An advertisement delivery data evaluation system based on multi-channel information integration

Abstract

The application relates to the field of evaluation optimization, and discloses an advertisement putting data evaluation system based on multi-channel information integration, which comprises a data standardization and fusion module, which is responsible for receiving multi-source heterogeneous original data, cleaning through an embedded data connector and an analysis engine, and forcibly converting all the data into a unified atomic event model containing a unique device identifier, a standard time stamp and a standard latitude and longitude coordinate. A scientific control group is generated by constructing an exposure group and using a propensity score matching algorithm, and finally, a conversion promotion rate is calculated, so that the technical effect of scientifically stripping interference factors and quantifying the online conversion net contribution value brought by offline advertisement putting in a cause-effect inference manner is achieved, and the problem that offline advertisement actual contribution to online conversion cannot be accurately attributed and quantified due to the lack of reliable cross-screen tracking and scientific attribution methods is solved.

Description

Technical Field

[0001] This invention relates to the field of evaluation and optimization technology, specifically to an advertising placement data evaluation system based on multi-channel information integration. Background Technology

[0002] Advertising effectiveness refers to the impact of advertising campaigns or works on consumers. In a narrow sense, advertising effectiveness refers to the economic results achieved by advertising, and the degree to which advertising achieves its objectives usually includes communication and sales effects. In a broader sense, advertising effectiveness includes psychological and social effects. Psychological effects are the degree to which advertising influences the audience's psychological cognition, emotions, and will; they are a concentrated manifestation of advertising's communication, economic, educational, and social functions. Social effects refer to the impact of advertising on social morality, culture, education, ethics, and the environment. Good social effects can also bring good economic benefits to enterprises. The evaluation of advertising effectiveness generally refers to the evaluation of advertising's economic effects. The evaluation of advertising effectiveness involves investigating consumers' exposure to various media, such as newspapers, magazines, radio, television, and outdoor advertising.

[0003] For example, Chinese invention application CN110264241A discloses an advertising placement evaluation and optimization system based on big data, including an advertising placement data collection module, an advertising placement data processing module, a database, a central processing unit, a display screen, an advertising placement effect analysis module, an advertising placement evaluation module, and a display screen. The advertising placement data collection module is used to collect data information on advertising placement, including click region information, page view information, click volume information, population information, and clicker account information. The account information records the clicker's age information.

[0004] Based on the aforementioned prior art documents, the proposed advertising data evaluation system based on multi-channel information integration has the following shortcomings in the existing technology:

[0005] Traffic flow data, advertising exposure logs, and user location events originate from different systems. The fundamental differences in data structure, time units, and geographic coordinates mean that, under current technology, the lack of a standardized data fusion model prevents them from being integrated into a unified view for correlation analysis.

[0006] Outdoor screens have fixed geographical locations and different playback times, but the audience changes dynamically in the urban space. Existing technologies cannot map discrete advertising exposure events and continuous crowd flow data on a unified spatiotemporal benchmark, thus failing to achieve a fair comparison of advertising effects across screens and regions.

[0007] The lack of reliable cross-device identification and tracking methods in current technology prevents the establishment of a data link between the anonymous audience exposed by offline advertising and online conversion behavior occurring on personal devices. This makes it impossible to accurately attribute and quantify the actual contribution of out-of-home advertising to online conversion.

[0008] To address these issues, this invention proposes an advertising placement data evaluation system based on multi-channel information integration. Summary of the Invention

[0009] To address the shortcomings of existing technologies, this invention provides an advertising placement data evaluation system based on multi-channel information integration, in order to solve the problems mentioned in the background section.

[0010] To achieve the above objectives, the present invention provides the following technical solution: an advertising placement data evaluation system based on multi-channel information integration, wherein the advertising placement data evaluation system comprises:

[0011] The data standardization and fusion module is responsible for receiving multi-source heterogeneous raw data, cleaning it through the built-in data connector and parsing engine, forcibly converting all data into a unified atomic event model containing a unique device identifier, standard timestamp and standard latitude and longitude coordinates, and finally outputting a standard atomic event stream.

