HK40038806B - Resource processing method and device, storage medium and electronic device - Google Patents

Description

Resource processing methods, apparatus, storage media and electronic devices

Technical Field

This invention relates to the field of computers, and more specifically, to a method, apparatus, storage medium, and electronic device for processing resources.

Background Technology

Currently, it is difficult to attract users to share or forward post-transaction activities using current technology, making it difficult to promote the activities and resulting in low user participation.

There is currently no effective solution to the above problems.

Summary of the Invention

This invention provides a method, apparatus, storage medium, and electronic device for processing resources, to at least address the technical problem of low user participation in resource rollback activities in related technologies.

According to one aspect of the present invention, a method for processing resources is provided, comprising:

After the target resource transfer operation is performed on the client logged in to the target account, a prompt message is displayed on the client. The prompt message is used to prompt the execution of the target operation, which is used to transfer a target amount of resources from the target account.

If the target operation is detected to have been performed on the client, a resource rollback parameter corresponding to the target account is determined, wherein the resource rollback parameter includes the probability of rolling back the target number of resources to the target account;

If, based on the probability indicated by the resource rollback parameters, it is determined that the target number of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client, wherein the resource rollback result indicates that the target number of resources has been rolled back to the target account.

According to another aspect of the present invention, a resource processing apparatus is also provided, comprising:

The first display module is used to display a prompt message on the client after the target resource transfer operation is performed on the client logged in by the target account. The prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer a target amount of resources from the target account.

The first determining module is used to determine resource rollback parameters corresponding to the target account when the target operation is detected to have been performed on the client, wherein the resource rollback parameters include the probability of rolling back the target number of resources to the target account;

The second display module is used to display the resource rollback result on the client when it is determined, according to the probability indicated by the resource rollback parameters, that the target number of resources need to be rolled back to the target account. The resource rollback result indicates that the target number of resources has been rolled back to the target account.

Optionally, the first acquisition module includes:

The third acquisition unit is used to acquire the threshold number of resources that need to be transferred to allow the transferred resources to be returned to the account that transferred the resources.

A division unit is used to divide the quantity threshold into the plurality of quantity intervals.

Optionally, the second determining module includes:

The second determining unit is used to determine the product of the total number of accounts and the trigger rate of the target operation to obtain a first product value;

The third determining unit is used to determine the ratio between the number of operations and the total number of operations to obtain a first ratio.

The fourth determining unit is used to determine the product between the first product value and the first ratio to obtain the second product value;

The fifth determining unit is used to determine the second ratio between the backoff ratio corresponding to each quantity interval and the second product value as the probability value corresponding to each quantity interval.

Optionally, the first determining unit includes:

The first determining subunit is used to determine the account identifier list containing the account identifier corresponding to the target account, wherein each account identifier list is used to record accounts belonging to the same account type; or...

The second determining subunit is used to determine the similarity between the target account and an account belonging to the target account type, wherein if the similarity is higher than the target similarity, the account type of the target account is determined to belong to the target account type.

Optionally, the second determining subunit is used for:

The target attribute information of the target account is input into the target neural network model, and the output information of the target neural network model is obtained. The target neural network model is a model obtained by training an initial neural network model using the attribute information corresponding to an account belonging to the target account type.

The output information is determined as the similarity.

Optionally, the device further includes:

The third determining module is used to determine the account that performs the sharing operation on the resource rollback result as an account belonging to the target account type before inputting the target attribute information of the target account into the target neural network model and obtaining the output information of the target neural network model;

The second acquisition module is used to acquire attribute information of a first number of accounts belonging to the target account type and attribute information of a second number of accounts not belonging to the target account type as training samples, wherein the first number is greater than the second number;

The training module is used to train the initial neural network model using the training samples to obtain the target neural network model.

Optionally, the first display module includes:

The first jump unit is used to jump the interface displayed on the client from the resource transfer interface that indicates that the target resource transfer operation has been performed to the active interface;

The first display unit is used to display controls on the active interface to prompt the execution of the target operation;

Specifically, if the target operation is detected to have been performed on the control, it is determined that the target operation has been detected.

Optionally, the second display module includes:

The second jump unit is used to jump the interface displayed on the client from the activity interface to the result interface;

The second display unit is used to display the resource rollback result on the result interface, wherein the resource rollback result includes at least one of the following: information indicating that the target number of resources has been successfully rolled back, the target number, and the rollback path of the target number of resources.

According to another aspect of the present invention, a storage medium is also provided, characterized in that the storage medium stores a computer program, wherein the computer program is configured to execute the method described in any of the preceding embodiments when running.

According to another aspect of the present invention, an electronic device is also provided, including a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to execute the method described in any of the preceding embodiments through the computer program.

In this embodiment of the invention, after a target resource transfer operation is performed on a client logged into the target account, a prompt message is displayed on the client. The prompt message indicates the execution of the target operation, which involves transferring a target amount of resources from the target account. Upon detecting the execution of the target operation on the client, resource rollback parameters corresponding to the target account are determined. These parameters include the probability of rolling back the target amount of resources to the target account. If, based on the probability indicated by the resource rollback parameters, it is determined that the target amount of resources needs to be rolled back to the target account, a resource rollback result is displayed on the client. This result indicates... The method of returning a target number of resources to a target account involves prompting the user to perform a target operation after the user executes the target resource transfer operation on the client. Executing this operation has a chance to return all the target number of resources transferred out through the target resource transfer operation to the target account, thereby attracting user participation. Furthermore, the probability of returning the target number of resources to the target account, and other resource return parameters, are specific to the target account; different accounts have different probabilities of return, thus controlling the cost of the activity. This achieves the technical effect of increasing user participation in resource return activities, thereby solving the technical problem of low user participation in resource return activities in related technologies.

