Medium-brand association degree quantitative model construction method

Abstract

The invention discloses a medium-brand association degree quantitative model construction method, relates to the technical field of brand propagation data quantification, and aims to solve the problem that the real situation of a medium propagation effect is difficult to reflect due to lack of targeted design for core characteristics of a quick-flash short-term brand in the prior art. The method comprises the following steps: S1, defining core parameters: determining the core parameters of the quick-flash short-term brand, wherein the core parameters comprise a brand life cycle directly determined by a brand party; a medium basic data acquisition system adaptive to the flash type short-term brand propagation scene is constructed, exposure data, interaction data, conversion data and time dimension data of a target medium are acquired, the exposure data comprise total exposure and target audience exposure, and the interaction data comprise unit time interaction frequency, average interaction duration and interaction content. The method has the advantage of improving the accuracy of a medium-brand association degree quantification result.

Description

Technical Field

[0001] This invention relates to the field of brand communication data quantification technology, and more specifically, to a method for constructing a media-brand association quantification model. Background Technology

[0002] Media-brand association measurement technology is a technical solution that assesses the strength of the association between specific media communication behaviors (such as exposure, interaction, and traffic generation) and core brand values ​​(such as brand awareness, user preference, and target conversion effect) by constructing a multi-dimensional quantitative indicator system and combining the collection, calculation, and analysis of media communication data and brand value data.

[0003] Its core is to transform the impact of media on brands from qualitative descriptions into quantifiable values ​​(such as relevance scores). By clearly defining indicators and data sources, it enables precise measurement of "whether media communication effectively reaches brand goals and how much it contributes to enhancing brand value." Ultimately, it provides data-driven decision-making support for brands in media selection, placement strategy optimization, and communication effect evaluation.

[0004] Pop-up short-term brands refer to brand formats with a lifespan limited to 1-3 months. Typical examples include limited-time collaborations, holiday-themed limited-time brands, and short-term pop-up events. Their core communication goal is to quickly achieve brand exposure, user interaction, and immediate conversion within a short period. However, current media-brand association measurement technologies are mostly designed based on the communication characteristics of long-term operating brands (with a lifespan typically ≥1 year), lacking targeted designs for the core characteristics of pop-up short-term brands, and thus failing to reflect the true state of media communication effectiveness. Therefore, we propose a method for constructing a media-brand association measurement model. Summary of the Invention

[0005] The purpose of this invention is to provide a method for constructing a media-brand association quantification model, which aims to solve the problem that existing technologies lack targeted designs for the core characteristics of pop-up short-term brands and are difficult to reflect the true state of media communication effects.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for constructing a media-brand association quantification model, comprising the following steps: S1. Core Parameter Definition: Determine the core parameters of the pop-up short-term brand. These core parameters include the brand lifecycle, which is directly determined by the brand owner. ; S2. Data Acquisition: Construct a media-based data collection system adapted to pop-up short-term brand communication scenarios. Collect exposure data, interaction data, conversion data, and time-related data from the target media. Exposure data includes total exposure and target audience exposure; interaction data includes interaction frequency per unit time, average interaction duration, and interaction content; conversion data includes actual conversions and media reach; and time-related data includes the media placement time, the interval between the data collection time and the start of the brand lifecycle. ; S3, Introducing a time decay coefficient :based on and ,pass The time decay coefficient is calculated to characterize the decay law of the effect of flash-style short-term brand communication over time. ; S4. Construction of a dynamic indicator system: Establish a multi-dimensional quantitative indicator system, including media exposure-related indicators. Interactive correlation indicators Transformation-related indicators Each indicator is assigned a dynamic weight. Furthermore, the range of values ​​for dynamic weights varies. Dynamically adjust and meet ; S5. Correlation Model Construction: Based on Time Decay Coefficient Dynamic weights and media exposure related indicators Interactive correlation indicators Transformation-related indicators Construct a correlation metric model.

[0007] Preferably, in the above S2, the target medium includes at least one of online social media platforms, offline pop-up scene media, AI-generated content media, and short video media.

