Data processing method, apparatus, device, and medium

Abstract

Embodiments of the present application provide a data processing method, device, equipment and medium, comprising: acquiring, in time sequence, a first user quantity in a target area in N first time periods and N second user quantities output by a model; calculating a ratio of a first difference value in each adjacent two first time periods in the N first time periods to obtain a first ratio; and in a case where N-1 first ratios are all greater than a first preset threshold, adjusting parameters of the model to make at least one of the N-1 first ratios less than the first preset threshold. Embodiments of the present application improve the accuracy of the model.

Description

Technical Field

[0001] This application belongs to the field of wireless network technology, and in particular relates to a data processing method, apparatus, device and medium. Background Technology

[0002] In communication systems, the tidal effect refers to the phenomenon where people gather in large numbers in central business districts during working hours and migrate to residential areas after get off work. A tidal model, based on the tidal effect, is used to predict changes in the number of users in a given area, preventing sudden surges in call volume and network congestion caused by a sudden increase in the number of users at a specific time.

[0003] However, in existing technologies, since tidal models are mainly static models built based on historical data, they are prone to distortion and deviation when facing sudden situations, resulting in low model accuracy. Summary of the Invention

[0004] This application provides a model parameter adjustment method, apparatus, device, and medium, which improves the accuracy of the model.

[0005] In a first aspect, embodiments of this application provide a data processing method, the method comprising:

[0006] In chronological order, the number of first users in the target area within N first time periods is continuously obtained, along with the number of N second users output by the model. The number of N second users is the predicted value of the number of users in the target area within the corresponding N first time periods, where N is a positive integer greater than 1.

[0007] Calculate the ratio of the first difference between any two adjacent first time periods in N first time periods to obtain the first ratio. The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users in the corresponding first time period output by the model.

[0008] If all N-1 first ratios are greater than the first preset threshold, the parameters of the model are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold, wherein the first ratio is the ratio of the first difference between any two adjacent first time periods in the N consecutive first time periods.

[0009] In an optional implementation of the first aspect, when all N-1 first ratios are greater than a first preset threshold, adjusting the model parameters includes:

[0010] When all N-1 first ratios are greater than the first preset threshold, the number of third users in the target area in multiple second time periods and the number of fourth users output by the model are obtained in chronological order. The number of fourth users is the predicted value of the number of users in the target area in the corresponding multiple second time periods. The sum of the durations of the multiple second time periods is equal to the duration of the first time period.

[0011] The first value is calculated based on the number of third users in the target area within multiple consecutive second time periods, and the number of fourth users output by the model.

[0012] If the first value does not meet the first preset condition, the parameters of the model are adjusted so that the first value calculated based on the number of second users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

[0013] In one optional implementation of the first aspect, a first value is calculated based on the number of third users in the target area within a plurality of consecutively acquired second time periods and the plurality of fourth user numbers output by the model. Calculating the first value includes:

[0014] Calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and obtain multiple second differences;

[0015] According to the time order, the multiple second differences are divided into M difference groups. Each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0.

[0016] Based on M first preset coefficients, a weighted sum is performed on at least one second difference included in the M difference groups to obtain a second value;

[0017] The ratio of the second value to the sum of M first preset coefficients is determined as the first value.

[0018] In one optional implementation of the first aspect, the first preset condition includes a first value greater than a second preset threshold, and the ratio of the first value to the first preset value being greater than a third preset threshold. The first preset value is the number of users in the target area when the physical resource block (PRB) utilization rate is within a preset range.

[0019] Secondly, embodiments of this application provide a data processing apparatus, which includes: an acquisition module, configured to acquire, in chronological order, the number of first users in a target area within N first time periods, and the number of N second users output by a model, wherein the number of N second users is a predicted value of the number of users in the target area within the corresponding N first time periods, and N is a positive integer greater than 1;

[0020] The calculation module is used to calculate the ratio of the first difference between every two adjacent first time periods in N first time periods, and obtain the first ratio. The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users in the corresponding first time period output by the model.

