Platform prize distribution method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a platform prize distribution method, a platform prize distribution device, platform prize distribution equipment, a storage medium and a program product. Comparing the user statistical coefficient corresponding to each prize at the current lottery drawing moment with the user statistical coefficient corresponding to each prize at the previous lottery drawing moment to determine first coefficient increment information, wherein the user statistical coefficient is generated based on the user prize issuing quantity of each prize and the corresponding user behavior information; according to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery drawing moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; and determining a first target prize based on the target winning probability of each prize, and distributing the first target prize to the client. According to the scheme, the best matched prize is reasonably distributed to the user, and the prize distribution accuracy and individuation level are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a platform prize distribution method, device, equipment, storage medium, and program product. Background Art

[0002] With the rapid iteration of information technology, online revenue activities have become an indispensable promotion strategy for enterprises, a revenue growth engine, and a key way to deepen user interaction. Among them, incentive mechanisms such as event draws can be used as an effective means to attract user participation and enhance user stickiness. The intelligence level of its prize distribution mechanism directly affects the success of the event.

[0003] However, in the lottery algorithm of the related art, the winning probability of each prize configured by different users is the same or fixed, and the prize distribution mechanism is single, which cannot meet the actual prize needs of users, affecting user satisfaction and participation. Summary of the invention

[0004] The embodiments of the present application provide a platform prize distribution method, apparatus, device, storage medium and program product, which solve the problem in the related art that the probability of winning each prize configured by different users is the same or fixed, the prize distribution mechanism is single, and the actual prize needs of users cannot be met, which affects the user's satisfaction and participation. It realizes the reasonable distribution of the most matching prizes to users, improves the accuracy and personalization level of prize distribution, is conducive to maximizing the use of prize value, and significantly improves user satisfaction and participation.

[0005] In a first aspect, an embodiment of the present application provides a platform prize distribution method, the method comprising:

[0006] When receiving a user lottery request sent by the client, comparing the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information;

[0007] According to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table;

[0008] A first target prize is determined based on the target winning probabilities of the respective prizes, and the first target prize is distributed to the client.

[0009] In a second aspect, an embodiment of the present application further provides a platform prize distribution device, the device comprising:

[0010] A coefficient increment determination module is configured to, upon receiving a user lottery request sent by a client, compare the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information;

[0011] a winning probability adjustment module, configured to adjust the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configure the target winning probability of each prize in the current prize pool based on the target user probability table;

[0012] The target prize distribution module is configured to determine a first target prize based on the target winning probabilities of the respective prizes, and distribute the first target prize to the client.

[0013] In a third aspect, an embodiment of the present application further provides a platform prize distribution device, the device comprising:

[0014] one or more processors;

[0015] a storage device configured to store one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the platform prize distribution method described in the embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application further provides a non-volatile storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are configured to execute the platform prize distribution method described in the embodiment of the present application.

[0018] In the fifth aspect, an embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor of the device reads and executes the computer program from the computer-readable storage medium, so that the device executes the platform prize distribution method described in the embodiment of the present application.

[0019] In an embodiment of the present application, upon receiving a user lottery request sent by a client, the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information, and the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; according to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; based on the target winning probability of each prize, the first target prize is determined, and the first target prize is distributed to the client. In the above scheme, by comparing the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the personal user data corresponding to each prize can be effectively analyzed, and the user's preference for different prizes can be predicted, providing reliable reference information for the subsequent adjustment of the user's winning probability; by adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain the target user probability table, it is possible to dynamically adjust the probability configuration of the prize, generate a personalized prize distribution strategy for each user, and configure the target winning probability of each prize in the current prize pool based on the target user probability table, and distribute the first target prize determined based on the target winning probability of each prize to the client, so that the most matching prize can be reasonably distributed to the user, thereby improving the accuracy and personalization level of prize distribution, and realizing the maximum utilization of the prize value, as well as a significant improvement in user satisfaction and participation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of a platform prize distribution method provided in an embodiment of the present application;

[0021] Figure 2 A flow chart of a platform prize distribution method including a process of determining a prize usage rate of a target user provided in an embodiment of the present application;

[0022] Figure 3 A flow chart of a platform prize distribution method including a process of determining a target user's interest statistical coefficient provided in an embodiment of the present application;

[0023] Figure 4 A flow chart of a platform prize distribution method including a process of adjusting a target prize according to a prize inventory balance provided in an embodiment of the present application;

[0024] Figure 5 A flow chart of a platform prize distribution method including a process of adjusting the inventory balance of each prize provided in an embodiment of the present application;

[0025] Figure 6A flow chart of a platform prize distribution method including a process of determining a target platform prize usage rate provided in an embodiment of the present application;

[0026] Figure 7 A flow chart of a platform prize distribution method including a process of determining a target platform interest statistical coefficient provided in an embodiment of the present application;

[0027] Figure 8 A flow chart of a platform prize distribution method including a process of configuring prize probabilities according to the draw interval duration provided in an embodiment of the present application;

[0028] Fig. 9 A structural block diagram of a platform prize distribution device provided in an embodiment of the present application;

[0029] Fig.10 A schematic diagram of the structure of a platform prize distribution device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, rather than to limit the embodiments of the present application. It should also be noted that, for ease of description, only parts related to the embodiments of the present application are shown in the accompanying drawings, rather than all structures.

[0031] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0032] The platform prize distribution method provided in the embodiments of the present application can be applied to scenarios involving prize distribution in business activities, especially high-traffic, highly interactive online activities, where prizes can be points, props, objects, etc. Related online activities include e-commerce promotions, game event rewards, live interactive draws, etc. For example, a draw in an online live broadcast scenario. The participation channels for this online activity can be mini-programs, live broadcast platforms, web platforms, etc. The several application scenarios listed above are only exemplary and explanatory. In actual applications, the platform prize distribution method can also be used in business activities in other scenarios, and the embodiments of the present application do not limit this.

[0033] In the platform prize distribution method provided in the embodiment of the present application, the executor of each step can be a computer device, which refers to any electronic device with data calculation, processing and storage capabilities, such as a server and other devices, and the embodiment of the present application does not limit this.

