Load Balancing Method, Device, Computer Equipment and Storage Medium of To-Do System

Abstract

The present application provides a load balancing method, device, computer device and storage medium for a to-do system. Among them, the method includes: when the first to-do item to be processed in the current period meets the preset conditions, obtaining a supplementary item set, where the supplementary item set includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods, and N is a positive integer; calculating the second score of each second to-do item in the current period; when the difference between the second score and the first score of any second to-do item is greater than the threshold, adding any second to-do item to the to-do items to be processed in the current period. This method not only realizes the load balancing of the to-do system, but also changes the processing of the added to-do items from the initial processing period to the current period, improving the global to-do connection rate.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a load balancing method, device, computer device, and storage medium for a to-do system. Background Art

[0002] In a to-do system, such as a collection system, when collecting overdue payments, the existing collection system usually allocates the to-be-collected items for the current day in advance in the early morning. Subsequently, the collection system conducts item collection based on the allocation result in the early morning.

[0003] However, in actual execution, situations may occur where the payment for an item allocated in the early morning has been cleared before the collection period, or the collection is cancelled, etc. In such cases, the collection system may have a situation where the number of to-be-collected items in a certain period is less than the actual number of collection items, resulting in a decrease in the load during the current period and the problem of uneven load of the collection system. Summary of the Invention

[0004] This application proposes a load balancing method, device, computer device, and storage medium for a to-do system.

[0005] An embodiment of one aspect of this application proposes a load balancing method for a to-do system, including:

[0006] When a first to-do item to be processed in the current period meets a preset condition, obtain a supplementary item set, where the supplementary item set includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods respectively, and N is a positive integer;

[0007] Calculate the second score of each second to-do item in the current period;

[0008] When the difference between the second score and the first score of any second to-do item is greater than a threshold, add the any second to-do item to the to-do items to be processed in the current period.

[0009] In a possible implementation manner of an embodiment of one aspect of this application, the obtaining of the supplementary item set includes:

[0010] Obtain the initial processing period to which each to-do item belongs and the reference scores corresponding to different periods;

[0011] When the period corresponding to the highest reference score of any to-do item is different from the initial processing period to which it belongs and the initial processing period is not the current period, determine the any to-do item as a supplementary item.

[0012] In a possible implementation manner of an embodiment of one aspect of the present application, the obtaining of the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods includes:

[0013] Determine the reference score corresponding to each to-do item in each time period according to the amount to be reminded corresponding to each to-do item, the connection rate of to-do items in each time period, and the recovery rate;

[0014] Extract the to-do items corresponding to each time period from each to-do item according to the order from high to low of the reference scores.

[0015] In a possible implementation manner of an embodiment of one aspect of the present application, the obtaining of the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods includes:

[0016] Use a preset neural network model to process the amount to be reminded corresponding to each to-do item, the connection rate of to-do items in each time period, and the recovery rate, so as to determine the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods.

[0017] In a possible implementation manner of an embodiment of one aspect of the present application, the calculating of the second score of each second to-do item in the current time period includes:

[0018] Determine the historical information of the to-do object corresponding to each second to-do item;

[0019] Calculate the second score of the second to-do item in the current time period according to the historical information of the to-do object.

[0020] In a possible implementation manner of an embodiment of one aspect of the present application, the historical information of the to-do object includes at least two of the following information: credit score, historical repayment rate, connection rate in the current time period, amount to be reminded, and total outstanding amount.

[0021] In a possible implementation manner of an embodiment of one aspect of the present application, after calculating the second score of each second to-do item in the current time period, it further includes:

[0022] Determine the current load capacity of the to-do system and the quantity of to-do items corresponding to the current time period;

[0023] Determine the number M of items to be supplemented according to the current load capacity and the quantity of to-do items corresponding to the current time period, where M is a natural number;

[0024] Select M second to-do items from the set of supplementary items, where the difference between the second score and the first score is greater than the threshold.

[0025] In a possible implementation manner of an embodiment of one aspect of the present application, after adding any of the second to-do items to the to-do items to be processed in the current period, the following is further included:

[0026] Delete any of the second to-do items from the set of added items.

[0027] In a possible implementation manner of an embodiment of one aspect of the present application, after the first to-do item to be processed in the current period meets a preset condition, the following is further included:

[0028] Verify whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets the preset condition;

[0029] In the case where the next unprocessed to-do item does not meet the preset condition, send a to-do message to the to-do object corresponding to the next unprocessed to-do item.

[0030] An embodiment of another aspect of the present application provides a load balancing device for a to-do system, including:

[0031] An acquisition module, configured to acquire a set of added items when the first to-do item to be processed in the current period meets a preset condition, where the set of added items includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods respectively, and N is a positive integer;

[0032] A calculation module, configured to calculate a second score of each of the second to-do items in the current period;

[0033] An addition module, configured to add any of the second to-do items to the to-do items to be processed in the current period when the difference between the second score and the first score of any of the second to-do items is greater than a threshold.

