Sports event sponsorship effect evaluation method, device and equipment and storage medium

Abstract

The invention relates to the technical field of sports event operation, and discloses a sports event sponsoring effect evaluation method, device and equipment and a storage medium, and the method comprises the steps: forming a contact event set carrying an effective exposure weight through obtaining a sponsoring contact event log, a sponsoring resource configuration table and an effect result event log; and generating a short-term effective anonymous associated signature, matching the short-term effective anonymous associated signature with the result event, forming an anonymous entity cluster to execute differential presentation on the same sponsored resource niche, calculating a sponsored effect increment index, and outputting a sponsored effect evaluation result. Therefore, under the condition of not using an account identifier, a third-party Cookie and an equipment advertisement identifier, the short-term association capability of the contact and the result can still be recovered, the sponsoring increment effect is output, and the problem that the contact is not associated with the result in a special scene that the audience views a competition anonymously and cannot use a cross-session stable identity identifier is solved. According to a traditional method, a sponsor contact event and an effect result event are difficult to reliably associate, so that the sponsor increment effect is difficult to accurately evaluate.

Description

Technical Field

[0001] This invention relates to the field of sports event operation technology, and in particular to a method, apparatus, equipment and storage medium for evaluating the effectiveness of sports event sponsorship. Background Technology

[0002] Sports event sponsorship, as a common business cooperation method in the sports industry, usually showcases sponsor materials to viewers through various viewing touchpoints such as live broadcast rooms, schedule pages, score pages, and graphic information pages. It is hoped that this will bring viewers attention to the brand, interaction, and subsequent observable effects such as receiving coupons, entering the brand page, submitting intentions, or placing orders in the official terminal.

[0003] Existing methods for evaluating sponsorship effectiveness largely rely on stable audience identification identifiers (such as account identifiers, third-party cookies, device advertising identifiers, etc.) to link touchpoint exposure / interaction with subsequent results over time, and then use rule-based attribution or statistical analysis to determine sponsorship contribution. This type of method can achieve relatively usable evaluation results in common scenarios where audiences are generally logged in and identification identifiers are sustainably obtainable.

[0004] However, with increasing user demands for privacy, stricter restrictions on identifier access by terminal platforms, and a growing proportion of viewing in guest mode, more and more sports viewing scenarios are unable to obtain stable cross-session identity identifiers: for example, viewers can watch without logging in, terminals have limited access to third-party identifiers, or viewing terminals frequently clear their caches, leading to a decline in cross-session association capabilities. In such scenarios, traditional methods struggle to reliably link sponsorship touchpoints with subsequent results, resulting in difficulties in constructing control groups, broken evaluation links, and difficulties in calculating incremental effects or significant calculation biases.

[0005] Therefore, how to restore the short-term correlation between touchpoints and results and output the incremental sponsorship effect that can be used for settlement or review without collecting information that can directly identify individuals or relying on stable identity identifiers across sessions has become a technical problem that urgently needs to be solved in the field of sports event operation. Summary of the Invention

[0006] This invention provides a method, apparatus, device, and storage medium for evaluating the effectiveness of sports event sponsorships, in order to at least address the problem that traditional methods struggle to reliably correlate sponsorship touchpoint events with effect outcome events, and thus make it difficult to accurately evaluate the incremental effect of sponsorships, in special scenarios where viewers are anonymous and cannot use stable cross-session identities.

[0007] To achieve the above objectives, the present invention provides a method for evaluating the effectiveness of sports event sponsorship, comprising the following steps: Collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, perform legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events. Based on the visibility duration, location type, and interaction marker of each touch event in the set of effective touch events, the effective exposure weight is calculated to form a sponsored exposure sequence aggregated by time slice; Based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, an anonymous association signature corresponding to the time slice is generated, and based on the anonymous association signature, a matching relationship between touch point events and result events is established in a preset association window to form an anonymous entity cluster. Anonymous and reproducible group tags are generated based on the anonymous associated signature, and differentiated presentation is performed according to the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparative data between the treatment group and the control group. Based on the anonymous entity cluster, the comparison data between the treatment group and the control group, and the sponsorship exposure sequence, the incremental effect index corresponding to the sponsor is calculated and the sponsorship effect evaluation result is output.

[0008] Optionally, sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals are collected. The sponsorship touchpoint event logs are then validated based on the sponsorship resource configuration table to form a set of valid touchpoint events, specifically including: When the viewing terminal detects that sponsored material enters or leaves the visible area or that an interactive operation occurs, a touch event record is generated, and touch association information is written into the touch event record; Read the sponsorship resource configuration table from the event operation backend and establish a configuration mapping indexed by material or resource slot identifier; When the viewing terminal detects a result operation, a result event record is generated, and the result type, result timestamp, and result value are written into the result event record; Based on the configuration mapping, the touch event records are subjected to a delivery window consistency check, and touch event records that do not meet the planned delivery window are removed or downgraded to obtain a valid set of touch events.

[0009] Optionally, based on the visibility duration, location type, and interaction tag of each touch event in the set of effective touch events, an effective exposure weight is calculated to form a sponsored exposure sequence aggregated by time slice, specifically including: For each touch event in the set of valid touch events, load its corresponding base weight and location type coefficient in the sponsor resource configuration table, and obtain the visibility duration and interaction tag of the touch event; The effective exposure weight is calculated based on the base weight, the visibility duration, the location type coefficient, and the interaction marker. Based on the event timestamp of the touch event, each touch event in the set of valid touch events is mapped to the corresponding time slice, and a time slice number is written for the touch event; For each sponsor ID and each time slot, the effective exposure weights of touchpoint events belonging to that sponsor ID and falling within that time slot are aggregated, and the aggregated results are organized as the sponsor exposure volume for that time slot into a sponsor exposure volume sequence according to the time slot order.