[0021] The adjustment module is used to adjust the parameters of the model when all N-1 first ratios are greater than the first preset threshold, so that at least one of the N-1 consecutive first ratios is less than the first preset threshold, wherein the first ratio is the ratio of the first difference between any two adjacent first time periods in the N consecutive first time periods.

[0022] In an alternative implementation of the second aspect, the adjustment module includes:

[0023] The acquisition submodule is used to continuously acquire the number of third users in the target area within multiple second time periods in chronological order, and the number of fourth users output by the model, when all N-1 first ratios are greater than the first preset threshold. The number of fourth users is the predicted value of the number of users in the target area within the corresponding multiple second time periods, and the sum of the durations of the multiple second time periods is equal to the duration of the first time period.

[0024] The calculation submodule is used to calculate the first value based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model.

[0025] The adjustment submodule is used to adjust the parameters of the model when the first value does not meet the first preset condition, so that the first value calculated based on the number of second users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

[0026] In an alternative implementation of the second aspect, the computation submodule includes:

[0027] The calculation unit is used to calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and to obtain multiple second differences.

[0028] A partitioning unit is used to divide multiple second differences into M difference groups according to time order. Each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0.

[0029] The weighted summation unit is used to perform a weighted summation on at least one second difference included in the M difference groups based on M first preset coefficients to obtain a second value;

[0030] The determining unit is used to determine the ratio of the second value to the sum of M first preset coefficients, which is the first value.

[0031] Thirdly, an electronic device is provided, comprising: a memory for storing computer program instructions; and a processor for reading and executing the computer program instructions stored in the memory to perform a data processing method provided by any optional embodiment of the first and second aspects.

[0032] Fourthly, a computer storage medium is provided, on which computer program instructions are stored, wherein when the computer program instructions are executed by a processor, the data processing method provided by any optional implementation of the first and second aspects is implemented.

[0033] Fifthly, a computer program product is provided, wherein when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device performs a data processing method that implements any optional embodiment of the first and second aspects.

[0034] In this embodiment, by sequentially acquiring the number of first users in the target area within N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, the ratio of the first difference between any two adjacent first time periods can be calculated based on the number of first users and the number of second users within the target area within the N first time periods. If all N-1 first ratios are greater than a first preset threshold, the model parameters are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold. Thus, by using the actual number of first users in the target area within the N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, it is possible to determine whether the model is abnormal, and the accuracy of the model can be improved by adjusting the model parameters. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating a data processing method provided in an embodiment of this application;

[0037] Figure 2 This is a flowchart illustrating another data processing method provided in an embodiment of this application;

[0038] Figure 3 This is a flowchart illustrating another data processing method provided in the embodiments of this application.

[0039] Figure 4 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0040] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0042] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0043] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0044] In real-world applications, to address the low accuracy of existing tidal models, this application provides a data processing method, apparatus, device, and medium. This method sequentially acquires the number of first users within a target area over N first time periods, along with the model's predicted number of users within the target area over the corresponding N first time periods. Based on the number of first users and N second users within the target area over the N first time periods, it calculates the ratio of the first difference between any two adjacent first time periods. If all N-1 first ratios are greater than a first preset threshold, the model parameters are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold. Thus, by using the actual number of first users within the target area over the N first time periods and the model's predicted number of users within the target area over the corresponding N first time periods, the model's accuracy can be determined, and the model's parameters can be adjusted to improve its accuracy.

[0045] The data processing method provided in this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] Figure 1 This is a flowchart illustrating a data processing method provided in an embodiment of this application.

[0047] like Figure 1 As shown, the execution device for this data processing method is the operator's server, and it may specifically include the following steps:

[0048] S110: In chronological order, continuously obtain the number of first users in the target area within N first time periods, and the number of second users output by the model.

