Information processing method, device, network equipment and storage medium

By predicting the future usage behavior and traffic demand of user equipment and dynamically adjusting network parameters, the problem of network parameter adjustment lag in the existing technology is solved, which improves user experience and optimizes operating costs.

CN113973315BActive Publication Date: 2024-11-08CHINA MOBILE COMM LTD RES INST +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010714160.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-22
Publication Date
2024-11-08
Estimated Expiration
2040-07-22

AI Technical Summary

Technical Problem

The existing technology has lag in adjusting network parameters when monitoring changes in business volume, resulting in a decline in user experience and being unable to respond to changes in traffic demand in a timely manner.

Method used

By determining the coverage range of the target cell and the historical data of the user equipment, predict the usage behavior and traffic requirements of the user equipment in the future time period, and dynamically adjust the network parameters to cope with the expected traffic requirements.

Benefits of technology

It realizes the activation of network resources in advance when the community resources are insufficient, avoids the lag of monitoring and activation after user access, improves user experience, and takes into account the control of operational costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113973315B_ABST
    Figure CN113973315B_ABST
Patent Text Reader

Abstract

The embodiments of the present invention provide an information processing method, apparatus, network device and storage medium. The method comprises: determining a target user set associated with the coverage of a target cell; the target user set comprises at least one user device; determining usage behavior data of at least one user device in the target user set within a first time range based on historical data; the usage behavior data comprises data of an application program that is expected to be used by the user device within the first time range; determining an expected traffic demand within the first time range based on the usage behavior data of the at least one user device; and controlling activation of a specific network parameter when determining that the expected traffic demand exceeds a first threshold.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of wireless communications, and in particular to an information processing method, device, network equipment and storage medium. Background Art

[0002] With the development and popularization of communication technology, smart terminals and their applications have become indispensable tools in people's lives, work and study. In order to improve the user experience of network services while taking into account network operating costs, it is necessary to flexibly configure network parameters and improve network service guarantees.

[0003] Currently, the network parameters are flexibly configured by monitoring the traffic volume changes in the cell. However, this method has a lag, and the network parameter configuration can only be adjusted when the traffic volume meets certain conditions, resulting in a decline in user experience. Summary of the invention

[0004] In order to solve the existing technical problems, the embodiments of the present invention provide an information processing method, apparatus, network equipment and storage medium.

[0005] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0006] An embodiment of the present invention provides an information processing method, the method comprising:

[0007] Determine a target user set associated with the coverage of the target cell; the target user set includes at least one user equipment;

[0008] Determine usage behavior data of at least one user device in the target user set within a first time range based on historical data; the usage behavior data includes data of an application program that is expected to be used by the user device within the first time range;

[0009] Determining an estimated traffic demand within the first time range based on the usage behavior data of the at least one user device;

[0010] When it is determined that the expected traffic demand exceeds a first threshold, control is performed to activate specific network parameters.

[0011] In the above solution, the step of determining a target user set associated with the coverage of the target cell includes:

[0012] Determine the coverage range of the target cell, and determine a first area range based on the coverage range; the first area range is an area range outside the coverage range and at a first set value from the boundary of the coverage range, or the first area range is an area range corresponding to a cell that is continuous with the coverage of the target cell;

[0013] The current location of each user equipment is obtained, and the target user set is determined based on the current location of each user equipment; the current location of the user equipment in the target user set will be within the coverage area or within the first area.

[0014] In the above scheme, the method also includes: obtaining the current position of each user device in the target user set, determining the trajectory prediction information of each user device within the first time range based on the current position and historical data of each user device, and updating the target user set based on the current position of the user device and the trajectory prediction information corresponding to the user device.

[0015] In the above solution, updating the target user set based on the current location of the user equipment and the trajectory prediction information corresponding to the user equipment includes:

[0016] When the current location of the user equipment belongs to the first area range and the trajectory prediction information corresponding to the user equipment indicates that the location of the user equipment within the first time range is within the coverage range, retaining the user equipment in the target user set; or,

[0017] When the current location of the user equipment belongs to the first area range and the trajectory prediction information corresponding to the user equipment indicates that the location of the user equipment within the first time range is not within the coverage range, deleting the user equipment from the target user set; or,

[0018] A second area range is determined based on the coverage range; the second area range is an area range within the coverage range and at a second set value away from the boundary of the coverage range; when the current position of the user device belongs to the second area range and the trajectory prediction information corresponding to the user device indicates that the position of the user device within the first time range is not within the coverage range, the user device is deleted from the target user set.