[0010] Optionally, based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, an anonymous association signature corresponding to the time slice is generated, and based on the anonymous association signature, a matching relationship between touchpoint events and result events is established within a preset association window to form an anonymous entity cluster, specifically including: In each time slice, a set of non-identified tokens is constructed in the viewing terminal, and a rotating salt value that changes with the time slice is sent to the viewing terminal. A count Bloom signature is generated based on the set of unidentified tokens and the rotated salt value, and the count Bloom signature is written as the anonymous associated signature into the touch event record and the result event record. Within the same time slice, read the count array of the touch event record and the count array of the result event record, and calculate the similarity between the two counts; If the count similarity is not less than the matching threshold and the interval between the timestamp of the touch event and the timestamp of the result event does not exceed the preset association window, the touch event is determined to match the result event, and the two are merged into the same anonymous entity cluster.

[0011] Optionally, it also includes performing merging and conflict resolution on matching relationships when forming anonymous entity clusters, specifically including: Different anonymous associated signatures within each time slice are regarded as nodes to be merged, and cluster merging operations are performed on the touch event nodes and result event nodes that meet the matching conditions to obtain an anonymous entity cluster containing the touch event set and the result event set; When multiple anonymous entity cluster candidates match the same outcome event, the anonymous entity cluster with the highest count similarity is selected as the belonging cluster. If the count similarity is the same, the anonymous entity cluster to which the touch event with the closest distance to the timestamp of the result event belongs is selected as the affiliation cluster; If the affiliation cluster cannot be uniquely determined, a consistency priority rule is executed based on whether the result event carries a sponsor affiliation tag, so as to uniquely affix the result event to an anonymous entity cluster consistent with the sponsor affiliation tag; Write the resulting event attribution relationship after conflict resolution into the anonymous entity cluster.

[0012] Optionally, an anonymous and reproducible grouping tag is generated based on the anonymous associated signature, and differential presentation is performed according to the grouping tag when the control rules in the sponsored resource configuration table are met, so as to form comparison data between the treatment group and the control group, specifically including: A group marker is calculated based on the anonymous associated signature and time slice number written in the touch event record, and the group marker is reproducible for the same anonymous associated signature within the same time slice; Grouping tags are written to the contact event log and the result event log to form treatment group data and control group data that can be used for comparative statistics; When the sponsorship resource configuration table indicates that control rules can be executed, the viewing terminal performs differentiated presentation on the same material or resource position according to the grouping mark; wherein, the processing group presents interactive sponsorship enhancement controls, and the control group presents a basic exposure version without action guidance.

[0013] Optionally, based on the anonymous entity cluster, the comparison data between the treatment group and the control group, and the sponsored exposure sequence, the incremental effect index corresponding to the sponsor is calculated and the sponsorship effect evaluation result is output, specifically including: For each sponsor, the effective exposure weight corresponding to that sponsor is summarized based on the set of touch events within the anonymous entity cluster to form the exposure dose at the anonymous entity cluster level; The result occurrence marker of the sponsor is determined based on the set of result events within the anonymous entity cluster. Direct attribution is performed when the result event carries a sponsor attribution marker, and the touchpoint priority attribution rule is performed based on a preset result window when the result event does not carry a sponsor attribution marker. The number of anonymous entity clusters with the sponsor's exposure dose and the number of anonymous entity clusters that have occurred in the treatment group and the control group are counted respectively, and the conversion rate of the treatment group and the conversion rate of the control group are calculated. The incremental improvement index is calculated based on the conversion rates of the treatment group and the control group, and a conservative correction is performed on the incremental improvement index based on the misjudgment probability of the count Bloom structure. The output should include at least the sponsorship effect evaluation results, such as exposure dose, sample size of the treatment and control groups, conversion rate of the treatment and control groups, incremental improvement index, and correction results.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a device for evaluating the effectiveness of sports event sponsorships, comprising: The data acquisition module is used to collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, the module performs legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events. The forming module is used to calculate the effective exposure weight and form a sponsored exposure sequence aggregated by time slice based on the visibility duration, location type and interaction mark of each touch event in the set of effective touch events; The generation module is used to generate an anonymous association signature corresponding to the time slice based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, and to establish a matching relationship between touch point events and result events in a preset association window based on the anonymous association signature to form an anonymous entity cluster. The presentation module is used to generate anonymous and reproducible group tags based on the anonymous associated signature, and to perform differentiated presentation based on the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparison data between the processing group and the control group; The output module is used to calculate the incremental effect index corresponding to the sponsor and output the sponsorship effect evaluation result based on the anonymous entity cluster, the comparison data of the treatment group and the control group, and the sponsorship exposure sequence.

[0015] In addition, to achieve the above objectives, the present invention also provides a sports event sponsorship effectiveness evaluation device, which includes: a memory, a processor, and a sports event sponsorship effectiveness evaluation program stored in the memory and executable on the processor. When the sports event sponsorship effectiveness evaluation program is executed by the processor, it implements the steps of the sports event sponsorship effectiveness evaluation method as described above.

[0016] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a sports event sponsorship effectiveness evaluation program, which, when executed by a processor, implements the steps of the sports event sponsorship effectiveness evaluation method described above.

