Data transmission parameter determination method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a data transmission parameter determination method and device, equipment and a storage medium, and relates to the technical field of computers, and the method can comprise the steps: obtaining a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; wherein the historical actual service volume distribution sequence is a time sequence formed by historical actual service volume distribution parameters respectively corresponding to each acquisition period in a preset historical time period; taking the historical actual business volume distribution sequence as a current observation sequence, and determining a target predicted business volume distribution parameter corresponding to a preset future time period after the current moment through a preset exponential smoothing algorithm; and determining a transmission parameter for the service data in the preset future time period based on the target predicted service volume distribution parameter. By adopting the technical scheme of the embodiment of the invention, the occurrence of data backlog can be reduced, so that the real-time performance of transmission can be improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to a method, apparatus, device and storage medium for determining data transmission parameters. Background Art

[0002] At present, for a business management system including multiple business subsystems, there may be a need for data transmission between the business subsystems. In the prior art, data transmission between the business subsystems is generally carried out in a timed and quantitative transmission mode. For example, if the business management system is a logistics management system, the management system includes a collection subsystem and an analysis subsystem. The collection subsystem can use a timed and quantitative transmission mode to transmit the collected logistics business data of each logistics staff member to the analysis subsystem, so that the analysis subsystem can calculate the salary of each logistics staff member.

[0003] However, in the process of implementing the present invention, it was found that there are at least the following problems in the prior art: since the scale of data to be transmitted in a certain time period (for example, at the end of each month) may be very large, the use of the timed and quantitative data transmission method of the prior art can easily cause data backlog, resulting in a large amount of data being unable to be sent in time. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and storage medium for determining data transmission parameters, which can reduce the occurrence of data backlog and thus improve the real-time performance of transmission.

[0005] In the first aspect, an embodiment of the present invention provides a method for determining data transmission parameters, which may include: obtaining a historical actual business volume distribution sequence corresponding to a preset historical time period before a current moment; wherein the historical actual business volume distribution sequence is a time series sequence composed of historical actual business volume distribution parameters corresponding to each collection period within the preset historical time period; taking the historical actual business volume distribution sequence as the current observation sequence, determining the target predicted business volume distribution parameters corresponding to a preset future time period after the current moment through a preset exponential smoothing algorithm; and determining the transmission parameters for business data for the preset future time period based on the target predicted business volume distribution parameters.

[0006] In a second aspect, an embodiment of the present invention further provides a device for determining a data transmission parameter, which may include: an acquisition module and a determination module;

[0007] Specifically, the acquisition module is used to acquire a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; wherein the historical actual business volume distribution sequence is a time series sequence composed of historical actual business volume distribution parameters corresponding to each collection period in the preset historical time period;

[0008] A determination module is used to determine the target predicted business volume distribution parameters corresponding to a preset future time period after the current moment by using a preset exponential smoothing algorithm with a historical actual business volume distribution sequence as the current observation sequence;

[0009] The determination module is also used to determine the transmission parameters of the business data for a preset future time period based on the target predicted business volume distribution parameters.

[0010] In a third aspect, an embodiment of the present invention provides a device for determining a data transmission parameter, the device for determining a data transmission parameter including:

[0011] one or more processors;

[0012] A memory for storing one or more programs;

[0013] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining data transmission parameters provided by any embodiment of the present invention.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining data transmission parameters as provided in any embodiment of the present invention.

[0015] The embodiments of the above invention have the following advantages or beneficial effects:

[0016] In the technical solution provided by the embodiment of the present invention, when the current business subsystem has the need to transmit business data to another business subsystem, the existing timed and quantitative transmission mode is no longer used, and a preset future time period can be pre-determined according to the business transmission demand. Afterwards, the duration corresponding to the preset future time period can be used as the parameter adjustment period. In each parameter adjustment period, the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment can be predicted according to the historical actual business volume distribution sequence corresponding to the preset historical time period before the current moment; then, the transmission parameters of the business data for the preset future time period can be dynamically adjusted based on the target predicted business volume distribution parameter. Specifically, since the historical actual business volume distribution sequence is a time series sequence composed of the historical actual business volume distribution parameters corresponding to each acquisition cycle in the preset historical time period, the historical actual business volume distribution sequence can characterize the actual situation of the business volume changing over time in the preset historical time period. Based on this, the embodiment of the present invention can use the historical actual business volume distribution sequence as the current observation sequence, and determine the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment through a preset exponential smoothing algorithm, and the target predicted business volume distribution parameter can characterize the possible scale of the business volume in the preset future time period. Then, based on the target predicted traffic volume distribution parameters, the transmission parameters that match the scale of the traffic volume in the preset future time period can be determined. It can be seen that in the technical solution provided by the embodiment of the present invention, the scale of the traffic volume in the preset future time period can be predicted based on the actual changes in the traffic volume in the preset historical time period, and the transmission parameters can be dynamically adjusted according to the prediction results, so that the adjusted transmission parameters can be suitable for the scale of the traffic volume in the preset future time period. In this way, the transmission of service data with appropriate transmission parameters can reduce the occurrence of data backlog, thereby improving the real-time performance of transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of a method for determining data transmission parameters provided by an embodiment of the present invention;

[0018] Figure 2 is a flow chart of another method for determining data transmission parameters provided by an embodiment of the present invention;

[0019] Figure 3 It is a schematic diagram of a processing flow of data by an exponential smoothing algorithm model provided by an embodiment of the present invention;

[0020] Figure 4 is a flow chart of another method for determining data transmission parameters provided by an embodiment of the present invention;

[0021] Figure 5It is a schematic diagram of a flow chart of determining transmission parameters according to a target predicted total business volume provided by an embodiment of the present invention;

[0022] Figure 6 It is a structural schematic diagram of a device for determining data transmission parameters provided by an embodiment of the present invention;

[0023] Figure 7 It is a structural diagram of a device for determining data transmission parameters provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0026] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0027] It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present invention, unless otherwise specified, “plurality” or “each” means two or more than two.

[0029] Figure 1A flowchart of a method for determining data transmission parameters provided in an embodiment of the present invention, the method can be applicable to an application scenario of business data transmission between business subsystems in a business management system. The method can be executed by a device for determining data transmission parameters provided in an embodiment of the present invention, the device can be implemented in software and / or hardware, and integrated in a device for determining data transmission parameters. Exemplarily, the device for determining data transmission parameters can be a device corresponding to the current business subsystem (a business subsystem with data transmission requirements), such as a server of the current business subsystem.

