Lottery information processing method, device and equipment

Abstract

The application discloses a lottery information processing method, device and equipment, wherein the method comprises: obtaining a probability parameter group that has an influence on a winning probability of a product object lottery game; in response to a lottery request of a target user, obtaining user characteristic information and / or current winning condition information of the target user; selecting a target probability parameter related to the request from the probability parameter group according to the user characteristic information and / or the current winning condition information; determining a winning probability corresponding to the request according to the target probability parameter; determining product object lottery result data corresponding to the request according to the winning probability; and providing a product object operation option if the result data is winning. This processing method can adjust the winning probability of each lottery according to the user condition, thereby improving the user game experience, prompting the user to grab more products, and further promoting the user to place more orders and promoting the product transaction conversion. Therefore, the resource utilization rate of an e-commerce system can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method and apparatus for processing lottery information, as well as electronic equipment. Background Technology

[0002] With the development of e-commerce, e-commerce shopping is no longer limited to a continuously updated information feed that presents content to users. More and more different shopping scenarios have emerged. One new e-commerce shopping format involves offering users a claw machine-like game where they can grab discounted items. This increases the game's fun and engaging aspect, allowing users to experience a sense of accomplishment and become more interested in the game. This encourages users to grab more discounted items and place more orders, thereby boosting sales conversion on user devices (such as smartphones, tablets, and PCs).

[0003] Setting appropriate winning probabilities in a game is crucial for ensuring the effectiveness of a product-grabbing game. Currently, a typical method for setting winning probabilities is to manually determine a fixed probability based on experience. However, in developing this invention, the inventors discovered that this approach has at least the following problems: a fixed winning probability leads to a poor user experience, fails to effectively attract users, results in low game participation, and consequently affects metrics such as product conversion rates, leading to a waste of e-commerce system resources. Summary of the Invention

[0004] This application provides a method for processing lottery information to address the problem of wasted resources in e-commerce systems due to poor user gaming experience in existing technologies. This application also provides a lottery information processing device and electronic equipment.

[0005] This application provides a method for processing lottery information, including:

[0006] In response to a target user's lottery request, a set of target probability parameters that affect the winning probability of the product object lottery game is obtained; the set of probability parameters includes: probability parameters related to user characteristics and / or probability parameters related to the current winning situation;

[0007] Obtain the target user's user characteristics information and / or current winning status information;

[0008] Based on the user characteristic information and / or the current winning status information, select the target probability parameter related to the request from the target probability parameter group;

[0009] Based on the target probability parameters, determine the winning probability corresponding to the request;

[0010] Based on the winning probability, determine the lottery result data for the product object corresponding to the request;

[0011] If the result data indicates a winning prize, then the option to manipulate the product object is provided.

[0012] Optional, also includes:

[0013] Acquire multiple probability parameter sets and at least one game effect data corresponding to the probability parameter sets; the at least one game effect data includes: product object transaction conversion rate and / or product object click rate;

[0014] The target probability parameter set is determined based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets.

[0015] Optionally, determining the target probability parameter set based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets includes:

[0016] Based on at least one game effect data corresponding to the probability parameter set, determine the game effect score corresponding to the probability parameter set;

[0017] The target probability parameter set is determined based on the plurality of probability parameter sets and the scores corresponding to the probability parameter sets.

[0018] Optionally, determining the game effect score corresponding to the probability parameter set based on at least one game effect data corresponding to the probability parameter set includes:

[0019] The score is the weighted sum of the differences between the at least one game effect data and the corresponding lower limit value of the game effect.

[0020] Determining the target probability parameter set based on the plurality of probability parameter sets and the scores corresponding to the probability parameter sets includes:

[0021] Using the game effect data being greater than or equal to the corresponding lower limit of the game effect as a constraint, the target probability parameter set is determined based on the multiple probability parameter sets and the scores corresponding to the probability parameter sets.

[0022] Optional, also includes:

[0023] Set up multiple probability parameter groups and use the multiple probability parameter groups for different user ranges;

[0024] The target probability parameter set that affects the winning probability of the lottery game for acquiring product objects includes:

[0025] Obtain the target user range to which the target user belongs;

[0026] Determine the target probability parameter set corresponding to the target user range from the plurality of probability parameter sets.

[0027] The step of determining the target probability parameter set based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets includes:

[0028] The first probability parameter group is determined based on the plurality of probability parameter groups and at least one game effect data corresponding to the probability parameter groups;

[0029] Update the plurality of probability parameter groups according to the first probability parameter group.

[0030] Optionally, obtaining the user characteristic information of the target user includes:

[0031] Obtain the user group information to which the target user belongs;

[0032] The probability parameters related to user characteristics include: probability parameters corresponding to at least one user group;

[0033] Based on the user feature information, target probability parameters related to the request are selected from the target probability parameter group, including:

[0034] From the probability parameters corresponding to at least one user group, select the probability parameter corresponding to the user group information to which the user belongs, and use it as the target probability parameter.

[0035] Optionally, obtaining the user group information to which the target user belongs includes:

[0036] Obtain the target user's user information, historical behavior information regarding the product, and / or historical prize-winning information;

[0037] The user group information is determined based on the user information, the historical behavior information, and / or the historical winning information.

[0038] Optionally, the current winning status includes: consecutive losses or consecutive wins;

[0039] The probability parameters related to the current winning situation include:

[0040] Additional probability of consecutive failures and / or additional probability of consecutive wins;

[0041] Obtaining the target user's current winning status information includes:

[0042] Based on the current number of draws and the current number of wins, obtain the current winning status information.

[0043] Optionally, the target probability parameter set may further include: initial winning probability;

[0044] Determining the winning probability corresponding to the request based on the target probability parameter includes:

[0045] The sum of the initial winning probability and the target probability parameter is taken as the winning probability.