[0034] In a possible implementation manner of an embodiment of one aspect of the present application, the acquisition module includes:

[0035] An acquisition unit, configured to acquire the initial processing period to which each to-do item belongs and the reference scores corresponding to different periods;

[0036] A determination unit, configured to determine any of the to-do items as an added item when the period corresponding to the highest reference score of any of the to-do items is different from the initial processing period to which it belongs and the initial processing period is not the current period.

[0037] In a possible implementation manner of an embodiment of one aspect of the present application, the acquisition unit is configured to:

[0038] Determine the reference score corresponding to each to-do item in each time period according to the amount to be urged corresponding to each to-do item, the to-do connection rate in each time period, and the recovery rate.

[0039] According to the order from high to low of the reference scores, extract the to-do items corresponding to each time period from each to-do item.

[0040] In a possible implementation manner of an embodiment of one aspect of the present application, the obtaining unit is configured to:

[0041] Use a preset neural network model to process the amount to be urged corresponding to each to-do item, the to-do connection rate in each time period, and the recovery rate, so as to determine the initial processing time period to which each to-do item belongs and the reference score corresponding to different time periods.

[0042] In a possible implementation manner of an embodiment of one aspect of the present application, the calculation module is configured to:

[0043] Determine the historical information of the to-do object corresponding to each second to-do item;

[0044] Calculate the second score of the second to-do item in the current time period according to the historical information of the to-do object.

[0045] In a possible implementation manner of an embodiment of one aspect of the present application, the historical information of the to-do object includes at least two of the following information: credit score, historical repayment rate, connection rate in the current time period, amount to be urged, and total outstanding amount.

[0046] In a possible implementation manner of an embodiment of one aspect of the present application, the device includes:

[0047] The first determination module is configured to determine the current load capacity of the to-do system and the amount of to-do items corresponding to the current time period;

[0048] The second determination module is configured to determine the number M of items to be supplemented according to the current load capacity and the amount of to-do items corresponding to the current time period, where M is a natural number;

[0049] The selection module is configured to select M second to-do items from the set of supplementary items, where the difference between the second score and the first score is greater than the threshold.

[0050] In a possible implementation manner of an embodiment of one aspect of the present application, the device includes:

[0051] The deletion module is configured to delete any second to-do item from the set of supplementary items.

[0052] In a possible implementation manner of an embodiment of one aspect of the present application, the device includes:

[0053] A verification module, configured to verify whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets a preset condition;

[0054] A sending module, configured to send a to-do message to a to-do object corresponding to the next unprocessed to-do item when the next unprocessed to-do item does not meet the preset condition.

[0055] Another embodiment of the present application provides a computer device, including a processor and a memory;

[0056] Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the load balancing method of the to-do system as described in the above-mentioned embodiment of one aspect.

[0057] Another embodiment of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the load balancing method of the to-do system as described in the above-mentioned embodiment of one aspect.

[0058] In the load balancing method, device, computer device and storage medium of the to-do system according to the embodiments of the present application, when the first to-do item to be processed in the current period meets the preset condition, by obtaining a supplementary item set, where the supplementary item set includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods, and calculating the second score of each second to-do item in the current period, when the difference between the second score and the first score of any second to-do item is greater than a threshold, any second to-do item is supplemented into the to-do items to be processed in the current period. Thus, when there is a to-do item that meets the preset condition among the to-do items to be processed in the current period, by obtaining a supplementary item set, the to-do items in the supplementary item set that are more suitable for processing in the current period than in the initial processing period are supplemented into the to-do items to be processed in the current period, so as to supplement the to-do items in the current period, which not only realizes the load balancing of the to-do system, but also changes the processing of the supplemented to-do items from the initial processing period to the current period, improving the global to-do connection rate.

[0059] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0061] Figure 1 A flowchart of a load balancing method for a to-do system provided by an embodiment of the present application;

[0062] Figure 2 A flowchart of another load balancing method for a to-do system provided by an embodiment of the present application;

[0063] Figure 3 A flowchart of another load balancing method for a to-do system provided by an embodiment of the present application;

[0064] Figure 4 A schematic structural diagram of a load balancing device for a to-do system provided by an embodiment of the present application. Detailed implementation manners

[0065] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0066] The load balancing method, device, computer device, and storage medium of the to-do system according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0067] Figure 1 A flowchart of a load balancing method for a to-do system provided by an embodiment of the present application.

[0068] The load balancing method of the to-do system according to the embodiment of the present application can be executed by the load balancing device of the to-do system provided by the embodiment of the present application. The device can be configured in a computer device to achieve load balancing of the to-do system by supplementing the to-do items in the current period when the first to-do item in the current period meets the preset conditions.

[0069] Step 101: When the first to-do item to be processed in the current period meets the preset conditions, obtain a set of supplementary items, where the set of supplementary items includes: N second to-do items that are not processed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods, and N is a positive integer.