[0030] like Figure 1 As shown, the method for determining data transmission parameters provided by the embodiment of the present invention specifically includes the following steps:

[0031] S110: Obtain a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment.

[0032] The preset historical time period may be a predetermined time period. The historical actual business volume distribution sequence is a time series consisting of historical actual business volume distribution parameters corresponding to each collection period in the preset historical time period. The collection period may be a predetermined interval for collecting business volume distribution parameters. For each historical actual business volume distribution parameter in the historical actual business volume distribution sequence, the current historical actual business volume distribution parameter may represent the actual size of the business volume in the current collection period.

[0033] Taking the current business subsystem as an example, which is a collection subsystem for collecting logistics business data of each logistics staff, if the preset historical time period is the past 30 days and the collection cycle is one day, the business volume of logistics business data generated by the current business subsystem every day within the 30 days before the current moment can be counted to obtain the historical actual business volume distribution parameters corresponding to each day within 30 days. Afterwards, the statistically obtained historical actual business volume distribution parameters can be sorted in chronological order to obtain the historical actual business volume distribution sequence. For example, the historical actual business volume distribution sequence can be expressed as a sequence A = (A1; A2; A3; ...; A30), where A30 represents the historical actual business volume distribution parameter corresponding to the day before the current moment.

[0034] S120: Taking the historical actual business volume distribution sequence as the current observation sequence, determine the target predicted business volume distribution parameters corresponding to the preset future time period after the current moment by using a preset exponential smoothing algorithm.

[0035] The preset exponential smoothing algorithm may be a predetermined exponential smoothing algorithm. Exemplarily, the preset exponential smoothing algorithm may be a primary exponential smoothing algorithm or a secondary exponential smoothing algorithm. The preset future time period may be a time period predetermined according to business requirements, and the duration corresponding to the preset future time period is equal to the duration corresponding to the collection period. For example, if the collection period is one day, the preset future time period may be one day in the future.

[0036] In the embodiment of the present invention, the existing timed and quantitative transmission method is no longer used, but a preset future time period can be predetermined, and then the duration corresponding to the preset future time period can be used as the parameter adjustment period. In each parameter adjustment period, the traffic volume in the preset future time period after the current moment is predicted based on the acquired historical actual traffic volume distribution sequence to obtain the target predicted traffic volume distribution parameter. Afterwards, the transmission parameters of the traffic data for the preset future time period can be dynamically adjusted based on the target predicted traffic volume distribution parameter. Since the exponential smoothing algorithm is an algorithm that can quickly and accurately predict future data based on historical data, in the embodiment of the present invention, the target predicted traffic volume distribution parameter can be predicted by the exponential smoothing algorithm.

[0037] Taking the preset exponential smoothing algorithm as a first exponential smoothing algorithm as an example, the embodiment of the present invention can predict the target predicted traffic volume distribution parameter by expression (1):

[0038]

[0039] Where ∝ represents the smoothing coefficient of the preset exponential smoothing algorithm, which can be determined based on experience; x t Indicates the current observation value corresponding to the t-th collection period in the current observation sequence (that is, the actual traffic distribution parameter corresponding to the t-1-th collection period); represents the current prediction value (that is, the predicted traffic distribution parameter corresponding to the t-1th acquisition period); represents the predicted traffic volume distribution parameter corresponding to the tth collection period. Taking the historical actual traffic volume distribution sequence as sequence A as an example, A1 can be used as the current observation value x t and takes the predetermined traffic distribution parameters as the current prediction value The predicted value for A1 is determined by expression (1): Then, A2 can be used as the current observation value x t and use the predicted value for A1 as the current predicted value The predicted value for A2 is determined by expression (1): Similarly, the elements in sequence A can be traversed until the predicted value for A30 is determined. Then the predicted value for A30 can be Determine the target predicted business volume distribution parameters corresponding to the preset future time period.

[0040] S130: Determine transmission parameters for service data in a preset future time period based on target predicted service volume distribution parameters.

[0041] Exemplarily, the transmission parameters may include a transmission interval and a transmission batch, wherein the transmission interval is the duration between two transmissions of service data, and the transmission batch is the size of the service volume of each transmission of service data.

[0042] Since the target predicted traffic volume distribution parameter can characterize the possible size of the traffic volume in the preset future time period, the transmission parameters that match the size of the traffic volume in the preset future time period can be determined based on the target predicted traffic volume distribution parameter. For example, when the size of the traffic volume in the preset future time period is large, the transmission interval can be reduced; when the size of the traffic volume in the preset future time period is small, the transmission interval can be increased.

[0043] Optionally, for each historical actual business volume distribution parameter in the historical actual business volume distribution sequence, the current historical actual business volume distribution parameter includes the historical actual business components corresponding to each collection sub-period in the current collection period; the target predicted business volume distribution parameter includes the target predicted business components corresponding to each collection sub-period in a preset future time period.

[0044] The collection sub-cycle may be an interval obtained by further dividing the collection cycle into time periods. For example, if the collection cycle is 1 day, the collection sub-cycle may be 1 hour.

[0045] In a possible implementation, taking the preset historical time period as the past 30 days, the collection period as 1 day, and the collection sub-period as 1 hour as an example, in the embodiment of the present invention, the actual business volume (i.e., historical actual business component) of each hour of the past 30 days can be counted respectively, and the historical actual business volume distribution parameters corresponding to the 30 days can be obtained in sequence, and the historical actual business volume distribution parameters can be arranged in chronological order to obtain the historical actual business volume distribution sequence, for example, the sequence A = (A1; A2; A3; ...; A30). Taking A30 as an example, A30 = (a1; a2; a3; ...; a24), where a1 to a24 respectively represent the actual business volume corresponding to each hour of the day before the current moment. Correspondingly, the target predicted business volume distribution parameter A31 = (b1; b2; b3; ...; b24), where b1 to b24 respectively represent the predicted business volume corresponding to each hour of the day after the current moment (i.e., the target predicted business component).