Attached Figure Description

The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

Figure 1 is a schematic diagram of an optional resource processing method according to an embodiment of the present invention;

Figure 2 is a schematic diagram of the application environment of an optional resource processing method according to an embodiment of the present invention;

Figure 3 is a schematic diagram of an optional resource processing method according to an optional embodiment of the present invention;

Figure 4 is a schematic diagram of an optional resource processing method according to an optional embodiment of the present invention;

Figure 5 is a schematic diagram of an optional resource processing method according to an optional embodiment of the present invention;

Figure 6 is a schematic diagram of an optional resource processing method according to an optional embodiment of the present invention;

Figure 7 is a schematic diagram of an optional resource processing apparatus according to an embodiment of the present invention;

Figure 8 is a schematic diagram of an application scenario of an optional resource processing method according to an embodiment of the present invention; and

Figure 9 is a schematic diagram of an optional electronic device according to an embodiment of the present invention.

Detailed Implementation

To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

According to one aspect of the present invention, a method for processing resources is provided, as shown in FIG1, the method comprising:

S102, After the target resource transfer operation is performed on the client logged in by the target account, a prompt message is displayed on the client. The prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer the target amount of resources from the target account.

S104, if the target operation is detected to have been performed on the client, determine the resource rollback parameters corresponding to the target account, wherein the resource rollback parameters include the probability of rolling back the target amount of resources to the target account;

S106, if it is determined according to the probability indicated by the resource rollback parameters that the target number of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client, wherein the resource rollback result is used to indicate that the target number of resources have been rolled back to the target account.

Optionally, in this embodiment, the above-described resource processing method can be applied to the hardware environment constituted by the client 202 shown in FIG2. As shown in FIG2, the client 202 is installed on the terminal device 204. After the target account logs in on the client 202 and performs the target resource transfer operation on the client 202, a prompt message is displayed on the client 202. The prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer the target amount of resources from the target account. When the client 202 detects that the target operation has been executed, the resource rollback parameters corresponding to the target account are determined. The resource rollback parameters include the probability of rolling back the target amount of resources to the target account. If it is determined according to the probability indicated by the resource rollback parameters that the target amount of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client 202. The resource rollback result is used to indicate that the target amount of resources has been rolled back to the target account.

Optionally, in this embodiment, the resource processing method described above can be applied, but is not limited to, scenarios involving the processing of resources transferred from a client. The client can be, but is not limited to, various types of applications, such as online education applications, instant messaging applications, social networking applications, game applications, shopping applications, browser applications, financial applications, multimedia applications, live streaming applications, etc. Specifically, it can be applied, but is not limited to, scenarios involving the processing of resources transferred in the aforementioned instant messaging applications, or scenarios involving the processing of resources in the aforementioned game applications, to improve user participation in resource rollback activities. The above is merely an example, and this embodiment does not impose any limitations on it.

Optionally, in this embodiment, the target account is an account registered on the application corresponding to the client. The target account can use the client to perform resource transfer operations, transferring resources to other accounts or to the application corresponding to the client. For example, the target account can be an instant messaging account, and the target account can use the payment function provided on the instant messaging application client to perform operations such as transferring money or making payments to friends or merchants.

Optionally, in this embodiment, the resources mentioned above may include, but are not limited to, funds, currency, trade goods, props, equipment, etc.

Optionally, in this embodiment, the above-mentioned prompts may be, but are not limited to, prompts to perform the target operation in the form of text or animation.

Optionally, in this embodiment, the target operation may include, but is not limited to, shaking, clicking, swiping, and touching operations. Alternatively, the target operation may be a combination of one or more more interesting operations. For example, in a game, if the target account successfully completes a level by performing multiple operations according to the game instructions on the client, then the target account has performed the target operation.

Optionally, in this embodiment, the resource rollback parameters include the probability of rolling back the target number of resources to the target account. They may also include any parameters used to determine whether to roll back the target number of resources to the target account. For example, parameters used to calculate the probability of rolling back the target number of resources to the target account, information used to indicate whether to roll back the target number of resources to the target account, etc.

Optionally, in this embodiment, if it is determined according to the probability indicated by the resource rollback parameters that the target number of resources needs to be rolled back to the target account, the server corresponding to the client can perform the resource rollback operation, and when the rollback is successful, indicate to the client that the rollback is successful, and the client displays the resource rollback result on the display interface.

In an optional implementation, as shown in Figure 3, after the target account performs a target resource transfer operation on the instant messaging application client, a prompt message "Shake it for a surprise, a free order prize awaits you" is displayed on the client. This prompt message indicates that the target operation "shake the terminal device" has been performed, and the target resource transfer operation involves transferring 157 yuan from the target account to Merchant A. Upon detecting that the terminal device shaking operation has been performed on the client, resource rollback parameters corresponding to the target account are determined. These parameters include a 37% probability of returning 157 yuan to the target account. If the probability indicated by the resource rollback parameters determines that 157 yuan needs to be returned to the target account, the client displays the resource rollback result "Congratulations on winning the free order prize."

