Method and apparatus for recommending electronic entitlements

Abstract

Embodiments of the present application disclose a method and a device for recommending electronic right certificates. The method comprises: obtaining historical order data of a resource provider; determining a unit order consumption index value of the resource provider based on the historical order data; determining a threshold value of the electronic right certificates based on the unit order consumption index value, the threshold value being in a positive linear relationship with the unit order consumption index value, a multiple coefficient and an offset coefficient in the linear relationship being determined according to a numerical interval in which the unit order consumption index value is located, and the multiple coefficient and the offset coefficient being in a negative correlation with the unit order consumption index value; screening electronic right certificates with a certificate use threshold less than or equal to the threshold value from a candidate right certificate pool; and recommending the screened electronic right certificates to a resource consumer.

Description

Technical Field

[0001] This application relates to the field of information technology, and in particular to a method and apparatus for recommending electronic rights certificates. Background Technology

[0002] With the development of internet technology, in order to improve the consumption experience and resource utilization efficiency of resource consumers, many online service platforms recommend various electronic rights certificates to resource consumers, such as coupons, discount coupons, and vouchers. These certificates usually come with specific usage conditions, such as thresholds, like "valid for purchases over X yuan" or "Y yuan off for purchases over X yuan".

[0003] In practical applications, accurately recommending electronic rights certificates that resource consumers are likely to use and that will generate positive feedback is a common technical problem. Traditional recommendation methods often focus on the attributes of the certificate itself, such as its face value, validity period, or level of discount. However, when such a singular recommendation logic is applied to multiple resource providers with significantly different consumption levels, it can easily lead to a mismatch between the recommended electronic rights certificates and the specific resource providers, making it difficult to dynamically adapt to the actual situation of different resource providers. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for recommending electronic rights certificates.

[0005] This application provides the following solution: According to the first aspect, a recommended method for electronic rights certificates is provided, the method comprising: Obtain historical order data from resource providers; The unit order consumption index value of the resource provider is determined based on the historical order data; Based on the unit order consumption index value, a threshold for electronic rights certificates is determined. The threshold is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value. Both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value. Select electronic rights certificates from the candidate rights certificate pool that have a certificate usage threshold less than or equal to the threshold threshold. The selected electronic rights certificates will be recommended to resource consumers.

[0006] Optionally, determining the unit order consumption index value of the resource provider based on the historical order data includes: Obtain the total order amount and number of orders from the historical order data; The ratio of the total order amount to the number of orders is determined as the unit order consumption index value.

[0007] Optionally, the linear relationship includes: Th = N × Avg + M, where Th is the threshold value, Avg is the unit order consumption index value, N is the multiplier coefficient, and M is the offset coefficient.

[0008] Optionally, the multiplier and the offset coefficient are determined in the following manner: Obtain historical usage data of electronic rights certificates for orders with amounts falling within preset ranges; Based on the historical usage data, the relationship between the ratio of the electronic rights certificate usage threshold to the unit order consumption index value and the electronic rights certificate usage rate is analyzed. Determine the ratio range corresponding to the peak usage rate of the corresponding electronic equity certificate; Determine the multiple coefficient and offset coefficient that the threshold obtained based on the linear relationship falls within the ratio range.

[0009] Optionally, the multiplier and the offset coefficient are determined in the following manner: Obtain multiple combinations of multiplier coefficients and offset coefficients; Experiments were conducted on each of the aforementioned combinations, and the comprehensive index value of the electronic rights certificate corresponding to each combination was statistically analyzed. The comprehensive index value was determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate. Determine the multiplier and offset coefficients included in the optimal combination of comprehensive index values ​​for the corresponding electronic equity certificates.

[0010] Optionally, before recommending the selected electronic rights certificates to resource consumers, the method further includes: The selected electronic rights certificates are ranked based on the matching index value between the usage threshold of electronic rights certificates and the unit order consumption index value.

[0011] Optionally, the ranking of the selected electronic rights certificates based on the matching index value between the usage threshold of the electronic rights certificate and the unit order consumption index value includes: The matching index value is determined based on the absolute value of the difference between the ratio of the electronic rights certificate's usage threshold to the unit order consumption index value and the target ratio coefficient. The selected electronic rights certificates are sorted according to the matching index values ​​from smallest to largest.

[0012] Optionally, the target scaling factor is determined in the following manner: Obtain historical usage data of electronic rights certificates; Based on the historical usage data of the electronic rights certificate, the distribution data of the ratio of the electronic rights certificate usage threshold to the unit order consumption index value is statistically analyzed. Based on the distribution data, the comprehensive index value of electronic rights certificates is calculated, corresponding to the ratio values ​​of the usage threshold of electronic rights certificates and the unit order consumption index value. The comprehensive index value is determined by at least one of the click rate, usage rate and negative feedback rate of electronic rights certificates. The optimal ratio value of the comprehensive index of the corresponding electronic rights certificate is determined as the target ratio coefficient.

[0013] Optionally, the target scaling factor is determined in the following manner: The ratio of the usage threshold for obtaining multiple electronic rights certificates to the unit order consumption index value; Experiments were conducted on multiple of the stated ratio values, and the comprehensive index value of the electronic rights certificate corresponding to each stated ratio value was statistically analyzed. The comprehensive index value was determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate. The optimal ratio value of the comprehensive index of the corresponding electronic rights certificate is determined as the target ratio coefficient.

