Account matching processing method and device, electronic equipment and storage medium

Abstract

The invention provides an account matching processing method and device, electronic equipment and a storage medium, and relates to the technical field of games. Comprising the following steps: acquiring basic matching information of a current to-be-matched account; the basic matching information at least comprises matching starting time; and determining reference matching information according to the matching start time, determining a matching waiting duration of the current to-be-matched account by adopting a pre-trained matching duration prediction model according to the basic matching information and the reference matching information, and displaying the matching waiting duration through a terminal device corresponding to the current to-be-matched account. And performing dynamic time sequence data pulling based on the basic matching information to generate the reference matching information, thereby fusing the basic matching information and the reference matching information, and performing prediction so as to improve the accuracy of a prediction result of the account matching waiting duration. The matching waiting duration is displayed through the terminal equipment corresponding to the account, so that the user can master the matching progress, the experience in the matching waiting process is improved, and the retention rate of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and more specifically, to an account matching processing method, device, electronic device, and storage medium. Background Art

[0002] In some software applications, such as gaming, social, and lifestyle apps, users often need to match their accounts before they can officially access the app and use its features. Because account matching often takes into account user balance, rationality, and user experience, the account matching process can be time-consuming.

[0003] Currently, during the account matching process, the application interface can only show users the length of time the account has been matched. There is a lack of clear expectations for the matching waiting time, resulting in a poor user experience. Summary of the Invention

[0004] The purpose of this application is to provide an account matching processing method, device, electronic device and storage medium to address the deficiencies in the above-mentioned prior art, so as to improve the user's application matching experience.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides an account matching processing method, comprising:

[0007] Obtain basic matching information of the current account to be matched; the basic matching information at least includes the matching start time;

[0008] Determining reference matching information based on the matching start time, the reference matching information including at least one of the following: average matching duration, number of online accounts, and number of matching accounts in a target historical period before the matching start time;

[0009] According to the basic matching information and the reference matching information, a pre-trained matching time prediction model is used to determine the matching waiting time of the current account to be matched, and the matching waiting time is displayed through the terminal device corresponding to the current account to be matched.

[0010] In a second aspect, an embodiment of the present application further provides an account matching processing device, comprising: an acquisition module, a determination module, and a prediction module;

[0011] The acquisition module is used to acquire basic matching information of the current account to be matched; the basic matching information at least includes the matching start time;

[0012] The determination module is configured to determine reference matching information based on the matching start time, the reference matching information including at least one of the following: an average matching duration, a number of online accounts, and a number of matching accounts in a target historical period before the matching start time;

[0013] The prediction module is used to determine the matching waiting time of the current account to be matched based on the basic matching information and the reference matching information using a pre-trained matching time prediction model, and display the matching waiting time through the terminal device corresponding to the current account to be matched.

[0014] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to perform the account matching processing method provided in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is run by a processor, the account matching processing method provided in the first aspect is executed.

[0016] The beneficial effects of this application are:

[0017] The present application provides an account matching processing method, device, electronic device and storage medium, including: obtaining basic matching information of the current account to be matched; the basic matching information includes at least the matching start time; determining reference matching information based on the matching start time, using a pre-trained matching time prediction model based on the basic matching information and the reference matching information to determine the matching waiting time of the current account to be matched, and displaying the matching waiting time through the terminal device corresponding to the current account to be matched. This method obtains the basic matching information of the account and performs dynamic time series data pulling based on the basic matching information to generate reference matching information, thereby fusing the basic matching information and the reference matching information to perform predictions to improve the accuracy of the prediction results of the matching waiting time of the account. By displaying the matching waiting time to the terminal device corresponding to the account, users using the account can grasp the matching progress, improve the experience during the matching waiting process, and improve user retention.

[0018] In addition, when it is detected that an account has been switched out of the application, relevant prompt information about the account matching process can be displayed on the terminal device through "Spirit Island" and / or the mobile phone lock screen, so that the user can still view the account matching progress and matching waiting progress outside the application interface, and can quickly enter the application when the match is successful, thereby reducing the account's idle rate and improving the gaming experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of an account matching processing method provided in an embodiment of the present application;

[0021] Figure 2 A flowchart of an account matching processing method provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0023] Figure 4 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0024] Figure 5 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0025] Figure 6 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0026] Figure 7 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0027] Figure 8 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0028] Figure 9 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0029] Figure 10 A schematic diagram of a display template provided in an embodiment of the present application;

[0030] Figure 11 A schematic diagram showing a display screen of a terminal in an unlocked state provided in an embodiment of the present application;

[0031] Figure 12 A schematic diagram showing a display screen in a terminal locked screen state provided in an embodiment of the present application;

[0032] Figure 13A flowchart of another account matching processing method provided in an embodiment of the present application;

[0033] Figure 14 A flowchart of another account matching processing method provided in an embodiment of the present application;

[0034] Figure 15 A schematic diagram of an account matching processing device provided in an embodiment of the present application;

[0035] Figure 16 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0037] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0038] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0039] The account matching process in current application software has the following pain points:

[0040] 1. There is a lack of clear expectations about the waiting time for matching, and some accounts will cancel the matching midway, resulting in a decrease in the number of participating accounts.

[0041] 2. If some accounts are temporarily disconnected from the app and idle, they may forget to switch their accounts back to the app because there is no real-time matching completion message, which will affect the app experience of other users.

[0042] Based on this, this solution provides an account matching processing method that dynamically pulls reference matching information related to the basic matching information based on the account's basic matching information, and combines the basic matching information and reference matching information to predict the matching wait time, thereby improving the accuracy of the matching wait time prediction. At the same time, through a real-time message interaction method, when an account exits the application matching interface, the terminal device corresponding to the account displays matching prompt-related information to the user using the account in real time. This allows the account to switch back to the application in a timely manner when a match is successful even if the account exits the application matching interface, thereby improving the user experience and interaction while waiting for matching and reducing the account's idle rate.

[0043] Figure 1 A flowchart of an account matching processing method provided in an embodiment of the present application; Figure 1 As shown, the method may include:

[0044] S101: Obtain basic matching information of the current account to be matched.

[0045] It is worth noting that this method can be applied to various applications to predict the waiting time for application account matching, such as gaming, social, and lifestyle apps. After logging into the game app using their game account, game accounts are matched before entering the game battle to complete the game team. After a successful match, the game battle officially begins. After a user logs into the ride-hailing app using their ride-hailing account, the app needs to match their account to a suitable vehicle while searching for a vehicle. The matching process requires waiting. After a successful match, the driver will go to the user's location to pick up the user.