[0012] The spatiotemporal data fusion and indexing module is used to receive the output standard atomic event stream. Through spatial gridding and temporal slicing technology, each standard atomic event is mapped to a unique spatiotemporal coordinate to build a spatiotemporal index database that supports efficient querying.

[0013] The incremental conversion attribution analysis module, based on the constructed database, defines the exposure group according to the advertising campaign definition, generates the corresponding control group using a propensity score matching algorithm, and finally calculates and compares the conversion rate to obtain the conversion improvement rate of the advertising effect.

[0014] The incremental conversion attribution analysis module further includes:

[0015] The exposure group delineation unit is used to receive the geographic grid set and time slice set of the advertising campaign, and based on the spatiotemporal index data output by the spatiotemporal data fusion and indexing module, extract all unique device identifiers that appear in the geographic grid set of the advertising campaign within the time slice set of the advertising campaign, and form an exposure group.

[0016] The control group generation unit receives the exposure group generated by the exposure group selection unit and executes a propensity score matching algorithm to generate a control group. The algorithm first calculates a propensity score for the exposure group and candidate devices that have not been exposed to the advertising campaign using a logistic regression model. The logistic regression model is as follows:

[0017]

[0018] Where p(X) is the probability that the device belongs to the exposure group, e is the base of the natural logarithm, and X is the probability of a device belonging to the exposure group based on a preset user profile covariate X. i The eigenvectors formed by β0 and β i These are the regression coefficients obtained through model training;

[0019] The algorithm then describes the control group for each device in the exposure group, which consists of the candidate devices with the closest matching tendency score.

[0020] The conversion attribution calculation unit is used to receive the generated exposure group and the control group generated by the control group generation unit, count the number of conversion devices within a preset attribution period, and then calculate the conversion improvement rate in the following manner:

[0021]

[0022] Where Lift is the final calculated conversion improvement rate, and N C,E |P represents the number of devices that underwent conversion within the exposure group. E | represents the total number of devices in the exposure group, N C,C |P represents the number of devices that underwent transformation in the control group. C | represents the total number of devices in the control group;

[0023] The statistical significance testing unit receives the calculated conversion improvement rate and the conversion data of each group, and uses a two-sample proportion Z-test to calculate the Z-statistic to determine the statistical significance of the conversion improvement rate. The formula for calculating the Z-statistic is as follows:

[0024]

[0025] Where Z is the calculated Z-statistic, CR E For the conversion rate of the exposure group, CR C The conversion rate of the control group is shown. For fusion conversion rate;

[0026] When the absolute value of the Z statistic is greater than the critical value corresponding to the preset significance level, the conversion improvement rate is determined to be statistically significant.

[0027] The data application and visualization module is used to receive the output conversion improvement rate and related statistical test results, and present the quantitative evaluation indicators to the end user through the application programming interface or visualization dashboard.

[0028] Preferably, the data standardization and fusion module uses a built-in device ID map to uniformly map device identifiers from different sources to unique device identifiers within the system.

[0029] Preferably, the data standardization and fusion module converts imprecise location information such as base station IDs or IP addresses into standard latitude and longitude coordinates by calling a geocoding service.

[0030] Preferably, the spatiotemporal data fusion and indexing module uses the Geohash algorithm to divide the geographic space into the geographic grid and divide the time axis into time slices at fixed intervals.

[0031] Preferably, the incremental conversion attribution analysis module identifies the exposure group by extracting the set of all unique device identifiers that appear in the geographic grid set of the advertising campaign within the time slice set of the advertising campaign;

[0032] The incremental conversion attribution analysis module generates the control group by using a propensity score matching algorithm to select a set of devices that are similar to the exposure group in terms of preset user profile covariates from devices that have not been exposed to the advertising campaign.

[0033] Preferably, the conversion improvement rate is calculated as follows: first, the conversion rates of the exposure group and the control group within a preset attribution period are calculated, and then the difference between the conversion rates of the exposure group and the control group is divided by the conversion rate of the control group.

[0034] Preferably, the incremental conversion attribution analysis module is used to perform a statistical significance test on the conversion improvement rate to determine whether the conversion improvement brought about by the advertising campaign is statistically significant.