[0046] Optionally, the target probability parameter set further includes: an upper limit value for winning probability and a lower limit value for winning probability;

[0047] The method further includes:

[0048] If the winning probability determined according to the target probability parameter exceeds the upper limit of the winning probability, then the upper limit of the winning probability shall be taken as the winning probability.

[0049] If the determined probability of winning is lower than the lower limit of the probability of winning, then the lower limit of the probability of winning shall be taken as the probability of winning.

[0050] Optionally, the target probability parameter set includes: the number of capture attempts;

[0051] The method further includes:

[0052] If the current consecutive number of times you don't win is equal to the number of guaranteed wins minus one, then the probability of winning is guaranteed.

[0053] This application also provides a lottery information processing device, including:

[0054] The probability parameter acquisition unit is used to acquire a set of probability parameters that affect the winning probability of the product object lottery game; the set of probability parameters includes: probability parameters related to user characteristics and / or probability parameters related to the current winning situation;

[0055] The user data acquisition unit is used to acquire user characteristic information and / or current winning status information of the target user in response to the target user's lottery request;

[0056] The probability parameter selection unit is used to select a target probability parameter related to the request from the probability parameter group based on the user feature information and / or the current winning status information.

[0057] The winning probability determination unit is used to determine the winning probability corresponding to the request based on the target probability parameter;

[0058] The game result determination unit is used to determine the lottery result data of the product object corresponding to the request based on the winning probability;

[0059] An operation option providing unit is used to provide operation options for a product object if the result data indicates a winning prize.

[0060] This application also provides an electronic device, including:

[0061] Processor and memory;

[0062] The memory is used to store a program that implements any of the above-described lottery information processing methods, and the device is powered on and runs the program of the method through the processor.

[0063] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the various methods described above.

[0064] This application also provides a computer program product including instructions that, when run on a computer, cause the computer to perform the various methods described above.

[0065] Compared with the prior art, this application has the following advantages:

[0066] The lottery information processing method provided in this application embodiment obtains a set of probability parameters that affect the winning probability of a product object lottery game. The probability parameter set includes probability parameters related to user characteristics and / or probability parameters related to the current winning status. In response to a target user's lottery request, the method obtains the target user's user characteristic information and / or current winning status information. Based on the user characteristic information and / or the current winning status information, it selects a target probability parameter related to the request from the probability parameter set. Based on the target probability parameter, it determines the winning probability corresponding to the request. Based on the winning probability, it determines the product object lottery result data corresponding to the request. If the result data indicates a winning result, it provides product object operation options. This processing method allows the winning probability of each lottery to be adjusted according to the user's situation, thereby improving the user's gaming experience, encouraging users to grab more products, and thus promoting more orders and increasing product transaction conversion on the user's end. Therefore, it can effectively improve the resource utilization rate of the e-commerce system. Attached Figure Description

[0067] Figure 1 This application provides a flowchart illustrating the lottery information processing method.

[0068] Figure 2 This application provides a schematic diagram illustrating the application scenario of the lottery information processing method. Detailed Implementation

[0069] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0070] This application provides a method and apparatus for processing lottery information, as well as an electronic device. The various solutions are described in detail in the following embodiments.

[0071] First Embodiment

[0072] Please refer to Figure 1 This is a flowchart illustrating an embodiment of the lottery information processing method of this application. In this embodiment, the method may include the following steps:

[0073] Step S101: In response to the target user's lottery request, obtain the target probability parameter set of the product object lottery game that affects the winning probability.

[0074] The aforementioned product lottery game, also known as a shopping game, allows users to draw products through gameplay. Winning products can then be ordered, added to the cart, or added to favorites. By offering this shopping game format, e-commerce platforms can increase the fun and engagement of the shopping experience, giving users a sense of accomplishment and fostering their interest. This encourages users to select and order more products, thereby boosting sales conversion rates on the user's device. The user's device can be a smartphone, tablet, or other mobile device, or a personal computer.

[0075] The product object lottery game can be a lottery game for a group of product objects or a lottery game for a single product object.

[0076] For a game involving drawing lots from a set of product objects, multiple product objects can be provided in the game interface. Users can draw a product object through a lottery system. The result may be any one of the multiple product objects, or no product object drawn. For each user's lottery request, the e-commerce platform adjusts the winning probability of each draw using the method provided in this application embodiment, and determines the drawn product object or the undrawn product object based on the winning probability.

[0077] A claw machine-like game for grabbing a specific product object can provide multiple product objects in the game interface, allowing users to grab a product object of interest, similar to an offline claw machine. The result can be either successfully grabbing the product object or failing to grab it. For each user grabbing request, the e-commerce platform adjusts the winning probability of each grab using the method provided in this application embodiment, and determines the grabbing result for the user-specified product object based on the winning probability.

[0078] like Figure 2 As shown in this embodiment, the e-commerce platform offers a special-offer item grabbing game in its limited-time flash sale channel. The game interface provides multiple item objects. Similar to a claw machine, the target user aims the handle at an item they are interested in and clicks "Start Grabbing." After receiving the "Start Grabbing" command from the target user, the client sends a lottery request to the server. The server adjusts the winning probability of the grab using the method provided in this embodiment, determining whether the item is successfully grabbed based on the probability. If the item is successfully grabbed, "Place Order Now" is displayed, which the user can then click. After receiving the "Place Order Now" command from the user, the client sends an order request to the server. The server generates an order for the item, and the item is then visible as delivered to the user's address.