[0046] This embodiment mainly uses the matching of game accounts as an example to illustrate the prediction process of the matching waiting time.

[0047] The basic matching information at least includes the matching start time.

[0048] The current account to be matched refers to the account that is about to enter the application matching. After the user clicks the match button, the matching can begin. After the matching is successful, the user can start using the application functions. For example, after the game matching is successful, the user can officially enter the game battle.

[0049] The basic matching information of the current account to be matched may include the matching start time, which refers to the instant when the user clicks the matching button to start matching.

[0050] Of course, in addition to this, in the game account matching scenario, basic matching information may also include but is not limited to matching stages (such as the beginning of the season, mid-season or end of the season, etc.), the account's character level, the server type used, the account's rank, the number of consecutive failures of the account, the account's character team and its sect type. Of course, some games may not have sects and other categories, so they can be ignored.

[0051] In the taxi account matching scenario, basic matching information may also include but is not limited to account credit score, account negative review rate, account points, etc.

[0052] The basic matching information can be used as characteristic information of the account to be matched and used to estimate the matching waiting time.

[0053] S102: Determine reference matching information according to the matching start time.

[0054] The reference matching information includes at least one of the following: an average matching duration in a target historical period before the matching start time, the number of online accounts, and the number of matching accounts.

[0055] In some embodiments, based on the basic matching information, some dynamic timing reference data can be expanded and generated.

[0056] Optionally, based on the matching start time in the basic matching information, the queue dynamic indicator data in the historical period before the matching start time can be pulled, or some application hall instantaneous status data under the matching start time can be pulled to generate reference matching information.

[0057] In some possible implementations, the reference matching information may include one or more of the following, but is certainly not limited to the following: average matching duration of the target historical period before the matching start time, the number of online accounts, and the number of matching accounts.

[0058] It is worth noting that the average matching duration of the target historical period before the matching start time reflects the matching time in the recent period before the matching start time of the account to be matched, and to a certain extent can serve as a benchmark reference for matching time in the current environment.

[0059] The more online accounts there are, the more accounts may participate in the matching, and the shorter the matching waiting time may be; similarly, the more accounts there are in the matching, the more accounts may participate in the matching at the same time, the easier it is to successfully match, and the shorter the matching waiting time may be.

[0060] S103: Based on the basic matching information and the reference matching information, a pre-trained matching time prediction model is used to determine the matching waiting time of the current account to be matched, and the matching waiting time is displayed on the terminal device corresponding to the current account to be matched.

[0061] The basic matching information of the current account to be matched and the reference matching information are input into a pre-trained matching time prediction model. The model can then predict the matching wait time for the current account to be matched based on various feature information. At the same time, the matching wait time can be displayed to the terminal device corresponding to the current account to improve the user's waiting experience.

[0062] In summary, the account matching processing method provided by this embodiment includes: obtaining the basic matching information of the current account to be matched; the basic matching information includes at least the matching start time; determining the reference matching information based on the matching start time, using the pre-trained matching time prediction model based on the basic matching information and the reference matching information, determining the matching waiting time of the current account to be matched, and displaying the matching waiting time through the terminal device corresponding to the current account to be matched. This method obtains the basic matching information of the account and performs dynamic time series data pulling based on the basic matching information to generate reference matching information, thereby fusing the basic matching information and the reference matching information to perform predictions to improve the accuracy of the prediction results of the matching waiting time of the account. By displaying the matching waiting time to the terminal device corresponding to the account, users using the account can grasp the matching progress, improve the experience during the matching waiting process, and improve the user retention rate.

[0063] Figure 2 A flowchart of an account matching processing method provided in an embodiment of the present application; optionally, in step S102, determining reference matching information based on the matching start time may include:

[0064] S201: Determine the matching period type according to the matching start time.

[0065] Based on the matching start time, the matching period type can be determined. The matching period types include: prime time or regular time. During prime time, more accounts join the application, the matching speed is faster, and the matching waiting time is shorter.

[0066] S202: Determine the target historical period according to the matching start time and the data pulling window size under the matching period type.

[0067] The size of the data pull window can be adaptively adjusted according to the matching period type. For example, the data pull window is 5 minutes during prime time and 10 minutes during regular time.

[0068] The target historical period can be determined based on the matching start time and the data pulling window size under the matching period type.

[0069] For example, assuming the match start time is 19:00 on January 1, which is prime time, the target historical period can be 18:55-19:00 on January 1. That is, the target historical period and a period before and consecutive to the match start time can be used as the recent reference period for the match start time.

[0070] S203: Obtain account matching data for the target historical period.

[0071] The target historical period is a historical period, so the account matching data obtained for the target historical period is the account matching data that has completed matching under the target historical period.

[0072] S204: Determine the average matching duration based on the account matching data of the target historical period.

[0073] Since there may be multiple account matching data in the target historical period, the average matching time in the target historical period can be determined through multiple account matching data.

[0074] That is, when the matching period of the current account to be matched is the prime time, the historical account matching data within 5 minutes before the matching start time of the current account to be matched can be pulled, and the average matching time in the past 5 minutes can be calculated as a reference information for estimating the current matching waiting time.

[0075] Optionally, in step S204, determining the average matching duration based on the account matching data of the target historical period may include: determining the average matching duration based on the matching duration information of each historical account having the same attributes as the current account to be matched during the target historical period.

[0076] In one implementation, using a game account matching scenario as an example, the actual match duration of each historical account with the same character level, account rank, character type, and sect type as the current account to be matched during the target historical period can be obtained. The average of the actual match durations of each historical account is calculated to obtain the average match duration. In other words, the actual match duration of historical accounts with the same character rank, character level, and character type as the current account to be matched is used as a reference.

[0077] Taking the taxi account matching scenario as an example, the actual matching time of each historical account with the same account points, account level, and account reputation as the current account to be matched during the target historical period can be obtained, and the average actual matching time of each historical account can be calculated.

[0078] Of course, in another implementation method, the actual matching duration of all historical accounts in the target historical period can be directly pulled to calculate the average matching duration.

[0079] Figure 3 A flowchart of another account matching processing method provided in an embodiment of the present application is provided. Optionally, in step S102, determining reference matching information based on the matching start time may include:

[0080] S301. Determine the number of online accounts under each attribute based on attribute information of each online account in the application lobby at the matching start time.

[0081] In some embodiments, taking the game account matching scenario as an example, when the account character is distinguished by attributes such as sect and level, the number of online accounts of each sect and the number of online accounts of each level in the game lobby at the start time of the matching can be obtained respectively.