[0014] Optionally, sorting the selected electronic rights certificates based on the ascending order of the matching index values ​​includes: The selected electronic rights certificates are sorted according to the matching index values ​​from smallest to largest. If multiple electronic rights certificates have the same matching index value, the multiple electronic rights certificates shall be sorted based on at least one of the preferential degree and validity period of the electronic rights certificates.

[0015] According to the second aspect, a device for recommending electronic rights certificates is provided, the device comprising: The data acquisition unit is configured to acquire historical order data from resource providers; The indicator determination unit is configured to determine the unit order consumption indicator value of the resource provider based on the historical order data; The threshold determination unit is configured to determine a threshold for electronic rights certificates based on the unit order consumption index value. The threshold is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value. Both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value. The credential filtering unit is configured to filter electronic rights certificates from the candidate rights certificate pool whose credential usage threshold is less than or equal to the threshold threshold. The voucher recommendation unit is configured to recommend selected electronic rights vouchers to resource consumers.

[0016] According to a third aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects above.

[0017] According to the fourth aspect, an electronic device is provided, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any one of the first aspects above.

[0018] According to a fifth aspect, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects above.

[0019] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application utilizes the aforementioned scheme to dynamically adjust the threshold used for screening electronic rights certificates based on the unit order consumption index value of resource providers. The linear relationship used ensures a positive correlation between the threshold and the unit order consumption index value. Resource providers with low consumption levels are matched with lower certificate thresholds, while resource providers with high consumption levels are matched with higher certificate thresholds. This allows resource providers with different consumption levels to be matched with electronic rights certificates that are appropriate to their consumption levels, effectively reducing the negative perception of resource consumers who see electronic rights certificates that are not appropriate for the resource providers, and improving the click-through rate and usage rate of electronic rights certificates.

[0020] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a system architecture diagram applicable to the embodiments of this application.

[0023] Figure 2 A flowchart illustrating a recommended method for providing electronic rights certificates in embodiments of this application.

[0024] Figure 3 This is a schematic diagram showing a coupon card displayed on a search results page provided in an embodiment of this application.

[0025] Figure 4 A schematic block diagram of a recommended device for an electronic rights certificate provided in an embodiment of this application.

[0026] Figure 5 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0028] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0029] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0030] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0031] In the field of electronic rights certificate recommendation technology, to recommend suitable electronic rights certificates to resource consumers, the common approach is to make recommendations based on the fixed attribute parameters of the electronic rights certificates themselves. Specifically, this approach extracts values ​​such as the usage threshold and discount level of coupons, and then sorts or simply filters candidate electronic rights certificates based on these values. Its basic working principle is to determine the coupon with the lowest threshold or the highest discount level as the most beneficial electronic rights certificate for resource consumers and display it first. Its widespread application is mainly because it can directly provide a ranking result based on the merits of electronic rights certificates, achieving a universal recommendation logic.

[0032] However, this solution performs poorly when applied to scenarios with significant differences in consumer spending. A fundamental contradiction lies in the fact that, in its pursuit of simplified recommendation logic, the solution relies on the fixed attributes of electronic vouchers for ranking. This inherent design inevitably ignores the spending power of the resource providers themselves, resulting in low usage rates for recommended electronic vouchers. Specifically, in stores with low average order values, such as beverage shops, where the average spending is only 15 yuan, a particular voucher might be ranked highly due to its significant discount of 30 yuan off a purchase of 100 yuan. This leads consumers to perceive the voucher as having a much higher barrier to entry than they expect, requiring them to buy a large number of drinks to use it, resulting in a poor experience and extremely low click-through and usage rates.

[0033] In view of this, this application provides a new approach. To facilitate understanding of this application, the system architecture on which this application is based will first be described. Figure 1 An exemplary system architecture that can be applied to embodiments of this application is shown, such as Figure 1 As shown, the system architecture may include: a user-side resource consumer and a server-side resource consumer.

[0034] The server side and the client side are the two main components of the application service. The server side uses a server as its primary hardware infrastructure and may include one or more software service modules. In this embodiment, it is mainly responsible for handling the receiving and sending binding relationships, forming a collaborative front-end and back-end with the client side.

[0035] The user terminal can include, but is not limited to, smart mobile terminals, wearable devices, and PCs (Personal Computers). Smart mobile devices can include mobile phones, tablets, PDAs (Personal Digital Assistants), and connected car terminals. Wearable devices can include smartwatches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality) devices, and mixed reality devices (devices that support both virtual and augmented reality), etc.

[0036] The user end of a resource consumer can be a client, mini-program, or web application located on the user terminal.

[0037] A server can be a standalone server, a server cluster, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a hosting product within the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) services, such as high management difficulty and weak service scalability.

[0038] As one possible approach, when a resource consumer requests data from a resource provider list page, resource list page, or resource provider page, the server can use the method provided in this application embodiment to filter electronic consumption vouchers for the resource providers involved in the page and recommend the filtered electronic rights vouchers to the resource consumer.

[0039] It should be understood that Figure 1 The server and client shown are merely illustrative. Depending on implementation needs, there can be any number of server and client components.

[0040] Figure 2 A flowchart illustrating a recommended method for obtaining an electronic rights certificate as provided in this application embodiment. This method can be performed by... Figure 1 The server-side execution in the system shown. For example... Figure 2 As shown, the method may include the following steps: Step 201: Obtain historical order data from resource providers.

[0041] Step 203: Determine the unit order consumption index value of the resource provider based on historical order data.

[0042] Step 205: Based on the unit order consumption index value, determine the threshold of the electronic rights certificate. The threshold value is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value. Both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value.

[0043] Step 207: Select electronic rights certificates from the candidate rights certificate pool that have a certificate usage threshold less than or equal to the threshold threshold.