As can be seen, through the above steps, after the user performs the target resource transfer operation on the client, the user is prompted to perform the target operation. Executing the target operation has a chance to return all the resources transferred out through the target resource transfer operation to the target account, thereby attracting users to participate in the activity. At the same time, the resource return parameters, such as the probability of returning the target amount of resources to the target account, are corresponding to the target account, and the probability of return is different for different accounts, thereby controlling the expenditure of activity costs. This achieves the technical effect of increasing user participation in the resource return activity, and thus solves the technical problem of low user participation in resource return activities in related technologies.

As an optional approach, determining the resource rollback parameters corresponding to the target account includes:

S1, Determine the target account type to which the target account belongs;

S2, obtain the probability distribution information corresponding to the target account type. The probability distribution information includes multiple quantity intervals and multiple probability values that correspond one-to-one. The probability value corresponding to each quantity interval is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the quantity of transferred resources falls into each quantity interval.

S3, obtain the target probability value corresponding to the target quantity range into which the target quantity falls from multiple corresponding quantity ranges and multiple probability values, wherein the resource rollback parameter includes the target probability value.

Optionally, in this embodiment, accounts of different account types may, but are not limited to, correspond to different probability distribution information. In other words, configuring different probability distribution information for accounts of different account types can effectively control activity costs and effectiveness. Different probability distribution information can be configured for different account types to meet different activity requirements.

Optionally, in this embodiment, the target account type may include, but is not limited to: users who love to share (i.e., user accounts that share events related to rollback resources), student users (e.g., accounts of high school students, university students, and graduate students), high-spending users (e.g., accounts of users with an average monthly spending of over 20,000 yuan), etc.

Optionally, in this embodiment, different quantity ranges can be configured with the same or different probability values, so that while allowing users to experience the randomness of resource rollback, the cost of resource rollback activities can be effectively controlled.

As an optional approach, before obtaining the probability distribution information corresponding to the target account type, the following steps are also included:

S1, obtain the average value of rollback resources corresponding to multiple quantity ranges and target account types;

S2, allocate a rollback ratio to each quantity interval based on the average value, where the rollback ratio is the ratio between the number of rollback resources falling into each quantity interval and the total number of rollback resources falling into multiple quantity intervals;

S3. Based on the rollback ratio corresponding to each quantity interval, the total number of accounts belonging to the target account type on the client's application, the trigger rate of the target operation, the number of resource transfer operations corresponding to each quantity interval, and the total number of resource transfer operations executed on the client's application, determine the probability value corresponding to each quantity interval to obtain probability distribution information. Among them, the trigger rate of the target operation is used to indicate the probability of executing the target operation in the client's application.

Optionally, in this embodiment, the rollback ratio can be allocated to each quantity range based on the predicted or preset average value of the rollback resources, but is not limited to.

Optionally, in this embodiment, accounts of different account types may, but are not limited to, correspond to different average values of rollback resources. For example, since users who like to share may take screenshots and share their free reward, they can configure more high-value free rewards compared to ordinary users. After multiple rounds of operational testing and optimization, the allocation ratios have stabilized as follows: For the "Love Sharing" user package, the average free order value is 20 yuan (i.e., the average of the returned resources mentioned above). The return rate is 31% for the quantity range [5,10], 51% for the quantity range (10,30], 17% for the quantity range (30,50], 0.9% for the quantity range (50,100], and 0.1% for the quantity range (100,200]. For the "Regular User Package," the average free order value is 10 yuan. The return rate is 85% for the quantity range [5,10], 8.4% for the quantity range (10,30], 6.5% for the quantity range (30,50], 0.08% for the quantity range (50,100], and 0.02% for the quantity range (100,200).

As an optional approach, obtaining multiple quantity ranges includes:

S1, obtain the threshold number of resources that need to be transferred to allow the transferred resources to be returned to the account that transferred the resources;

S2 divides the quantity threshold into multiple quantity intervals.

Optionally, in this embodiment, during resource rollback activities, the threshold number of resources required to roll back the transferred resources to the account that transferred the resources can be configured or automatically predicted, but is not limited to. That is, the upper and lower limits of resource rollback can be configured to control costs. For example, taking monetary payment as an example, by observing the distribution and sharing rate of several rounds of free lottery, the breakpoint relationship between the free lottery amount and the sharing rate can be found, as shown in Figure 4. The intervals with similar sharing rates are merged, that is, the intervals are divided according to the similarity of the sharing rate through the correlation analysis of the free lottery amount and the sharing rate. In order to facilitate cost management and reduce the fluctuation of free lottery costs, the range of the amount interval should not be too large. Therefore, the free lottery interval [5,200] (i.e. the above quantity threshold) is divided into five major amount interval levels (i.e. the above multiple quantity intervals): [5,10], (10,30], (30,50], (50,100], (100,200).

As an optional approach, the probability value for each quantity range is determined based on the rollback ratio corresponding to each quantity range, the total number of accounts belonging to the target account type on the client's application, the trigger rate of the target operation, the number of resource transfer operations corresponding to each quantity range, and the total number of resource transfer operations executed on the client's application.

S1, determine the product of the total number of accounts and the trigger rate of the target operation to obtain the first product value;

S2, determine the ratio between the number of operations and the total number of operations to obtain the first ratio;

S3, determine the product between the first product value and the first ratio to obtain the second product value;

S4, the second ratio between the backoff ratio corresponding to each quantity interval and the second product value is determined as the probability value corresponding to each quantity interval.