[0049] The first time period can be any duration set by the operator's server, such as a one-hour period or a 24-hour period; no specific limitation is made here. The first user count can be the actual number of users accessing the internet within the target area during a specific first time period. The model is used to predict the number of users within the target area during a specific time period. The model outputs N second user counts, which are the predicted values ​​of the number of users within the target area during the corresponding N first time periods, where N is a positive integer greater than 1. The target area can be an area divided by cell blocks or an area managed by the operator's server; no specific limitation is made here.

[0050] Specifically, after a user logs into the server using a temporary network allocation code, the server can, in chronological order, capture the actual number of users online within each first time period by taking a snapshot, thus continuously obtaining the number of first users in the target area within N first time periods per year. Additionally, the server can use user counts from historical time periods to obtain N predicted user counts from the model output, corresponding to N first time periods within the target area; these are the N second user counts.

[0051] S120, calculate the ratio of the first difference between any two adjacent first time periods in N first time periods, and obtain the first ratio.

[0052] The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users in the corresponding first time period output by the model.

[0053] Specifically, after continuously acquiring the number of first users in the target area within N first time periods and the number of N second users output by the model, the data processing device can calculate a first difference based on the number of first users in the target area within each of the N first time periods and the number of second users output by the model for the corresponding first time period, thus obtaining N first differences. Furthermore, based on the ratio of the first differences between any two adjacent first time periods within the N first time periods, N-1 first ratios can be obtained. This allows for subsequent judgment of whether the model is abnormal based on the N-1 first ratios, thereby improving the accuracy of the model.

[0054] In one example, assuming N=3, the server needs to continuously obtain the number of first users in the target area within three consecutive time periods, as well as the number of three second users output by the model. If the three consecutive time periods are 10:00-11:00, 12:00-13:00, and 13:00-14:00, the server needs to continuously obtain the number of first users in the target area for each of these three time periods, A1, A2, and A3, respectively, and the number of second users in the target area for each of these three time periods, B1, B2, and B3, respectively, output by the model. For the time period from 10:00 to 11:00, the server needs to calculate the first difference C1 between the number of first users A1 in the target area during 10:00-11:00 and the number of second users B1 in the target area during the same period output by the model. Based on this, the server calculates the difference between the number of first users and the number of second users in the remaining two time periods to obtain the first difference C2 and the first difference C3. Then, based on the first difference corresponding to each two adjacent time periods, namely the first difference C1 and the first difference C2, and the first difference C2 and the first difference C3, the server can calculate the first ratio C2 / C1 and the first ratio C3 / C2.

[0055] S130, when all N-1 first ratios are greater than the first preset threshold, adjust the parameters of the model so that at least one of the N-1 consecutive first ratios is less than the first preset threshold.

[0056] The first ratio is the ratio of the first difference between any two adjacent first time periods within N consecutive first time periods. The first preset threshold is a threshold preset based on actual conditions or experience, and is not specifically limited here.

[0057] After obtaining N-1 first ratios, if all N-1 first ratios are greater than the first preset threshold, it indicates that the change in the number of users in the target area exceeds expectations, meaning the model is abnormal. In this case, the model parameters need to be adjusted until at least one of the N-1 consecutive first ratios is less than the first preset threshold. This indicates that the change in the number of users in the target area has not exceeded expectations, the model can run normally, and there is no need to adjust the model parameters.

[0058] In this embodiment, by sequentially acquiring the number of first users in the target area within N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, the ratio of the first difference between any two adjacent first time periods can be calculated based on the number of first users and the number of second users within the target area within the N first time periods. If all N-1 first ratios are greater than a first preset threshold, the model parameters are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold. Thus, by using the actual number of first users in the target area within the N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, it is possible to determine whether the model is abnormal, and the accuracy of the model can be improved by adjusting the model parameters.

[0059] To more accurately determine whether a model is abnormal, and thus to accurately adjust the model's parameters, in one embodiment, such as... Figure 2 As shown, the S130 mentioned above can specifically include the following steps:

[0060] S210, when all N-1 first ratios are greater than the first preset threshold, the number of third users in the target area within multiple second time periods and the number of fourth users output by the model are continuously acquired in chronological order.