[0082] Because in some games, when matching, accounts of the same level or the same sect may need to be matched to one team. Therefore, the more online accounts with the same sect and level as the current account to be matched, the faster the current account to be matched will be matched successfully, and the shorter the required matching waiting time may be.

[0083] S302: Determine the number of matching accounts under each attribute based on the attribute information of each matching account at the matching start time.

[0084] You can also retrieve the number of accounts of different sects or levels currently matching at the match start time. The more accounts currently matching with the same sect or level as the current account, the faster the current account will be matched, and the shorter the matching wait time may be.

[0085] In other embodiments, in scenarios where attributes such as sects and levels are not distinguished, the total number of online accounts in the game lobby at the start time of the match and the total number of accounts being matched at the start time of the match can also be directly obtained as reference matching information.

[0086] Optionally, feature processing can be performed on some feature information, for example: mapping the match time type to a vector, such as [0.3, -0.7] representing "golden time"; mapping the match stage code to a vector; mapping the account character team to a vector, etc. In other words, some categorical data can be mapped to a numerical value.

[0087] Secondly, feature fusion can be performed on the features mapped into vectors to achieve the purpose of feature dimensionality reduction.

[0088] Figure 4 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, in step S103, based on the basic matching information and the reference matching information, a pre-trained matching duration prediction model is used to determine the matching waiting time of the current account to be matched, which may include:

[0089] S401: Input basic matching information and reference matching information into a matching time prediction model, and determine the initial matching waiting time of the current account to be matched through the matching time prediction model.

[0090] In some embodiments, a matching duration prediction model may first perform a preliminary prediction to obtain an initial matching waiting duration.

[0091] S402: According to the matching start time of the current account to be matched, the matching result information of each account in the historical preset time period before the matching start time is collected.

[0092] Then, by matching the prediction residual information of recent historical accounts with the matching time prediction model, the initial matching waiting time can be compensated to improve the accuracy of the final prediction results.

[0093] Optionally, recent data of the matching start time can be collected based on the matching start time of the current account to be matched. Here, the historical preset period before the matching start time can be used as the recent time of the matching start time.

[0094] The length of the historical preset period here may be different from the length of the above-mentioned target historical period.

[0095] S403: Determine a residual sequence based on the matching result information of each account within a preset historical period.

[0096] The residual sequence can be calculated using the matching results of each account within the preset historical period. All accounts within the preset historical period have been matched, so the matching results can be directly obtained.

[0097] S404: Correct the initial matching waiting time of the current account to be matched according to the residual sequence to determine the matching waiting time of the current account to be matched.

[0098] The initial matching waiting time can be compensated according to the residual sequence to determine the matching waiting time of the current account to be matched.

[0099] Figure 5 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, in step S402, based on the matching start time of the current account to be matched, collecting matching result information of each account within a preset historical period before the matching start time may include:

[0100] S501: Determine a historical preset time period according to the matching start time and the preset data collection window.

[0101] In one embodiment, the historical preset period can be determined based on the preset data collection window size and the matching start time. Assuming the matching start time is 17:00 and the preset data collection window size is 5 minutes, the historical preset period is 16:55-17:00.

[0102] S502: Collect the actual matching duration of each account and the predicted matching waiting time of each account within a preset historical period.

[0103] Optionally, the collected historical matching result information of each account within a preset period may include: the actual matching time of the account and the predicted matching waiting time of the account. The predicted matching waiting time here is also predicted using the matching time prediction model.

[0104] In another embodiment, the sliding window can be set to 50 times, for example, to pull 50 account data before the matching start time. Each account data includes: the actual matching time of the account and the predicted matching waiting time of the account.

[0105] Figure 6 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, in step S403, determining the residual sequence based on the matching result information of each account within a preset historical period may include:

[0106] S601. Determine the prediction residual value of each account according to the actual matching time of each account and the predicted matching waiting time of each account.

[0107] For each account, the difference between the actual matching time and the predicted matching waiting time can be calculated to obtain the predicted residual value of each account.

[0108] S602: Determine a residual sequence based on the predicted residual value of each account.

[0109] The predicted residual values ​​of each account can be sorted according to the size of the residual value to form a residual sequence, that is, the residual sequence contains the predicted residual value of each account.

[0110] Figure 7 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, in step S404, correcting the initial matching waiting time of the current account to be matched based on the residual sequence to determine the matching waiting time of the current account to be matched may include:

[0111] S701. Determine an average residual according to a residual sequence.

[0112] The average residual can be obtained by calculating the average of the predicted residual values ​​in the residual sequence.

[0113] S702. Perform linear compensation on the initial matching waiting duration according to the average residual and a preset weight to obtain the matching waiting duration of the currently waiting-to-be-matched account.

[0114] In some embodiments, the following formula can be used to perform linear compensation on the initial matching waiting duration:

[0115] t_adjusted = t_pred + α * e_avg

[0116] where, t_pred represents the initial matching waiting duration, e_avg represents the average residual, α represents the dynamic weight, α can be adjusted according to the error fluctuation range, and t_adjusted represents the final matching waiting duration obtained after compensation.

[0117] By substituting the values of each parameter into the above formula, the matching waiting duration of the currently waiting-to-be-matched account can be calculated.

[0118] It should be noted that for the correction part of the initial matching waiting duration, it can be implemented by the matching duration prediction model or by other compensation modules outside the model. When implemented by an external module, the initial matching waiting duration output by the matching duration prediction model can be used as the input and input to the external module for compensation calculation.

[0119] Figure 8 This is a schematic flowchart of another account matching processing method provided by an embodiment of the present application; optionally, in step S404, according to the residual sequence, correcting the initial matching waiting duration of the currently waiting-to-be-matched account to determine the matching waiting duration of the currently waiting-to-be-matched account may include:

[0120] S801. Determine whether the residual distribution is skewed according to the residual sequence.

[0121] In some embodiments, it is also possible to determine whether the residual distribution is skewed according to the residual sequence. When there is no skewness, linear compensation is performed according to the method flow shown in Figure 7 When there is skewness, non-linear compensation can be performed according to the following steps in Figure 8 Non-linear compensation can be implemented by a quantile regression correction method, such as P75 quantile compensation.

[0122] Optionally, according to the residual sequence, the lower quartile Q1, median Q2, and upper quartile Q3 of the residual sequence can be calculated.

[0123] Set the skewness index S = (Q3 - Q2) / (Q2 - Q1). If S > 2, it is considered significantly right-skewed; if S < 0.5, it is considered significantly left-skewed. If 0.5 < S < 2, it is considered that there is no skewness.