[0017] The beneficial effects of this invention are as follows: It proposes a method, apparatus, device, and storage medium for evaluating the effectiveness of sports event sponsorships. By acquiring sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs, a set of touchpoint events carrying effective exposure weights is formed. Short-term effective anonymous association signatures are generated and matched with result events to form anonymous entity clusters that perform differentiated presentations on the same sponsorship resource position. The incremental sponsorship effect index is calculated, and the sponsorship effect evaluation result is output. Thus, this invention, without using stable cross-session identity identifiers such as account identifiers, third-party cookies, or device advertising identifiers, can still restore the short-term association between touchpoints and results based on official terminal data. It constructs processing / control groups through anonymous reproducible grouping and differentiated presentation, and robustly processes the results through similarity threshold adaptation and mismatch probability estimation, thereby outputting the incremental sponsorship effect. This solves the problem that traditional methods struggle to reliably associate sponsorship touchpoint events with effect result events and thus accurately evaluate the incremental sponsorship effect in special scenarios where viewers watch anonymously and cannot use stable cross-session identity identifiers. This improves the feasibility, interpretability, and stability of sponsorship effect evaluation. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating an embodiment of the sports event sponsorship effectiveness evaluation method of the present invention; Figure 3 This is a structural block diagram of a sports event sponsorship effect evaluation device according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0021] like Figure 1As shown, the device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0022] Those skilled in the art will understand that Figure 1 The structure of the device shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0023] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a sports event sponsorship effectiveness evaluation program.

[0024] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate data with it; user interface 1003 is mainly used to connect to the client (user terminal) and communicate data with it; while processor 1001 can be used to call the sports event sponsorship effect evaluation program stored in memory 1005 and perform the following operations: Collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, perform legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events. Based on the visibility duration, location type, and interaction marker of each touch event in the set of effective touch events, the effective exposure weight is calculated to form a sponsored exposure sequence aggregated by time slice; Based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, an anonymous association signature corresponding to the time slice is generated, and based on the anonymous association signature, a matching relationship between touch point events and result events is established in a preset association window to form an anonymous entity cluster. Anonymous and reproducible group tags are generated based on the anonymous associated signature, and differentiated presentation is performed according to the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparative data between the treatment group and the control group. Based on the anonymous entity cluster, the comparison data between the treatment group and the control group, and the sponsorship exposure sequence, the incremental effect index corresponding to the sponsor is calculated and the sponsorship effect evaluation result is output.

[0025] The specific embodiments of the present invention applied to the device are basically the same as the embodiments of the application of the sports event sponsorship effect evaluation method described below, and will not be repeated here.

[0026] This invention provides a method for evaluating the effectiveness of sports event sponsorships, referring to... Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the sports event sponsorship effectiveness evaluation method of the present invention.

[0027] In this embodiment, a method for evaluating the effectiveness of sports event sponsorship includes the following steps: S10: Collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, perform legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events.

[0028] Specifically, when the viewing terminal detects that sponsored materials have entered or left the visible area, or that an interactive operation has occurred, a touch event record is generated, and touch point association information is written into the touch event record; the sponsor resource configuration table is read from the event operation backend, and a configuration mapping is established with the material or resource position identifier as the index; when the viewing terminal detects a result operation, a result event record is generated, and the result type, result timestamp, and result value are written into the result event record; based on the configuration mapping, a consistency check of the delivery window is performed on the touch event records, and touch event records that do not meet the planned delivery window are removed or downgraded to obtain a set of valid touch events.

[0029] In this embodiment of the invention, step S10 is used to acquire the key data required for the evaluation and to provide a unified data boundary for subsequent anonymous association and incremental calculation. It should be noted that among the three types of data acquired in this step, touch events will be used to calculate the effective exposure weight and exposure dose, the resource configuration table will be used for touch event legality verification and weight loading, and result events will be used to form cluster-level result variables and participate in incremental comparison.

[0030] In practical applications, the viewing terminal generates touchpoint events and writes them to the sponsor touchpoint event log when it detects sponsored content entering or leaving the visible area or when interactive behavior occurs. In one executable implementation, each touchpoint event includes at least the sponsor identifier, content identifier, event occurrence time, visible duration, interaction marker, and scene code. The scene code is used to distinguish different touchpoint environments such as the live broadcast room, schedule page, and score page, so as to differentiate the exposure quality differences between different touchpoints in subsequent statistics.

[0031] Simultaneously, the evaluation system reads the sponsor resource configuration table from the event operations backend and establishes a mapping relationship between material identifiers and sponsor identifiers, placement windows, location types, basic exposure weights, and comparative presentation control rules. In practical applications, the sponsor resource configuration table can be configured by operations personnel before the event begins and adjusted as needed during the event. As is easily understood, the configuration table serves as the reference basis for evaluation calculations and can be used to determine the legality of placement windows for touchpoint events, thereby reducing the noise impact caused by cached echoes, duplicate triggers, etc.

[0032] Furthermore, when the viewing terminal detects actions such as claiming coupons, entering brand pages, submitting intentions, or placing orders within the official terminal, it generates result events and writes them to the result event log. Specifically, the result event includes at least the result type, the time the result occurred, and the result value. In one optional implementation, when the result event naturally belongs to a sponsor (e.g., claiming a sponsor coupon), the corresponding sponsor identifier can also be recorded to prioritize the use of strong attribution information in subsequent attribution.

[0033] After acquiring the touch event and result event, this embodiment of the invention maps the touch event and result event to time slice numbers based on the event occurrence time of the touch event and the result occurrence time of the result event, respectively. It is easy to understand that the time slice number will be used in subsequent stages such as anonymous association signature generation, similarity matching, threshold adaptation, and group tag generation, thereby limiting subsequent association and statistics to the same time slice and avoiding erroneous chaining caused by direct association across long periods.

[0034] Following this, the evaluation system retrieves the delivery window information from the configuration index based on the material identifier for each touchpoint event and determines whether the event's occurrence time falls within the delivery window. If not, the touchpoint event is marked as abnormal and either removed or demoted. In practical applications, the removal or demotion strategy can be configured according to the event platform's log stability, caching strategy, and fault tolerance requirements; this invention does not impose any limitations on this.

[0035] S20: Based on the visibility duration, location type, and interaction marker of each touch event in the set of effective touch events, calculate the effective exposure weight to form a sponsored exposure sequence aggregated by time slice.