[0061] The third user count is the actual number of users in the target area within a certain second time period. The multiple fourth user counts are the predicted values ​​of the number of users in the target area within the corresponding multiple second time periods. In other words, the fourth user count is the predicted value of the number of users in the target area output by the model within a certain second time period. The sum of the durations of the multiple second time periods is equal to the duration of the first time period.

[0062] Specifically, if N-1 first ratios are all greater than a first preset threshold, the server can, in chronological order, capture the actual number of users online within the current second time period by taking instantaneous photos at each second time period, thereby continuously acquiring the number of third users in the target area within multiple second time periods. Additionally, the server can utilize user counts from historical time periods to obtain multiple predicted values ​​of user counts in the target area corresponding to multiple second time periods, i.e., N fourth user counts. Thus, even if N-1 consecutive first ratios are greater than the first preset threshold, indicating potential model anomalies, by using second time periods smaller than the first time periods, the server can acquire multiple third user counts in the target area within multiple second time periods, as well as multiple fourth user counts output by the model, for further evaluation of the model.

[0063] S220, calculate the first value based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model.

[0064] After the server continuously acquires the number of third users in the target area within multiple second time periods, and the model outputs multiple fourth user counts, the server can calculate a first value based on the acquired number of third users in the target area within multiple second time periods and the model output multiple fourth user counts. This first value is useful for subsequently judging whether the model is abnormal, so that the model parameters can be adjusted more accurately and the model accuracy can be improved.

[0065] S230, if the first value does not meet the first preset condition, adjust the parameters of the model so that the first value calculated based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

[0066] If the calculated first value does not meet the first preset condition, the server can determine that the model is abnormal. It can then adjust the model's parameters so that the first value, calculated based on the number of third users in the target area over multiple consecutive second time periods and the number of fourth users output by the model, meets the first preset condition. This adjustment continues until the model functions normally. The first preset condition is a pre-set condition based on actual needs or empirical values, used to determine whether the model is abnormal.

[0067] In this embodiment, if all N-1 first ratios are greater than a first preset threshold (i.e., the model is abnormal), the server can sequentially acquire the number of third users in the target area within multiple second time periods, as well as the number of fourth users output by the model. Based on these acquired numbers of third users and fourth users, a first value can be calculated. This first value, along with the first preset condition, allows for further determination of model abnormality. If the model is abnormal, its parameters are adjusted to ensure normal operation. Thus, by using a second time period shorter than the first time period and acquiring the number of third users and fourth users within the target area within multiple second time periods, the server can further determine model abnormality. This allows for adjustment of model parameters in case of abnormality, effectively correcting the model and improving its accuracy.

[0068] In order to accurately calculate the first value, in one embodiment, the above-mentioned S220 may specifically include the following steps:

[0069] Calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and obtain multiple second differences;

[0070] According to the time order, the multiple second differences are divided into M difference groups. Each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0.

[0071] Based on M first preset coefficients, a weighted sum is performed on at least one second difference included in the M difference groups to obtain a second value;

[0072] The ratio of the second value to the sum of M first preset coefficients is determined as the first value.

[0073] The second difference is the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users output by the model corresponding to that second time period. The M first preset coefficients are set based on the temporal relationship of the M third time periods in the first time period, and the sum of the durations of the M third time periods is equal to the duration of the first time period. For example, the first time period is from 10:00 to 11:00, which includes three third time periods: 10:00 to 10:20, 10:20 to 10:40, and 10:40 to 11:00. Each third time period corresponds to a first preset coefficient, which can be set according to the temporal relationship of the three third time periods within the first time period of 10:00 to 11:00. For example, the first preset coefficient corresponding to the time period of 10:40 to 11:00 can be the largest, the first preset coefficient corresponding to the time period of 10:20 to 10:40 can be the second largest, and the first preset coefficient corresponding to the time period of 10:00 to 10:20 can be the smallest. The specific setting method of the first preset coefficient is not specifically limited here.

[0074] Specifically, the first value can be calculated using the following formula (1). :

[0075] = (1)

[0076] Where i is the number of the third time period, and its value ranges from i= , The first preset coefficient, This is the second difference.