[0046] Specifically, when determining the target predicted business volume distribution parameters through a preset exponential smoothing algorithm based on the historical actual business volume distribution sequence, the first target predicted business component in the target predicted business volume distribution parameters can be predicted according to the first historical actual business components in each historical actual business volume distribution parameter, and then the second target predicted business component in the target predicted business volume distribution parameters can be predicted according to the second historical actual business components in each historical actual business volume distribution parameter, until the last target predicted business component in the target predicted business volume distribution parameters is predicted according to the last historical actual business components in each historical actual business volume distribution parameter, and the target predicted business volume distribution parameters can be obtained. For example, taking the historical actual business volume distribution sequence as sequence C, sequence C = (C1; C2; C3), C1 = (c1; c2; c3; ...; c24), C2 = (d1; d2; d3; ...; d24), C3 = (e1; e2; e3; ...; e24), if C4 is used to represent the target predicted business volume distribution parameters, C4 = (f1; f2; f3; ...; f24), then f1 can be determined based on c1, d1, e1, and then f2 can be determined based on c2, d2, e2, until f24 is determined.

[0047] In order to improve the accuracy of the business volume scale predicted by the preset exponential smoothing algorithm, in the embodiment of the present invention, the collection period can be further divided to obtain each collection sub-period. Specifically, the predicted business volume of each collection sub-period corresponding to the preset future time period can be predicted based on the actual business volume of each collection sub-period corresponding to each collection period in the preset historical time period, and then the predicted business volume of each collection sub-period corresponding to the preset future time period can be integrated to determine the size of the business volume of the preset future time period. In this way, the accuracy of the determined business volume scale is higher.

[0048] Optionally, after determining the transmission parameters for business data for a preset future time period based on the target predicted business volume distribution parameters, the method for determining data transmission parameters provided by an embodiment of the present invention may further include: obtaining the target actual business volume distribution parameters corresponding to the preset future time period; and updating the historical actual business volume distribution sequence based on the target actual business volume distribution parameters.

[0049] In the embodiment of the present invention, the target actual traffic volume distribution parameter can be dynamically determined based on the change of each historical actual traffic volume distribution parameter, and the transmission parameter can be dynamically adjusted based on the target actual traffic volume distribution parameter. Based on this, the historical actual traffic volume distribution sequence can be dynamically updated with the duration corresponding to the preset future time period as the update cycle.

[0050] For example, if the historical actual traffic volume distribution sequence is sequence A, and A31 is used to represent the target predicted traffic volume distribution parameter, the historical actual traffic volume distribution sequence can be updated based on the first-in-first-out update principle to obtain sequence E=(A2; A3; A4; ...; A31). Then, in the next parameter adjustment cycle, sequence E can be used as the historical actual traffic volume distribution sequence.

[0051] In the method for determining data transmission parameters provided by the embodiment of the present invention, when the current business subsystem has a demand for business data transmission to another business subsystem, the existing timed and quantitative transmission mode is no longer used, and a preset future time period can be pre-determined according to the business transmission demand. Afterwards, the duration corresponding to the preset future time period can be used as the parameter adjustment cycle. In each parameter adjustment cycle, the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment can be predicted according to the historical actual business volume distribution sequence corresponding to the preset historical time period before the current moment; then, the transmission parameters of the business data for the preset future time period can be dynamically adjusted based on the target predicted business volume distribution parameter. Specifically, since the historical actual business volume distribution sequence is a time series sequence composed of the historical actual business volume distribution parameters corresponding to each acquisition cycle in the preset historical time period, the historical actual business volume distribution sequence can characterize the actual situation of the business volume changing over time in the preset historical time period. Based on this, the embodiment of the present invention can use the historical actual business volume distribution sequence as the current observation sequence, and determine the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment through a preset exponential smoothing algorithm, and the target predicted business volume distribution parameter can characterize the possible scale of the business volume in the preset future time period. Then, based on the target predicted traffic volume distribution parameter, a transmission parameter that is consistent with the scale of the traffic volume in the preset future time period can be determined. It can be seen that in the embodiment of the present invention, the scale of the traffic volume in the preset future time period can be predicted based on the actual change of the traffic volume in the preset historical time period, and the transmission parameter can be dynamically adjusted according to the prediction result, so that the adjusted transmission parameter can be suitable for the scale of the traffic volume in the preset future time period. In this way, the transmission of service data with appropriate transmission parameters can reduce the occurrence of data backlog, thereby improving the real-time performance of transmission.

[0052] Reference Figure 2 , is a flow chart of another method for determining data transmission parameters provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the method for determining data transmission parameters provided by the previous embodiment, and the method for determining data transmission parameters provided by the previous embodiment is further optimized. Figure 2 As shown, the specific steps include:

[0053] S210: Obtain a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment.

[0054] S220, using the historical actual business volume distribution sequence as the current training set, and determining the historical predicted business volume distribution sequence output by each pre-created prediction thread through a preset exponential smoothing algorithm.

[0055] Wherein, each prediction thread is a plurality of parallel executable threads pre-created for a preset exponential smoothing algorithm, and each prediction thread corresponds to a different smoothing coefficient. Exemplarily, an embodiment of the present invention can pre-create 17 prediction threads for a preset exponential smoothing algorithm, and the smoothing coefficients corresponding to the 17 prediction threads are 0.1, 0.15, 0.2, 0.25, 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, 0.60, 0.65, 0.7, 0.75, 0.8, 0.85, and 0.9, respectively.

[0056] Optionally, in order to further improve the accuracy of the determined target predicted business volume distribution parameters, in an embodiment of the present invention, the preset exponential smoothing algorithm is a cubic exponential smoothing algorithm, and the historical actual business volume distribution sequence is used as the current training set. The preset exponential smoothing algorithm is used to determine the historical predicted business volume distribution sequences output by each pre-created prediction thread, including: for each prediction thread, the historical actual business volume distribution sequence is used as the current training set, and the preset exponential smoothing algorithm is used to determine the first current historical prediction sequence, the second current historical prediction sequence, and the third current historical prediction sequence output in sequence by the current prediction thread, and the third current historical prediction sequence is determined as the historical predicted business volume distribution sequence output by the current prediction thread.