[0044] Step 209: Recommend the selected electronic rights certificates to resource consumers.

[0045] As can be seen from the above process, this application, through the above scheme, allows the threshold used to screen electronic rights certificates to be dynamically adjusted according to the unit order consumption index value of resource providers. The linear relationship used makes the threshold positively correlated with the unit order consumption index value. Resource providers with low consumption correspond to lower certificate thresholds, while resource providers with high consumption correspond to higher certificate thresholds. Thus, resource providers with different consumption levels can be matched with electronic rights certificates that are appropriate to their consumption levels, effectively reducing the negative perception of resource consumers due to seeing electronic rights certificates that are not appropriate to resource providers, and improving the click-through rate and usage rate of electronic rights certificates.

[0046] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments.

[0047] First, the above step 201, namely "obtaining historical order data of resource providers", will be described in detail with reference to the embodiments.

[0048] This step is the initial data collection phase, the purpose of which is to provide the raw data foundation for subsequent indicator calculations and resource allocation. In this application, "resource provider" refers to any entity capable of providing goods or services to resource consumers, such as shops on e-commerce platforms, restaurants on food delivery platforms, and drivers on sharing economy platforms. "Resource" refers to the goods and services that resource providers can offer to resource consumers, where goods can include physical goods or virtual goods (such as virtual game items, digital resources, online courses, etc.).

[0049] Historical order data is a collection describing the past transaction records of a resource provider, and may include, but is not limited to: order identifier, resource provider identifier, order amount, number of consumers in the order, and order time. Data within a certain historical time window can be extracted from the data warehouse at preset periods (e.g., daily), or it can be obtained in real-time in response to the generation of orders. For example, in a T+1 model, data from the previous T days (e.g., the previous 10 days) can be obtained at midnight each day, where T is a preset positive integer representing the length of the historical time window. For scenarios with high real-time requirements, relevant statistics can be accumulated and updated in real-time after an order is generated.

[0050] The following describes step 203, namely "determining the unit order consumption index value of the resource provider based on historical order data", in detail with reference to the embodiments.

[0051] The unit order consumption index is a quantitative value used to measure the average consumption level of a resource provider per unit order. One feasible method is to obtain the total order amount and order quantity from historical order data, and determine the ratio of total order amount to order quantity. This ratio is then used as the unit order consumption index. The total order amount refers to the sum of all order amounts within a specific historical time window. For example, if a food delivery merchant completed 100 orders in the past week, with each order amounting to 20 yuan, 30 yuan, etc., the total order amount is the sum of these amounts. The order quantity is the total number of valid orders within that historical time window, such as the 100 orders mentioned above. Then, the ratio of total order amount to order quantity is calculated: Unit order consumption index = Total order amount ÷ Order quantity. This ratio directly reflects the average consumption level of resource consumers per order from the resource provider, and can be called the average order amount. For example, if the total order amount is 5000 yuan and the order quantity is 100, then the unit order consumption index is 50 yuan per order.

[0052] This unit order consumption metric only requires two basic fields (total order amount and order quantity) and a single division operation, eliminating the need for complex data cleaning, aggregation, or multidimensional analysis. This significantly reduces computational resource and time costs, making it particularly suitable for real-time or near-real-time processing of large-scale order data. This ratio, representing the average order amount, is a widely understood business metric in the industry, facilitating the understanding of its business implications and effectively guiding resource allocation. Furthermore, with a sufficient number of historical orders (e.g., more than 30), this ratio effectively smooths fluctuations in exceptionally large or small orders, reflecting the stable consumption level of resource providers and avoiding misjudgments due to individual extreme values, thus demonstrating greater robustness.

[0053] Besides the methods mentioned above, other approaches can be used to determine the unit order consumption index value for resource providers. For example, the individual amounts of all orders placed by the resource provider within a certain historical time window can be extracted, and the median and mode can be calculated as the unit order consumption index value. Another example is to consider the time attribute of orders, assigning higher weight to recent orders and calculating a weighted average consumption amount as the unit order consumption index value.

[0054] The following describes in detail step 205, namely, "Based on the unit order consumption index value, determine the threshold of the electronic rights certificate. The threshold value is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value, and both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value."

[0055] In this step, a threshold (Th) for resource allocation decisions is generated using a pre-defined linear relationship. This linear relationship can be represented as: Th = N × Avg + M Where Th is the threshold value, used as the basis for subsequent screening of electronic rights certificates. Avg is the unit order consumption index value. N is the multiplier coefficient, and M is the offset coefficient. Using this linear formula, the consumer psychology of "the higher the consumption, the higher the acceptable threshold" can be intuitively reflected. At the same time, the parameters N and M can be used to adjust the rate at which the threshold value increases with the consumption index value and the basic offset, respectively, taking into account both high and low consumption scenarios.

[0056] This formula involves only one multiplication and one addition operation, requiring no iteration or complex fitting, and can be calculated in microseconds. It is particularly suitable for resource allocation systems requiring real-time or high-concurrency processing (such as thousands of judgments per second), significantly reducing CPU and memory overhead. The multiplier N and offset coefficient M have clear physical meanings—N controls the sensitivity of Avg to the threshold, and M sets the baseline offset to prevent the threshold from being too low, resulting in no usable electronic rights certificates. Operations personnel or algorithm engineers can intuitively understand the impact of parameter adjustments on the output results, facilitating manual intervention. The linear relationship ensures that Th increases monotonically with Avg, avoiding jumps or reversals that might occur with nonlinear functions (such as overfitted curves showing local threshold drops).