[0079] In a product-based lottery game scenario, a user's outcome each time they play is related to their winning probability. In existing technologies, a uniform winning probability is typically set, and the game result is determined by this fixed probability regardless of the user or the game session—meaning the winning probability is uniform for everyone. In the method provided in this application, the winning probability can be adjusted according to the user's actual situation. The winning probability varies from person to person and from situation to situation; each person's winning probability may be different, and even the same user's winning probability may differ across different games. Because the adjusted winning probability better reflects the user's actual situation, the user will experience a greater sense of accomplishment in the game, encouraging them to try their luck and place more orders.

[0080] The method provided in this application sets multiple probability parameters that affect the probability of winning a prize, and these probability parameters as a whole are referred to as a probability parameter group. The probability of winning a prize can be the cumulative value of multiple target probability parameters related to user circumstances in the target probability parameter group. The probability parameter group that affects the probability of winning a prize may include probability parameters related to user characteristics, probability parameters related to the current winning situation, or both probability parameters related to user characteristics and probability parameters related to the current winning situation.

[0081] Probability parameters related to user characteristics can include multiple probability parameters corresponding to different user characteristics. User characteristics include, but are not limited to, user group characteristics, and can also be personalized user characteristics. A user may belong to one or more user groups. For example, user A belongs to the high-value user group and the active user group, user B belongs to the new user group, user C belongs to the active user group and the user group with bad luck in games, user C does not belong to any user group, and user D belongs to the lucky user group. Accordingly, probability parameters related to user characteristics include multiple probability parameters corresponding to different user groups, such as the additional probability for high-value users, the additional probability for active users, the additional probability for new users, the additional probability for users with bad luck, and the additional probability for users with good luck. The probability parameter set includes probability parameters related to user characteristics, so that the probability of winning is affected by user characteristics.

[0082] In practice, the additional probabilities corresponding to high-value user groups, new user groups, unlucky user groups, and active user groups can be positive, while the additional probability corresponding to lucky user groups can be negative. The winning probability can be accumulated with the additional probabilities corresponding to user groups. If a user belongs to a high-value user group, a new user group, an unlucky user group, or an active user group, the winning probability is increased; if a user belongs to a lucky user group, the winning probability is suppressed.

[0083] Probability parameters related to the current winning situation include, but are not limited to: additional probability of consecutive losses and additional probability of consecutive wins. This probability parameter group includes probability parameters related to the current winning situation, allowing the winning probability to be dynamically adjusted based on the user's current winning status.

[0084] In practice, the additional probability of consecutive losses can be positive, and the additional probability of consecutive wins can be negative. If a user has consecutive losses in the current lottery, the probability of winning in subsequent game interactions can be increased by accumulating the additional probability of consecutive losses. Conversely, if a user has consecutive wins in the current lottery, the probability of winning in subsequent game interactions can be decreased by accumulating the additional probability of consecutive wins.

[0085] In one example, the probability parameter set affecting the winning probability can include not only probability parameters related to user circumstances but also the initial winning probability. The initial winning probability, also known as the default winning probability, is the base value for the winning probability, and each person is assigned an initial winning probability every time they play the game. Probability parameters related to user circumstances are assigned based on the user's specific situation; a corresponding probability is only assigned when the user meets certain conditions (such as user group, current winning status, etc.). In this case, the winning probability is adjusted based on the initial winning probability according to the user's specific circumstances. When adjusting the winning probability based on the initial winning probability, some additional probabilities are positive, which is equivalent to increasing the winning probability based on the initial winning probability; some additional probabilities are negative, which is equivalent to decreasing the winning probability based on the initial winning probability.

[0086] In practice, the probability parameter set that affects the probability of winning may only include probability parameters related to the user's situation, and not the initial probability of winning.

[0087] The inventors analyzed the user experience of the game-based shopping method and found that if the difficulty of winning is too high, it will cause users to feel frustrated, and they may churn after failing to win a few times, which is detrimental to the e-commerce platform's final sales goals. Conversely, if the difficulty of winning is too low, it will reduce the fun of the game, making users feel there is no challenge and losing the surprise of winning, which is also detrimental to the final sales goals. To avoid these situations, the probability parameter group affecting the winning probability can also include at least one of the following parameters: an upper limit value for the winning probability and a lower limit value for the winning probability, to prevent the winning difficulty from being too high or too low. For example, if the winning probability calculated based on the initial winning probability and the additional probability related to the user's actual situation exceeds the upper limit value, then the winning probability is set to the upper limit value to prevent the winning difficulty from being too low and to avoid users feeling there is no challenge; if the winning probability is lower than the lower limit value for the winning probability, then the winning probability is set to the lower limit value to prevent the winning difficulty from being too high and to avoid users feeling frustrated.

[0088] Probability parameters are factors influencing the probability of winning. These can include not only the various additional probabilities mentioned above, the initial winning probability, and the upper and lower limits of the winning probability, but also parameters related to the number of attempts, such as the guaranteed number of attempts. In one example, the probability parameter group affecting the winning probability could also include the guaranteed number of attempts, such as 8 or 6 attempts. Using the guaranteed number of attempts N ensures that the winning probability is affected by the number of attempts; the user's winning probability on the Nth attempt is influenced by the results of the previous N-1 attempts. If a user's current number of game attempts (e.g., the number of times they participate in the lottery that day) reaches the guaranteed number of attempts N, and the user has failed to win in N-1 consecutive attempts, then there should be a guaranteed win mechanism. This mechanism would ensure a 100% winning probability on the Nth attempt, guaranteeing the user's win and preventing excessive frustration from causing churn.

[0089] In practice, the values ​​of each probability parameter can be set according to their respective ranges, and the ranges can be determined based on the actual application. The table below shows the probability parameters and their ranges in this embodiment.