[0124] S802: If yes, determine a preset quantile of the residual sequence according to the residual sequence, where the preset quantile includes: a lower quartile or an upper quartile.

[0125] If skewness occurs, you can determine the lower or upper quartile of the residual series.

[0126] S803: Perform linear compensation on the initial matching waiting time according to the preset quantile and preset weight of the residual sequence to obtain the matching waiting time of the current account to be matched.

[0127] By replacing the average residual in the above linear compensation formula with the lower quartile or upper quartile of the residual sequence, nonlinear compensation can be performed on the initial matching waiting time.

[0128] Figure 9 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, the method may further include:

[0129] S901: In response to the application-exit operation of the current account to be matched, obtain the matching waiting time and the current matching time of the current account to be matched.

[0130] In some scenarios, the predicted matching wait time information can be displayed on the application matching interface, and users can view the matching wait time and the current matching time in real time on the application matching interface.

[0131] In other scenarios, some users may feel bored while waiting for matching and may switch out of the application matching interface to use other software. In this scenario, users are usually unable to view matching-related prompt information unless they switch back to the application to continue viewing the prompt information.

[0132] For this scenario, this solution can still display prompt information such as the matching waiting time and the current matching time to the user in real time after the user cuts the account out of the application. When the match is successful, the user can click outside the application to directly enter the application.

[0133] Optionally, in response to the operation of the current account to be matched switching out of the application, the matching waiting time and the current matching time of the current account to be matched are obtained.

[0134] The current matching duration is a dynamically changing data. The current matching duration is relative to the matching start time, which refers to the time that has passed from the matching start time to the current time.

[0135] S902: Generate a display screen according to the matching waiting time of the current account to be matched, the current matching time, and a pre-configured display template.

[0136] Using our internally developed backend widget platform, we can design display templates that include the parameters to be displayed and background images. These templates determine how the aforementioned prompts are displayed to users.

[0137] A display screen may be generated based on the matching waiting time of the current account to be matched, the current matching time, and the display template.

[0138] S903: Display a display screen on the terminal device corresponding to the current account to be matched.

[0139] In the case that the current account to be matched switches out of the application, the generated display screen can be displayed on the interface of the terminal device corresponding to the current account to be matched.

[0140] Optionally, in step S902, a display screen is generated based on the matching waiting time of the current account to be matched, the current matching time and a pre-configured display template, which may include: filling the matching waiting time of the current account to be matched into the matching waiting time parameter item in the display template; dynamically filling the current matching time obtained in real time into the current matching time parameter item in the display template, and generating a display screen.

[0141] Optionally, the current matched time and matching waiting time can be dynamically pulled from the application in real time through the system's data interface, and the matching waiting time can be filled into the matching waiting time parameter item in the display template, and the current matched time can be dynamically filled into the current matched time parameter item in the display template to generate the current display screen.

[0142] Since the current matching duration is continuously updated as time goes by until the match is successful, the current matching duration in the display screen is continuously updated, resulting in some differences in the specific parameter values ​​in each frame of the display screen, thereby forming a real-time display screen.

[0143] Figure 10 A schematic diagram of a display template provided in an embodiment of the present application is shown as follows: Figure 10 As shown in (a), the display template displays the matching waiting time parameter item and the current matching time parameter item, and of course, it can also include a cancel control. The user may not be able to continue using the application due to other things while waiting for the match, and can cancel the match through the cancel control.

[0144] When the match is successful, the display template can jump to Figure 10In (b), the control is canceled and switched to the app control. The match waiting time parameter and the current matching time parameter are no longer displayed, and a prompt message indicating a successful match is displayed. Users can directly return to the app by clicking the app control. This allows users to view real-time time prompts even when exiting the app and quickly return to the game without affecting normal use of the app.

[0145] Optionally, in step S903, displaying a display screen on a terminal device corresponding to the current account to be matched may include: displaying the display screen in an unlocked state of the terminal device.

[0146] In one implementation, when the terminal device supports the "Smart Island" function, the "Smart Island" function can be used to display the display screen when the account switches out of the application and uses other mobile phone software in real time.

[0147] That is, when the terminal device is unlocked, the generated display screen is displayed in real time while the account switches out of the application and uses other mobile software. For example, while the user is browsing video software, the display screen is displayed above the terminal device interface.

[0148] Figure 11 This is a schematic diagram showing a display screen in a terminal unlocked state provided by an embodiment of the present application. Figure 11 As shown in (a), during the matching process, the matching waiting time and the current matching time can be displayed on the top of the terminal device interface. When the match is successful, you can jump to Figure 11 In (b), users can enter the app by clicking and then return directly to the app.

[0149] Alternatively, the display screen is displayed in the locked screen state of the terminal device.

[0150] In one implementation, the display screen can also be displayed when the terminal is in lock screen state. This method is similar to the function implemented by current mobile phones. When the mobile phone is locked, when there is a new notification message, the notification message will pop up in the middle area of ​​the mobile phone in the lock screen state.

[0151] Figure 12 This is a schematic diagram showing a display screen in a terminal lock screen state provided by an embodiment of the present application. Figure 12 As shown in (a), during the matching process, the matching waiting time and the current matching time can be displayed in the middle area of ​​the terminal device interface. When the match is successful, you can jump to Figure 12 In (b), users can directly return to the app by clicking to enter the app.

[0152] It is worth noting that when the terminal does not support the "Smart Island" function, the display screen can be displayed through the lock screen display method. When the terminal supports the "Smart Island" function, the display screen can be displayed through the unlocked state display method or the lock screen display method, and of course both methods can be used simultaneously.

[0153] Figure 13 A flowchart of another account matching processing method provided in an embodiment of the present application is provided; optionally, the training process of the matching duration prediction model includes:

[0154] S1001. Collect a training sample data set, where the training sample data set includes multiple sample data. The sample data includes matching feature information of sample accounts that have been successfully matched in the past and actual matching duration of the sample accounts.

[0155] The matching feature information of the sample account includes: basic matching feature information and reference matching feature information.

[0156] Optionally, a training sample data set may be collected, wherein the matching feature information of each sample account that has been successfully matched historically may be used as a piece of sample data. The matching feature information here includes basic matching information and reference matching information used in the prediction process.

[0157] The actual matching duration of each sample account can be used as label information for the sample data to guide model training.

[0158] S1002: Determine the sample weight of the sample data corresponding to each sample account according to the matching start time of each sample account.

[0159] In addition, a time decay function can be designed to dynamically adjust the weight of sample data. The closer the sample data is to the current time, the higher the corresponding weight.