[0077] In this embodiment, after obtaining the number of third users in the target area within multiple time periods and the number of fourth users output by the model, the server calculates the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users output by the model corresponding to that second time period, thus obtaining multiple second differences. Based on the existing order of the multiple second preset time periods corresponding to these second differences, the multiple second time periods are divided into M difference groups. Subsequently, based on M first preset coefficients, at least one second difference included in the M difference groups is weighted and summed to obtain a second value. Then, the ratio of the second value to the sum of the M first preset coefficients is used as the first value. In this way, the first value can be accurately determined, facilitating a more accurate determination of whether the model is abnormal, thereby improving the model's accuracy.

[0078] In one embodiment, the first preset condition involved in S230 above includes a first value being less than a second preset threshold, and the ratio of the first value to the first preset value being less than a third preset threshold, wherein the first preset value is the number of users in the target area when the physical block resource (PRB) utilization rate is within a preset range.

[0079] The second preset threshold, first preset value, third preset threshold, and preset range are all preset based on actual conditions or experience values, and are not specifically limited here. For example, the first threshold value could be the number of users in the target area when the PRB utilization rate is between 25% and 30%, or the number of users in the target area when the PRB utilization rate is between 30%.

[0080] In this embodiment, after the server calculates the first value, it can determine whether the model is abnormal by judging whether the first value is less than a second preset threshold. If the first value is greater than the second preset threshold, it indicates that the model is abnormal. It can further determine whether the model is abnormal by judging whether the ratio of the first value to the first preset value is less than a third preset threshold. If the ratio of the first value to the first preset value is greater than the third preset threshold, it can be determined that the model is abnormal. In this way, by accurately judging whether the model is abnormal, the model parameters can be adjusted more accurately, thereby improving the accuracy of the model.

[0081] To more clearly and completely describe the data processing method provided in the embodiments of this application, such as... Figure 3 As shown, the data processing method provided in this application embodiment may specifically include the following steps:

[0082] S301: In chronological order, continuously obtain the number of first users in the target area within N first time periods, and the number of N second users output by the model. See S110 for details, which will not be repeated here.

[0083] S302 calculates the ratio of the first difference between any two adjacent first time periods in the N first time periods to obtain the first ratio. For details, please refer to S120, which will not be repeated here.

[0084] S303, determine whether all N-1 first ratios are greater than the first preset threshold. If yes, execute S304; otherwise, execute S308.

[0085] S304: In chronological order, continuously acquire the number of third users within the target area during multiple second time periods, as well as the number of fourth users output by the model. See S210 for details; it will not be repeated here.

[0086] S305: Calculate the first value based on the number of third users within the target area during multiple consecutively acquired second time periods, and the number of fourth users output by the model. See S220 for details, which will not be repeated here.

[0087] S306, determine whether the first value does not meet the first preset condition. If yes, execute S307; otherwise, execute S308.

[0088] S307, Adjust the model parameters

[0089] S308, the model is executing normally.

[0090] In this embodiment, by sequentially acquiring the number of first users in the target area within N first time periods and the number of N second users output by the model, a first ratio is obtained by calculating the ratio of the first difference between any two adjacent first time periods within the N first time periods. Then, if all N-1 first ratios are greater than a first preset threshold, the number of third users in the target area within multiple second time periods and the number of fourth users output by the model are acquired. Based on this, a first value is calculated. If the first value does not meet a first preset condition, the model parameters are adjusted. This allows for effective judgment of model anomalies, and if anomalies are determined, model parameters can be adjusted, improving the model's accuracy.

[0091] Based on the same inventive concept, embodiments of this application also provide a data processing apparatus. (Specifically combined with...) Figure 4 The data processing apparatus provided in the embodiments of this application will be described in detail.

[0092] Figure 4 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application.

[0093] like Figure 4 As shown, the data processing device 400 may include: an acquisition module 410, a calculation module 420, and an adjustment module 430.