Optionally, in this embodiment, based on operational experience, it is known that for a single user, the distribution of transaction order amounts on weekends is volatile and unstable. However, for a large user base, the overall transaction amount distribution ratio of all orders on weekends is relatively stable. This can be understood as the probability that a user making a payment will incur a specific amount of expenditure on weekends being predictable. Therefore, in order to achieve a uniform distribution of free orders within a specific amount range on the same day, the probability value corresponding to each quantity range can be determined using, but is not limited to, the following formula:

The probability of winning a free order in each quantity range = the number of free orders in that range / the estimated number of participants in that range's accounts.

= Number of free orders in this range / Expected number of participating accounts * Percentage of total orders paid in this price range across the market

= Number of free orders in this range / (Total number of accounts * Activity participation rate (i.e., the first product value above)) * (Number of payment orders in this range in the overall market / Total number of payment orders in the overall market (i.e., the first ratio above)) (i.e., the second product value above).

The above formula achieves two goals. First, it distributes a specific number of freebies evenly using statistical principles, mimicking the random distribution of bonuses. Furthermore, this method is scalable; besides distributing a specific number of freebies evenly to the "Sharing" user group, it can also be applied to any defined target user group. That is, the target account type mentioned above can be replaced with any user group whose median freebie distribution rate needs to be calculated, such as the "Sharing" user group, students, etc.

As an optional approach, determining the target account type includes:

S1, determine the list of account identifiers corresponding to the target account, where each list of account identifiers records accounts belonging to the same account type; or,

S2, determine the similarity between the target account and accounts belonging to the target account type, wherein if the similarity is higher than the target similarity, determine that the account type of the target account belongs to the target account type.

Optionally, in this embodiment, the accounts registered on the client can be categorized, but not limited to, and the account identifiers of each category can be recorded in an account identifier list. The account type of the target account is determined by searching the account identifier list where the target account's account identifier is located. Alternatively, the account type of the target account can also be determined by the similarity between the target account and accounts of known account types.

As an optional approach, determining the similarity between the target account and accounts belonging to the target account type includes:

S1, Input the target attribute information of the target account into the target neural network model as input information, and obtain the output information of the target neural network model. The target neural network model is a model obtained by training the initial neural network model using the attribute information corresponding to the account belonging to the target account type.

S2, the output information is determined as similarity.

Optionally, in this embodiment, the model can be trained using machine learning to obtain a target neural network model, and then the similarity between accounts can be determined using the target neural network model.

As an optional approach, before inputting the target account's target attribute information as input into the target neural network model and obtaining the output information of the target neural network model, the method further includes:

S1, the account that performs the sharing operation on the resource rollback result is identified as an account belonging to the target account type;

S2, obtain the attribute information of a first number of accounts belonging to the target account type and the attribute information of a second number of accounts not belonging to the target account type as training samples, wherein the first number is greater than the second number;

S3, use training samples to train the initial neural network model to obtain the target neural network model.

Optionally, in this embodiment, the target neural network model can be trained for users who like to share resources. Users who like to share resources can refer to, but are not limited to, user accounts that perform sharing operations on resource rollback results.

Optionally, in this embodiment, since the targeted users share certain similar characteristics, deviating from the principle of randomness, by allocating a certain proportion of freebies to non-target users, all users in the overall pool can have a chance to win a freebie, thus creating randomness, increasing the sense of randomness in winning, and eliminating traces of human intervention. In the machine learning process for users who love sharing, if the user samples are all pre-selected manually, there will be bias, affecting the final effect of the machine learning model. Therefore, each machine learning sample can include randomly generated samples (i.e., attribute information of a second number of accounts that do not belong to the target account type), which can increase the comprehensiveness and accuracy of the learning results.

As an optional solution, after performing the target resource transfer operation on the client logged into the target account, the client displays the following prompt information:

S1, the interface displayed on the client jumps from the resource transfer interface, which indicates that the target resource transfer operation has been performed, to the activity interface;

S2 displays controls on the activity interface to prompt for the execution of the target operation;

Specifically, if a target operation is detected to have been performed on a control, then the target operation is determined to have been performed.

Optionally, in this embodiment, the resource transfer interface is an interface used to indicate that a target resource transfer operation has been performed. For example, the resource transfer interface may include, but is not limited to, a payment interface, a transaction interface, a transfer interface, etc.

Optionally, in this embodiment, after displaying the fund transfer interface to remind the user of the resource transfer result, the interface can be redirected to an activity interface to remind the user to participate in the activity. The activity interface can display controls for performing the target operation, which may include, but are not limited to, buttons, icons, text, animations, images, etc. The interface redirection can be automatic or triggered by an operation of the target account.

In an optional implementation, as shown in Figure 5, after a user with the target account performs a payment operation on the instant messaging application client, the client displays the payment result, such as: "50 yuan has been successfully paid to Zhang Moumou." The client stays on the screen for 3 seconds. Alternatively, after detecting that the user clicks the "Complete" button displayed on the screen, the client is redirected to the lottery screen for the free order activity, and the screen displays the prompt message "Shake it for a surprise and win a free order." If the user is detected to have performed a shaking operation on the client, it can be determined that the target account has performed the target operation.