[0160] S1003: Train a matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set.

[0161] The training sample data set and the sample weight of each sample data in the training sample data set can be input into the model to train and obtain a matching duration prediction model.

[0162] Optionally, the matching feature information of the sample account may include: basic matching feature information and reference matching feature information; taking the game account matching scenario as an example, the basic matching feature information may include multiple or all of the following: matching stage, matching start time, account character level, server type, character team and school type, account rank, and the number of consecutive failures of the account;

[0163] The reference matching feature information may include one or more of the following: the average matching duration in a preset window period before the matching start time, the number of online accounts in the game lobby at the matching start time, and the number of matching accounts at the matching start time.

[0164] That is, the matching feature information of the sample account used when training the model is the same as the basic matching information and reference matching information of the current account to be matched based on when the model is applied for prediction.

[0165] Figure 14 A flowchart of another account matching processing method provided in an embodiment of the present application; optionally, in step S1003, training a matching duration prediction model based on a training sample dataset and the sample weights of each sample data in the training sample dataset may include:

[0166] S1101: Train and obtain an initial matching duration prediction model based on a training sample data set and a sample weight of each sample data in the training sample data set.

[0167] In some embodiments, after obtaining the initial matching duration prediction model based on the training sample data set and the sample weights of each sample data in the training sample data set, real-time prediction can also be performed based on the initial matching duration prediction model to automatically trigger fine-tuning of the model parameters according to the prediction error and optimize the model in real time.

[0168] S1102: If the prediction errors of the initial matching duration prediction model for multiple times exceed a preset threshold, a preset number of new sample data are collected to optimize the initial matching duration prediction model to obtain a matching duration prediction model.

[0169] Optionally, an initial matching time prediction model can be used for prediction. When the prediction error exceeds a threshold for multiple consecutive times, the initial matching time prediction model can be fine-tuned. The fine-tuning here can refer to retraining the initial matching time prediction model by collecting a small amount of new sample data to fine-tune the network parameters of the initial matching time prediction model, and finally obtain the matching time prediction model.

[0170] The number of consecutive times here can be 5 times, of course this number can be adjusted flexibly.

[0171] The number of new sample data collected can be less than 100.

[0172] In some embodiments, if after fine-tuning the model, it is found that the loss of the fine-tuned model does not meet expectations, that is, the fine-tuned model is not ideal, then you can return to the initial matching duration prediction model and use the initial matching duration prediction model as the final matching duration prediction model.

[0173] In summary, the account matching processing method provided by this embodiment includes: obtaining the basic matching information of the current account to be matched; the basic matching information includes at least the matching start time; determining the reference matching information based on the matching start time, using the pre-trained matching time prediction model based on the basic matching information and the reference matching information, determining the matching waiting time of the current account to be matched, and displaying the matching waiting time through the terminal device corresponding to the current account to be matched. This method obtains the basic matching information of the account and performs dynamic time series data pulling based on the basic matching information to generate reference matching information, thereby fusing the basic matching information and the reference matching information to perform predictions to improve the accuracy of the prediction results of the matching waiting time of the account. By displaying the matching waiting time to the terminal device corresponding to the account, users using the account can grasp the matching progress, improve the experience during the matching waiting process, and improve the user retention rate.

[0174] In addition, when it is detected that an account has been switched out of the application, relevant prompt information about the account matching process can be displayed on the terminal device through "Spirit Island" and / or the mobile phone lock screen, so that the user can still view the account matching progress and matching waiting progress outside the application interface, and can quickly enter the application when the match is successful, thereby reducing the account's idle rate and improving the gaming experience.

[0175] The following describes the apparatus, device, storage medium, etc. used to execute the account matching processing method provided in this application. The specific implementation process and technical effects are described above and will not be repeated below.

[0176] Figure 15 This is a schematic diagram of an account matching processing device provided in an embodiment of the present application. The functions implemented by the account matching processing device correspond to the steps performed by the above method. The device can be understood as the above server or server processor, or as a component independent of the above server or processor that implements the functions of the present application under the control of the server. The device may include: an acquisition module 150, a determination module 151, and a prediction module 152;

[0177] An acquisition module 150 is configured to acquire basic matching information of the current account to be matched; the basic matching information at least includes a matching start time;

[0178] A determination module 151 is configured to determine reference matching information based on the matching start time, the reference matching information including at least one of the following: an average matching duration, a number of online accounts, and a number of matching accounts in a target historical period before the matching start time;

[0179] The prediction module 152 is used to determine the matching waiting time of the current account to be matched based on the basic matching information and the reference matching information using a pre-trained matching time prediction model, and display the matching waiting time through the terminal device corresponding to the current account to be matched.

[0180] Optionally, the determination module 151 is specifically configured to determine the matching period type according to the matching start time;

[0181] Determine the target historical period based on the matching start time and the data pull window size under the matching period type;

[0182] Obtain account matching data for the target historical period;

[0183] Determine the average matching time based on the account matching data for the target historical period.

[0184] Optionally, the determination module 151 is specifically configured to determine an average matching duration based on matching duration information of each historical account having the same attributes as the current account to be matched during a target historical period.

[0185] Optionally, the determination module 151 is specifically configured to determine the number of online accounts under each attribute based on the attribute information of each online account in the application lobby at the matching start time;

[0186] According to the attribute information of each matching account at the matching start time, the number of matching accounts under each attribute is determined.

[0187] Optionally, the prediction module 152 is specifically configured to input the basic matching information and the reference matching information into a matching time prediction model, and determine the initial matching waiting time of the current to-be-matched account via the matching time prediction model;

[0188] According to the matching start time of the current account to be matched, the matching result information of each account in the historical preset period before the matching start time is collected;

[0189] Determine the residual sequence based on the matching result information of each account within the historical preset period;

[0190] The initial matching waiting time of the current account to be matched is corrected according to the residual sequence to determine the matching waiting time of the current account to be matched.

[0191] Optionally, the prediction module 152 is specifically configured to determine a historical preset period based on the matching start time and a preset data collection window;

[0192] Collect the actual matching time of each account and the predicted matching waiting time of each account within the preset historical period.

[0193] Optionally, the prediction module 152 is specifically configured to determine the prediction residual value of each account based on the actual matching time of each account and the predicted matching waiting time of each account;

[0194] Determine the residual sequence based on the predicted residual value of each account.