[0035] Preferably, the data standardization and fusion module further includes:

[0036] The data access and parsing unit is used to receive multi-source heterogeneous raw data through a preset data connector, call the parsing engine to extract fields from the raw data, and generate a raw record containing the original device identifier, the original timestamp, and the original location information.

[0037] A data validity verification unit is used to receive the generated original records, execute a validity verification function based on each original record, and output valid original records that pass the validity verification. The validity verification function has the following criteria:

[0038] F valid (R raw ) = (ID raw ≠NULL)∧IsParsable(Traw )∧IsGeocodable(L raw ),

[0039] Among them, F valid For the validity check function, R raw For a single original record, ID raw T is the original device identifier contained in the original record. raw L is the original timestamp contained in the original record. raw The IsParsable function is used to determine whether the format of this timestamp can be parsed by the system, and the IsGeocodable function is used to determine whether this location information can be converted into geographic coordinates.

[0040] The core field standardization unit receives the output valid original record and calls the following transformation function to perform standardization transformation on the fields in the valid original record to generate standard device identifiers, standard timestamps, and standard latitude and longitude coordinates:

[0041] Device identifier mapping function M(ID) raw )→ID std This is used to map the original device identifier to a unique standard device identifier within the system by querying the built-in device ID graph;

[0042] Timestamp conversion function C(T) raw →T std This is used to uniformly convert the parsable original timestamps into the standard timestamps in Coordinated Universal Time (UTC) millisecond units;

[0043] Geographic location transformation function G(L) raw )→L std This is used to uniformly convert the geocoded original location information into the standard latitude and longitude coordinates of the WGS-84 coordinate system;

[0044] The standard event generation unit is used to receive the generated standard device identifier, standard timestamp, and standard latitude and longitude coordinates, and encapsulate the standard fields into a preset unified atomic event model. Finally, all generated unified atomic event models are collected to form the standard atomic event stream.

[0045] Preferably, the spatiotemporal data fusion and indexing module further includes:

[0046] A standard event receiving unit is used to receive the standard atomic event stream and distribute the standard atomic events one by one. Each standard atomic event contains a standard timestamp and standard latitude and longitude coordinates.

[0047] A spatial dimension mapping unit is used to receive the distributed standard atomic events and call a spatial encoding function to process the standard latitude and longitude coordinates contained in the standard atomic events to generate a unique geographic grid ID. The spatial encoding function is:

[0048] ID grid =GeohashEncode(L std ,P geo ),

[0049] Among them, ID grid For the generated geographic grid ID, GeohashEncode is the standard Geohash algorithm function that encodes latitude and longitude coordinates. std P is the input standard latitude and longitude coordinates. geo These are the preset geographic grid coding parameters;

[0050] The time dimension mapping unit is used to receive the standard atomic event with the geographic grid ID appended after processing, and to call the time slicing function to process the standard timestamp contained in the standard atomic event to generate a unique time slice ID. The time slicing function is as follows:

[0051]

[0052] Among them, ID slot For the generated time slice ID, T is the floor function. std The input is the standard timestamp, and Δt is the preset fixed duration of a single time slice;

[0053] The spatiotemporal event indexing unit is used to receive the standard atomic event after processing, which is simultaneously appended with the geographic grid ID and the time slice ID, and to store the device identifier in the standard atomic event into the index database pointed to by the composite key formed by the geographic grid ID and the time slice ID, thus ultimately forming the spatiotemporal index data.

[0054] Preferably, the data application and visualization module further includes:

[0055] The attribution result receiving unit is used to receive the conversion improvement rate, Z statistic and related conversion data output by the incremental conversion attribution analysis module, and to encapsulate the received data into a structured attribution result object.