[0094] The acquisition module 410 is used to continuously acquire, in chronological order, the number of first users in the target area within N first time periods, and the number of N second users output by the model. The number of N second users is the predicted value of the number of users in the target area within the corresponding N first time periods, and N is a positive integer greater than 2.

[0095] The calculation module 420 is used to calculate the ratio of the first difference between every two adjacent first time periods in N first time periods, and obtain the first ratio. The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users in the corresponding first time period output by the model.

[0096] The adjustment module 430 is used to adjust the parameters of the model when all N-1 first ratios are greater than the first preset threshold, so that at least one of the N-1 consecutive first ratios is less than the first preset threshold, wherein the first ratio is the ratio of the first difference between any two adjacent first time periods in the N consecutive first time periods.

[0097] In one embodiment, the adjustment module includes an acquisition submodule, a calculation submodule, and an adjustment submodule.

[0098] The acquisition submodule is used to continuously acquire, in chronological order, the number of third users in the target area within multiple second time periods, and the number of fourth users output by the model, when all N-1 first ratios are greater than the first preset threshold. The number of fourth users is the predicted value of the number of users in the target area within the corresponding multiple second time periods, and the sum of the durations of the multiple second time periods is equal to the duration of the first time period.

[0099] The calculation submodule is used to calculate the first value based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model.

[0100] The adjustment submodule is used to adjust the parameters of the model when the first value does not meet the first preset condition, so that the first value calculated based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

[0101] In one embodiment, the calculation submodule includes a calculation unit, a partitioning unit, a weighted summation unit, and a determination unit.

[0102] The calculation unit is used to calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and to obtain multiple second differences.

[0103] A partitioning unit is used to divide multiple second differences into M difference groups according to time order. Each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0.

[0104] The weighted summation unit is used to perform a weighted summation on at least one second difference included in the M difference groups based on M first preset coefficients to obtain a second value;

[0105] The determining unit is used to determine the ratio of the second value to the sum of M first preset coefficients, which is the first value.

[0106] In one embodiment, the first preset condition includes a first value being less than a second preset threshold, and the ratio of the first value to the first preset value being less than a third preset threshold. The first preset value is the number of users in the target area when the physical resource block (PRB) utilization rate is within a preset range.

[0107] In this embodiment, by sequentially acquiring the number of first users in the target area within N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, the ratio of the first difference between any two adjacent first time periods can be calculated based on the number of first users and the number of second users within the target area within the N first time periods. If all N-1 first ratios are greater than a first preset threshold, the model parameters are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold. Thus, by using the actual number of first users in the target area within the N first time periods and the predicted number of users in the target area within the corresponding N first time periods output by the model, it is possible to determine whether the model is abnormal, and then improve the model's accuracy by adjusting the model parameters.

[0108] The various modules in the data processing apparatus provided in the embodiments of this application can achieve... Figure 1 and Figure 2 The method steps of the illustrated embodiment, and the corresponding technical effects they achieve, will not be described in detail here for the sake of brevity.

[0109] Figure 5 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0110] An electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0111] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0112] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.

[0113] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0114] The processor 501 implements any of the data processing methods described in the above embodiments by reading and executing computer program instructions stored in the memory 502.

[0115] In one example, the electronic device may also include a communication interface 503 and a bus 510. Wherein, as... Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0116] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0117] Bus 510 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0118] Furthermore, in conjunction with the data processing methods described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the data processing method provided in this application embodiment.

[0119] This application also provides a computer program product, in which instructions are executed by the processor of an electronic device, causing the electronic device to perform the scientific and technological innovation achievement evaluation method provided in this application.

[0120] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0121] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0122] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0123] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0124] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A data processing method, characterized in that, The method includes: In chronological order, the number of first users in the target area within N first time periods and the number of N second users output by the model are obtained consecutively. The N second user numbers are the predicted values ​​of the number of users in the target area within the corresponding N first time periods, and N is a positive integer greater than 1. Calculate the ratio of the first difference between any two adjacent first time periods in the N first time periods to obtain the first ratio. The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users output by the model in the corresponding first time period. If all N-1 first ratios are greater than the first preset threshold, the parameters of the model are adjusted so that at least one of the N-1 consecutive first ratios is less than the first preset threshold, wherein the first ratio is the ratio of the first difference between any two adjacent first time periods in N consecutive first time periods.