[0070] In this embodiment, when processing the first to-do item to be processed in the current period, if it is determined that the first to-do item meets the preset conditions, such as the bill has been paid off, the to-do has been cancelled, etc., then obtain the set of supplementary items. Among them, the to-do items can be various items that need to be to-done, such as an overdue electricity bill, a credit that needs to be repaid, etc.

[0071] That is to say, if the to-do item to be processed currently does not need to be processed in the current period, obtain the supplementary item set.

[0072] For example, when processing the to-do item p in the current period, if the bill of the to-do item p has been paid off, obtain the supplementary item set.

[0073] Among them, the obtained supplementary item set includes N second to-do items that are not processed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods respectively. Here, N is a positive integer. That is to say, the N second to-do items included in the supplementary item set are unprocessed to-do items and do not belong to the current period.

[0074] Among them, the reason why the N second to-do items do not belong to the current period is to avoid double to-do of the same to-do item in the same period.

[0075] The initial processing period here can be understood as the initial time period assigned to the to-do item. For example, if there are 80 to-do items to be processed on a certain day, at 0 o'clock on that day, the 80 to-do items are assigned to the corresponding time periods. It can be considered that the time periods to which the to-do items are assigned at this time are the initial processing periods corresponding to the to-do items.

[0076] In this embodiment, the first score of each second to-do item in its corresponding initial processing period can be used to measure the to-do effect brought by to-doing the second to-do item in the initial processing period. Among them, the higher the first score, the better it can be considered to-do the second to-do item in the initial processing period. The first score can be the score calculated when determining the initial processing period. When calculating the first score, it can be calculated according to a pre-trained model or calculated by other means.

[0077] Step 102, calculate the second score of each second to-do item in the current period.

[0078] After obtaining the supplementary item set, calculate the score of each second to-do item in the supplementary item set in the current period. For the convenience of description and distinction, it is called the second score here.

[0079] When calculating the second score, it can also be calculated through a model or calculated by other means.

[0080] As an implementation method, the second score can be calculated according to the historical information of the to-do object corresponding to the second to-do item. Specifically, for each second to-do item, obtain the historical information of the to-do object corresponding to the second to-do item. After obtaining the historical information of the to-do object, the second score of the second to-do item in the current period can be calculated according to the historical information of the to-do object.

[0081] Among them, the historical information of the to-be-handled object can be at least two of credit score, historical repayment rate, connection rate in the current period, to-be-handled amount, total outstanding amount, etc. For example, taking the collection system as an example, the to-be-handled amount is the amount to be collected.

[0082] For example, the historical information credit score α, historical repayment rate β, connection rate λ in the current period, to-be-handled amount d (such as in the collection system, d is the amount to be collected), and total outstanding amount d can be obtained. max The second score S is calculated through the following formula score ,

[0083]

[0084] Since the historical information of the to-be-handled object can reflect the to-be-handled effect of the to-be-handled item in a certain period, in this embodiment, by calculating the second score of the second to-be-handled item in the current period according to the historical information of the to-be-handled object corresponding to the second to-be-handled item, the accuracy of the calculation is improved.

[0085] Step 103, in the case where the difference between the second score and the first score of any second to-be-handled item is greater than the threshold, add any second to-be-handled item to the to-be-handled items to be processed in the current period.

[0086] In this embodiment, after obtaining the second score of each second to-be-handled item in the current period, for each second to-be-handled item, the difference between the second score of the second to-be-handled item in the current period and the first score of the second to-be-handled item in the initial processing period can be calculated.

[0087] If the difference between the second score and the first score is greater than the threshold, it means that the to-be-handled of this second to-be-handled item in the current period is better than that in the initial processing period, then add this second to-be-handled item to the to-be-handled items to be processed in the current period to process the added second to-be-handled item in the current period.

[0088] When adding, after the last to-be-handled item to be processed in the current period, each added item can be added to the to-be-handled items to be processed in the current period in the order of the difference from large to small. Or, the added items can also be added between the first to-be-handled item and the next to-be-handled item adjacent to the first to-be-handled item in the order of the difference from large to small. Or, the preset number of added items with the largest difference, such as one second to-be-handled item with the largest difference, can be added between the first to-be-handled item and the next to-be-handled item adjacent to the first to-be-handled item, and the remaining added items can be added after the last to-be-handled item.

[0089] For example, the second to-do item p2 in the current period meets the preset condition. The number of second to-do items included in the obtained supplementary item set is 20. Among them, there are 10 second to-do items, and the difference between their second scores and the first score is greater than the threshold. Then, the second to-do item with the largest difference among these 10 second to-do items can be added between the second to-do item p2 and the third to-do item p3 in the current period, and the remaining 9 can be added until after the last to-do item in the current period.

[0090] It should be noted that the above supplementary method is only an example, and the specific supplementary method can be determined according to needs.

