Method and terminal for predicting probability change of a probability event within software

Abstract

The application discloses a kind of probability change prediction method and terminal of probability event in software, according to the historical execution data of target probability event of target software, target probability event appears target result's probability promotion condition is analyzed to obtain;Real-time acquisition target user in target software's first user data;Whether first user data is in line with probability promotion condition is judged, if yes, then feedback probability promotion to target user, otherwise feedback probability is not promoted and corresponding probability promotion condition's execution suggestion to target user.The application helps target user to determine or find suitable opportunity to execute target probability event, with the difference between user data, the user of executing target probability event is shunted, relieve server stress, and since probability promotion prompt is given, the participation experience of user can also be guaranteed.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and terminal for predicting probability changes in probabilistic events within software. Background Technology

[0002] Many existing software programs include probability-based events, the most common of which are lottery events. In games, the random rules for some lottery events or random item drops are usually pre-set by the game developers and hidden in the game's background logic, so players cannot know the exact probability of winning or dropping items in the game at any given time.

[0003] During the design process, on the one hand, because software cannot generate truly probabilistic events, and on the other hand, to ensure a better player experience, game developers often use player levels, number of draws, and even player spending data as input data for random rules. They then use a series of random formulas to determine the results of draws or random item drops. Without knowing these underlying rules, players can easily perform numerous ineffective actions within the game, thus wasting game resources that would otherwise be used to participate in draws or random item drops.

[0004] In particular, popular software or games already have a large user base. When hosting online random events, a large number of users will simultaneously access the event page and send requests to the server. When the number of requests exceeds the server's processing capacity and load limit, the server will become overloaded, causing the event page to become unresponsive and crash. At the same time, many players may also experience a decreased user experience due to repeated unsuccessful attempts to participate. Summary of the Invention

[0005] The technical problem to be solved by this invention is to provide a method and terminal for predicting the probability changes of probabilistic events within software, so as to help players participate in probabilistic events more rationally and reasonably, reduce server pressure, and ensure the user's participation experience.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for predicting probability changes of probabilistic events within software, comprising the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

[0007] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is as follows: A software-defined terminal for predicting the probability change of probabilistic events includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor runs the computer program, it performs the following steps:

[0008] S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

[0009] The beneficial effects of this invention are as follows: It provides a method and terminal for predicting the probability changes of probabilistic events within software. By analyzing the historical execution data of target probabilistic events in the target software, it infers that the random rules of the target probabilistic events may reference a certain data item. Changes in this data item can increase the probability of the target result, i.e., the probability increase condition. Then, it determines whether the target user's first user data meets the probability increase condition. If it does, it means that the user is more likely to obtain the target result by executing the target probabilistic event. Even if it does not meet the condition, it can still provide execution suggestions. In this way, it helps the target user to identify or find a suitable opportunity to execute the target probabilistic event. By leveraging the differences between user data, it diverts users executing the target probabilistic event, reducing server pressure. At the same time, since a probability increase prompt is provided, it also ensures the user's participation experience. Attached Figure Description

[0010] Figure 1 This is a schematic diagram illustrating the steps of a method for predicting probability changes in probabilistic events within software according to the present invention. Figure 2 This is a system block diagram of a software-based probability event probability change prediction terminal according to the present invention.

[0011] Label Explanation: 1. A software-defined terminal for predicting the probability changes of probabilistic events; 2. A memory; 3. A processor. Detailed Implementation

[0012] To explain in detail the technical content, objectives, and effects of the present invention, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0013] Please refer to Figure 1 A method for predicting probability changes of probabilistic events within software, comprising the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

[0014] As can be seen from the above description, the beneficial effects of the present invention are as follows: by analyzing the historical execution data of the target probability event of the target software, it is inferred that the random rules of the target probability event may reference a certain data as a reference, and the change of this data can cause an increase in the probability of the target result, i.e., the probability increase condition; then it is determined whether the target user's first user data meets the probability increase condition. If it does, it means that the user is more likely to obtain the target result by executing the target probability event. Even if it does not meet the condition, an execution suggestion can still be given. In this way, the target user can identify or find a suitable opportunity to execute the target probability event. By using the differences between user data, users executing the target probability event are diverted, reducing server pressure. At the same time, since a probability increase prompt is given, the user's participation experience can also be guaranteed.

[0015] Further, step 1 includes: S11. Select the first set of all users who obtained the target result from the historical execution data; S12. Compare the similarities of the second user data of all users in the first user set before executing the target probability event, and determine the probability enhancement condition based on the comparison results.

[0016] As can be seen from the above description, in the historical execution data of the target probability event, the first set of users is determined with the premise of obtaining the target result. Then, by analyzing the commonalities of the second user data that each user had before executing the target probability event, it is helpful to find common factors that are favorable to the users in obtaining the target result, thereby improving the reliability of the probability enhancement conditions.