[0057] When the preset exponential smoothing algorithm is a cubic exponential smoothing algorithm, the embodiment of the present invention can predict the target predicted traffic volume distribution parameter by expression (2):

[0058]

[0059] Where ∝ represents the smoothing coefficient of the preset exponential smoothing algorithm, x t Indicates the current observation value corresponding to the t-th collection period in the current observation sequence (that is, the actual traffic distribution parameter corresponding to the t-1-th collection period); Represents the current forecast value, which is an exponential smoothing forecast value for the t-1th collection period; Represents an exponential smoothing forecast value for the tth collection period; represents the quadratic exponential smoothing forecast value for the t-1th collection period; represents the quadratic exponential smoothing forecast value for the tth collection period; represents the triple exponential smoothing prediction value for the t-1th collection period, that is, the predicted business volume distribution parameter for the t-1th collection period; It represents the cubic exponential smoothing prediction value for the t-th collection period, that is, the predicted business volume distribution parameter for the t-th collection period (that is, the target predicted business volume distribution parameter).

[0060] Optionally, taking the historical actual business volume distribution sequence as the current training set, determining the first current historical prediction sequence, the second current historical prediction sequence, and the third current historical prediction sequence outputted in sequence by the current prediction thread through a preset exponential smoothing algorithm, and determining the three current historical prediction sequences as the historical prediction business volume distribution sequence outputted by the current prediction thread, including: taking the first historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value, and taking the preset business volume distribution parameter as the current prediction value, determining the first sequence element of the first current historical prediction sequence outputted by the current prediction thread through a preset exponential smoothing algorithm, and determining the first sequence element as the current observation value; Previous sequence element; taking the next historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value and the current sequence element as the current prediction value, determine the next sequence element of the current historical prediction sequence output by the current prediction thread through a preset exponential smoothing algorithm, and determine the next sequence element as the new current sequence element until the historical actual business volume distribution sequence is traversed; determine a current historical prediction sequence according to each sequence element output in sequence by the current prediction thread, and based on the current historical prediction sequence, determine the second current historical prediction sequence and the third current historical prediction sequence output in sequence by the current prediction thread through a preset exponential smoothing algorithm.

[0061] The preset traffic distribution parameter may be a predetermined traffic distribution parameter.

[0062] For example, taking the historical actual business volume distribution sequence as sequence A, we can first take A1 as the current observation value x t , taking the preset traffic distribution parameter M as the current prediction value The first sequence element of the current historical prediction sequence output by the current prediction thread is determined by expression (2): And determine the first sequence element as the current sequence element N1; then, A2 can be used as the current observation value And taking the current sequence element as the current prediction value, the next sequence element N2 of the current historical prediction sequence output by the current prediction thread is determined by expression (2), and the next sequence element is determined as the new current sequence element, until the historical actual business volume distribution sequence is traversed and the last sequence element N30 of the current historical prediction sequence is obtained, then the current historical prediction sequence N can be obtained based on N1 to N30; similarly, the second current historical prediction sequence can be obtained based on the first current historical prediction sequence, and the third current historical prediction sequence can be obtained based on the second current historical prediction sequence.

[0063] S230 : Determine a target prediction thread from among the prediction threads based on the historical actual business volume distribution sequence and each historical predicted business volume distribution sequence.

[0064] In one possible implementation, after determining each historical predicted business volume distribution sequence, each historical predicted business volume distribution sequence can be compared with the historical actual business volume distribution sequence, and a historical predicted business volume distribution sequence with the smallest error with the historical actual business volume distribution sequence can be determined from each historical predicted business volume distribution sequence. Then, the prediction thread corresponding to the historical predicted business volume distribution sequence can be determined as the target prediction thread.

[0065] Optionally, determining a target prediction thread from each prediction thread based on a historical actual business volume distribution sequence and each historical predicted business volume distribution sequence may include: for each historical predicted business volume distribution sequence, determining an error parameter corresponding to the current historical predicted business volume distribution sequence based on each historical actual business volume distribution parameter in the historical actual business volume distribution sequence and historical predicted business volume distribution parameters corresponding to each historical actual business volume distribution parameter in the current historical predicted business volume distribution sequence; determining a target historical predicted business volume distribution sequence from each historical predicted business volume distribution sequence according to the error parameters corresponding to each historical predicted business volume distribution sequence, and determining the prediction thread corresponding to the target historical predicted business volume distribution sequence as the target prediction thread.

[0066] In a possible implementation, the embodiment of the present invention may pre-create an exponential smoothing algorithm model based on a preset exponential smoothing algorithm, and the model may include multiple prediction threads. Figure 3 , is a schematic diagram of the processing flow of data by an exponential smoothing algorithm model provided by an embodiment of the present invention. Figure 3As shown, the historical actual business volume distribution sequence can be used as the current training set to input the exponential smoothing algorithm model. The model can first determine the error parameter RMSE corresponding to each prediction thread (i.e., 17 RMSEs corresponding to 17 threads) through a preset exponential smoothing algorithm based on the historical actual business volume distribution sequence, and then the smoothing coefficient ∝ corresponding to the smallest RMSE among the 17 RMSEs can be determined as the target smoothing coefficient, and the prediction thread corresponding to the target smoothing coefficient can be determined as the target prediction thread. Finally, the target prediction business volume distribution parameters output by the target prediction thread can be determined through a preset exponential smoothing algorithm based on the historical actual business volume distribution sequence.

[0067] S240: Taking the historical actual business volume distribution sequence as the current observation sequence, determining the target predicted business volume distribution parameters output by the target prediction thread through a preset exponential smoothing algorithm.

[0068] Optionally, taking the historical actual business volume distribution sequence as the current observation sequence, the target predicted business volume distribution parameters output by the target prediction thread are determined by a preset exponential smoothing algorithm, including: based on the last historical actual business volume distribution parameter in the historical actual business volume distribution sequence and the last sequence element in the first target historical prediction sequence output by the target prediction thread, determining the first exponential smoothing parameter output by the target prediction thread by a preset exponential smoothing algorithm; based on the first exponential smoothing parameter and the last sequence element in the second target historical prediction sequence output by the target prediction thread, determining the second exponential smoothing parameter output by the target prediction thread by a preset exponential smoothing algorithm; based on the second exponential smoothing parameter and the last sequence element in the third target historical prediction sequence output by the target prediction thread, determining the third exponential smoothing parameter output by the target prediction thread by a preset exponential smoothing algorithm, and determining the third exponential smoothing parameter as the target predicted business volume distribution parameter.