[0091] In this embodiment, to-do items in the supplementary item set whose difference between the second score in the current period and the first score in the initial processing period is greater than the threshold can be supplemented into the to-do items to be processed in the current period, so that these supplemented to-do items are changed from being processed in the corresponding initial processing period to being processed in the current period.

[0092] For the second to-do items supplemented into the to-do items to be processed in the current period, after the second to-do items are processed in the current period, the second to-do items can be marked so that when the second to-do items are processed in subsequent periods, the second to-do items are regarded as having been processed.

[0093] The to-do system in this embodiment can be a collection system, such as an electricity bill collection system, a credit collection system, etc. By using the load balancing method of the to-do system in this embodiment, the load balancing of the collection system can be achieved, and the global collection connection rate can be improved.

[0094] In the embodiment of the present application, when the first to-do item to be processed in the current period meets the preset condition, a supplementary item set is obtained. Among them, the supplementary item set includes: N unprocessed second to-do items that do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods, and the second score of each second to-do item in the current period is calculated. When the difference between the second score and the first score of any second to-do item is greater than the threshold, any second to-do item is supplemented into the to-do items to be processed in the current period. Thus, when the to-do items to be processed in the current period meet the preset condition, by obtaining the supplementary item set and supplementing the to-do items in the supplementary item set that are better to be done in the current period than in the initial processing period into the to-do items to be processed in the current period to supplement the to-do items in the current period, not only the load balancing of the to-do system is achieved, but also the supplemented to-do items are changed from being processed in the initial processing period to being processed in the current period, improving the global to-do connection rate.

[0095] In one embodiment of the present application, when obtaining the supplementary item set, the reference scores of each to-do item in each time period may be obtained first. According to the reference scores, the to-do items in the supplementary item set are determined. After obtaining the supplementary item set, the to-do items added to the current time period are determined. The following will be combined with Figure 2 for illustration. Figure 2 FIG. 2 is a schematic flowchart of another load balancing method for a to-do system provided by an embodiment of the present application.

[0096] As shown in Figure 2 FIG. 2, the load balancing method for the to-do system includes:

[0097] Step 201, when the first to-do item to be processed in the current time period meets the preset condition, obtain the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods.

[0098] In this embodiment, when processing the first to-do item to be processed in the current time period, if it is determined that the first to-do item meets the preset condition, for example, the bill corresponding to the first to-do item has been paid off or the to-do has been cancelled, etc., then the current to-do items are obtained, and the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods are determined.

[0099] The different time periods here can be obtained by dividing a long time period into multiple time periods in advance. For example, a day is evenly divided into 24 time periods, and each hour is used as a time period.

[0100] When obtaining the initial processing time period to which each to-do item belongs and the reference scores corresponding to each to-do item in different time periods, it can be obtained through a model or other means.

[0101] As a possible implementation manner, the to-do amount corresponding to each to-do item, the to-do connection rate in each time period, the recall rate, etc. can be obtained, and according to the to-do amount corresponding to each to-do item, the to-do connection rate in each time period, the recall rate, etc., the reference score corresponding to each to-do item in each time period is determined.

[0102] For example, the ratio of the product of the to-do connection rate and the recall rate to the to-do amount is used as the reference score, or other calculation methods can also be used to determine the reference score.

[0103] Among them, the to-do connection rate and the recall rate of the to-do item in each time period can be determined according to the historical situation of the to-do object corresponding to the to-do item, or can be determined according to the historical to-do data of to-do items similar to the to-do item.

[0104] After determining the reference score of each to-do item in each time period, you can first extract a certain number of to-do items from each to-do item in a certain time period according to the order of the reference scores of each to-do item in the time period from high to low, as the to-do items for the time period. For another time period, you can extract a certain number of to-do items according to the order of the reference scores of the unassigned to-do targets in the time period from high to low. And so on, you can get the to-do items corresponding to each time period.

[0105] In this embodiment, when extracting the to-do items corresponding to each time period, for each time period, the unassigned to-do items with a reference score greater than a set threshold can be assigned to each time period. Alternatively, the number of to-do items extracted for each time period can be determined based on the load of the to-do system for each time period, and the corresponding number of to-do items can be extracted in descending order of reference scores.

[0106] For example, there are 20 to-do items, and there are 3 time periods a, b, and c. According to the to-do system loads of the 3 time periods, the number of to-do items corresponding to the 3 time periods is determined to be 6, 10, and 4 respectively. When extracting, for time period a, 6 to-do items with the highest reference scores can be extracted according to the order of the reference scores of the 20 to-do items in time period a from high to low; for time period b, 10 to-do items with the highest reference scores can be extracted according to the order of the reference scores of the remaining 14 to-do items in time period b from high to low; for time period b, the remaining 4 to-do items can be allocated to time period c.

[0107] As another possible implementation, a preset neural network model may be used to determine the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods.