[0017] Furthermore, step 12 is followed by: S13. Select the second set of all users in the historical execution data who meet the probability enhancement condition; S14. Based on the proportion of users in the second user set who obtained the target result, obtain the expected probability corresponding to the probability enhancement condition; In step 3, the feedback probability is increased to the target user, who is then replaced with: The expected probability is fed back to the user.

[0018] As can be seen from the above description, when determining the expected probability after achieving the probability enhancement condition, the probability enhancement condition is used to reverse the calculation. The probability under this probability enhancement condition is accurately evaluated based on the overall execution results of all users who meet these conditions, providing a reference for users.

[0019] Furthermore, step 1 also includes: In the historical execution data, select all execution records in which the target probability event yields the target result, and determine the historical running data of the target software corresponding to all the execution records; The probability enhancement conditions are determined based on historical operating data; The first user data includes the running data of the target software obtained by the target user.

[0020] As described above, by starting with the historical operating data of the target software, we can explore situations where public data such as game running time and number of online users affect the probability of events. Based on the historical operating data, we can determine the conditions for increasing the probability. The first user data obtained subsequently includes the operating data of the target software obtained by the target user, thereby determining whether the current probability has been increased.

[0021] Furthermore, step 3 is followed by: S4. Obtain the latest execution record of the target probability event, and feed back all the latest execution records and the probability enhancement conditions to the software developer of the target software.

[0022] As described above, after introducing probability boosting conditions, the latest execution record of the target probability event is obtained, and all the latest execution records and probability boosting conditions are fed back to the software developer of the target software so that the software developer can judge whether the current probability boosting mechanism is set up reasonably and whether it needs to be adjusted.

[0023] Please refer to Figure 2 A software-defined terminal 1 for predicting the probability change of probabilistic events includes a memory 2, a processor 3, and a computer program stored in the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, it performs the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

[0024] As can be seen from the above description, the beneficial effects of the present invention are as follows: by analyzing the historical execution data of the target probability event of the target software, it is inferred that the random rules of the target probability event may reference a certain data as a reference, and the change of this data can cause an increase in the probability of the target result, i.e., the probability increase condition; then it is determined whether the target user's first user data meets the probability increase condition. If it does, it means that the user is more likely to obtain the target result by executing the target probability event. Even if it does not meet the condition, an execution suggestion can still be given. In this way, the target user can identify or find a suitable opportunity to execute the target probability event. By using the differences between user data, users executing the target probability event are diverted, reducing server pressure. At the same time, since a probability increase prompt is given, the user's participation experience can also be guaranteed.

[0025] Further, step 1 includes: S11. Select the first set of all users who obtained the target result from the historical execution data; S12. Compare the similarities of the second user data of all users in the first user set before executing the target probability event, and determine the probability enhancement condition based on the comparison results.

[0026] As can be seen from the above description, in the historical execution data of the target probability event, the first set of users is determined with the premise of obtaining the target result. Then, by analyzing the commonalities of the second user data that each user had before executing the target probability event, it is helpful to find common factors that are favorable to the users in obtaining the target result, thereby improving the reliability of the probability enhancement conditions.

[0027] Furthermore, step 12 is followed by: S13. Select the second set of all users in the historical execution data who meet the probability enhancement condition; S14. Based on the proportion of users in the second user set who obtained the target result, obtain the expected probability corresponding to the probability enhancement condition; In step 3, the feedback probability is increased to the target user, who is then replaced with: The expected probability is fed back to the user.

[0028] As can be seen from the above description, when determining the expected probability after achieving the probability enhancement condition, the probability enhancement condition is used to reverse the calculation. The probability under this probability enhancement condition is accurately evaluated based on the overall execution results of all users who meet these conditions, providing a reference for users.

[0029] Furthermore, step 1 also includes: In the historical execution data, select all execution records in which the target probability event yields the target result, and determine the historical running data of the target software corresponding to all the execution records; The probability enhancement conditions are determined based on historical operating data; The first user data includes the running data of the target software obtained by the target user.

[0030] As described above, by starting with the historical operating data of the target software, we can explore situations where public data such as game running time and number of online users affect the probability of events. Based on the historical operating data, we can determine the conditions for increasing the probability. The first user data obtained subsequently includes the operating data of the target software obtained by the target user, thereby determining whether the current probability has been increased.

[0031] Furthermore, step 3 is followed by: S4. Obtain the latest execution record of the target probability event, and feed back all the latest execution records and the probability enhancement conditions to the software developer of the target software.

[0032] As described above, after introducing probability boosting conditions, the latest execution record of the target probability event is obtained, and all the latest execution records and probability boosting conditions are fed back to the software developer of the target software so that the software developer can judge whether the current probability boosting mechanism is set up reasonably and whether it needs to be adjusted.