[0008] Preferably, in S5 above, the expression for the correlation model is: ,in, for Moment Media - Brand Relevance, with a value range of 0-1.

[0009] Preferably, in S2 above, the collection frequency of exposure data, interaction data, conversion data, and time-related data of the target media increases with... The changes are dynamically adjusted, specifically as follows: when At that time, the data collection frequency was daily; when At that time, the data collection frequency was every half day; when The data collection frequency is 1 hour.

[0010] Preferably, in S4 above, the media exposure correlation index The calculation formula is: ,in, For target audience exposure, Total exposure.

[0011] Preferably, in S4 above, the interaction correlation index The calculation formula is: ,in, This is the ratio of interaction frequency per unit time to the industry average. It is the ratio of average interaction time to industry benchmark time. The percentage of brand communication keywords in interactive content. , , The coefficient is , and .

[0012] Preferably, the industry average, industry benchmark duration, and brand communication keywords are directly determined by the brand owner, with coefficients... , , The values ​​range from 0.2 to 0.4, 0.3 to 0.5, and 0.2 to 0.4, respectively.

[0013] Preferably, in S4 above, the conversion-related indicators The calculation formula is: ,in, This represents the actual conversion amount. For media reach.

[0014] Preferably, in S4 above, the range of values ​​for the dynamic weights varies. The specific steps for dynamic adjustment are as follows: when hour, The value range is 0.4-0.5. The value range is 0.25-0.35. The value range is 0.2-0.3; when hour, The value range is 0.2-0.3. The value range is 0.4-0.5. The value range is 0.25-0.35; when hour, The value range is 0.15-0.25. The value range is 0.2-0.3. The value range is 0.5-0.6.

[0015] Preferably, in the above S2, when collecting exposure data, interaction data, conversion data and time dimension data of the target media, a multi-threaded parallel collection mechanism is adopted, and the collection time difference is controlled within 1 minute to ensure the time synchronization of exposure data, interaction data, conversion data and time dimension data.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention clarifies the brand lifecycle and constructs a data collection system adapted to its communication scenarios. It accurately collects exposure data, interaction data, conversion data, and time-dimensional data from multiple target media. Combined with the time decay coefficient calculated based on the brand lifecycle and time intervals, it constructs an indicator system that includes three types of dynamic indicators: media exposure correlation indicators, interaction correlation indicators, and conversion correlation indicators, with weights adjusted over time. Finally, it forms a correlation quantification model that can dynamically and accurately quantify the correlation between media and pop-up short-term brands at different points in time, providing a scientific and practical quantitative basis for evaluating the media communication effect of such brands.

[0017] 2. This invention, by setting differentiated collection frequencies at different stages of the brand lifecycle, ensures the comprehensiveness of data collection during key stages of brand communication, while also accurately capturing rapid changes in communication effects through high-frequency collection in the later stages of communication. This avoids data lag or redundancy issues caused by fixed collection frequencies, making the collected media data more closely aligned with the dynamic characteristics of flash-style short-term brand communication. This provides more accurate and timely data support for subsequent correlation model calculations, further improving the accuracy and reference value of media-brand correlation quantification results.

[0018] 3. By controlling the time difference of data collection to within 1 minute, this invention effectively ensures the time synchronization of exposure, interaction, conversion, and time-dimensional data, ensures the corresponding matching of data from different media at the same time point, reduces the deviation in indicator calculation caused by data time asynchrony, and makes the quantitative evaluation of the effect of flash-style short-term brand media communication more scientific and convincing. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the method in this invention; Figure 2 This is a schematic diagram illustrating the principle of the present invention. Detailed Implementation

[0020] Example 1 This embodiment is a targeted design for pop-up short-term brands, which solves the problem that current media-brand association measurement technologies are mostly based on the communication characteristics of long-term operating brands (lifecycle usually ≥1 year), making it difficult to reflect the true situation of the media communication effect of pop-up short-term brands.