[0019] In the above solution, determining the usage behavior data of at least one user device in the target user set within a first time range based on historical data includes:

[0020] Determining historical usage data of a target application based on historical data of any user device; the target application is any application that meets a preset condition;

[0021] Determine, based on the historical usage data of the target application, the historical usage probability that the target application is used in the first time range N days before the prediction date; N is a positive integer;

[0022] Determine the number of times the target application is used a preset number of time units before the first time range, and determine an inertial use probability based on the preset number and the number of times;

[0023] determining a probability that the target application is used in the first time range based on the historical use probability and the inertial use probability;

[0024] When the probability is greater than a second threshold, marking the target application as being used within the first time range;

[0025] The usage behavior data is determined based on target applications corresponding to all user devices in the target user set that are marked as being used within the first time range.

[0026] In the above solution, the method further includes: determining the first parameter based on the historical usage data of the target application; the determining the first parameter based on the historical usage data of the target application includes:

[0027] Count the first probability of the target day appearing when the target application has been used only once from N+n days to 2 days before the prediction day; n is a positive integer;

[0028] Counting the number of times the target application has been used in the first M time units of the day before the predicted day, and determining a first ratio based on the number of times; M is a positive integer;

[0029] Determine a process probability based on the first probability and the first ratio, and when the process probability is greater than a third threshold, mark the target application as being used for prediction within a preset time range of one day before the prediction day;

[0030] Determine the prediction accuracy of the target application marked as predicted use by using the historical usage data of the target application corresponding to the day before the prediction day, and count the prediction accuracy of the target application corresponding to the day before the prediction day;

[0031] The first parameter is determined based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than a fourth threshold; the first parameter represents the number of consecutive days among other consecutive historical prediction days adjacent to the prediction day whose prediction accuracy is greater than the fourth threshold.

[0032] In the above scheme, the determining, based on the historical usage data of the target application, the historical usage probability that the target application is used in the first time range N days before the prediction date includes: determining, based on the first parameter, the historical usage probability that the target application is used in the first time range N days before the prediction date; the determining, based on the first parameter, the historical usage probability that the target application is used in the first time range N days before the prediction date includes:

[0033] Determine a second probability that the target application is used in the first time range of each of the N days before the prediction date; wherein, if the target date is within the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0034]

[0035] If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0036] A=R; where factor is a preset value;

[0037] The second probabilities corresponding to each day are summed up, and the sum result is used as the historical usage probability.

[0038] In the above solution, the determining the probability of the target application being used in the first time range based on the historical use probability and the inertial use probability includes:

[0039] The historical usage probability and the habitual usage probability are weighted and summed to obtain the probability that the target application is used in the first time range.

[0040] The embodiment of the present invention further provides an information processing device, the device comprising: a first determining unit, a second determining unit, a third determining unit and a control unit; wherein,

[0041] The first determining unit is used to determine a target user set associated with the coverage of the target cell; the target user set includes at least one user equipment;

[0042] The second determination unit is used to determine, based on historical data, usage behavior data of at least one user device in the target user set within a first time range; the usage behavior data includes data on the expected use of an application by the user device within the first time range;

[0043] The third determining unit is used to determine the expected traffic demand within the first time range based on the usage behavior data of the at least one user equipment;

[0044] The control unit is used to control activation of specific network parameters when the estimated traffic demand determined by the third determination unit exceeds a first threshold.

[0045] In the above scheme, the first determination unit is used to determine the coverage range of the target cell, and determine the first area range based on the coverage range; the first area range is the area range outside the coverage range and the first set value away from the boundary of the coverage range, or the first area range is the area range corresponding to the cell that is continuous with the target cell; obtain the current position of each user device, and determine the target user set based on the current position of each user device; the current position of the user equipment in the target user set will be within the coverage range or within the first area range.

[0046] In the above scheme, the first determination unit is used to obtain the current position of each user device, determine the trajectory prediction information of each user device within the first time range based on the current position and historical data of each user device, and update the target user set based on the current position of the user device and the trajectory prediction information corresponding to the user device.

[0047] In the above scheme, the first determination unit is used to retain the user device in the target user set when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is within the coverage range; or, when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is not within the coverage range, delete the user device from the target user set; or, determine a second area range based on the coverage range; the second area range is an area range within the coverage range and a second set value away from the boundary of the coverage range; when the current location of the user device belongs to the second area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is not within the coverage range, delete the user device from the target user set.

[0048] In the above scheme, the second determination unit is used to determine the historical usage data of the target application based on the historical data of any user device; the target application is any application that meets the preset conditions; based on the historical usage data of the target application, determine the historical usage probability of the target application being used in the first time range N days before the prediction date; N is a positive integer; determine the number of times the target application is used a preset number of time units before the first time range, and determine the inertial usage probability based on the preset number and the number; determine the probability of the application being used in the first time range based on the historical usage probability and the inertial usage probability; when the probability is greater than a second threshold, mark the target application as being used in the first time range; determine the usage behavior data based on the target applications corresponding to all user devices in the target user set and marked as being used in the first time range.