[0034] Figure 1 This is a flow chart of a platform prize distribution method provided in an embodiment of the present application. Figure 1 As shown, the following steps are included:

[0035] Step S101: upon receiving a user lottery request sent by a client, compare the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0036] Among them, the user lottery request can be generated by the user's lottery triggering operation on the client, and the lottery triggering operation can be a click operation, a long press operation or a typing operation of the user on a specific control in the terminal device, etc., which is not limited in this application. If a user lottery request sent by the client is received, it can be regarded as triggering the prize distribution of the platform, and accordingly, the system time of receiving the user lottery request can be used as the current lottery time. It is understandable that the previous lottery time is the system time of the last time the user lottery request sent by the client was received. In this embodiment, the user statistical coefficient may include a user prize utilization rate, a user interest statistical coefficient, etc. Among them, the user prize utilization rate is used to characterize the statistics of a prize actually used by a user within a specific time range, and can be determined by the ratio of the number of prizes issued to the user within a specific time range to the number of prizes used by the user. The user interest statistical coefficient is used to characterize the user's interest in a certain prize within a specific time range. It can be determined by weighted fusion based on the user browsing prize data, the user clicking prize data, the user using prize data, etc. For example, the user browsing prize data and the user using prize data are weighted averaged to obtain the user interest statistical coefficient. For another example, the user browsing prize data, the user clicking prize data and the user using prize data are weighted averaged to obtain the user interest statistical coefficient. Specifically, the developer can adaptively select the generation method of the user statistical coefficient according to the statistical dimension setting of the actual application scenario and the user behavior characteristics, which is not limited in this application. In addition, the determination time node of the user statistical coefficient in this embodiment can be periodic, for example, every half hour, every hour, etc. In one embodiment, taking every hour as an example, the user statistical coefficient can be determined based on the user-related data of one hour after accumulating the user-related data of that hour. Optionally, the user statistical coefficient determined in that hour can also be weighted averaged with the user statistical coefficient determined in the same time period of the historical statistical cycle to obtain the final user statistical coefficient. For example, the final user statistical coefficient may be obtained by weighted fusion based on the user statistical coefficient calculated in the current time period, the user statistical coefficient calculated in the same time period one day ago, and the user statistical coefficient calculated in the same time period seven days ago.

[0037] Optionally, the first coefficient increment information can be determined by comparing and comparing one or more of the user statistical coefficients. In one embodiment, the first coefficient increment information can be determined by comparing and comparing one of the user prize usage rate, user interest statistical coefficient, etc. For example, the user prize usage rate corresponding to each prize at the current lottery moment and the previous lottery moment can be compared to determine the first coefficient increment information. For another example, the user interest statistical coefficient corresponding to each prize at the current lottery moment and the previous lottery moment can be compared to determine the first coefficient increment information. In one embodiment, the first coefficient increment information can be determined by comparing and comparing multiple types of user prize usage rate, user interest statistical coefficient, etc., by comparing the user prize usage rate, user interest statistical coefficient, etc. corresponding to each prize at the current lottery moment and the previous lottery moment to determine multiple coefficient increment information, and weighted fusion of multiple coefficient increment information to obtain the first coefficient increment information. Therefore, the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment may change, and the first coefficient increment information can be determined by comparing the two. The first coefficient increment information includes the increment information of the user statistical coefficients of each prize, such as the growth rate, the decline rate, the growth ratio, the decline ratio, etc. For example, the user statistical coefficient is the user prize utilization rate, the user prize utilization rate of prize A at the current lottery moment is p1, and the user prize utilization rate of prize A at the previous lottery moment is p2, p1 is greater than p2, then the growth rate of the user prize utilization rate is p1-p2, and the growth ratio of the user prize utilization rate at the current lottery moment relative to the previous lottery moment is (p1-p2) / p2, then the first coefficient increment information can be the growth rate p1-p2, or the growth ratio (p1-p2) / p2.

[0038] Step S102: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0039] Among them, the user probability table is the winning probability of each prize independently configured for each user. In one embodiment, the first coefficient increment information can be the growth rate or decline rate of the user statistical coefficient of each prize. By querying the preset mapping relationship, the probability adjustment range corresponding to the growth rate or decline rate can be obtained, and the winning probability of each prize is adjusted according to the probability adjustment range. For example, the winning probability corresponding to prize A at the previous lottery moment is z1, the growth rate of prize A in the first coefficient increment information is p1-p2, and the probability adjustment range corresponding to the growth rate is m1, then the winning probability should be adjusted to z1+m1. In one embodiment, the first coefficient increment information can be the growth ratio or decline ratio of the user statistical coefficient of each prize, and the winning probability of each prize can be adjusted in the same proportion directly according to the growth ratio or decline ratio. For example, the winning probability corresponding to prize A at the previous lottery moment is z1, the growth rate of prize A in the first coefficient increment information is p1-p2, and the growth ratio is (p1-p2) / p2, then the winning probability should be adjusted to z1×(p1-p2) / p2. In one embodiment, the sum of the winning probabilities of each prize is 1. Therefore, after adjusting the winning probabilities of each prize according to the first coefficient increment information, the sum of the winning probabilities of each prize may not be 1. The sum of the winning probabilities of each prize can be adjusted to 1 by normalization. Of course, there can be other adjustment methods, which are not limited in this application. Since the first coefficient increment information can characterize the changes in the user's actual usage or interest preferences, the target user probability table is equivalent to the probability adjustment obtained by adapting to the aforementioned changes. Based on the target user probability table, the winning probability of each prize in the current prize pool can be reasonably updated.

[0040] Step S103: Determine a first target prize based on the target winning probabilities of the various prizes, and distribute the first target prize to the client.

[0041] In one embodiment, the probability interval can be divided according to the target winning probability of each prize, a random number within a preset numerical interval can be generated, and the first target prize can be determined by judging in which probability interval the random number is located. For example, there are three prizes A, B, and C, and the target winning probabilities are 0.2, 0.3, and 0.5, respectively. Then the probability interval of prize A is set to [0, 0.2), the probability interval of prize B is set to [0.2, 0.5), and the probability interval of prize C is set to [0.5, 1]. A random number between 0 and 1 can be generated. For example, the generated random number is 0.4, which falls in the interval [0.2, 0.5), and the first target prize is prize B. In one embodiment, the cumulative probability boundary of each prize can be determined according to the target winning probability of each prize, a random number between 0 and 1 can be generated, and the random number can be compared with the cumulative probability boundary of each prize to determine the first target prize. For example, there are three prizes A, B, and C, and the target winning probabilities are 0.2, 0.3, and 0.5, respectively. Then, the cumulative probability boundary of prize A is set to 0.2, the cumulative probability boundary of prize B is set to 0.2+0.3=0.5, and the cumulative probability boundary of prize C is set to 0.2+0.3+0.5=1. A random number between 0 and 1 can be generated. For example, the generated random number is 0.6. Since 0.6 is greater than 0.5 and less than 1, the first target prize is prize C. Of course, there can be other ways of drawing prizes according to the target winning probabilities of each prize, which are not limited in this application.

[0042] In the above, upon receiving a user lottery request sent by the client, the first coefficient increment information is determined by comparing the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment, and the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; according to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; based on the target winning probability of each prize, the first target prize is determined, and the first target prize is distributed to the client. In the above scheme, by comparing the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the personal user data corresponding to each prize can be effectively analyzed, and the user's preference for different prizes can be predicted, providing reliable reference information for the subsequent adjustment of the user's winning probability; by adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain the target user probability table, it is possible to dynamically adjust the probability configuration of the prize, generate a personalized prize distribution strategy for each user, and configure the target winning probability of each prize in the current prize pool based on the target user probability table, and distribute the first target prize determined based on the target winning probability of each prize to the client, so that the most matching prize can be reasonably distributed to the user, thereby improving the accuracy and personalization level of prize distribution, and realizing the maximum utilization of the prize value, as well as a significant improvement in user satisfaction and participation.