[0056] The evaluation metric parsing and enhancement unit is used to receive the encapsulated attribution result object, and call the following function to parse and enhance the data in the attribution result object to generate enhanced evaluation metrics containing confidence intervals:

[0057] First, calculate the p-value corresponding to the Z-statistic:

[0058] ρ=2×(1-Φ(|Z|)),

[0059] Where ρ is the calculated p-value, |Z| is the absolute value of the |Z| statistic, and Φ is the cumulative distribution function of the standard normal distribution;

[0060] Calculate the confidence interval for the difference in conversion rates between the exposure group and the control group:

[0061]

[0062] Where CI is the calculated confidence interval, and CR E With CR C |P represents the conversion rate between the exposure group and the control group. E |and|P C | represents the total number of devices in the exposure group and the control group, z α / 2 To achieve the preset information level z α / 2 The critical value of the standard normal distribution under the given conditions;

[0063] A terminal output generation unit is configured to receive the generated enhanced evaluation metrics and perform formatting processing according to a preset output target. The formatting processing includes:

[0064] If the output target is an application programming interface (API), the enhanced evaluation metrics are serialized into a JSON-formatted response body.

[0065] If the output target is a visual dashboard, the enhanced evaluation index is converted into a visual chart component. Based on the comparison between the p-value and the preset significance level α, a judgment conclusion is generated. The conditions for generating the judgment conclusion are as follows:

[0066]

[0067] Here, Conclusion refers to the final judgment presented to the user.

[0068] The data standardization and fusion module, by establishing a unified atomic event model, fundamentally solves the initial obstacle of the inability to fuse and analyze multi-source heterogeneous data due to inconsistent standards. The benefit lies in providing the system with a single, reliable, and high-quality data entry point. By forcibly transforming all the chaotic raw data into a standardized and consistent stream of events, it ensures data interoperability and consistency in all subsequent analysis stages, providing a solid foundation for cross-channel data evaluation.

[0069] The spatiotemporal data fusion and indexing module cleverly solves the industry challenge of accurately aligning dynamically changing audiences with static advertising screens by constructing a unified, discrete spatiotemporal coordinate system. The benefit lies in providing each standard event with a spatiotemporal context that can be accurately queried and analyzed, transforming a flat data stream into a structured data cube. This makes efficient and fair audience selection within massive datasets possible, serving as a bridge connecting data and business scenarios.

[0070] The incremental conversion attribution analysis module employs a causal inference method based on controlled experiments, providing a scientifically rigorous measurement of advertising effectiveness, surpassing the limitations of traditional attribution models that can only reveal correlations. Its advantage lies in its ability to effectively isolate the interference of all exogenous variables, such as market trends, brand effects, and users' natural conversion intentions, through a propensity score matching algorithm. This allows for the calculation of the net increase in conversions brought about by advertising, providing advertisers with a true, reliable, and statistically significant basis for evaluating return on investment.

[0071] The data application and visualization module, as the final output layer of the system, is the "last mile" connecting complex data science with business decisions. Its advantage lies in transforming highly quantified but relatively abstract attribution analysis results into visual reports, dashboards, and API data services that business personnel can intuitively understand. This significantly lowers the barrier to data use, enabling data insights to be quickly and easily applied to real-world business scenarios such as advertising strategy optimization, budget allocation adjustments, and media value assessment, thus achieving a closed loop of data value.

[0072] This invention provides an advertising placement data evaluation system based on multi-channel information integration. It has the following beneficial effects:

[0073] 1. This invention achieves the technical effect of transforming data with different sources, formats, and definitions into a unified, standardized event stream that can be directly analyzed by forcibly converting all received multi-source heterogeneous data into a unified atomic event model. Compared with the technical solutions in the prior art that rely on independent processing scripts for different data sources or incompatible data systems, this invention solves the problem that data cannot be integrated into a unified view for correlation analysis due to fundamental differences in data structure, time unit, and geographical coordinates.

[0074] 2. This invention uses spatial gridding and temporal slicing techniques to accurately map all standard atomic events to a unified, discrete spatiotemporal coordinate system. This achieves the technical effect of accurately matching discrete advertising exposure events and continuous crowd flow data on a unified spatiotemporal reference. Compared with existing technologies that use fuzzy radius estimation or misaligned time-series data for matching, this invention solves the problem of the inability to fairly compare cross-screen and cross-regional advertising effects due to the inability to accurately map the data.