[0069] Since in the process of determining the target prediction thread, the last sequence element in the first target historical prediction sequence output by the target prediction thread, the last sequence element in the second target historical prediction sequence output by the target prediction thread, and the last sequence element in the third target historical prediction sequence output by the target prediction thread have been determined, then when determining the target prediction business volume distribution parameters, the three last sequence elements can be directly used as a reference without recalculating through the preset exponential smoothing algorithm, which can improve calculation efficiency.

[0070] S250: Determine transmission parameters for service data in a preset future time period based on target predicted service volume distribution parameters.

[0071] In the embodiment of the present invention, on the basis of the above-mentioned embodiment, each prediction thread can be created in advance for the preset exponential smoothing algorithm, and each prediction thread corresponds to a different smoothing coefficient. In each parameter adjustment cycle, before determining the target predicted traffic volume distribution parameters by the preset exponential smoothing algorithm, the historical actual traffic volume distribution sequence can be used as the current training set, and the historical predicted traffic volume distribution sequence corresponding to the historical actual traffic volume distribution sequence output by each prediction thread can be determined by the preset exponential smoothing algorithm; then, by comparing each historical predicted traffic volume distribution sequence with the historical actual traffic volume distribution sequence, a prediction effect is best determined from each prediction thread as the target prediction thread. It can be seen that in the embodiment of the present invention, the smoothing coefficient selected by the preset exponential smoothing algorithm is not a fixed value, but in each parameter adjustment cycle, the target smoothing coefficient (corresponding to the target prediction thread) is dynamically determined from each smoothing coefficient according to the prediction effect of each smoothing coefficient (corresponding to each prediction thread) on the traffic volume of the current stage. In this way, by dynamically adjusting the smoothing coefficient, the accuracy of the determined target predicted traffic volume distribution parameters can be further improved, so that the adaptability of the determined transmission parameters to the traffic volume scale of the preset future time period can be further improved, thereby reducing the occurrence of data backlog and improving the real-time performance of transmission.

[0072] It should be noted that the method for determining data transmission parameters proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0073] Reference Figure 4 , is a flow chart of another method for determining data transmission parameters provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the method for determining data transmission parameters provided by the previous embodiment, and the method for determining data transmission parameters provided by the previous embodiment is further optimized. Figure 4 As shown, the specific steps include:

[0074] S410: Obtain a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment.

[0075] S420: Taking the historical actual business volume distribution sequence as the current observation sequence, determine the target predicted business volume distribution parameters corresponding to the preset future time period after the current moment by using a preset exponential smoothing algorithm.

[0076] S430: Determine the target predicted total business volume corresponding to a preset future time period based on the target predicted business volume distribution parameters.

[0077] In one possible implementation, if the target predicted business volume distribution parameter is the total business volume predicted in a preset future time period (i.e., the collection period is not further divided), the target predicted business volume distribution parameter can be directly determined as the target predicted business volume. In another possible implementation, if the target predicted business volume distribution parameter includes target predicted business components corresponding to each collection sub-period in the preset future time period, each target predicted business component can be added to obtain the target predicted business volume.

[0078] S440, determining a target transmission batch and a target transmission interval for business data in a preset future time period based on the target predicted total business volume, the initial transmission batch, and the initial transmission time corresponding to the initial transmission batch.

[0079] The initial transmission batch may be the size of the business volume of each business data transmission that is predetermined; the initial transmission time may be the predetermined time interval between each two business data transmissions. The initial transmission time may be the sum of the initial query time and the initial sending time. The initial query time is the query time for searching the business data of the initial transmission batch from the database of the current business subsystem, and the initial sending time is the sending time for sending the business data of the initial transmission batch to another business subsystem.

[0080] Optionally, determining a target transmission batch and a target transmission interval of business data for a preset future time period based on the target predicted total business volume, the initial transmission batch, and the initial transmission time corresponding to the initial transmission batch may include: determining a current transmission interval based on the target predicted total business volume and the initial transmission batch, and determining the initial transmission batch as the current transmission batch, and determining the initial transmission time as the current transmission time; when it is determined that the current transmission interval and the current transmission time do not meet preset conditions, determining a next transmission batch based on the current transmission batch, and determining a next transmission interval based on the target predicted total business volume and the next transmission batch, and determining the next transmission batch as a new current transmission batch, determining the next transmission interval as a new current transmission interval, and determining the transmission time corresponding to the next transmission batch as a new current transmission time, until it is determined that the current transmission interval and the current transmission time meet the preset conditions; when it is determined that the current transmission interval and the current transmission time meet the preset conditions, determining the previous transmission interval of the current transmission interval as the target transmission interval, and determining the previous transmission batch of the current transmission batch as the target transmission batch.

[0081] The preset condition may be a predetermined condition, for example, the preset condition may be that the current transmission time is greater than the current transmission interval.

[0082] For example, if N represents the total target predicted business volume, M represents the initial transmission batch, and t1 represents the initial transmission time (in seconds), the current transmission interval t2 can be determined by expression (3):

[0083] t2=86400*M / N (3)

[0084] Wherein, 86400 is the number of seconds in a day. If t1 is less than or equal to t2, M=2M can be set, and a new t1 corresponding to 2M can be determined, and t2 can be recalculated until t1 is greater than t2. If t1 is greater than t2, the transmission interval determined in the previous cycle can be determined as the target transmission interval, and the transmission batch determined in the previous cycle can be determined as the target transmission batch.

[0085] Reference Figure 5 , is a flow chart of determining transmission parameters according to a target predicted total business volume provided by an embodiment of the present invention. Figure 5 As shown, the method comprises the following steps:

[0086] S4410. Determine an initial transmission batch, and determine an initial transmission time corresponding to the initial transmission batch.

[0087] S4420: Determine the initial transmission batch as the current transmission batch, and determine the initial transmission time as the current transmission time.

[0088] S4430, determining a current transmission interval based on the target predicted total business volume and the current transmission batch.

[0089] S4440. Determine whether the current transmission time is greater than the current transmission interval.

[0090] If it is determined that the current transmission time is less than or equal to the current transmission interval, execute S4450; if it is determined that the current transmission time is greater than the current transmission interval, execute S4460.