[0057] The multiplier and offset coefficients in the above linear relationship are both determined based on the numerical range of the unit order consumption index value, and both are negatively correlated with the unit order consumption index value. We can first divide the entire possible range of Avg values ​​into multiple consecutive numerical intervals based on the magnitude of the unit order consumption index value (Avg). For example: Low consumption range: Avg ∈ [0, 20) yuan Medium consumption range: Avg ∈ [20, 50) yuan High-consumption range: Avg ∈ [50, 100) yuan Ultra-high consumption range: Avg ∈ [50, +∞) yuan For each numerical interval, a pair of (N, M) parameter values ​​are pre-defined, and both N and M decrease as the interval containing Avg increases. That is: When Avg is in the low-consumption range, N and M take larger values. For example, N=1.5, because resource providers in the low-consumption range have resource consumers who are more sensitive to price, so the threshold needs to be relaxed to ensure the recommendation of electronic rights certificates. M=5 ensures the minimum threshold space and avoids the threshold being too low.

[0058] When Avg is in the medium consumption range, N and M take moderate values. For example, N=1.2, because resource providers in the medium consumption range have resource consumers with moderate price sensitivity, and the values ​​can be moderately relaxed to balance matching and supply. M=3 ensures balance.

[0059] When Avg is in the high-consumption range, N and M take the smaller values. For example, N=1.0, because resource providers in the high-consumption range have corresponding resource consumers with strong consumption capabilities, and normal matching is sufficient. M=0, because the multiplier is already sufficient at this point, and no additional offset is needed.

[0060] When Avg is in the high-consumption range, N and M take smaller values. For example, N=0.8, because resource providers in the ultra-high-consumption range have corresponding resource consumers with strong purchasing power, so the multiplier can be reduced to avoid overly broadening the selection. M=0, because the multiplier at this point is already sufficient, and no additional offset is needed.

[0061] In the embodiments of this application, there are multiple ways to determine the multiplier coefficient and the offset coefficient, and the preferred methods may include, but are not limited to, the following two: The first method: Determination based on historical usage data.

[0062] First, retrieve historical usage data for electronic rights certificates whose order amounts fall within preset ranges. Each record of electronic rights certificates in the historical usage data must include at least the usage threshold for that certificate (e.g., "X yuan" in "available for use with a minimum of X yuan"), the order amount at the time of use, whether it has been used (i.e., whether it has been redeemed), and the corresponding resource provider identifier.

[0063] Then, based on historical usage data, the relationship between the ratio of the electronic voucher usage threshold to the unit order consumption index value and the electronic voucher usage rate is analyzed. For each electronic voucher within a given interval, the ratio of its usage threshold to the corresponding resource provider's unit order consumption index value (Avg) is calculated and denoted as R. For example, if a merchant's Avg = 20 yuan and its issued discount coupon threshold is 15 yuan, then R = 0.75. Simultaneously, the usage rate of all electronic vouchers within that interval is calculated (i.e., the number of electronic vouchers used / the total number issued). Furthermore, a scatter plot or fitted curve is plotted between the R value and the usage rate to observe the relationship between the two.

[0064] Next, determine the ratio range corresponding to the peak usage rate of electronic vouchers. Through the above analysis, find the R value range corresponding to the point or interval with the highest usage rate. For example, statistics show that the usage rate of electronic vouchers is highest when R is in the range of [0.6, 0.8], indicating that consumers are most likely to use electronic vouchers when the order amount is 0.6 to 0.8 times Avg. Therefore, the range [0.6, 0.8] is defined as the ratio range corresponding to the peak.

[0065] Finally, determine the multiple coefficient and offset coefficient that ensure the threshold obtained based on the above linear relationship falls within the ratio range. This can be achieved by solving a set of (N, M) values ​​that ensure all or more thresholds obtained based on the above linear relationship fall within the aforementioned ratio range. For example, if the peak range is [0.6, 0.8], then 0.6 ≤ N + M / Avg ≤ 0.8 must be satisfied. Since Avg varies among different merchants, N and M can be solved by minimizing the deviation or setting a typical Avg value (such as the median).

[0066] By dividing Avg into intervals and setting negatively correlated N and M, the linear formula's "one-size-fits-all" approach to all consumption levels is avoided. Low-consumption merchants are not ignored by overly lenient thresholds, and high-consumption merchants are not unfairly affected by overly strict thresholds. This allows for differentiated and refined control of resource providers at different consumption levels within the constraints of limited resources. Through intervalization and negative correlation mechanisms, only a few interval boundaries and their corresponding parameter values ​​need to be set to cover the consumption scenarios corresponding to all resource providers, eliminating the need to configure parameters individually for each resource provider and significantly simplifying operational complexity.

[0067] The second approach: an experimental determination method.

[0068] First, obtain multiple combinations of multiplier coefficients and offset coefficients. For example, generate multiple candidate combinations of (N, M). For example, set the value range of N to [0.5, 1.5] with a step size of 0.25; and the value range of M to [0, 10] with a step size of 2, then a total of 30 combinations are obtained.

[0069] Then, experiments were conducted on each combination separately, and the comprehensive index value of the electronic rights certificate corresponding to each combination was statistically analyzed. The comprehensive index value was determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate. For each group (N, M), a threshold value (Th) was calculated according to the linear relationship described in the previous embodiment, and then electronic rights certificates (such as discount coupons) were generated and distributed based on Th. The experiment here can be an online A / B test, that is, simultaneously allocating electronic rights certificates of different combinations to resource consumers in different traffic buckets. During the experiment, consumer behavior data of the resources corresponding to each group of electronic rights certificates were recorded, and then the comprehensive index value of the electronic rights certificate was calculated.