[0043] Figure 2 A flowchart of a platform prize distribution method including a process of determining the prize usage rate of a target user provided in an embodiment of the present application. Figure 2 As shown, the following steps are included:

[0044] Step S201: When a preset time node is reached, the number of user prize usage within the preset time range is divided by the number of user prize distribution to obtain the user prize usage rate.

[0045] Among them, the preset time node can be a periodic time point for calculating the target user's prize usage rate, for example, every half hour, every hour, etc. Correspondingly, the preset time range can be a periodic time interval. Taking every hour as an example, the preset time range is the time range corresponding to the hour before the preset time node. For example, the preset time node is 13:00, and the corresponding preset time range is 12:00 to 13:00. The setting of the specific preset time node and the preset time range can be adaptively adjusted by the developer according to the activity characteristics and user behavior characteristics of the actual application scenario, and is not limited in this application. The number of user prizes used for each prize is the cumulative number of users using the prize within the preset time range. The number of user prizes issued for each prize is the cumulative number of prizes issued by the platform to users within the preset time range. Therefore, dividing the number of user prizes used by the number of user prizes issued can obtain the user prize usage rate within the preset time range corresponding to the current preset time node.

[0046] Step S202: Perform a weighted average calculation on the historical user prize usage rate corresponding to the first preset statistical period and the user prize usage rate to obtain the target user prize usage rate.

[0047] Among them, the first preset statistical period is a plurality of historical statistical time periods corresponding to different statistical time intervals adapted to the target user's prize usage rate setting. For example, if the current preset time node is 13:00, the corresponding preset time range is 12:00 to 13:00, and the statistical time intervals are set to 1 day and 7 days, then the first preset statistical period is 12:00 to 13:00 1 day ago and 12:00 to 13:00 7 days ago. If the historical user prize usage rate corresponding to 12:00 to 13:00 recorded 7 days ago is a1, the historical user prize usage rate corresponding to 12:00 to 13:00 1 day ago is a2, and the user prize usage rate is a3, then the corresponding weights are w and w respectively. a1 、w a2 and w a3 , for example, w a1 =10,w a2 =20,w a3 =70, therefore, the formula for calculating the target user prize utilization rate value1 is as follows:

[0048]

[0049] Of course, the aforementioned weight settings are only exemplary descriptions, and developers can make adaptive settings based on the data characteristics and impact size of different statistical periods in actual application scenarios, and this application does not limit this.

[0050] Step S203: upon receiving a user lottery request sent by the client, compare the target user prize usage rates corresponding to the prizes at the current lottery moment and the previous lottery moment to determine first coefficient increment information.

[0051] Step S204: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0052] Step S205: Determine a first target prize based on the target winning probabilities of the various prizes, and distribute the first target prize to the client.

[0053] As described above, by calculating the weighted average of the historical user prize usage rate and the user prize usage rate corresponding to the first preset statistical period recorded, the target user prize usage rate can be reasonably referenced to the statistical calculation results of multiple periods to evaluate the user prize usage, reduce the impact of the peak data that may appear in a single period on the overall value, and improve the accuracy and stability of the statistical results. By comparing the target user prize usage rate corresponding to each prize at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the reference information for adjusting the winning probability of each prize can be accurately determined according to the changes in the user's prize usage, and the probability configuration of the prize can be effectively tailored to the user's actual usage needs.

[0054] Figure 3 A flowchart of a platform prize distribution method including a process of determining a target user's interest statistical coefficient is provided in an embodiment of the present application. Figure 3 As shown, the following steps are included:

[0055] Step S301: When a preset time node is reached, the number of times a user browses a prize, the number of times a user clicks on a prize, and the number of times a user uses a prize within a preset time range are weighted averaged to obtain a user interest statistical coefficient.

[0056] Among them, the preset time node can be a periodic time point for calculating the target user's interest statistical coefficient, for example, every half hour, every hour, etc. Correspondingly, the preset time range can be a periodic time interval. Taking every hour as an example, the preset time range is the time range corresponding to the hour before the preset time node. For example, the preset time node is 15:00, and the corresponding preset time range is 14:00 to 15:00. The setting of the specific preset time node and the preset time range can be adaptively adjusted by the developer according to the activity characteristics and user behavior characteristics of the actual application scenario, and is not limited in this application. The number of user prize browsing times for each prize is the cumulative number of times the user refreshes the lottery page and the prize is exposed within the preset time range. The number of user prize clicks for each prize is the cumulative number of times the user clicks on the lottery page within the preset time range. The number of user prize usage times for each prize is the cumulative number of times the user uses the prize within the preset time range. By performing weighted average calculation on the number of user prize browsing times, the number of user prize clicks, and the number of user prize usage times, the user interest statistical coefficient within the preset time range corresponding to the current preset time node can be obtained by referring to the multi-dimensional behavior data of the user. For example, the number of times a user browses a prize is n1, the number of times a user clicks a prize is n2, and the number of times a user uses a prize is n3. The corresponding weights are w n1 、w n2 and w n3 , for example, w n1 =10,w n2 =30,w n3 =60, thus, the formula for calculating the user interest statistical coefficient data1 is as follows:

[0057]

[0058] Of course, the aforementioned weight settings are merely exemplary descriptions, and developers can make adaptive settings based on the degree of correlation between different user behaviors and user interest preferences in actual application scenarios, and this application does not limit this.

[0059] Step S302: Perform a weighted average calculation on the historical user interest statistical coefficient corresponding to the second preset statistical period and the user interest statistical coefficient to obtain the target user interest statistical coefficient.

[0060] Among them, the second preset statistical period is a plurality of historical statistical time periods corresponding to different statistical time intervals that are adapted to the target user interest statistical coefficient setting. For example, if the current preset time node is 15:00, the corresponding preset time range is 14:00 to 15:00, and the statistical time interval is set to 1 day, 7 days and 15 days, then the first preset statistical period is 14:00 to 15:00 15 days ago, 14:00 to 15:00 7 days ago and 14:00 to 15:00 15 days ago. If the historical user interest statistical coefficient corresponding to 14:00 to 15:00 recorded 15 days ago is b1, the historical user interest statistical coefficient corresponding to 14:00 to 15:00 7 days ago is b2, the historical user interest statistical coefficient corresponding to 14:00 to 15:00 1 day ago is b3, and the user interest statistical coefficient is b4, then the corresponding weights are w respectively. b1 、w b2 、w b3 and w b4 , for example, w b1 =10,w b2 =20,w b3 =30,w b4 =50, thus, the formula for calculating the target user interest statistical coefficient value2 is as follows:

[0061]

[0062] Of course, the aforementioned weight settings are only exemplary descriptions, and developers can make adaptive settings based on the data characteristics and impact size of different statistical periods in actual application scenarios, and this application does not limit this.