[0075] 3. This invention constructs an exposure group and uses a propensity score matching algorithm to generate a scientific control group. Finally, it calculates the conversion improvement rate, achieving the technical effect of scientifically removing interfering factors and quantifying the net contribution value of online conversion brought by offline advertising in a causal inference manner. Compared with the existing technical solutions that rely on correlation analysis or lack control group attribution models, this invention solves the problem that the actual contribution of offline advertising to online conversion cannot be accurately attributed and quantified due to the lack of reliable cross-screen tracking and scientific attribution methods. Attached Figure Description

[0076] Figure 1 This is a system framework diagram of the present invention. Detailed Implementation

[0077] To enable those skilled in the art to understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.

[0078] The present invention will now be described in detail with reference to the accompanying drawings:

[0079] Example 1: Evaluation of the Effectiveness of Outdoor Digital Media Advertising in Smart Cities

[0080] Please see the appendix Figure 1 This embodiment aims to evaluate the actual conversion improvement effect of an outdoor digital media advertisement placed by a coffee brand in a core urban business district based on online mini-program coupon redemption behavior.

[0081] Data standardization and integration:

[0082] Data reception: The data standardization and fusion module receives three types of heterogeneous raw data:

[0083] 1. Anonymized user signaling data provided by telecommunications operators, including device identifiers, timestamps, and base station locations;

[0084] 2. Ad playback logs provided by the ad screen media owner, including screen ID, ad creative ID, and playback time;

[0085] 3. The coupon redemption records provided by the coffee brand's mini-program backend include the user's unique identifier, redemption time, and coupon ID;

[0086] Standardized processing: Units within the module are executed sequentially:

[0087] First, the data validity verification unit removes records lacking necessary information. Next, the core field standardization unit maps the operator's device identifier and the mini-program OpenID to unique device identifiers within the system, unifies all times to UTC millisecond-level timestamps, and converts base station locations to WGS-84 standard latitude and longitude coordinates using a geocoding service. Finally, the standard event generation unit outputs three types of standard atomic event streams: LOCATION PING DOOH EXPOSURE ONLINE CONVERSION ;

[0088] Spatiotemporal data fusion and indexing:

[0089] Spatiotemporal mapping: The spatiotemporal data fusion and indexing module receives the aforementioned standard atomic event stream. The module uses a Geohash algorithm with a precision of 7 to grid the city and performs time slices at 5-minute intervals.

[0090] LOCATION PING With DOOH EXPOSURE Events are mapped to unique combinations and stored in a spatiotemporal index database;

[0091] Incremental conversion attribution analysis:

[0092] Targeting Groups: After the advertising campaign ends, the incremental conversion attribution analysis module is activated. The exposure group targeting unit extracts all matching device identifiers from the spatiotemporal index database based on the advertising campaign plan, forming exposure groups.

[0093] Generate a control group: The control group generation unit consists of a large number of devices that do not appear in the exposure geographic grid and time slice. The user's activity range entropy, historical business district visit frequency, and online consumption preference tags are used as covariates. The propensity score is calculated through a logistic regression model. The device with the closest score is matched to each device in the exposure group to form a control group that is highly similar to the profile of the exposure group.

[0094] Calculation and Verification: Within a 7-day attribution period after the ad ends, the conversion attribution calculation unit counts the number of mini-program coupons claimed by users.

[0095] Assuming the exposure group has 100,000 people and 1,200 people receive the product; and the control group has 100,000 people and 500 people receive the product; the conversion improvement rate is calculated to be 140%; then the statistical significance test unit calculates the Z-statistic, and if the absolute value is greater than 1.96 (corresponding to the 95% confidence level), it is determined that this campaign has brought about a statistically significant conversion improvement;

[0096] Data application and visualization:

[0097] Results: The data application and visualization module received a 140% conversion improvement rate and passed the significance test; the end user's dashboard will display this indicator in the form of a chart, with confidence interval and p-value. At the same time, the map component will display the geographical distribution of the exposed audience in the form of a heat map, providing the brand with a decision-making basis for optimizing future advertising locations.