[0195] Optionally, the prediction module 152 is specifically configured to determine an average residual based on the residual sequence;

[0196] Based on the average residual and the preset weight, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0197] Optionally, the prediction module 152 is specifically configured to determine whether the residual distribution is skewed based on the residual sequence;

[0198] If yes, then determine the preset quantile of the residual sequence according to the residual sequence, the preset quantile includes: lower quartile or upper quartile;

[0199] According to the preset quantile and preset weight of the residual sequence, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0200] Optionally, it further includes: a display module;

[0201] The display module is used to respond to the application switching operation of the current account to be matched, and obtain the matching waiting time and the current matching time of the current account to be matched;

[0202] Generate a display screen based on the current matching waiting time of the account to be matched, the current matching time, and the pre-configured display template;

[0203] The display screen is displayed on the terminal device corresponding to the current account to be matched.

[0204] Optionally, the display module is specifically configured to fill the matching waiting time of the current account to be matched into the matching waiting time parameter item in the display template;

[0205] The current matching duration obtained in real time is dynamically filled into the current matching duration parameter item in the display template, and a display screen is generated.

[0206] Optionally, a display module is specifically configured to display a display screen when the terminal device is in an unlocked state;

[0207] Alternatively, the display screen is displayed in the locked screen state of the terminal device.

[0208] Optionally, it further includes: a training module;

[0209] A training module is used to collect a training sample data set, which includes multiple sample data. The sample data includes matching feature information of sample accounts that have been successfully matched in the past and the actual matching duration of the sample accounts. The matching feature information of the sample accounts includes basic matching feature information and reference matching feature information.

[0210] Determine the sample weight of the sample data corresponding to each sample account based on the matching start time of each sample account;

[0211] According to the training sample data set and the sample weight of each sample data in the training sample data set, a matching time prediction model is trained.

[0212] Optionally, a training module is specifically used to train an initial matching duration prediction model based on a training sample data set and a sample weight of each sample data in the training sample data set;

[0213] If the prediction errors of the initial matching duration prediction model for multiple times exceed a preset threshold, a preset number of new sample data are collected to optimize the initial matching duration prediction model to obtain a matching duration prediction model.

[0214] The above modules can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), one or more digital single processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0215] The above modules can be connected or communicate with each other via a wired connection or a wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may include a connection in the form of a LAN, a WAN, Bluetooth, ZigBee, or NFC, or any combination thereof. Two or more modules can be combined into a single module, and any module can be divided into two or more units. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application.

[0216] Figure 16 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, including: a processor 801, a storage medium 802, and a bus 803. The storage medium 802 stores machine-readable instructions executable by the processor 801. When the electronic device executes an account matching processing method as described in the embodiment, the processor 801 communicates with the storage medium 802 via the bus 803. The processor 801 executes the machine-readable instructions to perform the following steps:

[0217] Obtain the basic matching information of the current account to be matched; the basic matching information at least includes the matching start time;

[0218] Determining reference matching information based on the matching start time, the reference matching information including at least one of the following: average matching duration, number of online accounts, and number of matching accounts in a target historical period before the matching start time;

[0219] Based on the basic matching information and the reference matching information, a pre-trained matching time prediction model is used to determine the matching waiting time of the current account to be matched, and the matching waiting time is displayed through the terminal device corresponding to the current account to be matched.

[0220] In a feasible implementation, when executing determining the reference matching information according to the matching start time, the processor 801 is specifically configured to: determine the matching period type according to the matching start time;

[0221] Determine the target historical period based on the matching start time and the data pull window size under the matching period type;

[0222] Obtain account matching data for the target historical period;

[0223] Determine the average matching time based on the account matching data for the target historical period.

[0224] In a feasible implementation scheme, when the processor 801 determines the average matching time based on the account matching data of the target historical period, it is specifically used to: determine the average matching time based on the matching time information of each historical account with the same attributes as the current account to be matched during the target historical period.

[0225] In one feasible embodiment, when determining reference matching information based on the matching start time, the processor 801 is specifically configured to: determine the number of online accounts with each attribute based on the attribute information of each online account in the application lobby at the matching start time;

[0226] According to the attribute information of each matching account at the matching start time, the number of matching accounts under each attribute is determined.

[0227] In one feasible embodiment, when the processor 801 determines the matching waiting time of the current account to be matched based on the basic matching information and the reference matching information using a pre-trained matching time prediction model, the processor 801 is specifically configured to: input the basic matching information and the reference matching information into the matching time prediction model, and determine the initial matching waiting time of the current account to be matched via the matching time prediction model;

[0228] According to the matching start time of the current account to be matched, the matching result information of each account in the historical preset period before the matching start time is collected;

[0229] Determine the residual sequence based on the matching result information of each account within the historical preset period;

[0230] The initial matching waiting time of the current account to be matched is corrected according to the residual sequence to determine the matching waiting time of the current account to be matched.

[0231] In one feasible embodiment, when collecting matching result information of each account within a preset historical period before the matching start time based on the matching start time of the current account to be matched, the processor 801 is specifically configured to: determine the preset historical period based on the matching start time and a preset data collection window;

[0232] Collect the actual matching time of each account and the predicted matching waiting time of each account within the preset historical period.

[0233] In one feasible embodiment, when determining the residual sequence based on the matching result information of each account within a preset historical period, the processor 801 is specifically configured to: determine the predicted residual value of each account based on the actual matching time of each account and the predicted matching waiting time of each account;

[0234] Determine the residual sequence based on the predicted residual value of each account.

[0235] In one feasible embodiment, when the processor 801 corrects the initial matching waiting time of the current account to be matched according to the residual sequence and determines the matching waiting time of the current account to be matched, it is specifically configured to: determine an average residual according to the residual sequence;

[0236] Based on the average residual and the preset weight, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0237] In one feasible embodiment, when the processor 801 corrects the initial matching waiting time of the current account to be matched based on the residual sequence and determines the matching waiting time of the current account to be matched, it is specifically configured to: determine whether the residual distribution is skewed based on the residual sequence;

[0238] If yes, then determine the preset quantile of the residual sequence according to the residual sequence, the preset quantile includes: lower quartile or upper quartile;

[0239] According to the preset quantile and preset weight of the residual sequence, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0240] In a feasible implementation, the processor 801 is further configured to: in response to the application switching operation of the current account to be matched, obtain the matching waiting time and the current matching time of the current account to be matched;

[0241] Generate a display screen based on the current matching waiting time of the account to be matched, the current matching time, and the pre-configured display template;

[0242] The display screen is displayed on the terminal device corresponding to the current account to be matched.

[0243] In one feasible embodiment, when the processor 801 generates a display screen based on the matching wait time of the current account to be matched, the current matching time, and a pre-configured display template, the processor 801 is specifically configured to: fill the matching wait time of the current account to be matched into the matching wait time parameter item in the display template;

[0244] The current matching duration obtained in real time is dynamically filled into the current matching duration parameter item in the display template, and a display screen is generated.