[0063] Step S303: upon receiving a user lottery request sent by the client, compare the target user interest statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine first coefficient increment information.

[0064] Step S304: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0065] Step S305: Determine a first target prize based on the target winning probabilities of each prize, and distribute the first target prize to the client.

[0066] As described above, by performing a weighted average calculation based on the historical user interest statistical coefficient corresponding to the second preset statistical period and the user interest statistical coefficient to obtain the target user interest statistical coefficient, the user interest preference situation can be evaluated with reasonable reference to the statistical calculation results of multiple periods to ensure the accuracy and stability of the statistical results. By comparing the target user interest statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the reference information for adjusting the winning probability of each prize can be accurately determined according to the changes in the user's interest preference situation, and the probability configuration of the prize can be effectively met to meet the user's interest preference needs.

[0067] Figure 4 A flow chart of a platform prize distribution method including a process of adjusting a target prize according to the prize inventory balance provided in an embodiment of the present application. Figure 4 As shown, the following steps are included:

[0068] Step S401: upon receiving a user lottery request sent by the client, compare the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0069] Step S402: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0070] Step S403: determine a first target prize based on the target winning probabilities of each prize, and query the inventory balance corresponding to the first target prize.

[0071] Among them, each prize is set with a corresponding basic inventory. As the platform prizes are distributed, the basic inventory of each prize will be lost to varying degrees. Therefore, by querying the inventory balance corresponding to the first target prize, it is possible to determine whether the first target prize has sufficient balance to support subsequent distribution operations.

[0072] Step S404: When the inventory balance is greater than the preset quantity threshold, distribute the first target prize to the client.

[0073] The preset quantity threshold may be zero or a set inventory warning line, which may be adaptively set by the developer according to the inventory configuration rules of the actual application scenario and the specific needs of the activity, and is not limited in this application. If the inventory balance is greater than the preset quantity threshold, it can be considered that the inventory balance of the first target prize is sufficient, and the first target prize can continue to be distributed to the client.

[0074] Step S405: When the inventory balance is less than or equal to the preset quantity threshold, the first target prize is replaced with the second target prize in the standby prize pool, and the second target prize is distributed to the client.

[0075] Among them, if the inventory balance is less than or equal to the preset quantity threshold, it can be regarded as insufficient inventory balance of the first target prize. By replacing the first target prize with the second target prize in the backup prize pool, the normal distribution of the prize is guaranteed, wherein the value of the second target prize is equivalent to the value of the first target prize.

[0076] As mentioned above, by querying the inventory balance corresponding to the first target prize, it can be determined whether the inventory status of the first target prize is sufficient and whether it can support the current distribution operation. By replacing the first target prize with the second target prize in the backup prize pool when the inventory balance is less than or equal to the preset quantity threshold, the prize distribution demand can be switched to other sufficient reserve backup prize pools in time to ensure the continuity of the activity and the smoothness of the user experience.

[0077] Figure 5 A flowchart of a platform prize distribution method including a process of adjusting the inventory balance of each prize provided in an embodiment of the present application. Figure 5 As shown, the following steps are included:

[0078] Step S501: When the inventory adjustment time node is reached, the platform statistical coefficients corresponding to the current adjustment time and the previous adjustment time are compared to determine the second coefficient increment information.

[0079] Among them, the inventory adjustment time node can be a pre-set periodic time point for adjusting the prize inventory. Optionally, when the inventory adjustment time node is reached, the early warning mechanism can be triggered synchronously to notify the activity management personnel whether the current prize inventory status is fully consumed or overly redundant. In this embodiment, when the inventory adjustment time node is reached, the inventory adjustment mechanism will be triggered. Among them, the previous adjustment time is the system time of the last adjustment of the prize inventory. The platform statistical coefficient may include platform prize utilization rate, platform interest statistical coefficient, etc. Among them, the platform prize utilization rate is used to characterize the statistics of a prize actually used by all users on the platform within a specific time range, and can be determined by the ratio of the number of prizes issued by the platform within a specific time range to the number of prizes used by all users on the platform. The platform interest statistical coefficient is used to characterize the interest of all users in the platform for a certain prize within a specific time range. It can be determined by weighted fusion based on the browsing prize data of all users in the platform, the click prize data of all users in the platform, and the use prize data of all users in the platform. For example, the browsing prize data and the use prize data are weighted averaged to obtain the platform interest statistical coefficient. For example, the browsing prize data, the click prize data, and the use prize data are weighted averaged to obtain the platform interest statistical coefficient. Specifically, the developer can adaptively select the generation method of the platform statistical coefficient according to the statistical dimension setting of the actual application scenario and the platform behavior characteristics, which is not limited in this application. In addition, in this embodiment, the determination time node of the platform statistical coefficient can be periodic, for example, every half hour, every hour, etc. In one embodiment, taking every hour as an example, the platform statistical coefficient can be determined based on the platform-related data of the hour after accumulating one hour of platform-related data. Optionally, the platform statistical coefficient determined by the hour and the platform statistical coefficient determined by the same time period of the historical statistical cycle can also be weighted averaged to obtain the final platform statistical coefficient. For example, the final platform statistical coefficient can be obtained by weighted fusion based on the platform statistical coefficient calculated in the current time period, the platform statistical coefficient calculated in the same time period one day ago, the platform statistical coefficient calculated in the same time period seven days ago, and the platform statistical coefficient calculated in the same time period 30 days ago.

[0080] Optionally, the second coefficient increment information can be determined by comparing and comparing one or more of the platform statistical coefficients. In one embodiment, the second coefficient increment information can be determined by comparing and comparing one of the platform prize usage rate, platform interest statistical coefficient, etc. For example, the platform prize usage rate corresponding to each prize at the current adjustment moment and the previous adjustment moment can be compared to determine the second coefficient increment information. For another example, the platform interest statistical coefficient corresponding to each prize at the current adjustment moment and the previous adjustment moment can be compared to determine the second coefficient increment information. In one embodiment, the second coefficient increment information can be determined by comparing and comparing multiple types of platform prize usage rate, platform interest statistical coefficient, etc., by comparing the platform prize usage rate, platform interest statistical coefficient, etc. corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine multiple coefficient increment information, and weighted fusion of multiple coefficient increment information to obtain the second coefficient increment information. Therefore, the platform statistical coefficients corresponding to each prize at the current adjustment moment and the previous adjustment moment may change, and the second coefficient increment information can be determined by comparing the two, and the second coefficient increment information includes the increment information of the platform statistical coefficients of each prize, for example, the growth rate, the decline rate, the growth ratio, the decline ratio, etc. For example, the platform statistical coefficient is the platform prize utilization rate, the platform prize utilization rate of prize A at the current adjustment moment is p′1, and the platform prize utilization rate of prize A at the previous adjustment moment is p′2, p′1 is greater than p′2, then the growth rate of the platform prize utilization rate is p′1-p′2, and the growth ratio of the platform prize utilization rate at the current adjustment moment relative to the previous adjustment moment is (p′1-p′2) / p′2, then the second coefficient increment information can be the growth rate p′1-p′2, or the growth ratio (p′1-p′2) / p′2.