[0108] Specifically, the amount to be collected, the connection rate of pending items in each time period, and the collection rate corresponding to each to-do item can be obtained. The preset neural network model is used to encode and decode the amount to be collected, the connection rate of pending items in each time period, and the collection rate corresponding to each to-do item to obtain the initial processing time period to which each to-do item belongs, and the reference scores corresponding to different time periods.

[0109] In this embodiment, in addition to using the amount to be collected corresponding to each to-do item, the to-do connection rate in each time period, and the collection rate as inputs to the neural network model, other features can also be input, such as the load capacity of the to-do system in each time period, each time period, the region to which each to-do item belongs, etc.

[0110] Since the to-do objects in different regions have different to-do connection rates in different time periods, the region to which each to-do item belongs can be used as the input of the neural network model to determine the time period to which each to-do item belongs and the reference score corresponding to each time period.

[0111] In this embodiment, by using a preset neural network model to determine the initial processing time period to which each to-do item belongs and the corresponding reference scores at different time periods, the accuracy of the determined initial processing time period and the accuracy of the reference scores can be improved.

[0112] Step 202: When the time period corresponding to the highest reference score of any to-do item is different from the initial processing time period to which it belongs and the initial processing time period is not the current time period, determine any to-do item as an additional item.

[0113] In practical applications, due to the limited load of each time period, there may be a situation where the current to-do item is not assigned to the optimal to-do time period. In order to improve the global to-do connection rate while achieving the load balance of the to-do system, in this embodiment, the to-do items that do not belong to the current time period and are not assigned to the optimal to-do time period can be used as the to-do items in the additional item set.

[0114] Specifically, after determining the initial processing time period to which each to-do item belongs and the corresponding reference scores at different time periods, for each to-do item, judge whether the time period corresponding to the highest reference score of each to-do item is the initial processing time period to which it belongs, and whether the initial processing time period is the current time period.

[0115] If the time period corresponding to the highest reference score of a certain to-do item is different from the initial processing time period to which the to-do item belongs and the initial processing time period is not the current time period, it means that the to-do item does not belong to the current time period and is not assigned to the optimal to-do time period, then the to-do item can be determined as an additional item.

[0116] Thus, an additional item set can be obtained according to the additional items determined from the current to-do items and the reference scores of each additional item in its initial processing time period.

[0117] Step 203: Calculate the second score of each second to-do item in the current time period.

[0118] Step 204: When the difference between the second score and the first score of any second to-do item is greater than the threshold, add any second to-do item to the to-do items to be processed in the current time period.

[0119] In this embodiment, Step 203 - Step 204 is similar to the above Step 102 - Step 103, so it will not be elaborated here.

[0120] In the embodiments of the present application, when obtaining the supplementary item set, the initial processing time period to which each to-do item belongs and the corresponding reference scores in different time periods are obtained. When the time period corresponding to the highest reference score of any to-do item is different from the initial processing time period to which it belongs and the initial processing time period is not the current time period, any to-do item is determined as a supplementary item. After obtaining the supplementary item set, the supplementary items with the difference between the second score and the first score greater than the threshold are supplemented into the to-do items to be processed in the current time period. Thus, by taking the to-do items that are not assigned to the optimal to-do time period and do not belong to the current time period as supplementary items, and supplementing the supplementary items with the difference between the score in the current time period and the score in the initial processing time period greater than the threshold into the current time period, not only is system balance achieved, but also the global to-do connection rate is improved.

[0121] In practical applications, the supplementary items with the difference between the score in the current time period and the score in the initial processing time period greater than the threshold can be supplemented into the current time period. To further improve load balancing, in an embodiment of the present application, the number of to-do items to be supplemented can also be determined first according to the current load of the to-do system and the amount of to-do items corresponding to the current time period, so as to supplement these numbers of to-do items selected from the supplementary item set into the to-do items to be processed in the current time period.

[0122] The following is combined with Figure 3 for illustration. Figure 3 FIG. is a schematic flowchart of another load balancing method for a to-do system provided by an embodiment of the present application.

[0123] Step 301, when the first to-do item to be processed in the current time period meets the preset conditions, obtain the supplementary item set, where the supplementary item set includes: N second to-do items that are not processed and do not belong to the current time period, and N first scores of the N second to-do items in the corresponding initial processing time periods respectively, and N is a positive integer.

[0124] Step 302, calculate the second score of each second to-do item in the current time period.

[0125] In this embodiment, steps 301 - 302 are similar to the above steps 101 - 102, so the details are not repeated here.

[0126] Step 303, determine the current load capacity of the to-do system and the amount of to-do items corresponding to the current time period.

[0127] In this embodiment, after calculating the second score of each second to-do item in the current time period, the current load capacity of the to-do system and the amount of to-do items corresponding to the current time period are obtained.