[0090]

[0091]

[0092] Table 1. Probability Parameters

[0093] In practice, each parameter in the target probability parameter group can be set manually based on experience, or it can be learned from multiple probability parameter groups and the game effect data corresponding to each probability parameter group through machine learning algorithms.

[0094] In one example, the target probability parameter set is determined using the following steps:

[0095] Step S201: Obtain multiple probability parameter groups and at least one game effect data corresponding to the probability parameter groups.

[0096] Game performance data includes performance data related to user interactions with product objects generated through playing the shopping game. Product object interactions can include clicking on a product to view its details page, adding it to the shopping cart or favorites, placing an order, etc. At least one game performance metric includes, but is not limited to, at least one of the following: product object conversion rate, product object click-through rate. Furthermore, from a game perspective, at least one game performance metric may also include the number of times users participated in the game.

[0097] Table 2 shows the game effect data for this embodiment.

[0098]

[0099] Table 2. Game Performance Data

[0100] As shown in Table 2, this embodiment uses multiple game effect data to achieve probability parameter optimization under multiple objectives.

[0101] Game performance data can also include repeat visit and / or repeat purchase data for specific products. While product conversion rate and click-through rate represent short-term performance data for game interaction, repeat visit and repeat purchase data represent long-term performance data. Optimizing probability parameters for long-term performance can encourage users to log in daily to participate and place orders.

[0102] Game effect data corresponding to the probability parameter set can be obtained in the following way: obtain game interaction data under the probability parameter set; obtain game effect data of the probability parameter set based on the game interaction data. The game interaction data includes, but is not limited to, the following data: user identifier, participation time, whether a prize was won, whether the user clicked to view product details after winning, whether the user placed an order to purchase the product after winning, etc.

[0103] Table 3 shows the game interaction data of this embodiment.

[0104]

[0105] Table 3. Game Interaction Data

[0106] In practice, user interaction data during gameplay can be stored in log files, and the game interaction data can be read from the log files.

[0107] The multiple probability parameter sets can be multiple probability parameter sets with different parameter values ​​used in different periods. In this case, different probability parameter sets are used in different periods. Table 4-1 below shows the 10 probability parameter sets used in the past 10 weeks.

[0108]

[0109] Table 4-1 Game Performance Data

[0110] The multiple probability parameter sets can also be multiple probability parameter sets with different parameter values ​​used in different user ranges at the same time, such as the 10 probability parameter sets used by an e-commerce platform for 10 user ranges, as shown in Table 4-2 below. The user ranges can be distinguished by region, such as Beijing users in one range and Hangzhou users in another. The user ranges can also be distinguished by user attributes, such as elderly users in one range and children in another. The user ranges can also be randomly assigned, that is, all users can be randomly grouped into 10 user ranges.

[0111]

[0112] Table 4-2 Game Performance Data

[0113] Step S203: Determine the target probability parameter set based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets.

[0114] In this embodiment, the target probability parameter set can be learned by machine learning algorithm based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets.

[0115] In one example, step S203 may include the following sub-steps:

[0116] Step S2031: Determine the game effect score corresponding to the probability parameter group based on at least one game effect data corresponding to the probability parameter group.

[0117] The score is a comprehensive score of the probability parameter set, related to at least one game effect data point of the probability parameter set. The score can be determined as follows: the weighted sum of the at least one game effect data point is used as the score. Specifically, it can be expressed using the following formula 1:

[0118]

[0119] As can be seen from the above formula, x represents a probability parameter group, including multiple probability parameter values; f(x) represents the score of this probability parameter group, which is a weighted sum of multiple game effect data. N represents the number of multiple game effects, and i represents the sequence number of the game effect. U1(x) can represent the number of times a user participates in the game; this is a core indicator with a corresponding weight of 1. i (x) represents the i-th game effect data, ω i The weight ω represents the weight of the i-th game effect data. i It can be determined according to actual needs.

[0120] The score can also be determined as follows: the weighted sum of the differences between the at least one game effect data and the corresponding lower limit value of the game effect is used as the score. Specifically, it can be expressed using the following formula 2:

[0121]

[0122] In Formula 2, h i This represents the lower limit (baseline value) of the i-th game effect, (U i (x)-h i ) represents the i-th game performance data relative to the baseline h. i The difference, the benchmark h i It can be determined according to actual needs.

[0123] In practice, the weight of the number of times a user participates in the game (e.g., the average number of times a user grabs the prize per day) can be set to 1. The goal of the product lottery game is primarily based on the number of times users participate in the interaction; the more times a user participates in the grabbing within a day, the more they enjoy it. At the same time, the click-through rate of users entering the product details page after winning and the final conversion rate can also be taken into account, ensuring that users do not lose the sense of surprise from winning because it is too easy, thus preventing them from placing an order.

[0124] Step S2033: Determine the target probability parameter set based on the plurality of probability parameter sets and the scores corresponding to the probability parameter sets.

[0125] After obtaining the scores corresponding to each set of probability parameters through any of the above methods, a regression model for the game effect score can be determined based on the multiple sets of probability parameters and the scores corresponding to the sets of probability parameters. The independent variable of this model is the set of probability parameters, and the dependent variable is the score. In specific implementation, a Bayesian optimization algorithm can be used to solve the regression model to obtain a set of probability parameter values ​​that maximize the dependent variable (i.e., the score).

[0126] In practical implementation, if the score is a weighted sum of at least one game effect data, then maximizing the score can be the optimization objective. The target probability parameter set is solved based on the multiple probability parameter sets and the scores corresponding to the probability parameter sets. Maximizing the score as the optimization objective can be expressed using the following formula 3:

[0127] argmax x∈X f(x) (Formula 3)

[0128] f(x) represents the objective function to be optimized (i.e., the regression model of game performance score), x represents the set of probability parameters, and X represents the candidate space (range of values) of multiple probability parameters.