As an optional solution, displaying resource rollback results on the client side includes:

S1, the interface displayed on the client jumps from the activity interface to the results interface;

S2, display the resource rollback results on the results interface, wherein the resource rollback results include at least one of the following: information indicating that the target number of resources were successfully rolled back, the target number, and the rollback path of the target number of resources.

Optionally, in this embodiment, if it is determined according to the probability indicated by the resource rollback parameters that a target number of resources need to be rolled back to the target account, the user can be prompted with the resource rollback result by displaying a result interface through interface redirection.

Optionally, in this embodiment, the resource rollback result displayed includes at least one of the following: information indicating a successful rollback of a target number of resources, the target number, and the rollback path for the target number of resources. That is, the user can be prompted with the successful rollback result, the number of resources rolled back, and information such as the account or location where the resources were rolled back. For example, the resource rollback result may include: "Congratulations on receiving a free order reward! This free order is 200 yuan, and it has been returned to the balance of payment account Li Moumou."

In one optional implementation, as shown in Figure 6, after a user with the target account performs a payment operation on the instant messaging application client, the client displays the payment result, for example: 50 yuan has been successfully paid to Mr. Zhang. The client remains on this screen for 3 seconds. Alternatively, if the user clicks the "Complete" button displayed on the screen, the client is redirected to a free order lottery page. The page displays the message "Click here for a surprise, win a free order," and a "Click here" button is displayed. If the user clicks this button, the resource rollback parameters corresponding to the target account are determined. If, according to the probability indicated by the resource rollback parameters, it is determined that 50 yuan needs to be refunded to the target account, the client's interface jumps from the lottery page to the result page, displaying "Congratulations on winning a free order reward from this application. This payment of 50.00 yuan has been returned to your wallet."

It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

According to another aspect of the present invention, a resource processing apparatus for implementing the above-described resource processing method is also provided, as shown in FIG7, the apparatus comprising:

The first display module 72 is used to display a prompt message on the client after the target resource transfer operation is performed on the client logged in by the target account. The prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer out the target amount of resources from the target account.

The first determining module 74 is used to determine the resource rollback parameters corresponding to the target account when the target operation is detected to have been performed on the client. The resource rollback parameters include the probability of rolling back the target number of resources to the target account.

The second display module 76 is used to display the resource rollback result on the client when it is determined according to the probability indicated by the resource rollback parameters that a target number of resources need to be rolled back to the target account. The resource rollback result indicates that the target number of resources have been rolled back to the target account.

As an optional approach, the first determining module includes:

The first determining unit is used to determine the target account type to which the target account belongs;

The first acquisition unit is used to acquire the probability distribution information corresponding to the target account type. The probability distribution information includes multiple quantity intervals and multiple probability values that correspond one-to-one. The probability value corresponding to each quantity interval is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the quantity of transferred resources falls into each quantity interval.

The second acquisition unit is used to acquire the target probability value corresponding to the target quantity range into which the target quantity falls from a plurality of one-to-one corresponding quantity ranges and a plurality of probability values, wherein the resource rollback parameter includes the target probability value.

As an optional solution, the above-mentioned device further includes:

The first acquisition module is used to acquire multiple quantity ranges and the average value of rollback resources corresponding to the target account type before acquiring the probability distribution information corresponding to the target account type;

The allocation module is used to allocate a rollback ratio to each quantity range based on the average value, wherein the rollback ratio is the ratio between the number of rollback resources falling into each quantity range and the total number of rollback resources falling into multiple quantity ranges.

The second determining module is used to determine the probability value corresponding to each quantity interval based on the rollback ratio corresponding to each quantity interval, the total number of accounts belonging to the target account type on the client's application, the trigger rate of the target operation, the number of resource transfer operations corresponding to each quantity interval, and the total number of resource transfer operations executed on the client's application, thereby obtaining probability distribution information. The trigger rate of the target operation is used to indicate the probability of executing the target operation in the client's application.

As an optional solution, the first acquisition module includes:

The third acquisition unit is used to acquire the threshold number of resources that need to be transferred to allow the transferred resources to be returned to the account that transferred the resources.

The division unit is used to divide the quantity threshold into multiple quantity intervals.

As an optional solution, the second determining module includes:

The second determining unit is used to determine the product of the total number of accounts and the trigger rate of the target operation to obtain the first product value;

The third determining unit is used to determine the ratio between the number of operations and the total number of operations, and obtain the first ratio.

The fourth determining unit is used to determine the product between the first product value and the first ratio to obtain the second product value;

The fifth determining unit is used to determine the probability value corresponding to each quantity interval by the second ratio between the backoff ratio corresponding to each quantity interval and the second product value.

As an optional approach, the first determining unit includes:

The first determining subunit is used to determine the list of account identifiers corresponding to the target account, wherein each list of account identifiers records accounts belonging to the same account type; or...

The second determining subunit is used to determine the similarity between the target account and an account belonging to the target account type. If the similarity is higher than the target similarity, the account type of the target account is determined to belong to the target account type.

As an optional approach, the second determining subunit is used for:

The target account's target attribute information is input into the target neural network model, and the output information of the target neural network model is obtained. The target neural network model is a model obtained by training the initial neural network model using the attribute information corresponding to the account belonging to the target account type.

The output information is determined as similarity.

As an optional solution, the above-mentioned device further includes:

The third determination module is used to determine the account that performs the sharing operation on the resource rollback result as an account belonging to the target account type before inputting the target attribute information of the target account into the target neural network model and obtaining the output information of the target neural network model.