[0081] Step S502: Adjust the inventory balance of each prize according to the second coefficient increment information.

[0082] Among them, in one embodiment, the second coefficient increment information can be the growth rate or decline rate of the platform statistical coefficient of each prize. By querying the preset mapping relationship, the inventory adjustment rate corresponding to the growth rate or decline rate can be obtained, and the inventory balance of each prize is adjusted according to the inventory adjustment rate. For example, the inventory balance corresponding to prize A at the previous adjustment moment is y1, the growth rate of prize A in the second coefficient increment information is p′1-p′2, and the inventory adjustment rate corresponding to the growth rate is m′1, then its inventory balance should be adjusted to y1+m′1. In one embodiment, the second coefficient increment information can be the growth ratio or decline ratio of the user statistical coefficient of each prize, and the inventory balance of each prize can be adjusted in the same proportion directly according to the growth ratio or decline ratio. For example, the inventory balance corresponding to prize A at the previous adjustment moment is y1, the growth rate of prize A in the second coefficient increment information is p′1-p′2, and the growth ratio is (p′1-p′2) / p′2, then its inventory balance should be adjusted to y1×(p′1-p′2) / p′2. Since the second coefficient increment information can represent the changes in the actual usage or interest preferences of all users in the platform, the inventory balance of each prize is equivalent to the adjustment to adapt to the aforementioned changes, and the inventory can be reasonably adjusted dynamically.

[0083] Step S503: upon receiving a user lottery request sent by the client, compare the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0084] Step S504: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0085] Step S505: determine a first target prize based on the target winning probabilities of each prize, and query the inventory balance corresponding to the first target prize.

[0086] Step S506: When the inventory balance is greater than the preset quantity threshold, distribute the first target prize to the client.

[0087] Step S507: When the inventory balance is less than or equal to the preset quantity threshold, the first target prize is replaced with the second target prize in the standby prize pool, and the second target prize is distributed to the client.

[0088] As mentioned above, by comparing the platform statistical coefficients corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine the second coefficient incremental information, the overall platform data corresponding to each prize can be effectively analyzed, and the actual demand changes for each prize can be evaluated, so as to provide reliable reference information for the subsequent adjustment of the inventory balance of each prize; by adjusting the inventory balance of each prize according to the second coefficient incremental information, the inventory balance of each prize can be dynamically adjusted, thereby realizing dynamic optimization and intelligent balance of inventory.

[0089] Figure 6 A flow chart of a platform prize distribution method including a process of determining the target platform prize utilization rate provided in an embodiment of the present application. Figure 6 As shown, the following steps are included:

[0090] Step S601: When a preset time node is reached, the number of platform prizes used within the preset time range is divided by the number of platform prizes issued to obtain a platform prize utilization rate.

[0091] Among them, the preset time node can be a periodic time point for calculating the target platform prize usage rate, for example, every half hour, every hour, etc. Correspondingly, the preset time range can be a periodic time interval. Taking every hour as an example, the preset time range is the time range corresponding to the hour before the preset time node. For example, the preset time node is 16:00, and the corresponding preset time range is 15:00 to 16:00. The setting of the specific preset time node and the preset time range can be adaptively adjusted by the developer according to the activity characteristics and user behavior characteristics of the actual application scenario, and is not limited in this application. The number of platform prizes used for each prize is the cumulative number of all users on the platform using the prize within the preset time range. The number of platform prizes issued for each prize is the cumulative number of the prize issued by the platform to all users within the preset time range. Therefore, dividing the number of platform prizes used by the number of platform prizes issued can obtain the platform prize usage rate within the preset time range corresponding to the current preset time node.

[0092] Step S602: Perform a weighted average calculation on the historical platform prize usage rate corresponding to the third preset statistical period and the platform prize usage rate to obtain a target platform prize usage rate.

[0093] Among them, the third preset statistical period is a plurality of historical statistical time periods corresponding to different statistical time intervals adapted to the target platform prize usage rate setting. For example, if the current preset time node is 16:00, the corresponding preset time range is 15:00 to 16:00, and the statistical time interval is set to 7 days and 15 days, then the third preset statistical period is 15:00 to 16:00 7 days ago and 15:00 to 16:00 15 days ago. If the historical platform prize usage rate corresponding to 15:00 to 16:00 recorded 15 days ago is c1, the historical platform prize usage rate corresponding to 15:00 to 16:00 7 days ago is c2, and the platform prize usage rate is c3, then the corresponding weights are w respectively. c1 、w c2 and w c3 , for example, w c1 =70,w c2 =20,w c3 =10, therefore, the formula for calculating the target platform prize utilization rate value3 is as follows:

[0094]

[0095] Of course, the aforementioned weight settings are only exemplary descriptions, and developers can make adaptive settings based on the data characteristics and impact size of different statistical periods in actual application scenarios, and this application does not limit this.

[0096] Step S603: When the inventory adjustment time node is reached, the target platform prize usage rate corresponding to each prize at the current adjustment time and the previous adjustment time is compared to determine the second coefficient increment information.

[0097] Step S604: adjust the inventory balance of each prize according to the second coefficient increment information.

[0098] Step S605: When receiving a user lottery request sent by the client, compare the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment to determine the first coefficient increment information, and the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0099] Step S606: According to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table.

[0100] Step S607: determine the first target prize based on the target winning probabilities of the various prizes, and query the inventory balance corresponding to the first target prize.

[0101] Step S608: When the inventory balance is greater than the preset quantity threshold, distribute the first target prize to the client.

[0102] Step S609: When the inventory balance is less than or equal to the preset quantity threshold, the first target prize is replaced with the second target prize in the standby prize pool, and the second target prize is distributed to the client.

[0103] As mentioned above, by calculating the weighted average of the historical platform prize usage rate and the platform prize usage rate corresponding to the third preset statistical period recorded, the target platform prize usage rate can be obtained. The statistical calculation results of multiple periods can be reasonably referred to for evaluating the platform prize usage, reducing the impact of peak data that may appear in a single period on the overall value, and improving the accuracy and stability of the statistical results. By comparing the target platform prize usage rate corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine the first coefficient increment information, the reference information for adjusting the inventory balance of each prize can be accurately determined based on the changes in the prize usage of all users on the platform, and the prize inventory can be adjusted effectively in accordance with the actual usage needs of the platform users as a whole.