[0245] In one feasible embodiment, when executing the display screen on the terminal device corresponding to the current account to be matched, the processor 801 is specifically configured to: display the display screen in the unlocked state of the terminal device;

[0246] Alternatively, the display screen is displayed in the locked screen state of the terminal device.

[0247] In one feasible embodiment, the processor 801 is further configured to: collect a training sample data set, the training sample data set including a plurality of sample data, the sample data including matching feature information of sample accounts with successful historical matching and actual matching duration of the sample accounts; the matching feature information of the sample accounts including basic matching feature information and reference matching feature information;

[0248] Determine the sample weight of the sample data corresponding to each sample account based on the matching start time of each sample account;

[0249] According to the training sample data set and the sample weight of each sample data in the training sample data set, a matching time prediction model is trained.

[0250] In one feasible embodiment, when the processor 801 executes the training to obtain the matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set, it is specifically configured to: train an initial matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set;

[0251] If the prediction errors of the initial matching duration prediction model for multiple times exceed a preset threshold, a preset number of new sample data are collected to optimize the initial matching duration prediction model to obtain a matching duration prediction model.

[0252] Among them, the storage medium 802 stores program code, and when the program code is executed by the processor 801, the processor 801 executes the various steps of the account matching processing method according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0253] The processor 801 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0254] The storage medium 802 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory can include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disc, etc. The memory is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The storage medium 802 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0255] Optionally, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps:

[0256] Obtain the basic matching information of the current account to be matched; the basic matching information at least includes the matching start time;

[0257] Determining reference matching information based on the matching start time, the reference matching information including at least one of the following: average matching duration, number of online accounts, and number of matching accounts in a target historical period before the matching start time;

[0258] Based on the basic matching information and the reference matching information, a pre-trained matching time prediction model is used to determine the matching waiting time of the current account to be matched, and the matching waiting time is displayed through the terminal device corresponding to the current account to be matched.

[0259] In a feasible implementation, when executing determining the reference matching information according to the matching start time, the processor 801 is specifically configured to: determine the matching period type according to the matching start time;

[0260] Determine the target historical period based on the matching start time and the data pull window size under the matching period type;

[0261] Obtain account matching data for the target historical period;

[0262] Determine the average matching time based on the account matching data for the target historical period.

[0263] In a feasible implementation scheme, when the processor 801 determines the average matching time based on the account matching data of the target historical period, it is specifically used to: determine the average matching time based on the matching time information of each historical account with the same attributes as the current account to be matched during the target historical period.

[0264] In one feasible embodiment, when determining reference matching information based on the matching start time, the processor 801 is specifically configured to: determine the number of online accounts with each attribute based on the attribute information of each online account in the application lobby at the matching start time;

[0265] According to the attribute information of each matching account at the matching start time, the number of matching accounts under each attribute is determined.

[0266] In one feasible embodiment, when the processor 801 determines the matching waiting time of the current account to be matched based on the basic matching information and the reference matching information using a pre-trained matching time prediction model, the processor 801 is specifically configured to: input the basic matching information and the reference matching information into the matching time prediction model, and determine the initial matching waiting time of the current account to be matched via the matching time prediction model;

[0267] According to the matching start time of the current account to be matched, the matching result information of each account in the historical preset period before the matching start time is collected;

[0268] Determine the residual sequence based on the matching result information of each account within the historical preset period;

[0269] The initial matching waiting time of the current account to be matched is corrected according to the residual sequence to determine the matching waiting time of the current account to be matched.

[0270] In one feasible embodiment, when collecting matching result information of each account within a preset historical period before the matching start time based on the matching start time of the current account to be matched, the processor 801 is specifically configured to: determine the preset historical period based on the matching start time and a preset data collection window;

[0271] Collect the actual matching time of each account and the predicted matching waiting time of each account within the preset historical period.

[0272] In one feasible embodiment, when determining the residual sequence based on the matching result information of each account within a preset historical period, the processor 801 is specifically configured to: determine the predicted residual value of each account based on the actual matching time of each account and the predicted matching waiting time of each account;

[0273] Determine the residual sequence based on the predicted residual value of each account.

[0274] In one feasible embodiment, when the processor 801 corrects the initial matching waiting time of the current account to be matched according to the residual sequence and determines the matching waiting time of the current account to be matched, it is specifically configured to: determine an average residual according to the residual sequence;

[0275] Based on the average residual and the preset weight, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0276] In one feasible embodiment, when the processor 801 corrects the initial matching waiting time of the current account to be matched based on the residual sequence and determines the matching waiting time of the current account to be matched, it is specifically configured to: determine whether the residual distribution is skewed based on the residual sequence;

[0277] If yes, then determine the preset quantile of the residual sequence according to the residual sequence, the preset quantile includes: lower quartile or upper quartile;

[0278] According to the preset quantile and preset weight of the residual sequence, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

[0279] In a feasible implementation, the processor 801 is further configured to: in response to the application switching operation of the current account to be matched, obtain the matching waiting time and the current matching time of the current account to be matched;

[0280] Generate a display screen based on the current matching waiting time of the account to be matched, the current matching time, and the pre-configured display template;

[0281] The display screen is displayed on the terminal device corresponding to the current account to be matched.

[0282] In one feasible embodiment, when the processor 801 generates a display screen based on the matching wait time of the current account to be matched, the current matching time, and a pre-configured display template, the processor 801 is specifically configured to: fill the matching wait time of the current account to be matched into the matching wait time parameter item in the display template;

[0283] The current matching duration obtained in real time is dynamically filled into the current matching duration parameter item in the display template, and a display screen is generated.

[0284] In one feasible embodiment, when executing the display screen on the terminal device corresponding to the current account to be matched, the processor 801 is specifically configured to: display the display screen in the unlocked state of the terminal device;

[0285] Alternatively, the display screen is displayed in the locked screen state of the terminal device.

[0286] In one feasible embodiment, the processor 801 is further configured to: collect a training sample data set, the training sample data set including a plurality of sample data, the sample data including matching feature information of sample accounts with successful historical matching and actual matching duration of the sample accounts; the matching feature information of the sample accounts including basic matching feature information and reference matching feature information;

[0287] Determine the sample weight of the sample data corresponding to each sample account based on the matching start time of each sample account;

[0288] According to the training sample data set and the sample weight of each sample data in the training sample data set, a matching time prediction model is trained.