[0021] This embodiment provides a method for constructing a media-brand association quantification model, which includes the following steps: S1. Core Parameter Definition: Determine the core parameters of the pop-up short-term brand. These core parameters include the brand lifecycle, which is directly determined by the brand owner. ; S2. Data Acquisition: Construct a media-based data collection system adapted to pop-up short-term brand communication scenarios. Collect exposure data, interaction data, conversion data, and time-related data from target media (target media include at least one of online social media platforms, offline pop-up scene media, AI-generated content media, and short video media). Exposure data includes total exposure and target audience exposure; interaction data includes interaction frequency per unit time, average interaction duration, and interaction content; conversion data includes actual conversions and media reach; and time-related data includes media placement time, the interval between the data collection time and the start of the brand lifecycle. ; S3, Introducing a time decay coefficient :based on and ,pass The time decay coefficient is calculated to characterize the decay law of the effect of flash-style short-term brand communication over time. ; S4. Construction of a dynamic indicator system: Establish a multi-dimensional quantitative indicator system, including media exposure-related indicators. Interactive correlation indicators Transformation-related indicators ; in: Media exposure related indicators The calculation formula is: ,in, For target audience exposure, Total exposure; Interactive Relationship Metrics The calculation formula is: ,in, This is the ratio of interaction frequency per unit time to the industry average. It is the ratio of average interaction time to industry benchmark time. The percentage of brand communication keywords in interactive content. , , The coefficient is , and Among them, the industry average, industry benchmark duration, and brand communication keywords are directly determined by the brand owner, and the coefficients are... , , The value ranges are 0.2-0.4, 0.3-0.5, and 0.2-0.4, respectively. Conversion-related metrics The calculation formula is: ,in, This represents the actual conversion amount. For media reach; It is important to note that dynamic weights need to be assigned to each indicator. Furthermore, the range of values ​​for dynamic weights varies. The specific steps for dynamic adjustment are as follows: when hour, The value range is 0.4-0.5. The value range is 0.25-0.35. The value range is 0.2-0.3; when hour, The value range is 0.2-0.3. The value range is 0.4-0.5. The value range is 0.25-0.35; when hour, The value range is 0.15-0.25. The value range is 0.2-0.3. The value range is 0.5-0.6; It is important to note that the values ​​of the dynamic weights must satisfy the following conditions: ; S5. Correlation Model Construction: Based on Time Decay Coefficient Dynamic weights and media exposure related indicators Interactive correlation indicators Transformation-related indicators Construct a correlation metric model, the expression of which is: ,in, for Moment-to-Brand Relevance, with a value range of 0-1, is an expression centered on the characteristics of flash-style, short-term brand communication. It first defines the brand lifecycle. and the interval between the data collection time point and the start point of the lifecycle. Based on the two through formula Derive the time decay coefficient Subsequently, a multi-dimensional quantitative indicator system was constructed, including media exposure-related indicators. For target audience exposure, (Total exposure) and interactive metrics ( This is the ratio of interaction frequency per unit time to the industry average. It is the ratio of average interaction time to industry benchmark time. The percentage of brand communication keywords in interactive content. , , (coefficients with a sum of 1), transformation correlation indicators ( This represents the actual conversion amount. (for media reach), and according to Location Different intervals , , Assign dynamic weights to each indicator , , And satisfy Finally, considering the impact of time decay on various dimensional indicators, the time decay coefficient is... The final result is derived by multiplying the sum of the indicators after weighting each dynamic weight.