The second acquisition module is used to acquire attribute information of a first number of accounts belonging to the target account type and attribute information of a second number of accounts not belonging to the target account type as training samples, wherein the first number is greater than the second number.

The training module is used to train the initial neural network model using training samples to obtain the target neural network model.

As an optional solution, the first display module includes:

The first jump unit is used to jump the interface displayed on the client from the resource transfer interface that indicates that the target resource transfer operation has been performed to the active interface;

The first display unit is used to display controls on the active interface to prompt for the execution of the target operation;

Specifically, if a target operation is detected to have been performed on a control, then the target operation is determined to have been performed.

As an optional solution, the second display module includes:

The second jump unit is used to jump from the activity interface to the result interface on the client side;

The second display unit is used to display the resource rollback results on the result interface, wherein the resource rollback results include at least one of the following: information indicating that the target number of resources were successfully rolled back, the target number, and the rollback path of the target number of resources.

The application environment of this invention embodiment can be, but is not limited to, the application environment described in the above embodiments, and will not be repeated here. This invention embodiment provides an optional specific application example for implementing the above-described real-time communication connection method.

As an optional embodiment, the above-mentioned resource processing method can be applied, but is not limited to, the scenario of a transaction payment lottery for a free reward activity as shown in Figure 8. In this scenario, in the operation of a long-term large-scale online platform activity, a set of activity configuration script templates was proposed for the first time using the statistical theory of large numbers, realizing the standardization and simplification of the operation activity configuration. At the same time, through numerical planning and design, the randomized distribution of activity prizes was realized, allowing prizes to be evenly distributed in daily transactions. After studying the relationship between the free order price range and sharing, the free order price range was divided, realizing more refined cost management. Through the distribution of several rounds of free orders and the observation of the sharing rate, the breakpoint relationship between the free order amount and the sharing rate was determined, and the ranges with similar sharing rates were merged. In order to facilitate cost management and reduce the fluctuation of free order costs, the range of amount should not be too large. Therefore, the free order range [5,200] is divided into five major amount range levels: [5,10], (10,30], (30,50], (50,100], (100,200).

To optimize the visible benefits of freebies (ensuring that the average freebie perceived by users is greater than the average cost of the freebies they actually pay), we extracted the "Love Sharing" user package and assigned specific numbers of freebies to each of its segments. Since the sharing of freebie screenshots by "Love Sharing" users ensures their influence on the campaign, they are assigned more high-value freebies compared to ordinary users. After multiple rounds of operational testing and optimization, the current allocation ratios are basically stable as follows: For users with the "Love Sharing" package, the average free order value is 20 yuan, with [5,10] accounting for 31%, (10,30] for 51%, (30,50] for 17%, (50,100] for 0.9%, and (100,200] for 0.1%. For regular users, the average free order value is 10 yuan, with [5,10] for 85%, (10,30] for 8.4%, (30,50] for 6.5%, (50,100] for 0.08%, and (100,200] for 0.02%. (Compared to the general user base, users with the "Love Sharing" package have a higher proportion of free orders in the high-value range, meaning these users are more likely to receive free orders in the medium to high value range.)

During the campaign operation, through summarizing operational experience, it was observed that although the distribution of transaction order amounts for individual users fluctuated and was unstable over the weekend, for the large payment platform with a user base of over 200 million, the distribution ratio of all orders over the weekend was relatively stable. This can be understood as the probability of a payment user making a specific expenditure over the weekend being predictable. Therefore, to ensure the even distribution of free orders within a specific amount range on the day of the campaign, the following formula was used to determine the probability of winning a free order within a specific amount range:

Probability of winning a free order within a specific amount range = Number of free orders within that range / Expected number of participants in the package within that range

= Number of free orders in this range / Expected number of participants in the package * Percentage of total orders paid in this price range across the market

= Number of free orders in this range / (Total number of participants in the package * Activity participation rate) * (Number of paid orders in this range across the entire market / Total number of paid orders across the entire market)

The above formula achieves the goal of distributing a specific number of freebies evenly (randomized distribution) using statistical principles. This method is scalable; besides distributing a specific number of freebies evenly to the "Sharing" user group, it can also be applied to any defined target user group.

During the prize allocation process, a specific proportion of free prizes were distributed to non-target user groups. This allocation serves two purposes: Firstly, since targeted users share similar characteristics, randomness is compromised. Distributing a certain percentage of free prizes to non-target users ensures that all users have a chance to win, introducing randomness, increasing the sense of chance in winning, and eliminating traces of human intervention. Secondly, in the machine learning process for the "sharing" population, if the population samples are all pre-selected manually, bias will exist, affecting the final effect of the machine learning model. Therefore, randomly generated samples are added to each machine learning sample, which increases the comprehensiveness and accuracy of the learning results.

As shown in Figure 8, after user Xiaojia pays 200 yuan, a prompt message is displayed on the client. This prompt message prompts the user to perform the target operation. Upon detecting that Xiaojia has performed the target operation on the client, the resource return parameters corresponding to Xiaojia's account are determined. Xiaojia is a "Sharing" user, and the probability of winning within the range of (100, 200) is the resource return parameter, for example, 0.85%. If the probability indicated by the resource return parameter determines that the target quantity of resources needs to be returned to the target account, the resource return result is displayed on the client. The resource return result includes: "Congratulations on winning a free order reward! This payment of 200.00 yuan has been returned to your WeChat Wallet."