[0289] In one feasible embodiment, when the processor 801 executes the training to obtain the matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set, it is specifically configured to: train an initial matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set;

[0290] If the prediction errors of the initial matching duration prediction model for multiple times exceed a preset threshold, a preset number of new sample data are collected to optimize the initial matching duration prediction model to obtain a matching duration prediction model.

[0291] In the embodiment of the present application, the computer program can also execute other machine-readable instructions when run by the processor to execute other methods described in the embodiment. For the specific execution method steps and principles, please refer to the description of the embodiment and will not be repeated here.

[0292] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0293] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0294] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0295] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (English: Read-Only Memory, abbreviated: ROM), a random access memory (English: Random Access Memory, abbreviated: RAM), a disk or an optical disk, and other media that can store program code.

Claims

1. An account matching processing method, characterized in that: include: Obtain basic matching information of the current account to be matched; the basic matching information at least includes the matching start time; Determining reference matching information based on the matching start time, the reference matching information including at least one of the following: average matching duration, number of online accounts, and number of matching accounts in a target historical period before the matching start time; According to the basic matching information and the reference matching information, a pre-trained matching time prediction model is used to determine the matching waiting time of the current account to be matched, and the matching waiting time is displayed through the terminal device corresponding to the current account to be matched.

2. The method according to claim 1, characterized in that The determining of reference matching information according to the matching start time includes: Determining a matching period type according to the matching start time; Determining the target historical period according to the matching start time and the data pulling window size under the matching period type; Obtain account matching data for the target historical period; The average matching duration is determined based on the account matching data of the target historical period.

3. The method according to claim 2, characterized in that Determining the average matching duration based on the account matching data of the target historical period includes: The average matching duration is determined according to matching duration information of each historical account having the same attribute as the current account to be matched during the target historical period.

4. The method according to claim 1, wherein The determining of reference matching information according to the matching start time includes: Determine the number of online accounts under each attribute based on the attribute information of each online account in the application lobby at the start time of the match; According to the attribute information of each matching account at the matching start time, the number of matching accounts under each attribute is determined.

5. The method according to claim 1, wherein The determining of the matching waiting time of the current account to be matched using a pre-trained matching time prediction model based on the basic matching information and the reference matching information includes: Inputting the basic matching information and the reference matching information into the matching time prediction model, and determining the initial matching waiting time of the current account to be matched via the matching time prediction model; According to the matching start time of the current account to be matched, the matching result information of each account in the historical preset time period before the matching start time is collected; Determine the residual sequence based on the matching result information of each account within the historical preset period; The initial matching waiting time of the current account to be matched is corrected according to the residual sequence to determine the matching waiting time of the current account to be matched.

6. The method according to claim 5, characterized in that The collecting, based on the matching start time of the current account to be matched, matching result information of each account within a preset historical period before the matching start time includes: Determining the historical preset time period according to the matching start time and a preset data collection window; The actual matching time of each account and the predicted matching waiting time of each account within the historical preset time period are collected.

7. The method according to claim 6, characterized in that The determining of the residual sequence based on the matching result information of each account within a preset historical period includes: Determine the predicted residual value for each account based on the actual matching time of each account and the predicted matching waiting time of each account; The residual sequence is determined according to the predicted residual value of each account.

8. The method according to claim 7, characterized in that The step of correcting the initial matching waiting time of the current account to be matched according to the residual sequence to determine the matching waiting time of the current account to be matched includes: Determining an average residual based on the residual sequence; According to the average residual and the preset weight, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

9. The method according to claim 7, characterized in that Correcting the initial matching waiting time of the current account to be matched according to the residual sequence to determine the matching waiting time of the current account to be matched includes: Determining whether a residual distribution is skewed based on the residual sequence; If yes, then determining a preset quantile of the residual sequence according to the residual sequence, the preset quantile including: a lower quartile or an upper quartile; According to the preset quantile and the preset weight of the residual sequence, the initial matching waiting time is linearly compensated to obtain the matching waiting time of the current account to be matched.

10. The method according to claim 1, characterized in that Also includes: In response to the application switching operation of the current account to be matched, obtaining the matching waiting time and the current matching time of the current account to be matched; Generate a display screen based on the matching waiting time of the current account to be matched, the current matching time, and a pre-configured display template; The display screen is displayed on the terminal device corresponding to the current account to be matched.

11. The method according to claim 10, characterized in that The generating of a display screen according to the matching waiting time of the current account to be matched, the current matching time and a pre-configured display template includes: Filling the matching waiting time of the current account to be matched into the matching waiting time parameter item in the display template; The currently matched duration acquired in real time is dynamically filled into the currently matched duration parameter item in the display template, and the display screen is generated.

12. The method according to claim 10, characterized in that The displaying of the display screen on the terminal device corresponding to the current account to be matched includes: Displaying the display screen in an unlocked state of the terminal device; Alternatively, the display screen is displayed in a locked screen state of the terminal device.

13. The method according to any one of claims 1 to 12, characterized in that The training process of the matching duration prediction model includes: Collecting a training sample data set, the training sample data set including a plurality of sample data, the sample data including matching feature information of sample accounts with successful historical matching and actual matching duration of the sample accounts; the matching feature information of the sample accounts including basic matching feature information and reference matching feature information; Determine the sample weight of the sample data corresponding to each sample account based on the matching start time of each sample account; The matching duration prediction model is trained based on the training sample data set and the sample weight of each sample data in the training sample data set.

14. The method according to claim 13, characterized in that The training to obtain the matching duration prediction model according to the training sample data set and the sample weight of each sample data in the training sample data set includes: Training an initial matching duration prediction model based on the training sample data set and the sample weight of each sample data in the training sample data set; If the prediction errors of the initial matching duration prediction model exceed a preset threshold value for multiple consecutive times, a preset number of new sample data are collected to optimize the initial matching duration prediction model to obtain the matching duration prediction model.

15. An account matching processing device, characterized in that: include: Acquisition module, determination module, prediction module; The acquisition module is used to obtain basic matching information of the current account to be matched; The basic matching information at least includes the matching start time; The determination module is configured to determine reference matching information based on the matching start time, the reference matching information including at least one of the following: an average matching duration, a number of online accounts, and a number of matching accounts in a target historical period before the matching start time; The prediction module is used to determine the matching waiting time of the current account to be matched based on the basic matching information and the reference matching information using a pre-trained matching time prediction model, and display the matching waiting time through the terminal device corresponding to the current account to be matched.

16. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the program instructions to perform the account matching processing method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which, when executed by a processor, executes the account matching processing method according to any one of claims 1 to 14.

Images