[0049] In the above scheme, the second determination unit is also used to determine the first parameter based on the historical usage data of the target application; specifically, it is used to count the first probability of the target day appearing when the target application is only used once in the N+n days to the 2 days before the prediction day; n is a positive integer; the number of times the target application is used in the first M time units before the day before the prediction day is counted, and the first ratio is determined based on the number; M is a positive integer; the process probability is determined based on the first probability and the first ratio, and when the process probability is greater than the third threshold, the target application is marked as predicted use within a preset time range of the day before the prediction day; the prediction accuracy of the target application marked as predicted use is determined using the historical usage data of the day before the prediction day corresponding to the target application, and the prediction accuracy of the target application corresponding to the day before the prediction day is counted; the first parameter is determined based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than the fourth threshold; the first parameter represents the number of consecutive days in other consecutive historical prediction days adjacent to the prediction day with a prediction accuracy greater than the fourth threshold.

[0050] In the above scheme, the second determination unit is further used to determine the historical usage probability of the target application being used in the first time range of the previous N days based on the first parameter; specifically, it is used to determine the second probability of the target application being used in the first time range of each of the N days before the prediction date; wherein, if the target day is within the date range corresponding to the first parameter, the second probability corresponding to the target day is expressed as:

[0051]

[0052] If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0053] A=R; where factor is a preset value;

[0054] The second probabilities corresponding to each day are summed up, and the sum result is used as the historical usage probability.

[0055] In the above solution, the second determining unit is used to perform weighted sum processing on the historical use probability and the inertial use probability to obtain the probability that the application is used in the first time range.

[0056] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the embodiment of the present invention are implemented.

[0057] An embodiment of the present invention further provides a network device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the embodiment of the present invention when executing the program.

[0058] The information processing method, device, network device and storage medium provided by the embodiment of the present invention include: determining a target user set associated with the coverage of a target cell; the target user set includes at least one user device; determining the usage behavior data of at least one user device in the target user set within a first time range based on historical data; the usage behavior data includes data of the application program expected to be used by the user device within the first time range; determining the expected traffic demand within the first time range based on the usage behavior data of the at least one user device; and controlling the activation of specific network parameters when it is determined that the expected traffic demand exceeds a first threshold. The technical solution of the embodiment of the present invention is adopted, firstly by determining the target user, and then determining the users and applications that may use the cell resources in a future period of time based on the historical data of the target user, thereby realizing the prediction of the traffic demand in the future period of time, so that the specific network parameters can be activated based on the prediction results, so as to activate the resources before the resources of the cell are insufficient to provide services to the user, avoiding the lag problem caused by the user first accessing, then monitoring, and then activating in the related scheme, and improving the user experience while taking into account the operating cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a flow chart of an information processing method according to an embodiment of the present invention;

[0060] Figure 2aA schematic diagram of a first area range and a second area range in an information processing method according to an embodiment of the present invention;

[0061] Figure 2b A schematic diagram of a first area range in an information processing method according to an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of a prediction processing flow of an application program in an information processing method according to an embodiment of the present invention;

[0063] Figure 4 A schematic diagram of the structure of an information processing device according to an embodiment of the present invention;

[0064] Figure 5 The figure is a schematic diagram of the hardware structure of the network device according to the embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0066] An embodiment of the present invention provides an information processing method, which can be applied to a network device. Figure 1 Schematic diagram of the information processing method according to an embodiment of the present invention; Figure 1 As shown, the method includes:

[0067] Step 101: determining a target user set associated with a coverage area of ​​a target cell; the target user set includes at least one user equipment;

[0068] Step 102: Determine usage behavior data of at least one user device in the target user set within a first time range based on historical data; the usage behavior data includes data on the application program that is expected to be used by the user device within the first time range;

[0069] Step 103: Determine the estimated traffic demand within the first time range based on the usage behavior data of the at least one user device;

[0070] Step 104: When it is determined that the expected traffic demand exceeds a first threshold, control activation of specific network parameters.

[0071] In this embodiment, the target cell represents an area covered by a base station or a part of a base station (sector antenna) in a cellular mobile communication system, within which a terminal or user equipment (UE) can reliably communicate with the base station through a wireless channel. The coverage area of ​​the target cell may be an area covered by a signal of the base station or a part of the base station (sector antenna).

[0072] Exemplarily, the coverage range of the target cell may be represented by a latitude and longitude range, or, when the coverage area is a circular area, may be represented by the position of the center point of the coverage range and the length of the radius.