[0033] Please refer to Figure 1 Embodiment 1 of the present invention is as follows: A method for predicting probability changes of probabilistic events within software, comprising the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; In this embodiment, the target software includes, but is not limited to, online games and office software, and the target probabilistic events include, for example, treasure drop events and lottery events. Historical execution data includes historical user data and historical runtime data, which represents the software's performance and the user's own data when the user participates in the target probabilistic event. Taking game software as an example, historical user data can represent the user's level and the number of tasks completed when performing the target random event, while historical runtime data can represent the number of online users and the time spent performing the target random event.

[0034] Therefore, after obtaining the historical execution data, select the first set of all users who obtained the target result from the historical execution data; compare the similarities of the second user data of all users in the first set before executing the target probability event, and determine the probability boosting conditions based on the comparison results; or select all execution records of the target probability event that obtained the target result, determine the historical running data of all execution records corresponding to the target software; and determine the probability boosting conditions based on the historical running data. The identification of similarities can be based on existing probabilistic events within the software to determine the data categories used for probability enhancement, such as the number of online players, player level, and player assets, rather than selecting common data like profession or gender that are not particularly relevant to designing probability enhancement conditions. For game software, a multi-source big data collection system should be established: in addition to collecting player behavior data (such as game time, participating game activities, acquired item information, skill usage frequency, and movement trajectory) and game server operation data (such as online players, game time periods, and server load) through regular in-game data collection points, external data should also be introduced. For example, relevant data from similar popular games can be collected, including their item drop rates and player activity trends during similar time periods, for comparative analysis and reference. This should be combined with player social data, such as player activity in the game community, frequency of interaction with other players, and team play, as these social behaviors may have a potential correlation with in-game item drop probabilities; for example, players who frequently team up may have different probabilities of obtaining items in certain activities.

[0035] In this embodiment, a deep reinforcement learning algorithm is used to construct an AI model. Through continuous simulation and learning, the model dynamically adjusts its analysis strategy for game item drop probabilities based on multi-source big data input (including historical and real-time execution data). This model can automatically discover complex relationships between different data features. For example, it can analyze the influence weights of player playtime and social behavior on the drop probability of a specific boss under specific server load and online player count conditions. Simultaneously, transfer learning technology is introduced to transfer model parameters and knowledge trained in other similar games or related fields to the item drop probability analysis model for this game, accelerating the model's training and optimization process and improving the accuracy and efficiency of the analysis.

[0036] As one implementation method, a second set of users meeting the probability enhancement conditions is selected from historical execution data; the expected probability of the corresponding probability enhancement condition is obtained based on the proportion of users in the second set who obtained the target result; in step 3, the feedback probability enhancement to the target user is replaced with the feedback expected probability to the user. After the probability enhancement condition is met, the probability of obtaining the target result by executing the target probability event will increase, and the specific increase is calculated by collecting the proportion of users in the second set of users meeting the probability enhancement condition who obtained the execution result.

[0037] S2. Real-time acquisition of the target user's first user data within the target software; In this embodiment, in order to address the situation where the data pointed to by the probability enhancement condition may be user data or software operation data, the first user data includes the operation data of the target software obtained by the target user.

[0038] S3. Determine whether the first user data meets the probability increase conditions. If so, provide feedback that the probability has been increased to the target user. Otherwise, provide feedback that the probability has not been increased and the corresponding execution suggestions for the probability increase conditions to the target user.

[0039] In this embodiment, feedback content is presented to players as fortune information in diverse ways. Taking games as an example, in addition to displaying it in specific areas of the game interface and pushing it through the in-game notification system, virtual reality (VR) or augmented reality (AR) technologies can be used to present it more intuitively in the game scene. For example, when a player approaches a BOSS spawn point, AR technology can be used to display a visual icon or prompt indicating the drop rate in the real-world scene. Interactive functionality between players and the drop rate information is enhanced. Players can provide feedback on the drop rate information, such as whether the information is accurate or helpful for their game decisions. This feedback is collected and re-inputted into the AI ​​model to further optimize the model's analysis and prediction capabilities. The system monitors various data changes within the game and player feedback on the drop rate information in real time, dynamically adjusting the prediction model for the game's drop probability and the generation strategy for the drop rate information based on this real-time data. For example, if it is found that player feedback on the drop rate information is generally low within a certain period, the system will automatically reanalyze the data and adjust the model parameters to improve the accuracy and usability of subsequent drop rate information. By taking into account factors such as game version updates and event planning, the parameters of the AI ​​model are adjusted and optimized in advance to ensure that the drop probability prediction and drop luck information still have reference value when the game content changes.