[0036] Specifically, for each touch event in the set of effective touch events, load its corresponding basic weight and location type coefficient in the sponsor resource configuration table, and obtain the visibility duration and interaction tag of the touch event; calculate the effective exposure weight based on the basic weight, the visibility duration, the location type coefficient, and the interaction tag; map each touch event in the set of effective touch events to the corresponding time slice based on the event timestamp of the touch event, and write a time slice number for the touch event; for each sponsor identifier and each time slice, summarize the effective exposure weights of touch events belonging to that sponsor identifier and falling into that time slice, and organize the summarized results as the sponsor exposure volume of that time slice into a sponsor exposure volume sequence according to the time slice order.

[0037] In this embodiment of the invention, step S20 is used to form a quantifiable exposure quality metric at the touch event level, so that subsequent exposure dose calculations can reflect factors such as display duration, positional importance, and interaction intensity. It should be noted that in anonymous scenarios, it is difficult to rely on user profiles or long-term behavioral trajectories for correction; therefore, the weight calculation of a single touch event is particularly important.

[0038] After the touch event verification passes, the evaluation system further loads the basic exposure weight and location type information corresponding to the touch event, and calculates the effective exposure weight based on the visibility duration, location type, and interaction marker. In one executable implementation, the effective exposure weight is calculated according to the following formula: ; In the formula: This represents the effective exposure weight of the i-th touchpoint event; This indicates the base exposure weight corresponding to the material identifier; This indicates the visible duration of the i-th touch event; ptype indicates the resource bit location type to which this touch event belongs; Represents the interaction flag or interaction count of the i-th touch event; g(·) is the visibility duration gain function; h(·) is the position type coefficient function; q(·) is the interaction enhancement function.

[0039] It should be noted that the basic exposure weight is used to reflect the basic value preset by the operations side for different sponsored resource positions, the position type coefficient is used to reflect the attention differences of different pages or different display formats, and the visibility duration and interaction enhancement are used to reflect the audience's actual attention investment in the material. Through the above combination, the effective exposure weight can form an interpretable and reusable exposure quality metric.

[0040] In this embodiment, the visible duration gain function is calculated according to the following formula: ; In the formula: ln is the natural logarithm function; This serves as a reference duration threshold. It's easy to understand that normalizing the visible duration using a logarithmic method reflects the diminishing marginal returns of attention, thus preventing excessive amplification of the weighting for long dwell times.

[0041] Furthermore, the interaction enhancement function is calculated according to the following formula: ; In the formula: α is the interaction enhancement coefficient. Specifically, when a touch event occurs, The effective exposure weight of this touchpoint event will be appropriately increased to reflect the common-sense principle that interactive behavior is more effective in capturing brand attention than pure display.

[0042] After the effective exposure weight is calculated, the calculated effective exposure weight is written into the corresponding touch event to form a set of touch events carrying the effective exposure weight for subsequent exposure dose calculation.

[0043] Following this, embodiments of the invention further generate a sequence description of the sponsored exposure dose at the time-slice scale, thereby reducing data size, facilitating real-time statistics, and providing intra-time-slice scale estimation input for subsequent similarity threshold adaptation. It should be noted that the output data of this step is used in subsequent steps to estimate the time-slice activity scale. This affects the similarity threshold. Adaptive adjustment.

[0044] In one executable implementation, touch events are grouped according to sponsor identifiers within each time slice, and the effective exposure weights of the same sponsor within that time slice are accumulated to obtain the exposure intensity of that sponsor within that time slice. Furthermore, the exposure intensities corresponding to each time slice are organized into exposure sequence data in chronological order, and an index relationship is established between the exposure sequence data and the time slice numbers.

[0045] It should be noted that time-slice aggregation not only reduces subsequent computational overhead, but also forms a natural hierarchical boundary in anonymous scenarios: when generating anonymous associated signatures in the future, the same rotated salt value is used within the same time slice, and the matching is also limited to the same time slice, thereby avoiding mis-chaining caused by direct matching across time slices.

[0046] S30: Based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, generate an anonymous association signature corresponding to the time slice, and establish a matching relationship between touch point events and result events in a preset association window based on the anonymous association signature to form an anonymous entity cluster.

[0047] Specifically, within each time slice, the viewing terminal constructs a set of unidentified tokens and issues a rotating salt value that changes with the time slice to the viewing terminal; a count Bloom signature is generated based on the set of unidentified tokens and the rotating salt value, and the count Bloom signature is written as the anonymous associated signature into the touch event record and the result event record; within the same time slice, the count arrays of the touch event record and the result event record are read, and their count similarity is calculated; if the count similarity is not less than the matching threshold and the interval between the touch event timestamp and the result event timestamp does not exceed a preset association window, the touch event and the result event are determined to match, and they are merged into the same anonymous entity cluster.

[0048] Building upon this, the process also includes merging and resolving conflicts when forming anonymous entity clusters. Specifically, this involves: treating different anonymous associated signatures within each time slice as nodes to be merged, and performing cluster merging operations on touch event nodes and result event nodes that meet the matching conditions to obtain anonymous entity clusters containing both touch event sets and result event sets; when multiple anonymous entity cluster candidates match the same result event, selecting the anonymous entity cluster with the highest count similarity as the assigned cluster; when the count similarity is the same, selecting the anonymous entity cluster to which the touch event closest to the result event's timestamp belongs as the assigned cluster; if the assigned cluster still cannot be uniquely determined, implementing a consistency priority rule based on whether the result event carries a sponsor attribution tag to uniquely assign the result event to an anonymous entity cluster consistent with the sponsor attribution tag; and writing the conflict-resolved result event attribution relationship into the anonymous entity cluster.

[0049] In this embodiment of the invention, step S30 is a key step in solving the difficulty of associating touchpoints and results in anonymous scenarios. It should be noted that in ordinary login scenarios, touchpoints and results can be directly associated through stable identities such as account identifiers, and there is usually no need to generate anonymous signatures; however, in the anonymous viewing scenario targeted by this invention, in order to avoid collecting identifiable identity information, it is necessary to introduce an anonymous association signature mechanism that can be associated in the short term but cannot be tracked in the long term.