[0098] Example 2: Targeted Traffic Acquisition Assessment for Smart Retail Stores

[0099] This embodiment aims to evaluate the effect of digital wayfinding screen advertising at the entrance of a large shopping mall on driving in-store traffic and member registration behavior for specific brands;

[0100] Scenario: A shopping mall is displaying new product advertisements for a sports brand store on its entrance screen;

[0101] Data source:

[0102] 1. Customer movement data provided by Wi-Fi probes or Bluetooth beacon systems deployed in shopping malls;

[0103] 2. Ad playback logs on the entrance screen;

[0104] 3. Backend data of the sports brand store's membership registration system and in-store customer flow counter data;

[0105] Exposure definition: Customers whose devices are captured by Wi-Fi probes in the vicinity of the entrance screen during the advertising playback period.

[0106] Transformation definition:

[0107] 1. Within one hour of entry, the device is detected by the customer flow counter or Wi-Fi probe at the entrance of the sports brand store;

[0108] 2. Complete the brand's online membership registration within 24 hours of entry;

[0109] Analysis process: The system identifies the exposure group that sees the advertisement at the entrance, and matches the control group from customers who enter from other entrances and have similar profiles. By comparing the store visit rate and the membership registration rate, the conversion improvement rate is calculated.

[0110] Beneficial effects: Shopping malls can provide brands with quantifiable data reports on traffic generation, proving the value of advertising space; brands can use this data to assess the actual effectiveness of offline advertising in attracting potential customers to their stores and expanding their private traffic.

[0111] Example 3: Assessment of Precise Reach of Urban Public Service Information

[0112] This embodiment aims to evaluate the effect of the "Residence Permit Appointment Application" public service advertisement displayed by the municipal government on the electronic screens of bus shelters on increasing the usage rate of citizens' online appointment service.

[0113] Scenario setting: The municipal government displays a scrolling notification on the electronic screens of smart bus shelters throughout the city, guiding citizens to make online appointments to apply for residence permits;

[0114] Data source:

[0115] 1. Urban population movement signaling data provided by telecommunications operators;

[0116] 2. Playback logs of the electronic screens at each bus shelter provided by the bus company;

[0117] 3. Online appointment records for residence permit processing in the municipal government service APP backend;

[0118] Exposure definition: Citizens whose device signals appear within a specific geographic grid around the bus shelter during the advertising broadcast period;

[0119] Definition of conversion: Successfully submitting a residence permit application appointment through the municipal government service APP within 3 days after the exposure;

[0120] Analysis process: The system identifies the exposure group that comes into contact with promotional information at bus shelters, and matches the control group with citizens across the city who have similar demographic characteristics but did not use bus shelters. The conversion improvement rate is calculated by comparing the online reservation rate.

[0121] Beneficial effects: The municipal government can scientifically assess the social benefits of this public information campaign, and based on the differences in conversion rates brought about by bus shelters in different areas, identify areas with good publicity effects or demand, and optimize future public resource allocation and information dissemination strategies.