[0070] This comprehensive index value is composed of at least one of the following indicators: Click-through rate: The percentage of resource consumers who click to view details after seeing the electronic rights certificate; Usage rate: The percentage of resource consumers who actually redeem the electronic rights certificate.

[0071] Negative feedback rate: The percentage of resource consumers who actively express dislike, complain, or close electronic benefit vouchers (e.g., clicking "not interested" or "block this offer").

[0072] The comprehensive indicator value can be calculated using a weighted sum, product, or normalized score. For example: Comprehensive Indicator = w1 × Click-through Rate + w2 × Usage Rate - w3 × Negative Feedback Rate, where w1, w2, and w3 are preset weights, which can be dynamically adjusted according to business objectives. If only the usage rate is used as an indicator, the comprehensive indicator value is simply the usage rate itself.

[0073] Finally, the multiplier and offset coefficients for the combination with the optimal comprehensive index value corresponding to the electronic equity certificate are determined. The comprehensive index values ​​corresponding to all (N, M) combinations are compared, and the combination with the optimal comprehensive index value for the electronic equity certificate is selected as the final coefficient. For example, if the comprehensive index value of the combination (N=1.0, M=5) is found to be 0.85, higher than other combinations such as 0.75 and 0.80, then N=1.0 and M=5 for this combination are determined as the coefficients for official use and deployed to the online system.

[0074] It can be seen that this method tests multiple sets of parameter combinations, finds the global optimal solution by covering the entire parameter space, and thus maximizes the overall benefits of electronic rights certificates.

[0075] In addition to the two methods mentioned above, other methods can be used or combined, such as rule-based determination methods, online adaptive adjustment methods based on reinforcement learning, and so on.

[0076] The above method can generate different threshold values ​​for resource providers with different consumption levels, as shown in Table 1 below.

[0077] Table 1 The following describes in detail step 207, namely "selecting electronic rights certificates from the candidate rights certificate pool whose certificate usage threshold is less than or equal to the threshold threshold", with reference to the embodiments.

[0078] After determining the threshold for resource providers, multiple electronic rights certificates in the candidate rights certificate pool can be filtered based on this threshold. One specific implementation method is to set the filtering condition as follows: the usage threshold of an electronic rights certificate is less than or equal to the threshold. The usage threshold refers to the minimum spending amount required to use the certificate. For example, an electronic rights certificate that requires a minimum purchase of X yuan has a usage threshold of X yuan; another example is an electronic rights certificate that offers a discount of B yuan for purchases of A yuan, with a usage threshold of A yuan. If the usage threshold of an electronic rights certificate is less than or equal to the threshold, it is retained; if the usage threshold is greater than the threshold, it is filtered. This allows for the removal of high-threshold certificates that are difficult for resource consumers to achieve, retaining certificates that match the spending level of resource providers, and preventing resource consumers from experiencing negative experiences due to seeing unusable electronic rights certificates.

[0079] Furthermore, since there may be multiple selected electronic rights certificates, in order to better recommend them to resource consumers, the selected electronic rights certificates can be sorted, and then step 209 can be performed based on the sorting results to recommend them to resource consumers.

[0080] One feasible approach is to rank the selected electronic rights certificates based on the matching index between the usage threshold of electronic rights certificates and the unit order consumption index value.

[0081] As can be seen, the ranking is based on a matching metric, which quantifies the match between the usage threshold of each electronic voucher and the average consumption per unit order (Avg). This method automatically prioritizes suitable electronic vouchers, thereby optimizing the user experience.

[0082] In this embodiment, the matching index value can be determined based on the absolute value of the difference between the ratio of the electronic rights certificate usage threshold and the unit order consumption index value and the target ratio coefficient; the selected electronic rights certificates are then sorted based on the order of the matching index values ​​from smallest to largest.

[0083] For example, the matching index value Mat can be determined using the following formula: Mat = |Req / Avg -Rat| Where Req is the usage threshold, Avg is the unit order consumption index value, and Rat is the target proportion coefficient.

[0084] By using the absolute value of the difference between the ratio and the target ratio as the matching score, two mismatch situations of excessively high and low thresholds can be symmetrically penalized. This ensures that electronic rights certificates that are closest to the optimal threshold ratio are always ranked first, thus naturally highlighting the certificates that best match consumers' consumption intentions at the sorting level and increasing usage rates.

[0085] Besides sorting based on this matching index value, other methods can also be used, such as sorting directly according to the usage threshold, or sorting based on the difference between the usage threshold and the unit order consumption index value, or sorting based on the ratio between the usage threshold and the unit order consumption index value, and so on.

[0086] The target ratio coefficient in the above formula is the benchmark used to calculate the matching index value, and its determination method can include, but is not limited to, the following two: The first method: Determine the target proportion coefficient based on historical data.

[0087] First, obtain historical usage data of electronic rights certificates. Extract usage records of electronic rights certificates from the database for resource providers, including the usage threshold for each electronic rights certificate, the corresponding unit order consumption index value (Avg), and logs of clicks, usage, and negative feedback for that electronic rights certificate.

[0088] Then, based on the historical usage data of electronic rights certificates, the distribution data of the ratio between the usage threshold of electronic rights certificates and the unit order consumption index value is statistically analyzed. For each electronic rights certificate, the ratio value can be divided into several continuous intervals, such as [0,0.2), [0.2,0.4), ..., and the number of electronic rights certificates in each interval is counted.