[0050] In practical applications, the spectator terminal constructs a set of non-identified tokens within each time slice. This set of non-identified tokens consists of coarse-grained features of the device and environment, as well as random variables within the time slice, and does not contain personally identifiable information such as account identifiers, advertising identifiers, or precise locations. It is easy to understand that coarse-grained features are used to improve the consistency of events on the same terminal in the short term, while random variables are used to reduce the probability of collisions caused by a large number of homogeneous devices generating the same token set within the same time slice.

[0051] Simultaneously, the evaluation system issues a rotating salt value for each time slice, and limits the validity of the rotating salt value to the corresponding time slice or a preset short-term validity period, so that the anonymous associated signatures generated by the same terminal in different time slices change with the time slice. In an optional implementation, the maximum retention time of the rotating salt value can also be limited, for example, not exceeding 7 days, to further limit the longest effective window of the association.

[0052] Furthermore, the spectator terminal generates a counted Bloom signature based on the set of unidentified tokens and the rotated salt value, and writes the counted Bloom signature as an anonymous associated signature into the touch event and the result event. In this embodiment, the generation of the counted Bloom signature includes at least determining the hash mapping position and performing count accumulation: ; ; ; In the formula: This indicates a non-identification token. Indicates time slice The corresponding rotational salt value, This indicates concatenation, where x is the salted input obtained by concatenating the non-identified token with the rotated salt value; Let m be the j-th hash function; m be the length of the counting array; and k be the number of hash functions. The position obtained by mapping the j-th hash function; For the counting array at position The count value.

[0053] As is easily understood, unlike a regular Bloom bitmap which can only indicate whether something has occurred, a counting array can represent the frequency of token occurrences within a time slice. Therefore, it is more suitable for characterizing multiple touchpoints or multiple result events of the same terminal within the same time slice. In addition, by combining the rotating salt value with time slice layering, anonymous signatures cannot be directly reused between different time slices, thereby reducing long-term tracking risks while ensuring short-term correlation capabilities.

[0054] Following this, the short-term correlation between the touchpoint event and the result event needs to be restored on the server side. It should be noted that anonymous associated signatures are not deterministic identifiers, so matching needs to be based on similarity rather than exact equality; at the same time, during peak event concurrency, the probability of collisions between anonymous signatures increases, requiring the introduction of a scale-related threshold adaptive mechanism to reduce the risk of mismatches.

[0055] In one executable implementation, the evaluation system extracts a first count array corresponding to the anonymous associated signature of the touch event and a second count array corresponding to the anonymous associated signature of the result event within the same time slice, and calculates the count similarity. The count similarity is calculated according to the following formula: ; In the formula: C represents the first counting array; This represents the second counting array; This represents the count value of the first counting array at position p; This represents the count value at position p in the second counting array; m is the length of the counting array. For counting similarity.

[0056] Furthermore, in this embodiment of the invention, the matching criteria are determined based on an adaptive threshold related to the time slice size, and the adaptive threshold is determined according to the following formula: In the formula: For time slices The corresponding similarity threshold; β is the basic threshold constant; β is the scale correction coefficient. For time slices Estimation of the number of deduplicated and anonymous associated signatures; This is the time slice number.

[0057] It is easy to understand, when Increasing this value brings the threshold closer to the baseline threshold; alternatively, it can also be adjusted... A more stringent thresholding strategy is implemented with β. This invention does not limit the specific parameter values ​​for threshold adaptation, but keeps the principle that the threshold is related to the time slice size unchanged, in order to suppress misconnections during peak viewing times.

[0058] When the similarity count is not less than the adaptive threshold and the time difference between the touch event and the result event does not exceed the preset association window, the evaluation system outputs a matching judgment result and generates candidate matching pairs. The association window can be 24 hours, 48 ​​hours, or 7 days, etc., and can be configured according to the type of sponsorship rights and evaluation requirements.

[0059] After generating candidate matching pairs, the evaluation system performs a cluster merging operation on the successfully matched touch events and result events within the same time slice to form anonymous entity clusters. Each anonymous entity cluster is associated with at least one touch event and at least one result event. In practical applications, the cluster merging operation can be implemented using mature data structures such as disjoint-set data structures. It's easy to understand that the introduction of clusters elevates the processing object from the event level to the anonymous entity level, allowing subsequent calculations of exposure dose and result variables to be statistically analyzed around anonymous entities, thus more closely approximating the effect representation of individual viewers.

[0060] Furthermore, when the same result event matches multiple anonymous entity clusters, the evaluation system performs unique attribution processing in the order of priority based on similarity count, minimum time difference, and consistency of the natural sponsor attribution of the result event, in order to avoid the same result event being repeatedly counted in multiple anonymous entity clusters and causing the incremental effect to be artificially inflated.

[0061] S40: Generate anonymous and reproducible group tags based on the anonymous associated signature, and perform differentiated presentation based on the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparison data between the treatment group and the control group.

[0062] Specifically, a grouping tag is calculated based on the anonymous associated signature and time slice number written in the touch event log, and the grouping tag is made reproducible for the same anonymous associated signature within the same time slice; the grouping tag is written into the touch event log and the result event log to form processing group data and control group data that can be used for comparative statistics; when the sponsorship resource configuration table indicates that the control rules can be executed, the viewing terminal performs differentiated presentation on the same material or resource position according to the grouping tag; wherein, the processing group presents interactive sponsorship enhancement controls, and the control group presents a basic exposure version without action guidance.