[0129] In specific implementation, if the score is a weighted sum of the differences between at least one game effect data point and its corresponding lower limit value, then maximizing the score can be the optimization objective. With the game effect data point being greater than or equal to the corresponding lower limit value as a constraint, the target probability parameter set is solved based on the multiple probability parameter sets and the scores corresponding to those probability parameter sets. Using the game effect data point being greater than or equal to the corresponding lower limit value as a constraint can be represented by the following formula 4:

[0130] U i (x)≥h i (Formula 4)

[0131] This constraint condition indicates that the i-th game performance data is relative to the baseline h. i It cannot fall.

[0132] In one example, different sets of probability parameters are used for different periods, such as the 10 sets of probability parameters used in the past 10 weeks as shown in Table 4-1 above. In this case, the set of probability parameters solved by Formula 3 or Formula 4 above can be directly used as the target set of probability parameters.

[0133] In another example, different probability parameter sets are used for different user ranges during the same period, such as the 10 probability parameter sets used by the e-commerce platform for 10 user ranges in 4-2 above. In this case, the method provided by the embodiments of this application may further include the following steps: setting multiple probability parameter sets and using the multiple probability parameter sets for different user ranges.

[0134] The multiple probability parameter groups include the same probability parameters, but each group has different parameter values. The product object lottery game involves a large number of users, who can be divided into different user ranges, with different probability parameter groups used for different ranges. For example, setting 10 probability parameter groups allows e-commerce websites to group users according to attributes such as region; for instance, users in Hangzhou might use probability parameter group 1, users in Beijing might use probability parameter group 2, and users in Tianjin might use probability parameter group 10.

[0135] When different probability parameter sets are used for different user ranges during the same period, step S101 may include the following sub-steps: obtaining the target user range to which the target user belongs; determining the target probability parameter set corresponding to the target user range from the plurality of probability parameter sets. For example, if the target user is located in Beijing based on the user's IP address, then the target probability parameter set is the probability parameter set corresponding to the Beijing area.

[0136] When different probability parameter groups are used for different user ranges during the same period, step S201 can be implemented as follows: based on the game interaction data of the different user ranges under the corresponding probability parameter groups, at least one game effect data for each probability parameter group is obtained. Correspondingly, step S203 can be implemented as follows: based on the multiple probability parameter groups and at least one game effect data corresponding to the probability parameter groups, a first probability parameter group is determined; based on the first probability parameter group, the multiple probability parameter groups are updated. The first probability parameter group can be a probability parameter group solved using a Bayesian optimization algorithm. By fine-tuning the first probability parameter group, updated data for each probability parameter group can be obtained. The updated data replaces the original data of each probability parameter group, and the updated probability parameter group is used for different user ranges.

[0137] In specific implementation, step S203 can be implemented in the following way: if the online update condition is met, then the target probability parameter group is determined based on the multiple probability parameter groups and at least one game effect data corresponding to the probability parameter group.

[0138] The online update conditions can be conditions for periodically updating probability parameters, such as updating them at a fixed time every day or week. Alternatively, the online update conditions can be conditions for updating probability parameters based on game performance data. For example, if the average number of times users participate in the game per day is less than a threshold, the probability parameters are updated; if the average number of times users participate in the game per day per week is greater than the threshold, the probability parameters are updated once a week. The online update conditions can be determined according to application requirements.

[0139] In practice, the initial values ​​of multiple probability parameter groups set for different user ranges can be set manually based on experience. Then, when the online update conditions are met, a first probability parameter group is determined based on the multiple probability parameter groups and at least one game effect data corresponding to the probability parameter groups; and the multiple probability parameter groups are updated based on the first probability parameter group.

[0140] The method provided in this application optimizes probability parameters online by determining whether online update conditions are met and updating multiple probability parameter groups when the conditions are met. This approach increases the frequency of probability parameter updates, effectively improving the rationality of the probability parameters and thus enhancing the overall probability of winning.

[0141] Step S103: Obtain the user characteristic information and / or current winning status information of the target user.

[0142] The method provided in this application can be executed by a server. A user plays a product object lottery game on their device, sending a lottery request to the server each time they play. This lottery request may carry user identification information. In a product object grabbing game scenario, the lottery request may also include the identification information of the target product object. Upon receiving the request, the server obtains the target user's user characteristic information, or the target user's current winning status information, or both the target user's user characteristic information and current winning status information.

[0143] User characteristic information includes, but is not limited to, the user group information to which the user belongs. User group information includes, but is not limited to, high-value users, active users, new users, and unlucky users. To obtain the user group information to which the target user belongs, the following methods can be used: obtain the target user's user information, historical behavior data of the product object, and / or historical prize-winning data; determine the target user's user group information based on the user information, historical behavior data, and / or historical prize-winning data.

[0144] In specific implementation, determining the target user's user group information based on the user information, historical behavior data, and / or historical prize-winning data can be achieved using at least one of the following methods: determining whether the target user is a new user, a high-value user, and / or an active user based on the historical behavior data; determining whether the target user is an unlucky user based on the historical prize-winning data. For example, determining whether a user is an active user based on the number of times they have visited an e-commerce website in the past 15 days; determining whether a user is a high-value user based on the number of recent orders and transaction amounts; determining whether a user is an unlucky user based on the number of times they have participated in lotteries and won prizes; and determining whether a user is a new user based on their registration time.

[0145] The current winning status information can include whether the user has either failed to win consecutively or won consecutively in the current lottery, such as whether they have failed to win consecutively or won consecutively in the same day's lottery. In practice, the user's current number of lottery draws and current number of winnings can be obtained, and the system can determine whether the current winning status is either consecutive failures or consecutive wins based on these two pieces of information.