[0089] Next, based on the above distribution data, the comprehensive index value of electronic rights certificates corresponding to the usage threshold of electronic rights certificates and the proportion values ​​of unit order consumption index values ​​is calculated. The comprehensive index value is determined by at least one of the click rate, usage rate and negative feedback rate of electronic rights certificates. The determination method can be referred to the relevant description in the previous embodiments.

[0090] Finally, the optimal ratio value for the comprehensive index of the corresponding electronic rights certificate is determined as the target ratio coefficient. For example, by comparing the comprehensive index values ​​of all intervals, the center value or representative value of the interval with the highest value (i.e., the best effect) is selected as the target ratio coefficient. If intervalization is not required, curve fitting can be performed directly on the continuous ratio values ​​to find the ratio value corresponding to the peak value.

[0091] The target ratio coefficient is determined by statistical analysis of historical usage data, so that the ideal matching ratio used for ranking corresponds to the peak of the actual usage preferences of the consumer group. This ensures that the ranking strategy can stably improve the usage rate over a long period of time, and the method is based on sufficient evidence and is highly interpretable.

[0092] The second method is to determine the optimal target ratio coefficient through online experiments.

[0093] First, obtain the ratio of the usage threshold of multiple electronic rights certificates to the unit order consumption index value. A set of candidate ratio values ​​is pre-defined, for example, {0.6, 0.8, 1.0, 1.2}. These ratio values ​​serve as candidates for the "target proportional coefficient" in different experimental groups.

[0094] Experiments were conducted on multiple ratio values, and the comprehensive index value of the electronic rights certificate corresponding to each ratio value was statistically analyzed. The comprehensive index value was determined by at least one of the electronic rights certificate's click-through rate, usage rate, and negative feedback rate. For each candidate ratio value, it was ranked and recommended as the target ratio coefficient. Then, through A / B testing or traffic binning, the comprehensive index value for each experimental group was statistically analyzed.

[0095] The optimal proportion of the comprehensive index value corresponding to the electronic rights certificate is determined as the target proportion coefficient. The comprehensive index values ​​of each group of experiments are compared, and the proportion value corresponding to the group with the highest value is selected as the final target proportion coefficient.

[0096] By directly comparing the impact of different target ratio values ​​on the comprehensive index value through online experiments, the optimal ratio value can be dynamically selected as the target ratio coefficient based on the current business environment and consumer group, avoiding the insufficient timeliness of static experience values ​​and ensuring that the ranking strategy is always in the best state.

[0097] Besides the two methods mentioned above, other methods can be used to determine the target ratio value, such as setting the target ratio value based on experience or research, or setting the target ratio value based on business rules. As one possible value, in this embodiment of the application, a target ratio value of 3 can be used, which means that resource consumers need to spend about twice as much, thus providing both the incentive to use electronic rights certificates and avoiding the negative experience of difficulty in reaching the minimum spending requirement.

[0098] In some cases, when multiple electronic rights certificates have the same matching index value (i.e., their deviations from the target ratio coefficient are consistent), relying solely on the matching index cannot further distinguish priorities. Therefore, this application further introduces auxiliary sorting rules for hierarchical sorting to ensure that electronic rights certificates with the same matching index value can be recommended in an orderly manner. Specifically, if multiple electronic rights certificates have the same matching index value, they can be sorted based on at least one of the following: the degree of discount and the validity period.

[0099] The level of discount refers to the actual discount that electronic benefit vouchers bring to resource consumers, such as the amount of reduction or the percentage of discount. Generally, the greater the level of discount (e.g., higher minimum spend or lower discount), the more attractive it is to resource consumers and should be prioritized.

[0100] The validity period refers to the expiration date of the electronic rights certificate. The closer to the expiration date (the shorter the validity period), the more priority should be given to displaying it to encourage resource consumers to use it as soon as possible and avoid waste.

[0101] The sorting logic adopted is as follows: First, strictly sort according to the matching index value from smallest to largest; for vouchers with the same matching index value, then perform a secondary sorting according to at least one of the following rules: Listed from largest to smallest discount (the larger the discount, the earlier it appears); Arranged in ascending order of expiration date (the shorter the expiration date, the earlier it appears); Or a combination of both (e.g., first by the level of discount, then by the validity period).

[0102] For example: There are three coupons, all with a matching index value of 0.1. Coupon A: ¥20 off for purchases over ¥50, valid for 10 days; Coupon B: ¥15 off for purchases over ¥50, valid for 3 days; Coupon C: ¥20 off for purchases over ¥50, valid for 20 days. Sorted by discount level, coupons A and C offer a larger discount (¥20 off) than coupon B (¥15 off). However, sorted by validity period, coupon B (3 days) takes the highest priority. A combined rule can be used: first sort by discount level in descending order, then by validity period in ascending order, resulting in the following order: Coupon A (largest discount, shortest validity period), Coupon C (largest discount, longest validity period), Coupon B (smallest discount, shortest validity period). Specific rules can be adjusted according to business strategies.

[0103] It can be seen that by introducing auxiliary sorting factors (discount level and validity period) to break the situation where matching indicator values ​​are tied, it ensures that each recommendation has a definite and reasonable display order. When the matching indicator values ​​are the same, priority is given to displaying vouchers with greater discount level or longer validity period. This can further improve the willingness of consumers to claim resources and the usage rate while ensuring matching accuracy.

[0104] The following describes step 209, namely "recommending the selected electronic rights certificates to resource consumers," in detail with reference to an embodiment.