[0128] Specifically, the current load capacity of the to-do system can be determined based on the current processor occupancy rate, the remaining storage space size, etc. of the to-do system; the to-do items corresponding to the current time period refer to the to-do items that need to be processed during the current time period, excluding the first to-do items that meet the preset conditions.

[0129] Among them, the current load capacity can be understood as the amount of to-do items that the to-do system can currently process.

[0130] Step 304, determine the number M of items to be supplemented according to the current load capacity and the amount of to-do items corresponding to the current time period, where M is a natural number.

[0131] After obtaining the current load capacity and the amount of to-do items corresponding to the current time period, the difference between the current load capacity and the to-do vector corresponding to the current time period can be calculated. Here, the difference is the amount of to-do items that the to-do system can still process, that is, the number M of items to be supplemented.

[0132] In practical applications, the current load capacity of the to-do system may be the same as the amount of to-do items corresponding to the current time period, or may be greater than the amount of to-do items corresponding to the current time period. Therefore, the number of items to be supplemented is 0 or an integer greater than 0, that is, M is a natural number.

[0133] Step 305, select M second to-do items from the supplementary item set whose difference between the second score and the first score is greater than the threshold.

[0134] In order to improve the global to-do connection rate, for each second to-do item in the supplementary item set, the difference between the second score of the second to-do item in the current time period and the first score of the second to-do item in the initial processing time period can be calculated, and it can be determined whether the difference is greater than the threshold. Then, select M second to-do items from the supplementary item set whose differences are greater than the threshold.

[0135] If the number of second to-do items whose differences are greater than the threshold is greater than M, then M second to-do items can be selected in the order of the differences from large to small. If the number of second to-do items whose differences are greater than the threshold is equal to M, then all second to-do items whose differences are greater than the threshold can be selected. If the number of second to-do items whose differences are greater than the threshold is less than M, all second to-do items whose differences are greater than the threshold can be selected, or M second to-do items can also be selected in the order of the differences from large to small.

[0136] Step 306, supplement the M second to-do items to the to-do items to be processed in the current time period.

[0137] After selecting M second to-do items whose difference between the second score and the first score is greater than the threshold, the M second to-do items can be added to the to-do items to be processed in the current period, so as to supplement the to-do items in the current period and achieve the load balancing of the to-do system. For the specific supplement method, reference can be made to the above embodiments and will not be elaborated here.

[0138] In the embodiment of the present application, after calculating the second score of each second to-do item in the current period, the load capacity of the to-do system at present and the amount of to-do items corresponding to the current period can be used, and according to the current load capacity and the amount of to-do items corresponding to the current period, the number M of items to be supplemented is determined. From the supplement item set, M second to-do items whose difference between the second score and the first score is greater than the threshold are selected and added to the to-do items to be processed in the current period. Thus, by determining the number of items to be supplemented according to the current load capacity of the to-do system and the amount of to-do items corresponding to the current period, the accuracy of the amount of items to be supplemented is improved, thereby improving the load balancing of the to-do system.

[0139] In order to avoid the uneven processing times of to-do items, in an embodiment of the present application, after adding any second to-do item to the to-do items to be processed in the current period, the second to-do item can be deleted from the supplement item set.

[0140] In this embodiment, in the supplement item set, if there is a second to-do item whose difference between the second score in the current period and the first score in the initial processing period is greater than the threshold, the second to-do item is added to the to-do items to be processed in the current period.

[0141] In practical applications, if the second to-do items in the supplement item set remain unchanged, it may occur that some second to-do items are processed multiple times while some second to-do items are not processed.

[0142] Based on this, after the second to-do item is added to the to-do items to be processed in the current period, the second to-do item can be deleted from the supplement item set.

[0143] In the embodiment of the present application, after adding any second to-do item to the to-do items to be processed in the current period as described above, the second to-do item can also be deleted from the supplement item set. Thus, the uneven processing times of the second to-do items in the supplement item set can be avoided.

[0144] In order to improve the processing efficiency of to-do items, in an embodiment of the present application, while adding items, to-do can be carried out, that is, to-do and item addition are carried out simultaneously.

[0145] Specifically, after the first to-do item to be processed in the current period meets the preset conditions, a supplementary item set can be obtained to supplement the to-do items to be processed in the current period through the supplementary item set, and it can also be verified whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets the preset conditions. Here, the adjacency can be determined according to the processing order of each to-do item in the current period.

[0146] If the next unprocessed to-do item does not meet the preset conditions, that is, it needs to be processed in the current period, a to-do message can be generated according to the to-do amount, total outstanding amount, information of the corresponding to-do object, etc. of the next unprocessed to-do item, and the to-do message can be sent to the corresponding to-do object.

[0147] Among them, the to-do message can be a text message, a voice message, etc. When sending, the to-do message can be sent to the to-do object in the form of sending an email, a text message, a voice, etc.