[0091] S4450, set the current transmission batch size = 2*current transmission batch size, and determine the new current transmission time consumption corresponding to the new current transmission batch size.

[0092] After S4450, return to execute step S4430.

[0093] S4460: Determine a transmission interval previous to the current transmission interval as a target transmission interval, and determine a transmission batch previous to the current transmission batch as a target transmission batch.

[0094] After determining the target transmission batch and the target transmission interval, the current business subsystem can start to transmit the business data of the preset future time period after the current moment to another business subsystem based on the target transmission batch and the target transmission interval. However, in actual applications, since there is a certain error between the predicted target predicted business volume distribution parameters and the target actual business volume distribution parameters, it may happen that the business data of the previous parameter adjustment cycle has not been sent completely. Therefore, in each parameter adjustment cycle, the business data that has not been sent completely in the previous parameter adjustment cycle can be transmitted first, and then the business data in the current parameter adjustment cycle can be transmitted.

[0095] In the embodiment of the present invention, on the basis of the above-mentioned embodiment, the initial transmission batch and the initial transmission time corresponding to the initial transmission batch can be predetermined. Afterwards, in each parameter adjustment cycle, the initial transmission batch is adjusted according to the target predicted total business volume determined in the parameter adjustment cycle, so that the adjusted target transmission batch and the target transmission interval corresponding to the target transmission batch are adapted to the scale of the business volume in the parameter adjustment cycle. In addition, the transmission time is also referred to in the process of adjusting the initial transmission batch, so that the target transmission time corresponding to the target transmission batch and the target transmission interval can be made as small as possible. Since the query time is included in the target transmission time, the embodiment of the present invention can also reduce the query time, thereby reducing the occupancy rate of the server resources of the current business subsystem.

[0096] It should be noted that the method for determining data transmission parameters proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0097] Figure 6 The present invention provides a schematic diagram of the structure of a device for determining data transmission parameters according to an embodiment of the present invention. The device includes: an acquisition module 610 and a determination module 620.

[0098] Exemplarily, the acquisition module 610 may execute S110 in the above method embodiment, and the determination module 620 may execute S120 and S130 in the above method embodiment.

[0099] Specifically, the acquisition module 610 is used to acquire a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; wherein the historical actual business volume distribution sequence is a time series sequence composed of historical actual business volume distribution parameters corresponding to each collection period in the preset historical time period;

[0100] A determination module 620 is used to determine the target predicted business volume distribution parameters corresponding to a preset future time period after the current moment by using a preset exponential smoothing algorithm with the historical actual business volume distribution sequence as the current observation sequence;

[0101] The determination module 620 is further configured to determine transmission parameters for service data in a preset future time period based on the target predicted service volume distribution parameters.

[0102] Optionally, in a possible implementation manner, the determining module 620 is specifically configured to:

[0103] Taking the historical actual business volume distribution sequence as the current training set, the historical predicted business volume distribution sequence output by each pre-created prediction thread is determined through a preset exponential smoothing algorithm; wherein each prediction thread corresponds to a different smoothing coefficient; based on the historical actual business volume distribution sequence and each historical predicted business volume distribution sequence, a target prediction thread is determined from each prediction thread; taking the historical actual business volume distribution sequence as the current observation sequence, the target predicted business volume distribution parameters output by the target prediction thread are determined through a preset exponential smoothing algorithm.

[0104] Optionally, in another possible implementation, the preset exponential smoothing algorithm is a cubic exponential smoothing algorithm, and the determination module 620 is further specifically configured to:

[0105] For each prediction thread, the historical actual business volume distribution sequence is used as the current training set, and the preset exponential smoothing algorithm is used to determine the first current historical prediction sequence, the second current historical prediction sequence, and the third current historical prediction sequence output in sequence by the current prediction thread, and the third current historical prediction sequence is determined as the historical prediction business volume distribution sequence output by the current prediction thread.

[0106] Optionally, in another possible implementation, the determining module 620 is further configured to:

[0107] Taking the first historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value and the preset business volume distribution parameter as the current prediction value, the first sequence element of the current historical prediction sequence output by the current prediction thread is determined by the preset exponential smoothing algorithm, and the first sequence element is determined as the current sequence element; taking the next historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value and the current sequence element as the current prediction value, the next sequence element of the current historical prediction sequence output by the current prediction thread is determined by the preset exponential smoothing algorithm, and the next sequence element is determined as the new current sequence element until the historical actual business volume distribution sequence is traversed; a current historical prediction sequence is determined according to each sequence element output in sequence by the current prediction thread, and based on the current historical prediction sequence, a second current historical prediction sequence and a third current historical prediction sequence output in sequence by the current prediction thread are determined by the preset exponential smoothing algorithm.

[0108] Optionally, in another possible implementation, the determining module 620 is further configured to:

[0109] Based on the last historical actual business volume distribution parameter in the historical actual business volume distribution sequence and the last sequence element in the first target historical prediction sequence output by the target prediction thread, the first exponential smoothing parameter output by the target prediction thread is determined by a preset exponential smoothing algorithm; based on the first exponential smoothing parameter and the last sequence element in the second target historical prediction sequence output by the target prediction thread, the second exponential smoothing parameter output by the target prediction thread is determined by a preset exponential smoothing algorithm; based on the second exponential smoothing parameter and the last sequence element in the third target historical prediction sequence output by the target prediction thread, the third exponential smoothing parameter output by the target prediction thread is determined by a preset exponential smoothing algorithm, and the third exponential smoothing parameter is determined as the target prediction business volume distribution parameter.

[0110] Optionally, in another possible implementation, the determination module 620 is specifically used to: for each historical predicted business volume distribution sequence, determine the error parameter corresponding to the current historical predicted business volume distribution sequence based on each historical actual business volume distribution parameter in the historical actual business volume distribution sequence and the historical predicted business volume distribution parameters corresponding to each historical actual business volume distribution parameter in the current historical predicted business volume distribution sequence; determine the target historical predicted business volume distribution sequence from each historical predicted business volume distribution sequence according to the error parameters corresponding to each historical predicted business volume distribution sequence, and determine the prediction thread corresponding to the target historical predicted business volume distribution sequence as the target prediction thread.