[0040] S4. Obtain the latest execution record of the target probability event and feed back all the latest execution records and probability enhancement conditions to the software developer of the target software.

[0041] In this embodiment, after the probability boosting conditions and feedback information are put into use, the latest execution record is obtained so that the software developer can determine whether the current probability boosting conditions and their corresponding expected probabilities are appropriate and whether adjustments are needed.

[0042] Please refer to Figure 2 Embodiment two of the present invention is as follows: A software-based probability event probability change prediction terminal 1 includes a memory 2, a processor 3, and a computer program stored in the memory 2 and executable on the processor 3. When the processor 3 executes the computer program, it implements the software-based probability event probability change prediction method of Embodiment 1.

[0043] In summary, the present invention provides a method and terminal for predicting probability changes in probabilistic events within software. By analyzing the historical execution data of target probabilistic events in the target software, it infers that the random rules of the target probabilistic events may reference a certain data item. Changes in this data item can increase the probability of the target result, i.e., the probability increase condition. Then, it determines whether the target user's first user data meets the probability increase condition. If it does, it indicates that the user is more likely to obtain the target result by executing the target probabilistic event. Even if it does not meet the condition, it can still provide execution suggestions. In this way, it helps the target user identify or find a suitable opportunity to execute the target probabilistic event. By leveraging the differences between user data, it diverts users executing the target probabilistic event, reducing server load. Furthermore, by providing probability increase prompts, it also ensures a positive user experience.

[0044] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent modifications made based on the content of the present invention specification and drawings, or direct or indirect applications in related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for predicting probability changes in probabilistic events within software, characterized in that, Includes the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

2. The method for predicting probability changes of probabilistic events within software according to claim 1, characterized in that, Step 1 includes: S11. Select the first set of all users who obtained the target result from the historical execution data; S12. Compare the similarities of the second user data of all users in the first user set before executing the target probability event, and determine the probability enhancement condition based on the comparison results.

3. The method for predicting probability changes of probabilistic events within software according to claim 2, characterized in that, Step 12 is followed by: S13. Select the second set of all users in the historical execution data who meet the probability enhancement condition; S14. Based on the proportion of users in the second user set who obtained the target result, obtain the expected probability corresponding to the probability enhancement condition; In step 3, the feedback probability is increased to the target user, who is then replaced with: The expected probability is fed back to the user.

4. The method for predicting probability changes of probabilistic events within software according to claim 1, characterized in that, Step 1 further includes: In the historical execution data, select all execution records in which the target probability event yields the target result, and determine the historical running data of the target software corresponding to all the execution records; The probability enhancement conditions are determined based on historical operating data; The first user data includes the running data of the target software obtained by the target user.

5. The method for predicting probability changes of probabilistic events within software according to claim 1, characterized in that, Step 3 is followed by: S4. Obtain the latest execution record of the target probability event, and feed back all the latest execution records and the probability enhancement conditions to the software developer of the target software.

6. A software-defined terminal for predicting the probability change of probabilistic events, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor runs the computer program, it performs the following steps: S1. Based on the historical execution data of the target probability events of the target software, analyze and obtain the probability enhancement conditions for the occurrence of the target result of the target probability event; S2. Real-time acquisition of the target user's first user data within the target software; S3. Determine whether the first user data meets the probability enhancement condition. If yes, then provide feedback that the probability has been enhanced to the target user; otherwise, provide feedback that the probability has not been enhanced and the execution suggestion corresponding to the probability enhancement condition to the target user.

7. A software-based probability event probability change prediction terminal according to claim 6, characterized in that, Step 1 includes: S11. Select the first set of all users who obtained the target result from the historical execution data; S12. Compare the similarities of the second user data of all users in the first user set before executing the target probability event, and determine the probability enhancement condition based on the comparison results.

8. A software-based probability event probability change prediction terminal according to claim 7, characterized in that, Step 12 is followed by: S13. Select the second set of all users in the historical execution data who meet the probability enhancement condition; S14. Based on the proportion of users in the second user set who obtained the target result, obtain the expected probability corresponding to the probability enhancement condition; In step 3, the feedback probability is increased to the target user, who is then replaced with: The expected probability is fed back to the user.

9. A software-based probability event probability change prediction terminal according to claim 6, characterized in that, Step 1 further includes: In the historical execution data, select all execution records in which the target probability event yields the target result, and determine the historical running data of the target software corresponding to all the execution records; The probability enhancement conditions are determined based on historical operating data; The first user data includes the running data of the target software obtained by the target user.

10. A software-based probability event probability change prediction terminal according to claim 6, characterized in that, Step 3 is followed by: S4. Obtain the latest execution record of the target probability event, and feed back all the latest execution records and the probability enhancement conditions to the software developer of the target software.

Images