[0063] In this embodiment of the invention, step S40 is used to construct a comparable control in an anonymous scenario. It should be noted that traditional A / B splitting usually relies on account identifiers or stable device identifiers, which makes it difficult to ensure consistent splitting for the same viewer within the same time slice in an anonymous viewing scenario; therefore, this invention utilizes anonymous associated signatures and time slice numbers to generate anonymous reproducible group tags, ensuring that the groups remain consistent for the same anonymous entity within the same time slice.

[0064] In one executable implementation, the grouping tag is calculated according to the following formula: ; In the formula: The group identifier is H(·), which takes the value of either the processing group or the control group; H(·) is the hash function; sig is the anonymous associated signature; || is the time slice number; || is the splicing symbol.

[0065] It is easy to understand that hash splitting has the characteristics of near-uniform distribution and reproducibility, and can still form near-equilibrium processing group and control group samples without relying on stable identity identifiers.

[0066] Furthermore, when the sponsorship resource configuration table indicates that the comparative presentation control rules are allowed, the viewing terminal performs differentiated presentation on the same material or resource position based on the grouping tags. Specifically, the processing group presents sponsored enhanced controls that include action guidance, such as brand story cards, limited-time coupon entry points, or special page guidance; the control group presents basic exposure without action guidance. It should be noted that differentiated presentation is not limited to specific control forms; its core is that the processing group and the control group only have the controllable difference of enhanced controls within the same resource position and the same delivery window, so that subsequent conversion differences can be interpreted as the incremental contribution brought by sponsorship enhancement.

[0067] After completing the differentiated presentation, the terminal records the corresponding touch events and writes them into the touch event log; and writes the grouping mark into the corresponding touch event and result event, so that the anonymous entity cluster can inherit the corresponding grouping mark after it is formed, providing a reference dimension for subsequent incremental effect calculation.

[0068] S50: Based on the anonymous entity cluster, the comparison data between the treatment group and the control group, and the sponsorship exposure sequence, calculate the incremental effect index corresponding to the sponsor and output the sponsorship effect evaluation result.

[0069] Specifically, for each sponsor, the effective exposure weight corresponding to the sponsor is summarized based on the set of touch events within the anonymous entity cluster to form an exposure dose at the anonymous entity cluster level; the result occurrence marker of the sponsor is determined based on the set of result events within the anonymous entity cluster, and direct attribution is performed when the result event carries a sponsor attribution marker, and touch point priority attribution rule is performed based on a preset result window when it does not carry a sponsor attribution marker; the number of anonymous entity clusters with the sponsor's exposure dose and the number of anonymous entity clusters with results are counted in the treatment group and the control group respectively, and the conversion rate of the treatment group and the conversion rate of the control group are calculated; the incremental improvement index is calculated based on the conversion rate of the treatment group and the conversion rate of the control group, and conservative correction is performed on the incremental improvement index based on the misjudgment probability of the count Bloom structure; the sponsorship effect evaluation result is output, which includes at least the exposure dose, the sample size of the treatment group and the control group, the conversion rate of the treatment group and the control group, the incremental improvement index, and the correction result.

[0070] In this embodiment of the invention, step S50 is used to output incremental effect indicators that can be used for settlement and review. It should be noted that in an anonymous scenario, if only correlation statistics are performed, it is easily affected by factors such as peak concurrency and page traffic fluctuations; by comparing the treatment group and the control group, a more causal explanatory incremental estimate can be obtained.

[0071] In one executable implementation, the evaluation system, for each sponsor, aggregates the effective exposure weights corresponding to that sponsor within the anonymous entity cluster to obtain a cluster-level exposure dose. As is readily understood, the cluster-level exposure dose represents the exposure dose received by an anonymous entity when it comes into contact with that sponsor within the evaluation window; it is formed by summing the effective exposure weights calculated in step S20, thus reflecting differences in exposure quality.

[0072] Furthermore, the evaluation system generates cluster-level result variables based on result events within anonymous entity clusters: when a result event naturally belongs to a certain sponsor, it is preferentially assigned to the corresponding sponsor; when there is no natural attribution information, the result event is assigned to the nearest touchpoint sponsor within the preset association window based on preset rules.

[0073] It should be noted that this attribution rule is a mature last-touchpoint rule, which helps to achieve fast and accurate result attribution.

[0074] After obtaining the sample sizes of the treatment group and the control group, as well as the number of transformation clusters in each group, the conversion rates of the treatment group and the control group were calculated as follows: ; ; In the formula: For processing group conversion rate; The conversion rate was for the control group. The number of clusters to be converted in the processing group; This represents the number of transformed clusters in the control group. The number of clusters with effective exposure in the processing group; This represents the number of clusters with effective exposure in the control group.

[0075] Furthermore, the incremental improvement and incremental conversion rate are calculated based on the conversion rates of the treatment group and the control group, as follows: ; ; In the formula: Lift is the incremental lift; Inc is the incremental conversion amount; ε is a minimal constant used to avoid the denominator being zero.

[0076] As is easily understood, the incremental lift is used to characterize the relative improvement of the treatment group compared to the control group, while the incremental conversion is used to characterize the absolute increase under the exposure sample size of the treatment group. In practical applications, Lift can also be calculated separately for different exposure dose ranges to obtain dose-effect piecewise curves, thereby providing a basis for sponsor resource optimization. This invention does not limit this.

[0077] To further enhance the robustness of the results, in one optional implementation, the evaluation system can also estimate the false match probability based on the length of the counting array, the number of hash functions, and the average number of tokens within a time slice, and perform a conservative correction on the incremental lift. The false match probability satisfies the following formula: ; In the formula: is the probability of a false match; e is the natural constant; k is the number of hash functions; n is the average number of tokens per time slice; m is the length of the counting array.

[0078] Furthermore, the corrected incremental lift satisfies the following formula: ; In the formula: This refers to the incremental lift after correction. This is a weighted average of the false match probabilities within the analysis window. It is easily understood that this correction is used to conservatively reduce the results when the collision probability increases during peak anonymity periods, thereby reducing the risk of artificially inflated results due to false concatenation.