[0146] Step S105: Select target probability parameters related to the request from the target probability parameter group based on the user feature information and / or the current winning status information.

[0147] The target probability parameter set includes probability parameters related to the user's situation. These probability parameters are assigned based on the user's specific circumstances, and the corresponding probability will only be assigned if the user meets the relevant conditions.

[0148] When user feature information includes information about the user group to which the target user belongs, a probability parameter corresponding to the user group information of the target user can be selected from the probability parameters corresponding to at least one user group as the target probability parameter. The probability parameters corresponding to at least one user group include, but are not limited to: active user additional probability, high-value user additional probability, new user additional probability, and bad luck additional probability. Step S105 can be implemented as follows: if the target user's user group is active users, then the active user additional probability is used as the target probability parameter; if the target user's user group is high-value users, then the high-value user additional probability is used as the target probability parameter; if the target user's user group is new users, then the new user additional probability is used as the target probability parameter; if the target user's user group is bad luck users, then the bad luck user additional probability is used as the target probability parameter.

[0149] When the probability parameter group includes probability parameters related to the current winning situation, the probability parameters related to the current winning situation include, but are not limited to: the probability of consecutive losses and the probability of consecutive wins. Step S105 can be implemented as follows: if the current winning situation information indicates consecutive losses, then the probability of consecutive losses is used as the target probability parameter; if the current winning situation information indicates consecutive wins, then the probability of consecutive wins is used as the target probability parameter.

[0150] Step S107: Determine the winning probability corresponding to the request based on the target probability parameter.

[0151] In the method provided in this application embodiment, the probability of winning a prize in the game may be different for each user, and even the probability of winning a prize may be different for the same user each time they play. When a user is playing the game, the corresponding probability of winning a prize is calculated for each lottery request. The probability of winning a prize can be the sum of multiple target probability parameters determined in step S105.

[0152] For example, if the target user is a high-value user and an active user, and the current winning status is consecutive losses, then the target probability parameters include: the additional probability of high-value users, the additional probability of active users, and the additional probability of consecutive losses. By summing these three probability parameters, the winning probability of the target user in this game can be obtained.

[0153] For example, in addition to the initial winning probability, other target probability parameters related to the user's specific situation should also be considered. If the additional probability is positive, the winning probability will be increased on the basis of the initial winning probability. For example, if the user does not win for several consecutive days, the probability of winning in the future will be increased. If the additional probability is negative, the winning probability will be decreased on the basis of the initial winning probability. For example, if the user wins for several consecutive days, the probability of winning in the future will be decreased.

[0154] In practical applications, if the difficulty of winning is too high, it will cause users to feel frustrated. If they fail to win after a few tries, they may leave, which is not conducive to the e-commerce platform's final sales target. On the other hand, if the difficulty of winning is too low, it will lose the fun of the game, making users feel that there is no challenge and no sense of surprise when they win, which is also not conducive to the final sales target.

[0155] To avoid these situations, the probability parameter set affecting the winning probability may further include: an upper limit value for the winning probability and a lower limit value for the winning probability, to prevent the winning probability from being too difficult or too easy. Step S107 can be implemented as follows: if the winning probability determined according to the target probability parameter exceeds the upper limit value for the winning probability, then the upper limit value for the winning probability is used as the winning probability; if the determined winning probability is lower than the lower limit value for the winning probability, then the lower limit value for the winning probability is used as the winning probability. For example, if the winning probability calculated based on the initial winning probability and the additional probability related to the user's actual situation exceeds the upper limit value for the winning probability, then the winning probability is set to the upper limit value to prevent the winning probability from being too easy; if the winning probability is lower than the lower limit value for the winning probability, then the winning probability is set to the lower limit value to prevent the winning probability from being too difficult.

[0156] In one example, the probability parameter set affecting the winning probability may also include the guaranteed number of attempts. The method may further include the following step: if the current consecutive number of unsuccessful attempts equals the guaranteed number of attempts minus one, then the winning probability is guaranteed. Using the guaranteed number of attempts N ensures that the winning probability is affected by the number of attempts; the user's winning probability on the Nth attempt is influenced by the winning results of the previous N-1 attempts. If the user's current number of game attempts (e.g., the number of times they participate in the lottery on a given day) reaches the guaranteed number of attempts N, and the user has already failed in N-1 consecutive attempts, then there should be a guaranteed mechanism where the winning probability is 100% on the Nth attempt, guaranteeing the user's win and preventing excessive frustration from causing user churn due to repeated failures.

[0157] Step S109: Determine the lottery result data of the product object corresponding to the request based on the winning probability.

[0158] The outcome of this game can be determined based on the probability of winning.

[0159] Step S111: If the result data indicates a winning prize, then provide the product object operation options.

[0160] The product object operation options include, but are not limited to: placing an order, adding to cart, and adding to favorites.

[0161] In specific implementation, the method may further include the following steps: in response to the target user's operation request for the selected target data object, the target data object is processed, and the operation request includes a content viewing request for the target data object, an order placement request for the target data object, etc.

[0162] like Figure 2 As shown, users can click the "Place Order Now" button on the prize results page. The user submits an order request to the server, which generates an order based on the request and delivers the goods to the user's address.

[0163] As can be seen from the above embodiments, the lottery information processing method provided in this application obtains a set of probability parameters that affect the winning probability of a product object lottery game. The probability parameter set includes probability parameters related to user characteristics and / or probability parameters related to the current winning status. In response to a target user's lottery request, the method obtains the target user's user characteristic information and / or current winning status information. Based on the user characteristic information and / or the current winning status information, it selects a target probability parameter related to the request from the probability parameter set. Based on the target probability parameter, it determines the winning probability corresponding to the request. Based on the winning probability, it determines the product object lottery result data corresponding to the request. If the result data indicates a winning prize, it provides product object operation options. This processing method allows the winning probability of each lottery to be adjusted according to the user's situation, thereby improving the user's gaming experience, encouraging users to grab more products, and thus promoting more orders and increasing product transaction conversion on the user's end. Therefore, it can effectively improve the resource utilization rate of the e-commerce system.