[0148] For example, when processing the third to-do item in the current period, the bill of the third to-do item has been paid off. At this time, a supplementary item set can be obtained, supplemented through the supplementary item set, and at the same time, the fourth to-do item adjacent to the third to-do item is verified. If the fourth to-do item does not meet the preset conditions, a to-do message is sent to the to-do object corresponding to the fourth to-do item.

[0149] In the embodiment of the present application, after the first to-do item to be processed in the current period meets the preset conditions, it can also be verified whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets the preset conditions, and when the next unprocessed to-do item does not meet the preset conditions, a to-do message is sent to the to-do object corresponding to the next unprocessed to-do item. Thus, by judging the next to-do item adjacent to the first to-do item while supplementing the first to-do item, the processing efficiency of the to-do system is improved through parallel processing of to-do and item supplementation.

[0150] To implement the above embodiment, the embodiment of the present application also proposes a load balancing device for a to-do system. Figure 4 It is a schematic structural diagram of a load balancing device for a to-do system provided by the embodiment of the present application.

[0151] As Figure 4 shown, the load balancing device 400 of the to-do system includes: an acquisition module 410, a calculation module 420, and a supplementation module 430.

[0152] The acquisition module 410 is used to acquire a set of supplementary items when the first to-do items to be processed in the current time period meet a preset condition, wherein the set of supplementary items includes: N unprocessed second to-do items that do not belong to the current time period, and N first scores of the N second to-do items in the corresponding initial processing time period, where N is a positive integer;

[0153] A calculation module 420, configured to calculate a second score of each second to-do item in the current time period;

[0154] The supplementing module 430 is used to supplement any second to-do item to the to-do items to be processed in the current time period when the difference between the second score and the first score of any second to-do item is greater than a threshold.

[0155] In a possible implementation of the embodiment of the present application, the acquisition module 410 includes:

[0156] An acquisition unit, used to acquire the initial processing period to which each to-do item belongs and the reference scores corresponding to different periods;

[0157] The determination unit is used to determine that any to-do item is a supplementary item when the time period corresponding to the highest reference score of any to-do item is different from the initial processing time period to which it belongs and the initial processing time period is not the current time period.

[0158] In a possible implementation manner of the embodiment of the present application, the acquiring unit is used to:

[0159] Determine the reference score for each to-do item in each time period based on the amount of money to be collected for each to-do item, the call-through rate for each time period, and the collection rate;

[0160] Based on the reference score from high to low, extract the to-do items corresponding to each time period from each to-do item.

[0161] In a possible implementation manner of the embodiment of the present application, the acquiring unit is used to:

[0162] Using the preset neural network model, the amount to be collected corresponding to each to-do item, the to-do connection rate in each time period, and the collection rate are processed to determine the initial processing time period to which each to-do item belongs and the corresponding reference scores in different time periods.

[0163] In a possible implementation of the embodiment of the present application, the calculation module 420 is used to:

[0164] Determine the historical information of the to-do object corresponding to each second to-do item;

[0165] According to the historical information of the to-do object, a second score of the second to-do item in the current time period is calculated.

[0166] In a possible implementation manner of an embodiment of the present application, the historical information of the to-do object includes at least two of the following information: credit score, historical repayment rate, connection rate in the current period, to-do amount, and total outstanding amount.

[0167] In a possible implementation manner of an embodiment of the present application, the device includes:

[0168] A first determination module, configured to determine the current load capacity of the to-do system and the amount of to-do items corresponding to the current period;

[0169] A second determination module, configured to determine the number M of items to be supplemented according to the current load capacity and the amount of to-do items corresponding to the current period, where M is a natural number;

[0170] A selection module, configured to select M second to-do items from the set of supplementary items, where the difference between the second score and the first score is greater than a threshold.

[0171] In a possible implementation manner of an embodiment of the present application, the device includes:

[0172] A deletion module, configured to delete any second to-do item from the set of supplementary items.

[0173] In a possible implementation manner of an embodiment of the present application, the device includes:

[0174] A verification module, configured to verify whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets a preset condition;

[0175] A sending module, configured to send a to-do message to the to-do object corresponding to the next unprocessed to-do item when the next unprocessed to-do item does not meet the preset condition.

[0176] It should be noted that the above explanation of the embodiment of the load balancing method for the to-do system also applies to the load balancing device of the to-do system in this embodiment, so it will not be repeated here.

[0177] The load balancing device of the to-do system according to the embodiment of the present application obtains a supplementary item set when the first to-do item to be processed in the current period meets a preset condition. The supplementary item set includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods, and calculates the second score of each second to-do item in the current period. When the difference between the second score and the first score of any second to-do item is greater than a threshold, any second to-do item is added to the to-do items to be processed in the current period. Thus, when there is a to-do item that meets the preset condition among the to-do items to be processed in the current period, by obtaining the supplementary item set, the to-do items in the supplementary item set that are more suitable to be processed in the current period than in the initial processing period are added to the to-do items to be processed in the current period to supplement the to-do items in the current period, which not only achieves the load balancing of the to-do system, but also changes the supplementary to-do items from being processed in the initial processing period to being processed in the current period, improving the global to-do connection rate.