[0104] Figure 7 A flowchart of a platform prize distribution method including a process of determining a target platform interest statistical coefficient is provided in an embodiment of the present application. Figure 7 As shown, the following steps are included:

[0105] Step S701: When a preset time node is reached, the number of platform prize browsing times, the number of platform prize clicks and the number of platform prize usage times within the preset time range are weighted averaged to obtain a platform interest statistical coefficient.

[0106] Among them, the preset time node can be a periodic time point for calculating the statistical coefficient of interest of the target platform, for example, every half hour, every hour, etc. Correspondingly, the preset time range can be a periodic time interval. Taking every hour as an example, the preset time range is the time range corresponding to the hour before the preset time node. For example, the preset time node is 17:00, and the corresponding preset time range is 16:00 to 17:00. The setting of the specific preset time node and the preset time range can be adaptively adjusted by the developer according to the activity characteristics and platform behavior characteristics of the actual application scenario, and is not limited in this application. The number of platform prize views for each prize is the cumulative number of times all users on the platform refresh the lottery page within the preset time range and the prize is exposed. The number of platform prize clicks for each prize is the cumulative number of times all users on the platform click on the lottery page for the prize within the preset time range. The number of platform prize uses for each prize is the cumulative number of times all users on the platform use the prize within the preset time range. By calculating the weighted average of the number of times the platform prize is viewed, the number of times the platform prize is clicked, and the number of times the platform prize is used, the platform interest statistical coefficient within the preset time range corresponding to the current preset time node can be obtained by referring to the multi-dimensional behavior data of the platform users as a whole. For example, the number of times the platform prize is viewed is n′1, the number of times the platform prize is clicked is n′2, and the number of times the platform prize is used is n′3, and the corresponding weights are w′ n1 , w′ n2 and w′ n3 , for example, w′ n1 =20, w′ n2 =30, w′ n3 =50, thus, the formula for calculating the platform interest statistical coefficient data2 is as follows:

[0107]

[0108] Of course, the aforementioned weight settings are merely exemplary descriptions, and developers can make adaptive settings based on the degree of correlation between different user behaviors and user interest preferences in actual application scenarios, and this application does not limit this.

[0109] Step S702: Perform a weighted average calculation on the historical platform interest statistical coefficient corresponding to the fourth preset statistical period and the platform interest statistical coefficient to obtain the target platform interest statistical coefficient.

[0110] Among them, the fourth preset statistical period is a plurality of historical statistical time periods corresponding to different statistical time intervals that are adapted to the target platform interest statistical coefficient setting. For example, if the current preset time node is 18:00, the corresponding preset time range is 17:00 to 18:00, and the statistical time intervals are set to 1 day, 7 days, and 30 days, then the fourth preset statistical period is 17:00 to 18:00 30 days ago, 17:00 to 18:00 7 days ago, and 17:00 to 18:00 1 day ago. If the historical platform interest statistical coefficient corresponding to 17:00 to 18:00 recorded 30 days ago is d1, the historical platform interest statistical coefficient corresponding to 17:00 to 18:00 7 days ago is d2, the historical platform interest statistical coefficient corresponding to 17:00 to 18:00 1 day ago is d3, and the platform interest statistical coefficient is d4, then the corresponding weights are w respectively. d1 、w d2 、w d3 and w d4 , for example, w d1 =50,w d2 =30,w d3 =20,w d4 =10, thus, the formula for calculating the target platform interest statistical coefficient value4 is as follows:

[0111]

[0112] Of course, the aforementioned weight settings are only exemplary descriptions, and developers can make adaptive settings based on the data characteristics and impact size of different statistical periods in actual application scenarios, and this application does not limit this.

[0113] Step S703: When the inventory adjustment time node is reached, the target platform interest statistical coefficients corresponding to the current adjustment moment and the previous adjustment moment are compared to determine the second coefficient increment information.

[0114] Step S704: adjust the inventory balance of each prize according to the second coefficient increment information.

[0115] Step S705: When a user lottery request is received from the client, the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0116] Step S706: According to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table.

[0117] Step S707: determine the first target prize based on the target winning probabilities of the various prizes, and query the inventory balance corresponding to the first target prize.

[0118] Step S708: When the inventory balance is greater than the preset quantity threshold, distribute the first target prize to the client.

[0119] Step S709: When the inventory balance is less than or equal to the preset quantity threshold, the first target prize is replaced with the second target prize in the standby prize pool, and the second target prize is distributed to the client.

[0120] As described above, by calculating the weighted average of the historical platform interest statistical coefficient and the platform interest statistical coefficient corresponding to the fourth preset statistical period recorded, the target platform interest statistical coefficient can be reasonably referenced to the statistical calculation results of multiple periods to evaluate the interest preferences of the platform's overall users, thereby improving the accuracy and stability of the statistical results. By comparing the target platform interest statistical coefficients corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine the second coefficient increment information, the reference information for adjusting the inventory balance of each prize can be accurately determined according to the changes in the interest preferences of the platform's overall users, effectively meeting the user's interest preference requirements to adjust the inventory of prizes.

[0121] Figure 8 A flowchart of a platform prize distribution method including a process of configuring prize probability according to the draw interval length provided in an embodiment of the present application. Figure 8 As shown, the following steps are included:

[0122] Step S801: upon receiving a user lottery request sent by a client, calculate the interval between the current lottery time and the previous lottery time.

[0123] Among them, since the user's lottery drawing behavior may be multiple draws in a short period of time, or may be drawn again after a long interval, it is necessary to determine whether the user probability table needs to be adjusted or reset according to different lottery intervals.

[0124] Step S802: when the interval time is less than the lower limit threshold of the set duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the user probability table corresponding to the previous lottery moment.

[0125] Among them, if the interval time is less than the lower limit threshold of the set time threshold interval, for example, the lower limit threshold is 24 hours, it can be regarded as the user triggering the lottery multiple times in a short period of time. If the user probability table is adjusted for each lottery, it will take up more computing resources and may even cause delays. Therefore, you can choose to continue to use the user probability table corresponding to the previous lottery time to configure the target winning probability of each prize.

[0126] Step S803: When the interval time is greater than the upper threshold of the duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the set basic probability table.

[0127] Among them, if the interval time is greater than the upper threshold of the time threshold interval, for example, the upper threshold is 48 hours, it can be regarded as the user drawing the lottery again after a long interval. The user probability table corresponding to the previous lottery moment may not be able to reasonably configure the target winning probability of each prize due to its early generation time, and the reference degree is low. Therefore, the user probability table can be reset and the basic probability table can be selected to configure the target winning probability of each prize.

[0128] Step S804: When the interval duration is within the duration threshold range, the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information.

[0129] Step S805: adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configuring the target winning probability of each prize in the current prize pool based on the target user probability table.