[0079] Finally, the aforementioned calculation results are output in the form of reports, interfaces, or visualizations. Specifically, the evaluation results output by the evaluation system should include at least the following metrics: conversion rate of the treatment group, conversion rate of the control group, incremental improvement, incremental conversion amount, and corrected incremental improvement. It should be noted that, to meet the requirements of reproducibility and auditability, in one optional implementation, the evaluation system can also output parameter version information, such as the length m of the counting array, the number of hash functions k, and the threshold parameter. Including β, time slice duration, associated windows, etc., so that the calculation process can be reproduced during post-match review or contract settlement.

[0080] In another possible implementation, the evaluation system may also output conversion rate confidence intervals or significance test results to indicate the statistical stability of the results; the calculation of the confidence intervals may employ mature statistical methods such as Wilson intervals, and this invention does not limit this to such methods.

[0081] Reference Figure 3 , Figure 3 This is a schematic diagram of an embodiment of the sports event sponsorship effect evaluation device of the present invention.

[0082] like Figure 3 As shown, the sports event sponsorship effectiveness evaluation device proposed in this embodiment of the invention includes: The data acquisition module is used to collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, the module performs legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events. The forming module is used to calculate the effective exposure weight and form a sponsored exposure sequence aggregated by time slice based on the visibility duration, location type and interaction mark of each touch event in the set of effective touch events; The generation module is used to generate an anonymous association signature corresponding to the time slice based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, and to establish a matching relationship between touch point events and result events in a preset association window based on the anonymous association signature to form an anonymous entity cluster. The presentation module is used to generate anonymous and reproducible group tags based on the anonymous associated signature, and to perform differentiated presentation based on the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparison data between the processing group and the control group; The output module is used to calculate the incremental effect index corresponding to the sponsor and output the sponsorship effect evaluation result based on the anonymous entity cluster, the comparison data of the treatment group and the control group, and the sponsorship exposure sequence.

[0083] Other embodiments or specific implementations of the sports event sponsorship effect evaluation device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0084] Furthermore, the present invention also proposes a sports event sponsorship effectiveness evaluation device, which includes: a memory, a processor, and a sports event sponsorship effectiveness evaluation program stored in the memory and executable on the processor. When the sports event sponsorship effectiveness evaluation program is executed by the processor, it implements the steps of the sports event sponsorship effectiveness evaluation method as described above.

[0085] The specific implementation method of the sports event sponsorship effect evaluation device in this application is basically the same as the various embodiments of the sports event sponsorship effect evaluation method described above, and will not be repeated here.

[0086] Furthermore, this invention also proposes a readable storage medium, comprising a computer-readable storage medium storing a sports event sponsorship effectiveness evaluation program thereon. The readable storage medium may be... Figure 1 The memory 1005 in the terminal can also be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The readable storage medium includes several instructions to cause a sports event sponsorship effect evaluation device with a processor to execute the sports event sponsorship effect evaluation method described in various embodiments of the present invention.

[0087] The specific implementation methods in the readable storage medium of this application are basically the same as the embodiments of the above-described sports event sponsorship effect evaluation method, and will not be described again here.

[0088] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0089] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0090] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0091] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method of evaluating the effect of a sports event sponsorship, characterized by, Includes the following steps: Collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, verify the legality of the sponsorship touchpoint event logs to form a set of valid touchpoint events. Based on the visibility duration, location type, and interaction marker of each touch event in the set of effective touch events, the effective exposure weight is calculated to form a sponsored exposure sequence aggregated by time slice; Based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, an anonymous association signature corresponding to the time slice is generated, and based on the anonymous association signature, a matching relationship between touch point events and result events is established in a preset association window to form an anonymous entity cluster. Anonymous and reproducible group tags are generated based on the anonymous associated signature, and differentiated presentation is performed according to the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparative data between the treatment group and the control group. Based on the anonymous entity cluster, the comparison data between the treatment group and the control group, and the sponsorship exposure sequence, the incremental effect index corresponding to the sponsor is calculated and the sponsorship effect evaluation result is output.

2. The sports event sponsorship effectiveness evaluation method of claim 1, wherein, The system collects sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, it performs a validity check on the sponsorship touchpoint event logs to form a set of valid touchpoint events, specifically including: When the viewing terminal detects that sponsored material enters or leaves the visible area or that an interactive operation occurs, a touch event record is generated, and touch association information is written into the touch event record; Read the sponsorship resource configuration table from the event operation backend and establish a configuration mapping indexed by material or resource slot identifier; When the viewing terminal detects a result operation, a result event record is generated, and the result type, result timestamp, and result value are written into the result event record; Based on the configuration mapping, the touch event records are subjected to a delivery window consistency check, and touch event records that do not meet the planned delivery window are removed or downgraded to obtain a valid set of touch events.

3. The sports event sponsorship effectiveness evaluation method of claim 1, wherein, Based on the visibility duration, location type, and interaction tag of each touch event in the set of effective touch events, the effective exposure weight is calculated to form a sponsored exposure sequence aggregated by time slice, specifically including: For each touch event in the set of valid touch events, load its corresponding base weight and location type coefficient in the sponsor resource configuration table, and obtain the visibility duration and interaction tag of the touch event; The effective exposure weight is calculated based on the base weight, the visibility duration, the location type coefficient, and the interaction marker. Based on the event timestamp of the touch event, each touch event in the set of valid touch events is mapped to the corresponding time slice, and a time slice number is written for the touch event; For each sponsor ID and each time slot, the effective exposure weights of touchpoint events belonging to that sponsor ID and falling within that time slot are aggregated, and the aggregated results are organized as the sponsor exposure volume for that time slot into a sponsor exposure volume sequence according to the time slot order.