[0178] To implement the above embodiment, the embodiment of the present application also proposes a computer device, including a processor and a memory;

[0179] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory to implement the load balancing method of the to-do system as described in the above embodiment.

[0180] To implement the above embodiment, the embodiment of the present application also proposes a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the load balancing method of the to-do system as described in the above embodiment.

[0181] In the description of this specification, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0182] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A load balancing method for a to-do system, characterized in that, include: When the first to-do items to be processed in the current time period meet the preset conditions, a set of supplementary items is obtained, wherein the set of supplementary items includes: N second to-do items that are not processed and do not belong to the current time period, and N first scores of the N second to-do items in the corresponding initial processing time period, wherein N is a positive integer, wherein the first score is used to measure the effect of processing the second to-do items in the initial processing time period, and the higher the first score, the better the effect of processing the second to-do items in the initial processing time period; Calculate a second score for each second to-do item in the current time period, where the second score is the product of the historical information credit score, historical repayment rate, connection rate in the current time period, and to-do amount of the to-do object corresponding to the second to-do item, and the ratio of the total outstanding amount of the to-do object corresponding to the second to-do item; Determine the current load capacity of the to-do system and the number of to-do items corresponding to the current time period; Determine the number of items to be added M according to the current load capacity and the number of items to be done corresponding to the current time period, where M is a natural number; Selecting, from the set of supplementary items, M second to-do items whose difference between the second score and the first score is greater than a threshold; Add the M second to-do items to the to-do items to be processed in the current period.

2. The method according to claim 1, characterized in that, The obtaining of the supplementary item set includes: Obtain the initial processing period of each to-do item and the reference scores corresponding to different periods; When the time period corresponding to the highest reference score of any to-do item is different from the initial processing time period to which it belongs, and the initial processing time period is not the current time period, the to-do item is determined to be a supplementary item.

3. The method according to claim 2, characterized in that, The obtaining of the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods includes: Determine the reference score for each to-do item in each time period based on the amount of money to be collected for each to-do item, the call-through rate for each time period, and the collection rate; Based on the reference score from high to low, extract the to-do items corresponding to each time period from each to-do item.

4. The method according to claim 2, characterized in that, The obtaining of the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods includes: Using a preset neural network model, the amount to be collected corresponding to each to-do item, the to-do connection rate in each time period, and the collection rate are processed to determine the initial processing time period to which each to-do item belongs and the reference scores corresponding to different time periods.

5. The method according to claim 1, characterized in that, The calculating the second score of each of the second to-do items in the current period includes: Determine historical information of a to-do object corresponding to each of the second to-do items; A second score of the second to-do item in the current time period is calculated according to the historical information of the to-do object.

6. The method according to claim 5, characterized in that, The historical information of the pending object includes at least two of the following information: credit score, historical repayment rate, connection rate in the current period, pending amount and total outstanding amount.

7. The method according to any one of claims 1-6, characterized in that, After adding any second to-do item to the to-do items to be processed in the current period, the method further includes: Delete any second to-do item from the supplementary item set.

8. The method according to any one of claims 1-6, characterized in that, After the first to-do item to be processed in the current period meets the preset conditions, it further includes: Verify whether the next unprocessed to-do item adjacent to the first to-do item in the current period meets the preset conditions; In the case that the next unprocessed to-do item does not meet the preset conditions, send a to-do message to the to-do object corresponding to the next unprocessed to-do item.

9. A load balancing device for a to-do system, characterized in that, It includes: An acquisition module, configured to, when the first to-do item to be processed in the current period meets the preset conditions, acquire a supplementary item set, where the supplementary item set includes: N second to-do items that are unprocessed and do not belong to the current period, and N first scores of the N second to-do items in their corresponding initial processing periods respectively, N is a positive integer, and the first score is used to measure the to-do effect of handling the second to-do item in the initial processing period, and the higher the first score, the better the to-do effect of handling the second to-do item in the initial processing period; A calculation module, configured to calculate the second score of each second to-do item in the current period, where the second score is the ratio of the product of the historical information credit score, historical repayment rate, connection rate in the current period, and to-do amount of the to-do object corresponding to the second to-do item to the total outstanding amount of the to-do object corresponding to the second to-do item; A supplementary module, configured to determine the current load capacity of the to-do system and the quantity of to-do items corresponding to the current period; determine the number of items M to be supplemented according to the current load capacity and the quantity of to-do items corresponding to the current period, where M is a natural number; select M second to-do items from the supplementary item set whose difference between the second score and the first score is greater than the threshold; supplement the M second to-do items to the to-do items to be processed in the current period.

10. A computer device, characterized in that, It includes a processor and a memory; Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the load balancing method of the to-do system as described in any one of claims 1-8.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the load balancing method of the to-do system as described in any one of claims 1-8.

Images