[0164] Second Embodiment

[0165] In the above embodiments, a method for processing lottery information is provided. Correspondingly, this application also provides a device for processing lottery information. This device corresponds to the embodiments of the above method. The parts of this embodiment that are the same as those in the first embodiment will not be repeated here; please refer to the corresponding parts in Embodiment 1.

[0166] The lottery information processing device provided in this application includes: a probability parameter acquisition unit, a user data acquisition unit, a probability parameter selection unit, a winning probability determination unit, a game result determination unit, and an operation option provision unit.

[0167] A probability parameter acquisition unit is used to acquire a set of target probability parameters that affect the winning probability of a product object lottery game; the probability parameter set includes: probability parameters related to user characteristics and / or probability parameters related to the current winning status; a user data acquisition unit is used to acquire user characteristic information and / or current winning status information of the target user in response to the lottery request of the target user; a probability parameter selection unit is used to select target probability parameters related to the request from the target probability parameter set according to the user characteristic information and / or the current winning status information; a winning probability determination unit is used to determine the winning probability corresponding to the request according to the target probability parameters; a game result determination unit is used to determine the product object lottery result data corresponding to the request according to the winning probability; and an operation option providing unit is used to provide product object operation options if the result data indicates a winning result.

[0168] In one example, the device further includes:

[0169] The data acquisition unit is used to acquire multiple probability parameter groups and at least one game effect data corresponding to the probability parameter groups; the at least one game effect data includes: product object transaction conversion rate and / or product object click rate;

[0170] The target probability parameter group determination unit is used to determine the target probability parameter group based on the plurality of probability parameter groups and at least one game effect data corresponding to the probability parameter groups.

[0171] In one example, the target probability parameter group determining unit is specifically used to determine the game effect score corresponding to the probability parameter group based on at least one game effect data corresponding to the probability parameter group; and to determine the target probability parameter group based on the plurality of probability parameter groups and the score corresponding to the probability parameter group.

[0172] In one example, the target probability parameter group determining unit is specifically used to take the weighted sum of the differences between the at least one game effect data and the corresponding game effect lower limit value as the score; and to determine the target probability parameter group based on the plurality of probability parameter groups and the scores corresponding to the probability parameter groups, with the game effect data being greater than or equal to the corresponding game effect lower limit value as a constraint condition.

[0173] In one example, the device may further include: a plurality of group allocation units, configured to set a plurality of probability parameter groups and apply the plurality of probability parameter groups to different user ranges; a probability parameter acquisition unit, specifically configured to acquire the target user range to which the target user belongs; determine the target probability parameter group corresponding to the target user range from the plurality of probability parameter groups; the target probability parameter group determination unit, specifically configured to determine a first probability parameter group based on the plurality of probability parameter groups and at least one game effect data corresponding to the probability parameter groups; and update the plurality of probability parameter groups based on the first probability parameter group.

[0174] In one example, obtaining the user characteristic information of the target user includes:

[0175] Obtain the user group information to which the target user belongs;

[0176] The probability parameters related to user characteristics include: probability parameters corresponding to at least one user group;

[0177] Based on the user feature information, selecting a target probability parameter related to the request from the target probability parameter group includes: selecting a probability parameter corresponding to the user group information from the probability parameters corresponding to at least one user group, and using it as the target probability parameter.

[0178] In one example, obtaining the user group information to which the target user belongs includes: obtaining the target user's user information, historical behavior information on the product object, and / or historical prize-winning information; and determining the user group information to which the target user belongs based on the user information, the historical behavior information, and / or the historical prize-winning information.

[0179] In one example, the current winning situation includes: consecutive losses or consecutive wins;

[0180] The probability parameters related to the current winning situation include: the additional probability of consecutive losses and / or the additional probability of consecutive wins;

[0181] Obtaining the target user's current winning status information includes: obtaining the current winning status information based on the current number of draws and the current number of winnings.

[0182] In one example, the target probability parameter set also includes: the initial winning probability;

[0183] The winning probability determination unit is specifically used to take the sum of the initial winning probability and the target probability parameter as the winning probability.

[0184] In one example, the target probability parameter set further includes: an upper limit value for winning probability and a lower limit value for winning probability; the device may further include: an upper limit control unit, configured to use the upper limit value for winning probability as the winning probability if the winning probability determined according to the target probability parameters exceeds the upper limit value for winning probability; and a lower limit control unit, configured to use the lower limit value for winning probability as the winning probability if the determined winning probability is lower than the lower limit value for winning probability.

[0185] In one example, the target probability parameter set includes: the number of guaranteed wins; the device may further include: a guaranteed win device, used to ensure that if the current consecutive number of unsuccessful wins is equal to the number of guaranteed wins minus one, then the winning probability is guaranteed to win.

[0186] Third Embodiment

[0187] This application also provides an electronic device. Since the device embodiments are substantially similar to the method embodiments, the description is relatively simple; relevant details can be found in the description of the method embodiments. The device embodiments described below are merely illustrative.

[0188] This embodiment provides an electronic device, which includes a processor and a memory; the memory stores a program for implementing a lottery information processing method, and the device is powered on and runs the program of the method through the processor.