[0111] Optionally, in another possible implementation, the determination module 620 is specifically used to: determine the target predicted total business volume corresponding to a preset future time period based on the target predicted business volume distribution parameters; determine the target transmission batch and target transmission interval of business data for a preset future time period based on the target predicted total business volume, the initial transmission batch, and the initial transmission time corresponding to the initial transmission batch.

[0112] Optionally, in another possible implementation, the determining module 620 is further configured to:

[0113] The current transmission interval is determined based on the target predicted total business volume and the initial transmission batch, and the initial transmission batch is determined as the current transmission batch, and the initial transmission time is determined as the current transmission time; when it is determined that the current transmission interval and the current transmission time do not meet the preset conditions, the next transmission batch is determined based on the current transmission batch, and the next transmission interval is determined based on the target predicted total business volume and the next transmission batch, and the next transmission batch is determined as the new current transmission batch, the next transmission interval is determined as the new current transmission interval, and the transmission time corresponding to the next transmission batch is determined as the new current transmission time, until it is determined that the current transmission interval and the current transmission time meet the preset conditions; when it is determined that the current transmission interval and the current transmission time meet the preset conditions, the previous transmission interval of the current transmission interval is determined as the target transmission interval, and the previous transmission batch of the current transmission batch is determined as the target transmission batch.

[0114] Optionally, in another possible implementation, for each historical actual business volume distribution parameter in the historical actual business volume distribution sequence, the current historical actual business volume distribution parameter includes the historical actual business components corresponding to each collection sub-period in the current collection period; the target predicted business volume distribution parameter includes the target predicted business components corresponding to each collection sub-period in a preset future time period.

[0115] Optionally, in another possible implementation manner, the device for determining data transmission parameters provided by the embodiment of the present invention may further include an updating module;

[0116] The acquisition module 610 is also used to obtain the target actual business volume distribution parameters corresponding to the preset future time period after determining the transmission parameters of the business data for the preset future time period based on the target predicted business volume distribution parameters; the update module is used to update the historical actual business volume distribution sequence based on the target actual business volume distribution parameters.

[0117] The device for determining data transmission parameters provided in an embodiment of the present invention belongs to the same inventive concept as the method for determining data transmission parameters provided in the aforementioned embodiments. For details not fully described in the embodiment of the device for determining data transmission parameters, reference can be made to the relevant contents of the aforementioned method embodiments, and the corresponding beneficial effects can also be referred to the beneficial effect analysis of the aforementioned method embodiments.

[0118] Figure 7 A schematic diagram of the structure of a device for determining data transmission parameters provided by an embodiment of the present invention. Figure 7 A block diagram of an exemplary data transmission parameter determination device 12 suitable for implementing an embodiment of the present invention is shown. Figure 7 The data transmission parameter determination device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0119] like Figure 7 As shown, the data transmission parameter determination device 12 is in the form of a general-purpose computing device. The components of the data transmission parameter determination device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0120] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0121] The data transmission parameter determination device 12 typically includes a variety of computer system readable media, which can be any available media that can be accessed by the data transmission parameter determination device 12, including volatile and non-volatile media, removable and non-removable media.

[0122] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory (i.e., Figure 7 The data transmission parameter determination device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0123] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0124] The data transmission parameter determination device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with the data transmission parameter determination device 12, and / or communicate with any device that enables the data transmission parameter determination device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the data transmission parameter determination device 12 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 20. Figure 7 As shown, the network adapter 20 communicates with other modules of the data transmission parameter determination device 12 via the bus 18. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with the data transmission parameter determination device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, such as implementing the steps of the method for determining the data transmission parameters provided in the embodiment of the present invention, the method comprising: obtaining a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; using the historical actual business volume distribution sequence as the current observation sequence, determining the target predicted business volume distribution parameters corresponding to the preset future time period after the current moment by a preset exponential smoothing algorithm; and determining the transmission parameters for the business data for the preset future time period based on the target predicted business volume distribution parameters.

[0126] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the method for determining data transmission parameters provided by any embodiment of the present invention.

[0127] The present embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of a method for determining data transmission parameters as provided in the aforementioned embodiment of the present invention are implemented. The method includes: obtaining a historical actual business volume distribution sequence corresponding to a preset historical time period before a current moment; using the historical actual business volume distribution sequence as a current observation sequence, determining a target predicted business volume distribution parameter corresponding to a preset future time period after the current moment by a preset exponential smoothing algorithm; and determining the transmission parameters for business data for the preset future time period based on the target predicted business volume distribution parameter.

[0128] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0129] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0130] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0131] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or a device determining data transmission parameters. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0132] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0133] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining data transmission parameters, characterized in that: The method comprises: Obtaining a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; wherein the historical actual business volume distribution sequence is a time series sequence composed of historical actual business volume distribution parameters corresponding to each collection period within the preset historical time period; Taking the historical actual business volume distribution sequence as the current observation sequence, determining the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment by a preset exponential smoothing algorithm; The transmission parameters of the service data for the preset future time period are determined based on the target predicted service volume distribution parameters.

2. The method for determining data transmission parameters according to claim 1, characterized in that: The method of taking the historical actual business volume distribution sequence as the current observation sequence and determining the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment by a preset exponential smoothing algorithm includes: Taking the historical actual business volume distribution sequence as the current training set, determining the historical predicted business volume distribution sequence output by each pre-created prediction thread respectively through the preset exponential smoothing algorithm; wherein each prediction thread corresponds to a different smoothing coefficient; Determining a target prediction thread from the prediction threads based on the historical actual business volume distribution sequence and each of the historical predicted business volume distribution sequences; The historical actual business volume distribution sequence is used as the current observation sequence, and the target predicted business volume distribution parameters output by the target prediction thread are determined by the preset exponential smoothing algorithm.

3. The method for determining data transmission parameters according to claim 2, characterized in that: The preset exponential smoothing algorithm is a cubic exponential smoothing algorithm, and the historical actual business volume distribution sequence is used as the current training set, and the historical predicted business volume distribution sequence output by each prediction thread created in advance is determined by the preset exponential smoothing algorithm, including: For each prediction thread, the historical actual business volume distribution sequence is used as the current training set, and the preset exponential smoothing algorithm is used to determine the first current historical prediction sequence, the second current historical prediction sequence, and the third current historical prediction sequence output in sequence by the current prediction thread, and the three current historical prediction sequences are determined as the historical prediction business volume distribution sequence output by the current prediction thread.