[0130] Step S806: Determine a first target prize based on the target winning probabilities of the various prizes, and distribute the first target prize to the client.

[0131] As mentioned above, by calculating the interval time between the current lottery time and the previous lottery time, the interval time can be used to judge the validity of the user probability table. When the interval time is less than the lower limit threshold of the time threshold interval, the user probability table corresponding to the previous lottery time is used to avoid frequent adjustments to the user probability table in a short period of time, which affects the user lottery experience. When the interval time is greater than the upper limit threshold of the time threshold interval, the set basic probability table is used to replace the user probability table generated too early to ensure data reliability.

[0132] Fig. 9This is a structural block diagram of a platform prize distribution device provided in an embodiment of the present application. The device is configured to execute the platform prize distribution method provided in the above embodiment and has the corresponding functional modules and beneficial effects of the execution method. Fig. 9 As shown, the device comprises:

[0133] The coefficient increment determination module 101 is configured to, upon receiving a user lottery request sent by a client, compare the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information;

[0134] The winning probability adjustment module 102 is configured to adjust the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configure the target winning probability of each prize in the current prize pool based on the target user probability table;

[0135] The target prize distribution module 103 is configured to determine a first target prize based on the target winning probability of each prize, and distribute the first target prize to the client.

[0136] In the above, upon receiving a user lottery request sent by the client, the first coefficient increment information is determined by comparing the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment, and the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; according to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; based on the target winning probability of each prize, the first target prize is determined, and the first target prize is distributed to the client. In the above scheme, by comparing the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the personal user data corresponding to each prize can be effectively analyzed, and the user's preference for different prizes can be predicted, providing reliable reference information for the subsequent adjustment of the user's winning probability; by adjusting the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain the target user probability table, it is possible to dynamically adjust the probability configuration of the prize, generate a personalized prize distribution strategy for each user, and configure the target winning probability of each prize in the current prize pool based on the target user probability table, and distribute the first target prize determined based on the target winning probability of each prize to the client, so that the most matching prize can be reasonably distributed to the user, thereby improving the accuracy and personalization level of prize distribution, and realizing the maximum utilization of the prize value, as well as a significant improvement in user satisfaction and participation.

[0137] In a possible embodiment, it further includes a user prize usage rate determination module configured to:

[0138] When the preset time node is reached, the number of user prizes used within the preset time range is divided by the number of user prizes issued to obtain the user prize utilization rate;

[0139] The target user prize utilization rate is obtained by performing a weighted average calculation of the historical user prize utilization rate corresponding to the first preset statistical period and the user prize utilization rate;

[0140] Correspondingly, the coefficient increment determination module 101 is further configured as follows:

[0141] The first coefficient increment information is determined by comparing the target user prize usage rates corresponding to the prizes at the current lottery moment and the previous lottery moment.

[0142] In a possible embodiment, the user statistical coefficient includes a target user interest statistical coefficient, and also includes a user interest statistical coefficient determination module, which is configured as follows:

[0143] When the preset time node is reached, the user interest statistical coefficient is obtained by weighted average calculation of the number of user prize browsing, user prize click and user prize use within the preset time range;

[0144] The target user interest statistical coefficient is obtained by performing weighted average calculation on the historical user interest statistical coefficient corresponding to the second preset statistical period and the user interest statistical coefficient;

[0145] Correspondingly, the coefficient increment determination module 101 is further configured as follows:

[0146] The target user interest statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information.

[0147] In a possible embodiment, it further includes a second target prize distribution module configured to:

[0148] Query the inventory balance corresponding to the first target prize;

[0149] When the inventory balance is less than or equal to the preset quantity threshold, the first target prize is replaced with the second target prize in the backup prize pool, and the second target prize is distributed to the client;

[0150] Correspondingly, the target prize distribution module 103 is further configured as follows:

[0151] When the inventory balance is greater than a preset quantity threshold, the first target prize is distributed to the client.

[0152] In a possible embodiment, it further includes an inventory balance adjustment module configured to:

[0153] When the inventory adjustment time node is reached, the platform statistical coefficients corresponding to each prize at the current adjustment time and the previous adjustment time are compared to determine the second coefficient increment information;

[0154] The inventory balance of each prize is adjusted according to the second coefficient increment information.

[0155] In a possible embodiment, the platform statistical coefficient includes a target platform prize utilization rate, and also includes a platform prize utilization rate determination module, which is configured as follows:

[0156] When the preset time node is reached, the number of platform prizes used within the preset time range is divided by the number of platform prizes issued to obtain the platform prize utilization rate;

[0157] The target platform prize utilization rate is obtained by performing a weighted average calculation of the historical platform prize utilization rate corresponding to the third preset statistical period and the platform prize utilization rate;

[0158] Correspondingly, the inventory balance adjustment module is also configured as follows:

[0159] The target platform prize usage rates corresponding to the prizes at the current adjustment moment and the previous adjustment moment are compared to determine the second coefficient increment information.

[0160] In a possible embodiment, the platform statistical coefficient includes a target platform interest statistical coefficient, and also includes a platform interest statistical coefficient determination module, which is configured as follows:

[0161] When the preset time node is reached, the platform interest statistical coefficient is obtained by weighted average calculation of the number of platform prize browsing times, platform prize click times and platform prize usage times within the preset time range;

[0162] The target platform interest statistical coefficient is obtained by performing a weighted average calculation on the historical platform interest statistical coefficient corresponding to the fourth preset statistical period and the platform interest statistical coefficient;

[0163] Correspondingly, the inventory balance adjustment module is also configured as follows:

[0164] The target platform interest statistical coefficients corresponding to the respective prizes at the current adjustment moment and the previous adjustment moment are compared to determine the second coefficient increment information.

[0165] In a possible embodiment, a second winning probability adjustment module is further included, configured as follows:

[0166] Calculate the interval between the current lottery time and the previous lottery time;

[0167] When the interval time is less than the lower limit threshold of the set duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the user probability table corresponding to the previous lottery moment;

[0168] When the interval time is greater than the upper threshold of the duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the set basic probability table;

[0169] Correspondingly, the winning probability adjustment module 102 is further configured as follows:

[0170] When the interval duration is within the duration threshold range, the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information.

[0171] Fig.10 A schematic diagram of the structure of a platform prize distribution device provided in an embodiment of the present application, such as Fig.10 As shown, the device includes a processor 201, a memory 202, an input device 203 and an output device 204; the number of processors 201 in the device can be one or more. Fig.10 A processor 201 is taken as an example; the processor 201, memory 202, input device 203 and output device 204 in the device can be connected by a bus or other means. Fig.10 In the example, the connection via bus is taken. The memory 202, as a computer-readable storage medium, can be configured to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the platform prize distribution method in the embodiment of the present application. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 202, that is, implements the above-mentioned platform prize distribution method. The input device 203 can be configured to receive input digital or character information, and generate key signal input related to user settings and function control of the device. The output device 204 may include a display device such as a display screen.