2. The method according to claim 1, characterized in that, When all N-1 first ratios are greater than a first preset threshold, adjusting the parameters of the model includes: When all N-1 first ratios are greater than the first preset threshold, the number of third users in the target area within multiple second time periods and the number of fourth users output by the model are obtained in chronological order. The number of fourth users is the predicted value of the number of users in the target area within the corresponding multiple second time periods. The sum of the durations of the multiple second time periods is equal to the duration of the first time period. The first value is calculated based on the number of third users in the target area within multiple consecutive second time periods and the number of fourth users output by the model. If the first value does not meet the first preset condition, the parameters of the model are adjusted so that the first value calculated based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

3. The method according to claim 2, characterized in that, The step of calculating the first value based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model includes: Calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and obtain multiple second differences; According to the time sequence, the plurality of second differences are divided into M difference groups, each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0; Based on M first preset coefficients, at least one second difference included in the M difference groups is weighted and summed to obtain a second value; The ratio of the second value to the sum of the M first preset coefficients is determined as the first value.

4. The method according to claim 2, characterized in that, The first preset condition includes a first value being less than a second preset threshold, and the ratio of the first value to the first preset value being less than a third preset threshold. The first preset value is the number of users in the target area when the physical resource block (PRB) utilization rate is within a preset range.

5. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to continuously acquire, in chronological order, the number of first users in the target area within N first time periods, and the number of N second users output by the model, wherein the number of N second users is the predicted value of the number of users in the target area within the corresponding N first time periods, and N is a positive integer greater than 1. The calculation module is used to calculate the ratio of the first difference between every two adjacent first time periods in the N first time periods, and obtain the first ratio. The first difference is the difference between the number of first users obtained in each of the N first time periods and the number of second users in the corresponding first time period output by the model. The adjustment module is used to adjust the parameters of the model when all N-1 first ratios are greater than a first preset threshold, so that at least one of the N-1 consecutive first ratios is less than the first preset threshold, wherein the first ratio is the ratio of the first difference between any two adjacent first time periods in N consecutive first time periods.

6. The apparatus according to claim 5, characterized in that, The adjustment module includes: The acquisition submodule is used to continuously acquire, in chronological order, the number of third users in the target area within multiple second time periods and the number of fourth users output by the model, when all N-1 first ratios are greater than the first preset threshold. The number of fourth users is the predicted value of the number of users in the target area within the corresponding multiple second time periods, and the sum of the durations of the multiple second time periods is equal to the duration of the first time period. The calculation submodule is used to calculate the first value based on the number of third users in the target area within multiple consecutively acquired second time periods and the number of fourth users output by the model. The adjustment submodule is used to adjust the parameters of the model when the first value does not meet the first preset condition, so that the first value calculated based on the number of third users in the target area within a number of consecutively acquired second time periods and the number of fourth users output by the model meets the first preset condition.

7. The apparatus according to claim 6, characterized in that, The computation submodule includes: The calculation unit is used to calculate the difference between the number of third users obtained in each of the multiple second time periods and the number of fourth users in the corresponding second time period output by the model, and to obtain multiple second differences. A partitioning unit is used to divide the plurality of second differences into M difference groups according to time order, wherein each of the M difference groups includes at least one second difference, and M is a positive integer greater than 0; The weighted summation unit is used to perform a weighted summation on at least one second difference included in the M difference groups based on M first preset coefficients to obtain a second value; The determining unit is used to determine the ratio of the second value to the sum of the M first preset coefficients, which is the first value.

8. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the data processing method as described in any one of claims 1-4.

9. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the data processing method as described in any one of claims 1-4.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the data processing method as described in any one of claims 1-4.

Images