According to another aspect of the present invention, an electronic device for implementing the processing of the above-described resources is also provided, as shown in FIG9. The electronic device includes: one or more (only one is shown in the figure) processors 902, memory 904, sensor 906, encoder 908, and transmission device 910. The memory stores a computer program, and the processor is configured to execute the steps of any of the above-described method embodiments through the computer program.

Optionally, in this embodiment, the electronic device may be located in at least one of a plurality of network devices in a computer network.

Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

S1, after the target resource transfer operation is performed on the client logged in to the target account, a prompt message is displayed on the client, wherein the prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer out the target amount of resources from the target account;

S2, if the target operation is detected to have been performed on the client, determine the resource rollback parameters corresponding to the target account, wherein the resource rollback parameters include the probability of rolling back the target number of resources to the target account;

S3, if it is determined according to the probability indicated by the resource rollback parameters that the target number of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client, wherein the resource rollback result is used to indicate that the target number of resources has been rolled back to the target account.

Optionally, those skilled in the art will understand that the structure shown in Figure 9 is merely illustrative, and the electronic device may also be a smartphone (such as an Android phone, iOS phone, etc.), tablet computer, PDA, mobile internet device (MID), PAD, and other terminal devices. Figure 9 does not limit the structure of the aforementioned electronic device. For example, the electronic device may also include more or fewer components (such as network interfaces, display devices, etc.) than shown in Figure 9, or have a different configuration than that shown in Figure 9.

The memory 904 can be used to store software programs and modules, such as program instructions/modules corresponding to the resource processing methods and apparatus in this embodiment of the invention. The processor 902 executes various functional applications and data processing by running the software programs and modules stored in the memory 904, thereby realizing the control method of the aforementioned target component. The memory 904 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 904 may further include memory remotely located relative to the processor 902, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The aforementioned transmission device 910 is used to receive or send data via a network. Specific examples of the network may include wired and wireless networks. In one example, the transmission device 910 includes a Network Interface Controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 910 is a radio frequency (RF) module used for wireless communication with the Internet.

Specifically, memory 904 is used to store application programs.

Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

S1, after the target resource transfer operation is performed on the client logged in to the target account, a prompt message is displayed on the client, wherein the prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer out the target amount of resources from the target account;

S2, if the target operation is detected to have been performed on the client, determine the resource rollback parameters corresponding to the target account, wherein the resource rollback parameters include the probability of rolling back the target number of resources to the target account;

S3, if it is determined according to the probability indicated by the resource rollback parameters that the target number of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client, wherein the resource rollback result is used to indicate that the target number of resources has been rolled back to the target account.

Optionally, the storage medium is also configured to store a computer program for performing the steps included in the methods of the above embodiments, which will not be described again in this embodiment.

Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

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

Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims (12)