[0172] An embodiment of the present application also provides a non-volatile storage medium containing computer executable instructions, which, when executed by a computer processor, is configured to execute a platform prize distribution method described in the above embodiment, which includes: when a user lottery request sent by a client is received, the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment are compared to determine first coefficient increment information, and the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; according to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; based on the target user probability table, a first target prize is determined based on the target winning probability of each prize, and the first target prize is distributed to the client.

[0173] It is worth noting that in the embodiment of the above-mentioned platform prize distribution device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not configured to limit the protection scope of the embodiments of the present application.

[0174] In some possible implementations, various aspects of the method provided in this application may also be implemented in the form of a program product, which includes a program code. When the program product is run on a computer device, the program code is configured to enable the computer device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification. For example, the computer device may execute the platform prize distribution method described in the embodiment of this application. The program product may be implemented in any combination of one or more readable media.

Claims

1. A platform prize distribution method, characterized in that: include: When receiving a user lottery request sent by the client, comparing the user statistical coefficients corresponding to each prize at the current lottery moment and the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; According to the first coefficient increment information, the winning probability of each prize in the user probability table corresponding to the previous lottery moment is adjusted to obtain a target user probability table, and the target winning probability of each prize in the current prize pool is configured based on the target user probability table; A first target prize is determined based on the target winning probabilities of the respective prizes, and the first target prize is distributed to the client.

2. The platform prize distribution method according to claim 1, characterized in that: The user statistical coefficient includes the target user prize utilization rate. Before comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, it also includes: When the preset time node is reached, the number of user prizes used within the preset time range is divided by the number of user prizes issued to obtain the user prize utilization rate; The target user prize utilization rate is obtained by performing a weighted average calculation of the historical user prize utilization rate corresponding to the first preset statistical period and the user prize utilization rate; Accordingly, the step of comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information includes: The first coefficient increment information is determined by comparing the target user prize usage rates corresponding to the prizes at the current lottery moment and the previous lottery moment.

3. The platform prize distribution method according to claim 1, characterized in that: The user statistical coefficient includes a target user interest statistical coefficient. Before comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the method further includes: When the preset time node is reached, the user interest statistical coefficient is obtained by weighted average calculation of the number of user prize browsing, user prize click and user prize use within the preset time range; The target user interest statistical coefficient is obtained by performing weighted average calculation on the historical user interest statistical coefficient corresponding to the second preset statistical period and the user interest statistical coefficient; Accordingly, the step of comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information includes: The target user interest statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information.

4. The platform prize distribution method according to claim 1, characterized in that: Before distributing the first target prize to the client, the method further includes: Querying the inventory balance corresponding to the first target prize; When the inventory balance is less than or equal to a preset quantity threshold, replacing the first target prize with a second target prize in a backup prize pool, and distributing the second target prize to the client; Correspondingly, distributing the first target prize to the client includes: When the inventory balance is greater than a preset quantity threshold, the first target prize is distributed to the client.

5. The platform prize distribution method according to claim 4, characterized in that: Before querying the inventory balance corresponding to the first target prize, the method further includes: When the inventory adjustment time node is reached, the platform statistical coefficients corresponding to each prize at the current adjustment time and the previous adjustment time are compared to determine the second coefficient increment information; The inventory balance of each prize is adjusted according to the second coefficient increment information.

6. The platform prize distribution method according to claim 5, characterized in that: The platform statistical coefficient includes the target platform prize utilization rate. Before comparing the platform statistical coefficients corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine the second coefficient increment information, it also includes: When the preset time node is reached, the number of platform prizes used within the preset time range is divided by the number of platform prizes issued to obtain the platform prize utilization rate; The target platform prize utilization rate is obtained by performing a weighted average calculation on the historical platform prize utilization rate corresponding to the third preset statistical period and the platform prize utilization rate; Accordingly, the step of comparing the platform statistical coefficients corresponding to the respective prizes at the current adjustment moment and the previous adjustment moment to determine the second coefficient increment information includes: The target platform prize usage rates corresponding to the prizes at the current adjustment moment and the previous adjustment moment are compared to determine the second coefficient increment information.

7. The platform prize distribution method according to claim 5, characterized in that: The platform statistical coefficient includes a target platform interest statistical coefficient. Before comparing the platform statistical coefficients corresponding to each prize at the current adjustment moment and the previous adjustment moment to determine the second coefficient increment information, it also includes: When the preset time node is reached, the platform interest statistical coefficient is obtained by weighted average calculation of the number of platform prize browsing times, platform prize click times and platform prize usage times within the preset time range; The target platform interest statistical coefficient is obtained by performing a weighted average calculation on the historical platform interest statistical coefficient corresponding to the fourth preset statistical period and the platform interest statistical coefficient; Accordingly, the step of comparing the platform statistical coefficients corresponding to the respective prizes at the current adjustment moment and the previous adjustment moment to determine the second coefficient increment information includes: The target platform interest statistical coefficients corresponding to the respective prizes at the current adjustment moment and the previous adjustment moment are compared to determine the second coefficient increment information.

8. The platform prize distribution method according to claim 1, characterized in that: Before comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information, the method further includes: Calculate the interval between the current lottery time and the previous lottery time; When the interval time is less than the lower limit threshold of the set duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the user probability table corresponding to the previous lottery moment; When the interval time is greater than the upper threshold of the duration threshold interval, the target winning probability of each prize in the current prize pool is configured based on the set basic probability table; Accordingly, the step of comparing the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment to determine the first coefficient increment information includes: When the interval duration is within the duration threshold range, the user statistical coefficients corresponding to the prizes at the current lottery moment and the previous lottery moment are compared to determine the first coefficient increment information.

9. A platform prize distribution device, characterized in that: include: A coefficient increment determination module is configured to, upon receiving a user lottery request sent by a client, compare the user statistical coefficients corresponding to each prize at the current lottery moment with those at the previous lottery moment to determine first coefficient increment information, wherein the user statistical coefficients are generated based on the number of user prizes issued for each prize and the corresponding user behavior information; a winning probability adjustment module, configured to adjust the winning probability of each prize in the user probability table corresponding to the previous lottery moment according to the first coefficient increment information to obtain a target user probability table, and configure the target winning probability of each prize in the current prize pool based on the target user probability table; The target prize distribution module is configured to determine a first target prize based on the target winning probabilities of the respective prizes, and distribute the first target prize to the client.

10. A platform prize distribution device, comprising: one or more processors; A storage device configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the platform prize distribution method described in any one of claims 1-8.

11. A non-volatile storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the platform prize distribution method according to any one of claims 1 to 8 when executed by a computer processor.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the platform prize distribution method according to any one of claims 1 to 8 is implemented.

Images