[0022] This embodiment first clarifies the core parameters of pop-up short-term brands, where the brand lifecycle is directly determined by the brand owner, aligning with its short-term operational nature. It then establishes a media-based data collection system adapted to pop-up scenarios, covering multiple target media including online social platforms, offline pop-up scenes, AI-generated content, and short videos. This comprehensively collects exposure data, interaction data, conversion data, and time-related data, ensuring data coverage of key aspects of pop-up brand communication. Based on this, a time decay coefficient is introduced to characterize the decay of the pop-up short-term brand communication effect over time. Simultaneously, a multi-dimensional dynamic indicator system is constructed, including media exposure-related indicators, interaction-related indicators, and conversion-related indicators. Furthermore, the weight of each indicator is dynamically adjusted according to different communication stages within the brand lifecycle, i.e., the initial stage of communication (…). Focusing on exposure dimensions, mid-term ( Focusing on the interactive dimension, later ( Focusing on the conversion dimension, the indicator system can match the communication priorities of pop-up brands at different stages. The resulting correlation quantification model can accurately represent the degree of correlation between media and pop-up short-term brands at different time points, and intuitively present the time decay trend of communication effects. It provides a scientific quantitative tool that fits the characteristics of pop-up short-term brands to evaluate media value and optimize communication strategies.

[0023] Example 2 This embodiment is basically the same as Embodiment 1, except that the collection frequency of exposure data, interaction data, conversion data, and time-related data of the target media in this embodiment varies. The changes are dynamically adjusted, specifically as follows: when At that time, the data collection frequency was daily; when At that time, the data collection frequency was every half day; when The data collection frequency is 1 hour.

[0024] This embodiment, based on Embodiment 1, dynamically optimizes the media data collection frequency to address the data change characteristics at different stages of a pop-up short-term brand's dissemination, further improving the quality of the collected data and the accuracy of the model's output. The core principle is that the rhythm and data fluctuation characteristics of pop-up short-term brands differ at different dissemination stages. For example, in the early stages of dissemination, brand popularity gradually increases with relatively smooth data changes; in the middle stages, as the brand enters a critical period of popularity, dynamic data changes accelerate; and in the later stages, nearing the end of the product lifecycle, data is prone to rapid fluctuations. Based on this characteristic, Embodiment 2 matches differentiated collection frequencies for different stages. In the initial stage (when... At the time of collection (daily collection), a collection frequency adapted to a gradual pace is adopted to avoid redundancy while ensuring complete data coverage. In the medium term (when...), The collection frequency was initially set at half-day, but was adjusted to a more flexible frequency to capture dynamic changes in data in a timely manner. Later (when...) (At the time, the collection frequency is 1 hour) adopts a high-frequency collection mode to accurately record key data details and avoid the loss of important information due to collection delays. This dynamic collection strategy makes the collected data more in line with the communication rhythm of the pop-up brand, providing more timely and targeted data support for the subsequent calculation of the correlation model, and improving the practical value of quantitative evaluation.

[0025] Example 3 This embodiment is basically the same as Embodiment 1. The difference is that when collecting exposure data, interaction data, conversion data and time dimension data of the target media in this embodiment, a multi-threaded parallel collection mechanism is adopted, and the collection time difference is controlled within 1 minute to ensure the time synchronization of exposure data, interaction data, conversion data and time dimension data.

[0026] This embodiment employs a multi-threaded parallel data collection mechanism to simultaneously collect data from online social media platforms, offline pop-up media, AI-generated content media, and short video media, avoiding the time differences caused by the sequential nature of single-threaded collection. Furthermore, by controlling the collection time interval, it ensures that all types of data from all media correspond to the same time point. This is particularly crucial for pop-up short-term brands (whose short lifespan and rapidly changing dissemination effects mean that time misalignment in data can directly lead to calculation deviations in various related indicators, affecting the adjustment effect of the time decay coefficient and dynamic weights, ultimately distorting the correlation results). This further enhances the reliability of the quantitative evaluation of the media dissemination effect of pop-up short-term brands.

[0027] The embodiments disclosed in this invention are preferred embodiments, but are not limited thereto. Those skilled in the art can easily understand the spirit of this invention based on the above embodiments and make different extensions and variations, but as long as they do not depart from the spirit of this invention, they are all within the protection scope of this invention.