[0122] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An advertising placement data evaluation system based on multi-channel information integration, characterized in that, The advertising data evaluation system includes: The data standardization and fusion module is responsible for receiving multi-source heterogeneous raw data, cleaning it through the built-in data connector and parsing engine, forcibly converting all data into a unified atomic event model containing a unique device identifier, standard timestamp and standard latitude and longitude coordinates, and finally outputting a standard atomic event stream. The spatiotemporal data fusion and indexing module is used to receive the output standard atomic event stream. Through spatial gridding and temporal slicing technology, each standard atomic event is mapped to a unique spatiotemporal coordinate to build a spatiotemporal index database that supports efficient querying. The incremental conversion attribution analysis module, based on the constructed database, defines the exposure group according to the advertising campaign definition, generates the corresponding control group using a propensity score matching algorithm, and finally calculates and compares the conversion rate to obtain the conversion improvement rate of the advertising effect. The incremental conversion attribution analysis module further includes: The exposure group delineation unit is used to receive the geographic grid set and time slice set of the advertising campaign, and based on the spatiotemporal index data output by the spatiotemporal data fusion and indexing module, extract all unique device identifiers that appear in the geographic grid set of the advertising campaign within the time slice set of the advertising campaign, and form an exposure group. The control group generation unit receives the exposure group generated by the exposure group selection unit and executes a propensity score matching algorithm to generate a control group. The algorithm first calculates a propensity score for the exposure group and candidate devices that have not been exposed to the advertising campaign using a logistic regression model. The logistic regression model is as follows: Where p(X) is the probability that the device belongs to the exposure group, e is the base of the natural logarithm, and X is the probability of a device belonging to the exposure group based on a preset user profile covariate X. i The eigenvectors formed by β0 and β i These are the regression coefficients obtained through model training; The algorithm then describes the control group for each device in the exposure group, which consists of the candidate devices with the closest matching tendency score. The conversion attribution calculation unit is used to receive the generated exposure group and the control group generated by the control group generation unit, count the number of conversion devices within a preset attribution period, and then calculate the conversion improvement rate in the following manner: Where Lift is the final calculated conversion improvement rate, and N C，E |P represents the number of devices that underwent conversion within the exposure group. E | represents the total number of devices in the exposure group, N C,C |P represents the number of devices that underwent transformation in the control group. C | represents the total number of devices in the control group; The statistical significance testing unit receives the calculated conversion improvement rate and the conversion data of each group, and uses a two-sample proportion Z-test to calculate the Z-statistic to determine the statistical significance of the conversion improvement rate. The formula for calculating the Z-statistic is as follows: Where Z is the calculated Z-statistic, CR E For the conversion rate of the exposure group, CR C The conversion rate of the control group is shown. For fusion conversion rate; When the absolute value of the Z statistic is greater than the critical value corresponding to the preset significance level, the conversion improvement rate is determined to be statistically significant. The data application and visualization module is used to receive the output conversion improvement rate and related statistical test results, and present the quantitative evaluation indicators to the end user through the application programming interface or visualization dashboard.

2. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The data standardization and fusion module uses a built-in device ID map to uniformly map device identifiers from different sources to unique device identifiers within the system.

3. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The data standardization and fusion module converts imprecise location information such as base station IDs or IP addresses into standard latitude and longitude coordinates by calling a geocoding service.

4. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The spatiotemporal data fusion and indexing module uses the Geohash algorithm to divide the geographic space into geographic grids and divide the time axis into time slices at fixed intervals.

5. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The incremental conversion attribution analysis module identifies the exposure group by extracting the set of all unique device identifiers that appear in the geographic grid set of the advertising campaign within the time slice set of the advertising campaign; The incremental conversion attribution analysis module generates the control group by using a propensity score matching algorithm to select a set of devices that are similar to the exposure group in terms of preset user profile covariates from devices that have not been exposed to the advertising campaign.

6. The advertising placement data evaluation system based on multi-channel information integration according to claim 5, characterized in that, The conversion improvement rate is calculated as follows: first, the conversion rates of the exposure group and the control group within a preset attribution period are calculated, and then the difference between the conversion rates of the exposure group and the control group is divided by the conversion rate of the control group.

7. The advertising placement data evaluation system based on multi-channel information integration according to claim 6, characterized in that, The incremental conversion attribution analysis module is used to perform a statistical significance test on the conversion improvement rate to determine whether the conversion improvement brought about by the advertising campaign is statistically significant.

8. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The data standardization and fusion module further includes: The data access and parsing unit is used to receive multi-source heterogeneous raw data through a preset data connector, call the parsing engine to extract fields from the raw data, and generate a raw record containing the original device identifier, the original timestamp, and the original location information. A data validity verification unit is used to receive the generated original records, execute a validity verification function based on each original record, and output valid original records that pass the validity verification. The validity verification function has the following criteria: F valid (R raw )=(ID raw ≠NULL)∧IsParsable(T raw )∧IsGeocodable(L raw ), Among them, F valid For the validity check function, R raw For a single original record, ID raw T is the original device identifier contained in the original record. raw L is the original timestamp contained in the original record. raw The IsParsable function is used to determine whether the format of this timestamp can be parsed by the system, and the IsGeocodable function is used to determine whether this location information can be converted into geographic coordinates. The core field standardization unit receives the output valid original record and calls the following transformation function to perform standardization transformation on the fields in the valid original record to generate standard device identifiers, standard timestamps, and standard latitude and longitude coordinates: Device identifier mapping function M(ID) raw )→ID std This is used to map the original device identifier to a unique standard device identifier within the system by querying the built-in device ID graph; Timestamp conversion function C(T) raw →T std This is used to uniformly convert the parsable original timestamps into the standard timestamps in Coordinated Universal Time (UTC) millisecond units; Geographic location transformation function G(L) raw )→L std This is used to uniformly convert the geocoded original location information into the standard latitude and longitude coordinates of the WGS-84 coordinate system; The standard event generation unit is used to receive the generated standard device identifier, standard timestamp, and standard latitude and longitude coordinates, and encapsulate the standard fields into a preset unified atomic event model. Finally, all generated unified atomic event models are collected to form the standard atomic event stream.

9. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The spatiotemporal data fusion and indexing module further includes: A standard event receiving unit is used to receive the standard atomic event stream and distribute the standard atomic events one by one. Each standard atomic event contains a standard timestamp and standard latitude and longitude coordinates. A spatial dimension mapping unit is used to receive the distributed standard atomic events and call a spatial encoding function to process the standard latitude and longitude coordinates contained in the standard atomic events to generate a unique geographic grid ID. The spatial encoding function is: ID grid =GeohashEncode(L std ,P geo ), Among them, ID grid For the generated geographic grid ID, GeohashEncode is the standard Geohash algorithm function that encodes latitude and longitude coordinates. std P is the input standard latitude and longitude coordinates. geo These are the preset geographic grid coding parameters; The time dimension mapping unit is used to receive the standard atomic event with the geographic grid ID appended after processing, and to call the time slicing function to process the standard timestamp contained in the standard atomic event to generate a unique time slice ID. The time slicing function is as follows: Among them, ID slot For the generated time slice ID, T is the floor function. std The input is the standard timestamp, and Δt is the preset fixed duration of a single time slice; The spatiotemporal event indexing unit is used to receive the standard atomic event after processing, which is simultaneously appended with the geographic grid ID and the time slice ID, and to store the device identifier in the standard atomic event into the index database pointed to by the composite key formed by the geographic grid ID and the time slice ID, thus ultimately forming the spatiotemporal index data.

10. The advertising placement data evaluation system based on multi-channel information integration according to claim 1, characterized in that, The data application and visualization module further includes: The attribution result receiving unit is used to receive the conversion improvement rate, Z statistic and related conversion data output by the incremental conversion attribution analysis module, and to encapsulate the received data into a structured attribution result object. The evaluation metric parsing and enhancement unit is used to receive the encapsulated attribution result object, and call the following function to parse and enhance the data in the attribution result object to generate enhanced evaluation metrics containing confidence intervals: First, calculate the p-value corresponding to the Z-statistic: ρ=2×(1-Φ(|Z|)), Where ρ is the calculated p-value, |Z| is the absolute value of the |Z| statistic, and Φ is the cumulative distribution function of the standard normal distribution; Calculate the confidence interval for the difference in conversion rates between the exposure group and the control group: Where CI is the calculated confidence interval, and CR E With CR C |P represents the conversion rate between the exposure group and the control group. E |and|P C | represents the total number of devices in the exposure group and the control group, z α / 2 To achieve the preset information level z α / 2 The critical value of the standard normal distribution under the given conditions; A terminal output generation unit is configured to receive the generated enhanced evaluation metrics and perform formatting processing according to a preset output target. The formatting processing includes: If the output target is an application programming interface (API), the enhanced evaluation metrics are serialized into a JSON-formatted response body. If the output target is a visual dashboard, the enhanced evaluation index is converted into a visual chart component. Based on the comparison between the p-value and the preset significance level α, a judgment conclusion is generated. The conditions for generating the judgment conclusion are as follows: Here, Conclusion refers to the final judgment presented to the user.

Images