4. The method for determining data transmission parameters according to claim 3, characterized in that: The method uses the historical actual business volume distribution sequence as the current training set, determines the first current historical prediction sequence, the second current historical prediction sequence, and the third current historical prediction sequence outputted in sequence by the current prediction thread through the preset exponential smoothing algorithm, and determines the third current historical prediction sequence as the historical prediction business volume distribution sequence outputted by the current prediction thread, including: Taking the first historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value and taking the preset business volume distribution parameter as the current prediction value, determining the first sequence element of the current historical prediction sequence output by the current prediction thread through the preset exponential smoothing algorithm, and determining the first sequence element as the current sequence element; Taking the next historical actual business volume distribution parameter in the historical actual business volume distribution sequence as the current observation value and the current sequence element as the current prediction value, determining the next sequence element of the current historical prediction sequence output by the current prediction thread through the preset exponential smoothing algorithm, and determining the next sequence element as the new current sequence element until the historical actual business volume distribution sequence is traversed; The first current historical prediction sequence is determined according to each sequence element sequentially output by the current prediction thread, and based on the first current historical prediction sequence, the second current historical prediction sequence and the third current historical prediction sequence sequentially output by the current prediction thread are determined by the preset exponential smoothing algorithm.

5. The method for determining data transmission parameters according to claim 3, characterized in that: The method of taking the historical actual business volume distribution sequence as the current observation sequence and determining the target predicted business volume distribution parameter output by the target prediction thread through the preset exponential smoothing algorithm includes: Based on the last historical actual business volume distribution parameter in the historical actual business volume distribution sequence and the last sequence element in the primary target historical prediction sequence output by the target prediction thread, determining the primary exponential smoothing parameter output by the target prediction thread by the preset exponential smoothing algorithm; Based on the first exponential smoothing parameter and the last sequence element in the second target historical prediction sequence output by the target prediction thread, determine the second exponential smoothing parameter output by the target prediction thread by the preset exponential smoothing algorithm; Based on the quadratic exponential smoothing parameters and the last sequence element in the triple target historical prediction sequence output by the target prediction thread, the triple exponential smoothing parameters output by the target prediction thread are determined by the preset exponential smoothing algorithm, and the triple exponential smoothing parameters are determined as the target prediction business volume distribution parameters.

6. The method for determining data transmission parameters according to claim 2, characterized in that: The determining a target prediction thread from the prediction threads based on the historical actual business volume distribution sequence and the historical predicted business volume distribution sequences includes: For each of the historical predicted traffic volume distribution sequences, based on each of the historical actual traffic volume distribution parameters in the historical actual traffic volume distribution sequence and the historical predicted traffic volume distribution parameters in the current historical predicted traffic volume distribution sequence that respectively correspond to each of the historical actual traffic volume distribution parameters, determine an error parameter corresponding to the current historical predicted traffic volume distribution sequence; According to the error parameters corresponding to each of the historical predicted business volume distribution sequences, a target historical predicted business volume distribution sequence is determined from each of the historical predicted business volume distribution sequences, and the prediction thread corresponding to the target historical predicted business volume distribution sequence is determined as the target prediction thread.

7. The method for determining data transmission parameters according to claim 1, characterized in that: The determining, based on the target predicted traffic volume distribution parameter, a transmission parameter for the traffic data in the preset future time period includes: Determining the target predicted business volume distribution parameter corresponding to the preset future time period; Based on the target predicted total business volume, the initial transmission batch, and the initial transmission time corresponding to the initial transmission batch, a target transmission batch and a target transmission interval for business data in the preset future time period are determined.

8. The method for determining data transmission parameters according to claim 7, characterized in that: The determining, based on the target predicted total business volume, the initial transmission batch, and the initial transmission time consumption corresponding to the initial transmission batch, a target transmission batch and a target transmission interval for business data in the preset future time period comprises: Determine a current transmission interval based on the target predicted total business volume and the initial transmission batch, determine the initial transmission batch as the current transmission batch, and determine the initial transmission time as the current transmission time; In the case where it is determined that the current transmission interval and the current transmission time do not meet the preset conditions, the next transmission batch is determined based on the current transmission batch, and the next transmission interval is determined based on the target predicted total business volume and the next transmission batch, and the next transmission batch is determined as the new current transmission batch, the next transmission interval is determined as the new current transmission interval, and the transmission time corresponding to the next transmission batch is determined as the new current transmission time, until it is determined that the current transmission interval and the current transmission time meet the preset conditions; When it is determined that the current transmission interval and the current transmission time meet the preset condition, the previous transmission interval of the current transmission interval is determined as the target transmission interval, and the previous transmission batch of the current transmission batch is determined as the target transmission batch.

9. The method for determining data transmission parameters according to claim 1, characterized in that: After determining the transmission parameters of the service data for the preset future time period based on the target predicted service volume distribution parameters, the method further includes: Obtaining target actual business volume distribution parameters corresponding to the preset future time period; The historical actual traffic volume distribution sequence is updated based on the target actual traffic volume distribution parameter.

10. The method for determining data transmission parameters according to any one of claims 1 to 9, characterized in that: For each historical actual business volume distribution parameter in the historical actual business volume distribution sequence, the current historical actual business volume distribution parameter includes the historical actual business components corresponding to each acquisition sub-period in the current acquisition period; the target predicted business volume distribution parameter includes the target predicted business components corresponding to each acquisition sub-period in the preset future time period.

11. A device for determining data transmission parameters, characterized in that: include: An acquisition module is used to acquire a historical actual business volume distribution sequence corresponding to a preset historical time period before the current moment; wherein the historical actual business volume distribution sequence is a time series sequence composed of historical actual business volume distribution parameters corresponding to each collection period in the preset historical time period; A determination module, configured to use the historical actual business volume distribution sequence as the current observation sequence and determine the target predicted business volume distribution parameter corresponding to the preset future time period after the current moment by a preset exponential smoothing algorithm; The determination module is further configured to determine, based on the target predicted traffic volume distribution parameter, a transmission parameter for the traffic data in the preset future time period.

12. A device for determining data transmission parameters, characterized in that: The data transmission parameter determination device includes: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining data transmission parameters as described in any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining data transmission parameters as described in any one of claims 1 to 10 is implemented.

Images