Claims

1. A media-brand association quantification model construction method, characterized in that, The method comprises the following steps: S1, Core parameter definition: determining the core parameter of the flash short-term brand, the core parameter including the brand life cycle directly determined by the brand party ; S2, acquiring data: constructing a media basic data collection system suitable for the flash short-term brand communication scene, collecting exposure data, interaction data, conversion data and time dimension data of the target media, wherein the exposure data includes total exposure and target audience exposure, the interaction data includes unit time interaction frequency, average interaction time, and interaction content, the conversion data includes actual conversion and media reach, and the time dimension data includes the interval length between the media delivery time point, the data collection time point and the brand life cycle starting point ; S3, introducing time decay coefficient : based on and , the time decay coefficient is calculated by to characterize the decay law of the flash-like short-term brand communication effect over time, wherein ; S4, dynamic index system construction: establish a multi-dimensional quantitative index system, including media exposure correlation indicators , interactive correlation indicators , conversion correlation indicators , and give dynamic weight to each indicator , and the value range of dynamic weight is dynamically adjusted , and meets ; S5, correlation degree model construction: based on time attenuation coefficient , dynamic weight and media exposure correlation index , interactive correlation index , conversion correlation index Construct a correlation quantification model.

2. The method of claim 1, wherein the media-brand association quantification model is constructed by: In the above S2, the target medium includes at least one of online social platform medium, offline flash scene medium, AI generated content medium and short video medium.

3. The method of claim 1, wherein the method further comprises: determining a plurality of media-brand association metrics; and determining a plurality of media-brand association metric weights. In the above S5, the expression of the correlation degree model is wherein, is The moment media-brand correlation degree, the value range is 0-1.

4. The method of claim 1, wherein the media-brand association quantification model is constructed by: In S2 above, the collection frequency of exposure data, interaction data, conversion data, and time-related data of the target media varies. The changes are dynamically adjusted, specifically as follows: When the collection frequency is daily collection; When the acquisition frequency is every half day; When the collection frequency is every hour.

5. The method of claim 1, wherein the media-brand association quantification model is constructed by: In the above S4, the media exposure correlation index The calculation formula is: Wherein, is the target audience exposure, is the total exposure.

6. The method of claim 1, wherein the method further comprises: In the above S4, the interactive correlation index The calculation formula is: Wherein, is the ratio of the interaction frequency per unit time to the industry average, is the ratio of the average interaction time to the industry benchmark time, is the proportion of brand communication keywords in the interaction content, , , is a coefficient, and .

7. The method of claim 6, wherein the method further comprises: determining a plurality of media-brand association metrics; and determining a plurality of media-brand association metric weights. The industry average, industry benchmark duration, and brand communication keywords are determined directly by the brand owner, and the coefficients are... , , The values ​​range from 0.2 to 0.4, 0.3 to 0.5, and 0.2 to 0.4, respectively.

8. The method of claim 1, wherein the method further comprises: determining a plurality of media-brand association metrics; and determining a plurality of media-brand association metric weights. In the above S4, the conversion association index The calculation formula is: Wherein, is the actual conversion amount, is the media reach amount.

9. The method of claim 1, wherein the method further comprises: determining a plurality of media-brand association metrics; and determining a plurality of media-brand association metric weights. In the above S4, the value range of the dynamic weight is changed with The specific steps of the dynamic adjustment are as follows: when hour, The value range is 0.4-0.

5. The value range is 0.25-0.

35. The value range is 0.2-0.3; when hour, The value range is 0.2-0.

3. The value range is 0.4-0.

5. The value range is 0.25-0.35; when hour, The value range is 0.15-0.

25. The value range is 0.2-0.

3. The value range is 0.5-0.

6.

10. The method of claim 4, wherein the method further comprises: determining a plurality of media-brand association metrics; and determining a plurality of media-brand association metric weights. In the above S2, when collecting exposure data, interaction data, conversion data and time dimension data of the target medium, a multi-thread parallel collection mechanism is adopted, the collection time difference is controlled within 1 minute, and the time synchronization of the exposure data, the interaction data, the conversion data and the time dimension data is ensured.

Images