4. The method for evaluating the effectiveness of sports event sponsorship as described in claim 1, characterized in that, Based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, an anonymous association signature corresponding to the time slice is generated. Then, based on the anonymous association signature, a matching relationship between touchpoint events and result events is established within a preset association window to form an anonymous entity cluster, specifically including: In each time slice, a set of non-identified tokens is constructed in the viewing terminal, and a rotating salt value that changes with the time slice is sent to the viewing terminal. A count Bloom signature is generated based on the set of unidentified tokens and the rotated salt value, and the count Bloom signature is written as the anonymous associated signature into the touch event record and the result event record. Within the same time slice, read the count array of the touch event record and the count array of the result event record, and calculate the similarity between the two counts; If the count similarity is not less than the matching threshold and the interval between the timestamp of the touch event and the timestamp of the result event does not exceed the preset association window, the touch event is determined to match the result event, and the two are merged into the same anonymous entity cluster.

5. The method for evaluating the effectiveness of sports event sponsorship as described in claim 4, characterized in that, This also includes performing merging and conflict resolution on matching relationships when forming anonymous entity clusters, specifically including: Different anonymous associated signatures within each time slice are regarded as nodes to be merged, and cluster merging operations are performed on the touch event nodes and result event nodes that meet the matching conditions to obtain an anonymous entity cluster containing the touch event set and the result event set; When multiple anonymous entity cluster candidates match the same outcome event, the anonymous entity cluster with the highest count similarity is selected as the belonging cluster. If the count similarity is the same, the anonymous entity cluster to which the touch event with the closest distance to the timestamp of the result event belongs is selected as the affiliation cluster; If the affiliation cluster cannot be uniquely determined, a consistency priority rule is executed based on whether the result event carries a sponsor affiliation tag, so as to uniquely affix the result event to an anonymous entity cluster consistent with the sponsor affiliation tag; Write the resulting event attribution relationship after conflict resolution into the anonymous entity cluster.

6. The method for evaluating the effectiveness of sports event sponsorship as described in claim 1, characterized in that, Anonymous and reproducible group tags are generated based on the anonymous associated signatures, and differentiated presentation is performed according to the group tags when the control rules in the sponsored resource configuration table are met, so as to form comparative data between the treatment group and the control group, specifically including: A group marker is calculated based on the anonymous associated signature and time slice number written in the touch event record, and the group marker is reproducible for the same anonymous associated signature within the same time slice; Grouping tags are written to the contact event log and the result event log to form treatment group data and control group data that can be used for comparative statistics; When the sponsorship resource configuration table indicates that control rules can be executed, the viewing terminal performs differentiated presentation on the same material or resource position according to the grouping mark; wherein, the processing group presents interactive sponsorship enhancement controls, and the control group presents a basic exposure version without action guidance.

7. The method for evaluating the effectiveness of sports event sponsorship as described in claim 1, characterized in that, Based on the anonymous entity cluster, the comparative data of the treatment group and the control group, and the sponsorship exposure sequence, the incremental effect index corresponding to the sponsor is calculated and the sponsorship effect evaluation result is output, specifically including: For each sponsor, the effective exposure weight corresponding to that sponsor is summarized based on the set of touch events within the anonymous entity cluster to form the exposure dose at the anonymous entity cluster level; The result occurrence marker of the sponsor is determined based on the set of result events within the anonymous entity cluster. Direct attribution is performed when the result event carries a sponsor attribution marker, and the touchpoint priority attribution rule is performed based on a preset result window when the result event does not carry a sponsor attribution marker. The number of anonymous entity clusters with the sponsor's exposure dose and the number of anonymous entity clusters that have occurred in the treatment group and the control group are counted respectively, and the conversion rate of the treatment group and the conversion rate of the control group are calculated. The incremental improvement index is calculated based on the conversion rates of the treatment group and the control group, and a conservative correction is performed on the incremental improvement index based on the misjudgment probability of the count Bloom structure. The output should include at least the sponsorship effect evaluation results, such as exposure dose, sample size of the treatment and control groups, conversion rate of the treatment and control groups, incremental improvement index, and correction results.

8. A device for evaluating the effectiveness of sports event sponsorship, characterized in that, include: The data acquisition module is used to collect sponsorship touchpoint event logs, sponsorship resource configuration tables, and effect result event logs reported by the event viewing terminals. Based on the sponsorship resource configuration table, the module performs legality verification on the sponsorship touchpoint event logs to form a set of valid touchpoint events. The forming module is used to calculate the effective exposure weight and form a sponsored exposure sequence aggregated by time slice based on the visibility duration, location type and interaction mark of each touch event in the set of effective touch events; The generation module is used to generate an anonymous association signature corresponding to the time slice based on the sponsored exposure sequence aggregated by the time slice and the effect result event log, and to establish a matching relationship between touch point events and result events in a preset association window based on the anonymous association signature to form an anonymous entity cluster. The presentation module is used to generate anonymous and reproducible group tags based on the anonymous associated signature, and to perform differentiated presentation based on the group tags when the control rules in the sponsor resource configuration table are met, so as to form comparison data between the processing group and the control group; The output module is used to calculate the incremental effect index corresponding to the sponsor and output the sponsorship effect evaluation result based on the anonymous entity cluster, the comparison data of the treatment group and the control group, and the sponsorship exposure sequence.

9. A device for evaluating the effectiveness of sports event sponsorship, characterized in that, The sports event sponsorship effectiveness evaluation device includes: a memory, a processor, and a sports event sponsorship effectiveness evaluation program stored in the memory and executable on the processor. When the sports event sponsorship effectiveness evaluation program is executed by the processor, it implements the steps of the sports event sponsorship effectiveness evaluation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a sports event sponsorship effectiveness evaluation program, which, when executed by a processor, implements the steps of the sports event sponsorship effectiveness evaluation method as described in any one of claims 1 to 7.

Images