehicle types; a component promotion determining device, the component promotion determining device determining the component promotion value based on the correlation; as well as A modification device is configured to modify an allocation of computing resources to at least one of the vehicle types of the advertising campaign based on the comparison of the determined component boost values.

22. The apparatus according to claim 21, wherein The corresponding carrier type includes at least one of a digital carrier, a television carrier, a newspaper carrier, or a radio carrier.

23. The apparatus of claim 21, wherein: The component boost determining means calculates the component boost value relative to a baseline boost value.

24. The apparatus of claim 21, wherein: The modifying means also changes a budget associated with at least one of the vehicle types.

25. The apparatus of claim 21, wherein: The modification device also redesigns an advertisement associated with a vehicle type among the vehicle types based on the determined component boost value.

26. The apparatus of claim 21, wherein: The component improvement determination means determines the component improvement value using a least squares numerical method.

27. The apparatus of claim 21, wherein: The component boost determination means evaluates a ratio of a sum of the component boost values ​​multiplied by the component boost values ​​to a sum of corresponding impression counts to determine the component boost value based on the correlation.

Images