1. A method for processing a resource, characterized in that it includes: After the target resource transfer operation is performed on the client logged in to the target account, a prompt message is displayed on the client. The prompt message is used to prompt the execution of the target operation, which is used to transfer a target amount of resources from the target account. When the target operation is detected to have been performed on the client, the average value of multiple quantity intervals and the return resources corresponding to the target account type to which the target account belongs is obtained. The probability value corresponding to each of the multiple quantity intervals is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the number of transferred resources falls into each quantity interval. A rollback ratio is allocated to each quantity interval based on the average value, wherein the rollback ratio is the ratio between the number of rollback resources falling into each quantity interval and the total number of rollback resources falling into the multiple quantity intervals; The probability distribution information is obtained by determining the probability value corresponding to each quantity interval based on the rollback ratio corresponding to each quantity interval, the total number of accounts belonging to the target account type on the application corresponding to the client, the trigger rate of the target operation, the number of resource transfer operations corresponding to each quantity interval, and the total number of resource transfer operations performed on the application corresponding to the client. This includes: determining the product of the total number of accounts and the trigger rate of the target operation to obtain a first product value, wherein the trigger rate of the target operation indicates the probability of performing the target operation in the application corresponding to the client; determining the ratio between the number of operations and the total number of operations to obtain a first ratio; determining the product between the first product value and the first ratio to obtain a second product value; and determining the second ratio between the rollback ratio corresponding to each quantity interval and the second product value as the probability value corresponding to each quantity interval to obtain the probability distribution information corresponding to the account. The probability distribution information includes a one-to-one correspondence between the plurality of quantity intervals and the plurality of probability values. The target probability value corresponding to the target quantity interval into which the target quantity falls is obtained from the multiple quantity intervals and multiple probability values that correspond one-to-one. The resource rollback parameter includes the target probability value, which is used to indicate the probability of rolling back the target quantity of resources to the target account. If it is determined, according to the probability indicated by the resource rollback parameters, that the target number of resources needs to be rolled back to the target account, the resource rollback result is displayed on the client, wherein the resource rollback result is used to indicate that the target number of resources has been rolled back to the target account. 2. The method according to claim 1, wherein determining the resource rollback parameters corresponding to the target account includes: Determine the target account type to which the target account belongs; Obtain the probability distribution information corresponding to the target account type, wherein the probability distribution information includes multiple quantity intervals and multiple probability values that correspond one-to-one, and the probability value corresponding to each quantity interval is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the quantity of transferred resources falls into each quantity interval; The target probability value corresponding to the target quantity interval into which the target quantity falls is obtained from the multiple corresponding quantity intervals and multiple probability values, wherein the resource rollback parameter includes the target probability value. 3. The method according to claim 1, wherein obtaining the plurality of quantity intervals includes: Get the threshold number of resources that need to be transferred to allow the transferred resources to be returned to the account that transferred the resources; The quantity threshold is divided into the plurality of quantity intervals. 4. The method according to claim 2, wherein determining the target account type to which the target account belongs includes: Determine the list of account identifiers corresponding to the target account, wherein each list of account identifiers is used to record accounts belonging to the same account type; or, Determine the similarity between the target account and an account belonging to the target account type, wherein if the similarity is higher than the target similarity, determine that the account type of the target account belongs to the target account type. 5. The method according to claim 4, wherein determining the similarity between the target account and an account belonging to the target account type includes: The target attribute information of the target account is input into the target neural network model, and the output information of the target neural network model is obtained. The target neural network model is a model obtained by training an initial neural network model using the attribute information corresponding to an account belonging to the target account type. The output information is determined as the similarity. 6. The method according to claim 5, characterized in that, before inputting the target attribute information of the target account as input information into the target neural network model and obtaining the output information of the target neural network model, the method further includes: The account that performs the sharing operation on the resource rollback result is identified as an account belonging to the target account type; Obtain attribute information of a first number of accounts belonging to the target account type and attribute information of a second number of accounts not belonging to the target account type as training samples, wherein the first number is greater than the second number; The initial neural network model is trained using the training samples to obtain the target neural network model. 7. The method according to claim 1, characterized in that, after the target resource transfer operation is performed on the client logged in by the target account, displaying the prompt information on the client includes: The interface displayed on the client jumps from the resource transfer interface, which indicates that the target resource transfer operation has been performed, to the activity interface; A control is displayed on the activity interface to prompt the user to perform the target operation; Specifically, if the target operation is detected to have been performed on the control, it is determined that the target operation has been detected. 8. The method according to claim 7, characterized in that displaying the resource rollback result on the client includes: The interface displayed on the client jumps from the activity interface to the results interface; The resource rollback results are displayed on the results interface, wherein the resource rollback results include at least one of the following: information indicating that the target number of resources has been successfully rolled back, the target number, and the rollback path of the target number of resources. 9. A resource processing apparatus, characterized in that it comprises: The first display module is used to display a prompt message on the client after the target resource transfer operation is performed on the client logged in by the target account. The prompt message is used to prompt the execution of the target operation, and the target resource transfer operation is used to transfer a target amount of resources from the target account. The device is further configured to, when the target operation is detected to have been performed on the client, obtain the average value of multiple quantity intervals and the target account type to which the target account belongs, wherein the probability value corresponding to each of the multiple quantity intervals is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the quantity of the transferred resources falls into each of the quantity intervals. The device is further configured to allocate a rollback ratio to each quantity interval based on the average value, wherein the rollback ratio is the ratio between the number of rollback resources falling into each quantity interval and the total number of rollback resources falling into the plurality of quantity intervals. The device is further configured to determine the probability value corresponding to each quantity interval based on the rollback ratio corresponding to each quantity interval, the total number of accounts belonging to the target account type on the application corresponding to the client, the trigger rate of the target operation, the number of resource transfer operations corresponding to each quantity interval, and the total number of resource transfer operations performed on the application corresponding to the client, thereby obtaining the probability distribution information. This includes: determining the product of the total number of accounts and the trigger rate of the target operation to obtain a first product value, wherein the trigger rate of the target operation is used to indicate the probability of performing the target operation in the application corresponding to the client; determining the ratio between the number of operations and the total number of operations to obtain a first ratio; determining the product between the first product value and the first ratio to obtain a second product value; and determining the second ratio between the rollback ratio corresponding to each quantity interval and the second product value as the probability value corresponding to each quantity interval to obtain the probability distribution information corresponding to the account. The probability distribution information includes a one-to-one correspondence of multiple quantity intervals and multiple probability values. The device is further configured to obtain the target probability value corresponding to the target quantity interval into which the target quantity falls from the one-to-one correspondence of the plurality of quantity intervals and the plurality of probability values, wherein the resource rollback parameter includes the target probability value, and the target probability value is used to indicate the probability of rolling back the target quantity of resources to the target account; The second display module is used to display the resource rollback result on the client when it is determined, according to the probability indicated by the resource rollback parameters, that the target number of resources need to be rolled back to the target account. The resource rollback result indicates that the target number of resources has been rolled back to the target account. 10. The apparatus according to claim 9, wherein the apparatus further comprises: The first determining unit is used to determine the target account type to which the target account belongs; The first acquisition unit is used to acquire probability distribution information corresponding to the target account type. The probability distribution information includes multiple quantity intervals and multiple probability values that correspond one-to-one. The probability value corresponding to each quantity interval is used to indicate the probability of returning the transferred resources to the account that transferred the resources when the quantity of transferred resources falls into each quantity interval. The second acquisition unit is used to acquire the target probability value corresponding to the target quantity interval into which the target quantity falls from the multiple quantity intervals and multiple probability values that correspond to each other, wherein the resource rollback parameter includes the target probability value. 11. A storage medium, characterized in that the storage medium stores a computer program, wherein the computer program is configured to execute the method described in any one of claims 1 to 8 when it is run. 12. An electronic device comprising a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to perform the method of any one of claims 1 to 8 via the computer program.