[0105] After screening, a set of electronic rights certificates matching the consumption level of resource providers is obtained, and this set or a portion thereof can be displayed to resource consumers. This application does not restrict the display medium for electronic rights certificates; they can be displayed on formats such as coupon cards (e.g., coupon cards). Figure 3 It is shown in the image, coupon component, or POI details page, etc.

[0106] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0107] According to another embodiment, a device for recommending electronic rights certificates is provided. Figure 4 This is a schematic block diagram of a recommended device for an electronic rights certificate provided in an embodiment of this application. The device is disposed in... Figure 1 The server side in the illustrated architecture. For example... Figure 4 As shown, the device 400 includes: a data acquisition unit 401, an indicator determination unit 402, a threshold determination unit 403, a voucher filtering unit 404, and a voucher recommendation unit 405, and may also include a voucher sorting unit 406. The main functions of each component are as follows: The data acquisition unit 401 is configured to acquire historical order data from the resource provider.

[0108] The indicator determination unit 402 is configured to determine the unit order consumption indicator value of the resource provider based on the historical order data.

[0109] The threshold determination unit 403 is configured to determine a threshold for electronic rights certificates based on the unit order consumption index value. The threshold is positively correlated with the unit order consumption index value in a linear relationship. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value, and both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value.

[0110] The credential filtering unit 404 is configured to filter electronic rights certificates from the candidate rights certificate pool that have a credential usage threshold less than or equal to the threshold threshold.

[0111] The voucher recommendation unit 405 is configured to recommend selected electronic rights vouchers to resource consumers.

[0112] As one possible implementation method, the indicator determination unit 402 can be specifically configured to: obtain the total order amount and the number of orders from the historical order data; and determine the ratio of the total order amount to the number of orders as the unit order consumption indicator value.

[0113] As one possible implementation, the linear relationship includes: Th = N × Avg + M, where Th is the threshold value, Avg is the unit order consumption index value, N is the multiplier coefficient, and M is the offset coefficient.

[0114] As one possible implementation method, the threshold determination unit 403 can determine the multiplier coefficient and the offset coefficient in the following way: obtain historical usage data of electronic rights certificates with order amounts falling within preset numerical ranges; based on the historical usage data, analyze the relationship between the ratio of the electronic rights certificate usage threshold to the unit order consumption index value and the electronic rights certificate usage rate; determine the ratio range corresponding to the peak of the corresponding electronic rights certificate usage rate; and determine the multiplier coefficient and offset coefficient that fall within the ratio range for the threshold obtained based on the linear relationship.

[0115] As another possible approach, the threshold determination unit 403 can determine the multiplier coefficient and the offset coefficient in the following manner: obtain multiple combinations of multiplier coefficients and offset coefficients; conduct experiments on each combination separately, and statistically analyze the comprehensive index value of the electronic rights certificate corresponding to each combination, wherein the comprehensive index value is determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate; determine the multiplier coefficient and offset coefficient contained in the combination with the optimal comprehensive index value of the corresponding electronic rights certificate.

[0116] Furthermore, the voucher sorting unit 406 can be configured to sort the selected electronic rights vouchers based on the matching index value between the usage threshold of the electronic rights voucher and the unit order consumption index value.

[0117] As one possible implementation method, the voucher sorting unit 406 can be specifically configured to: determine the matching index value based on the absolute value of the difference between the ratio of the electronic rights voucher's usage threshold and the unit order consumption index value and the target ratio coefficient; and sort the selected electronic rights vouchers based on the order of the matching index values ​​from smallest to largest.

[0118] As one possible approach, the voucher sorting unit 406 can determine the target ratio coefficient by: acquiring historical usage data of electronic vouchers; based on the historical usage data of electronic vouchers, statistically analyzing the distribution data of the ratio between the usage threshold of electronic vouchers and the unit order consumption index value; based on the distribution data, statistically analyzing the comprehensive index value of electronic vouchers corresponding to each ratio between the usage threshold of electronic vouchers and the unit order consumption index value, wherein the comprehensive index value is determined by at least one of the click-through rate, usage rate, and negative feedback rate of electronic vouchers; and determining the optimal ratio value of the corresponding comprehensive index value of electronic vouchers as the target ratio coefficient.

[0119] As another possible approach, the voucher sorting unit 406 can determine the target ratio coefficient by: obtaining the ratio values ​​of the usage threshold of multiple electronic rights vouchers to the unit order consumption index value; conducting experiments on the multiple ratio values ​​respectively, and statistically analyzing the comprehensive index value of the electronic rights vouchers corresponding to each ratio value, wherein the comprehensive index value is determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights vouchers; and determining the optimal ratio value of the corresponding comprehensive index value of the electronic rights vouchers as the target ratio coefficient.

[0120] As another possible implementation, the certificate sorting unit 406 can be specifically configured to: sort the selected electronic rights certificates based on the order of the matching index values ​​from smallest to largest; if multiple electronic rights certificates have the same matching index value, then sort the multiple electronic rights certificates based on at least one of the preferential degree and validity period of the electronic rights certificates.

[0121] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The system and device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0123] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0124] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0125] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0126] in, Figure 5 An exemplary architecture of an electronic device is shown, which may include a processor 510, a video display adapter 511, a disk drive 512, an input / output interface 513, a network interface 514, and a memory 520. The processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, and memory 520 can communicate with each other via a communication bus 530.

[0127] The processor 510 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0128] The memory 520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 520 can store the operating system 521 for controlling the operation of the electronic device 500, and the basic input / output system (BIOS) 522 for controlling the low-level operations of the electronic device 500. Additionally, it can store a web browser 523, a data storage management system 524, and a recommendation device 400, etc. The aforementioned recommendation device 400 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 520 and is called and executed by the processor 510.