[0189] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

[0190] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0191] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0192] 1. Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0193] 2. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

Claims

1. A method for processing lottery information, characterized in that, include: In response to a lottery request from a target user, obtain the target probability parameter set for the lottery game of the product object that affects the probability of winning; The target probability parameter set includes: probability parameters related to user characteristics and / or probability parameters related to the current winning situation; the probability parameters related to user characteristics include multiple probability parameters corresponding to different user characteristics, the user characteristics including user group characteristics or user personalized characteristics; the probability parameters related to the current winning situation include at least the probability of consecutive losses and the probability of consecutive wins. Obtain the target user's user characteristics information and / or current winning status information; Based on the user characteristic information and / or the current winning status information, select the target probability parameter related to the request from the target probability parameter group; Based on the target probability parameters, determine the winning probability corresponding to the request; Based on the winning probability, determine the lottery result data for the product object corresponding to the request; If the result data indicates a winning prize, then the option to manipulate the product object is provided.

2. The method according to claim 1, characterized in that, Also includes: Obtain multiple probability parameter sets and at least one game effect data corresponding to the probability parameter sets; The at least one game performance data includes: product object transaction conversion rate and / or product object click-through rate; The target probability parameter set is determined based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets.

3. The method according to claim 2, characterized in that, The step of determining the target probability parameter set based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets includes: Based on at least one game effect data corresponding to the probability parameter set, determine the game effect score corresponding to the probability parameter set; The target probability parameter set is determined based on the plurality of probability parameter sets and the scores corresponding to the probability parameter sets.

4. The method according to claim 3, characterized in that, The step of determining the game effect score corresponding to the probability parameter set based on at least one game effect data corresponding to the probability parameter set includes: The score is the weighted sum of the differences between the at least one game effect data and the corresponding lower limit value of the game effect. Determining the target probability parameter set based on the plurality of probability parameter sets and the scores corresponding to the probability parameter sets includes: Using the game effect data being greater than or equal to the corresponding lower limit of the game effect as a constraint, the target probability parameter set is determined based on the multiple probability parameter sets and the scores corresponding to the probability parameter sets.

5. The method according to claim 2, characterized in that, Also includes: Set up multiple probability parameter groups and use the multiple probability parameter groups for different user ranges; The target probability parameter set that affects the winning probability of the lottery game for acquiring product objects includes: Obtain the target user range to which the target user belongs; Determine the target probability parameter set corresponding to the target user range from the plurality of probability parameter sets; The step of determining the target probability parameter set based on the plurality of probability parameter sets and at least one game effect data corresponding to the probability parameter sets includes: The first probability parameter group is determined based on the plurality of probability parameter groups and at least one game effect data corresponding to the probability parameter groups; Update the plurality of probability parameter groups according to the first probability parameter group.

6. The method according to claim 1, characterized in that, Obtaining the user characteristic information of the target user includes: Obtain the user group information to which the target user belongs; The probability parameters related to user characteristics include: probability parameters corresponding to at least one user group; Based on the user feature information, target probability parameters related to the request are selected from the target probability parameter group, including: From the probability parameters corresponding to at least one user group, select the probability parameter corresponding to the user group information to which the user belongs, and use it as the target probability parameter.

7. The method according to claim 6, characterized in that, The step of obtaining the user group information to which the target user belongs includes: Obtain the target user's user information, historical behavior information regarding the product, and / or historical prize-winning information; The user group information is determined based on the user information, the historical behavior information, and / or the historical winning information.

8. The method according to claim 1, characterized in that, The current winning status includes: consecutive periods without winning or consecutive periods of winning; The probability parameters related to the current winning situation include: Additional probability of consecutive failures and / or additional probability of consecutive wins; Obtaining the target user's current winning status information includes: Based on the current number of draws and the current number of wins, obtain the current winning status information.

9. The method according to claim 1, characterized in that, The target probability parameter set also includes: the initial winning probability; Determining the winning probability corresponding to the request based on the target probability parameter includes: The sum of the initial winning probability and the target probability parameter is taken as the winning probability.

10. The method according to claim 1, characterized in that, The target probability parameter set also includes: an upper limit value for winning probability and a lower limit value for winning probability; The method further includes: If the winning probability determined according to the target probability parameter exceeds the upper limit of the winning probability, then the upper limit of the winning probability shall be taken as the winning probability. If the determined probability of winning is lower than the lower limit of the probability of winning, then the lower limit of the probability of winning shall be taken as the probability of winning.

11. The method according to claim 1, characterized in that, The target probability parameter set includes: the number of capture attempts; The method further includes: If the current consecutive number of times you don't win is equal to the number of guaranteed wins minus one, then the probability of winning is guaranteed.

12. A lottery information processing device, characterized in that, include: The probability parameter acquisition unit is used to acquire the target probability parameter set that affects the winning probability of the product object lottery game. The target probability parameter set includes: probability parameters related to user characteristics and / or probability parameters related to the current winning situation; the probability parameters related to user characteristics include multiple probability parameters corresponding to different user characteristics, the user characteristics including user group characteristics or user personalized characteristics; the probability parameters related to the current winning situation include at least the probability of consecutive losses and the probability of consecutive wins. The user data acquisition unit is used to acquire user characteristic information and / or current winning status information of the target user in response to the target user's lottery request; The probability parameter selection unit is used to select a target probability parameter related to the request from the target probability parameter group based on the user feature information and / or the current winning status information; The winning probability determination unit is used to determine the winning probability corresponding to the request based on the target probability parameter; The game result determination unit is used to determine the lottery result data of the product object corresponding to the request based on the winning probability; An operation option providing unit is used to provide operation options for a product object if the result data indicates a winning prize.

13. An electronic device, characterized in that, include: Processor and memory; A memory for storing a program for implementing the lottery information processing method according to any one of claims 1-11, wherein the device is powered on and the program of the method is executed by the processor.

Images