[0129] Input / output interface 513 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0130] Network interface 514 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0131] Bus 530 includes a pathway for transmitting information between various components of the device, such as processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, and memory 520.

[0132] It should be noted that although the above-described device only shows the processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, memory 520, bus 530, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0133] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0134] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for recommending electronic rights certificates, characterized in that, The method includes: Obtain historical order data from resource providers; The unit order consumption index value of the resource provider is determined based on the historical order data; Based on the unit order consumption index value, a threshold for electronic rights certificates is determined. The threshold is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value. Both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value. Select electronic rights certificates from the candidate rights certificate pool that have a certificate usage threshold less than or equal to the threshold threshold. The selected electronic rights certificates will be recommended to resource consumers.

2. The method according to claim 1, characterized in that, The step of determining the unit order consumption index value of the resource provider based on the historical order data includes: Obtain the total order amount and number of orders from the historical order data; The ratio of the total order amount to the number of orders is determined as the unit order consumption index value.

3. The method according to claim 1, characterized in that, The linear relationship includes: Th = N × Avg + M, where Th is the threshold value, Avg is the unit order consumption index value, N is the multiplier coefficient, and M is the offset coefficient.

4. The method according to claim 1, characterized in that, The multiplier coefficient and the offset coefficient are determined in the following manner: Obtain historical usage data of electronic rights certificates for orders with amounts falling within preset ranges; Based on the historical usage data, the relationship between the ratio of the electronic rights certificate usage threshold to the unit order consumption index value and the electronic rights certificate usage rate is analyzed. Determine the ratio range corresponding to the peak usage rate of the corresponding electronic equity certificate; Determine the multiple coefficient and offset coefficient that the threshold obtained based on the linear relationship falls within the ratio range.

5. The method according to claim 1, characterized in that, The multiplier coefficient and the offset coefficient are determined in the following manner: Obtain multiple combinations of multiplier coefficients and offset coefficients; Experiments were conducted on each of the aforementioned combinations, and the comprehensive index value of the electronic rights certificate corresponding to each combination was statistically analyzed. The comprehensive index value was determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate. Determine the multiplier and offset coefficients included in the optimal combination of comprehensive index values ​​for the corresponding electronic equity certificates.

6. The method according to any one of claims 1 to 5, characterized in that, Before recommending the selected electronic rights certificates to resource consumers, the following steps are also included: The selected electronic rights certificates are ranked based on the matching index value between the usage threshold of electronic rights certificates and the unit order consumption index value.

7. The method according to claim 6, characterized in that, The ranking of the selected electronic rights certificates based on the matching index value between the usage threshold of the electronic rights certificate and the unit order consumption index value includes: The matching index value is determined based on the absolute value of the difference between the ratio of the electronic rights certificate's usage threshold to the unit order consumption index value and the target ratio coefficient. The selected electronic rights certificates are sorted according to the matching index values ​​from smallest to largest.

8. The method according to claim 7, characterized in that, The target proportionality coefficient is determined in the following manner: Obtain historical usage data of electronic rights certificates; Based on the historical usage data of the electronic rights certificate, the distribution data of the ratio of the electronic rights certificate usage threshold to the unit order consumption index value is statistically analyzed. Based on the distribution data, the comprehensive index value of electronic rights certificates is calculated, corresponding to the ratio values ​​of the usage threshold of electronic rights certificates and the unit order consumption index value. The comprehensive index value is determined by at least one of the click rate, usage rate and negative feedback rate of electronic rights certificates. The optimal ratio value of the comprehensive index of the corresponding electronic rights certificate is determined as the target ratio coefficient.

9. The method according to claim 7, characterized in that, The target proportionality coefficient is determined in the following manner: The ratio of the usage threshold for obtaining multiple electronic rights certificates to the unit order consumption index value; Experiments were conducted on multiple of the stated ratio values, and the comprehensive index value of the electronic rights certificate corresponding to each stated ratio value was statistically analyzed. The comprehensive index value was determined by at least one of the click-through rate, usage rate, and negative feedback rate of the electronic rights certificate. The optimal ratio value of the comprehensive index of the corresponding electronic rights certificate is determined as the target ratio coefficient.

10. The method according to claim 7, characterized in that, The process of sorting the selected electronic rights certificates based on the ascending order of the matching index values ​​includes: The selected electronic rights certificates are sorted according to the matching index values ​​from smallest to largest. If multiple electronic rights certificates have the same matching index value, the multiple electronic rights certificates shall be sorted based on at least one of the preferential degree and validity period of the electronic rights certificates.

11. A device for recommending electronic rights certificates, characterized in that, The device includes: The data acquisition unit is configured to acquire historical order data from resource providers; The indicator determination unit is configured to determine the unit order consumption indicator value of the resource provider based on the historical order data; The threshold determination unit is configured to determine a threshold for electronic rights certificates based on the unit order consumption index value. The threshold is positively correlated with the unit order consumption index value. The multiplier and offset coefficient in the linear relationship are determined based on the numerical range of the unit order consumption index value. Both the multiplier and offset coefficient are negatively correlated with the unit order consumption index value. The credential filtering unit is configured to filter electronic rights certificates from the candidate rights certificate pool whose credential usage threshold is less than or equal to the threshold threshold. The voucher recommendation unit is configured to recommend selected electronic rights vouchers to resource consumers.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 10.

13. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 10.

14. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 10.

Images