[0073] In this embodiment, the target user set is a set of user equipment whose locations are associated with the coverage of the target cell, or it can also be understood that the locations of the user equipment in the target user set are associated with the coverage of the target cell. In some optional embodiments, the locations of the user equipment in the target user set are within the coverage of the target cell. In other optional embodiments, the locations of the user equipment in the target user set may not be within the coverage of the target cell, but close to the coverage of the target cell.

[0074] In some optional embodiments of the present invention, determining a target user set associated with the coverage range of a target cell includes: determining the coverage range of the target cell, and determining a first area range based on the coverage range; the first area range is an area range outside the coverage range and at a first set value away from the boundary of the coverage range, or the first area range is an area range corresponding to a cell that is continuous with the coverage of the target cell; obtaining the current position of each user device, and determining the target user set based on the current position of each user device; the current position of the user equipment in the target user set will be within the coverage range or within the first area range.

[0075] In this embodiment, the coverage of the target cell is determined, and the boundary of the target cell is determined. In some optional embodiments, the first set value is extended in a direction away from the target cell based on the boundary of the target cell, and the determined boundary is used as the boundary of the first area range. Figure 2a As shown, it is a schematic diagram of an outdoor cell. Assuming that the coverage range of the target cell is a circular area, the first set value is extended in the direction away from the target cell based on the boundary of the circular area, and the range of the obtained circular area is recorded as the above-mentioned first area range.

[0076] In some optional embodiments, the coverage of the target cell may be determined by the relevant information of the base station corresponding to the target cell, or may be determined according to a measurement report (MR). In one example, when the base station is deployed, the coverage of the corresponding target cell is preconfigured in the relevant information of the base station. In another example, the coverage of the target cell may be determined by the relevant information (e.g., coverage) in the measurement report.

[0077] In this embodiment, the first area range may also be referred to as an admission range, which indicates an area range within a certain range outside the coverage range of the target cell. Figure 2aAs shown, in the scenario of an outdoor cell, the coverage range of the target cell and the first area range are area ranges arranged in the horizontal dimension. In other optional embodiments, such as Figure 2b As shown, in the scenario of an indoor cell, such as in a high-rise residential building, the coverage range of the target cell and the first area range are area ranges arranged in the vertical dimension. It can be understood that the cell corresponding to the first area range of the target small area is an adjacent cell.

[0078] Furthermore, the current location of each user device is obtained. In some optional embodiments, the current location of the user device can be obtained through the positioning module of the user device itself, and the network device obtains the current location of the user device through the information interaction between the user device and the network device. Exemplarily, the positioning module of the user device itself can be a global positioning system (GPS) module. In other optional embodiments, the network device can also determine the current location of the user device through the relevant information of the base station accessed by the user device or the relevant information of the wireless fidelity (WiFi) accessed by the user device. For example, the approximate area of ​​the user device is determined based on the deployment location of the base station, and then the distance between the user device and the base station is determined based on relevant parameters such as the received signal strength of the user device, and then the current location of the user device is determined in combination with the deployment location of the above-mentioned base station and the distance between the user device and the base station.

[0079] In this embodiment, the target user set may be formed based on user equipment whose current location is within the coverage of the target cell and within the first area. Exemplarily, the target user set may include relevant information of user equipment that meets the above conditions, such as an identifier of the user equipment, which may uniquely identify the user equipment in the network.

[0080] It is understandable that the target user set needs to be updated at regular intervals. Optionally, the target user set may be updated at a first preset interval, that is, the current location of each user device is re-obtained, and the user device whose current location is within the coverage of the target cell or within the first area is added to the target user set, and correspondingly, the user device whose current location is not within the coverage of the target cell or within the first area is deleted from the target user set.

[0081] In some optional embodiments of the present invention, the method further includes: obtaining the current position of each user device in the target user set, determining the trajectory prediction information of each user device within a first time range based on the current position and historical data of each user device, and updating the target user set based on the current position of the user device and the trajectory prediction information corresponding to the user device.

[0082] In this embodiment, for the user devices in the target user set, the trajectory of each user device may be predicted, and the target user set may be updated according to the trajectory prediction result (ie, trajectory prediction information) and the current location of the user device.

[0083] In some optional embodiments of the present invention, updating the target user set based on the current location of the user device and the trajectory prediction information corresponding to the user device includes: retaining the user device in the target user set when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the position of the user device within the first time range is within the coverage range; or, deleting the user device from the target user set when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the position of the user device within the first time range is not within the coverage range; or, determining a second area range based on the coverage range; the second area range is an area range within the coverage range and a second set value away from the boundary of the coverage range; deleting the user device from the target user set when the current location of the user device belongs to the second area range and the trajectory prediction information corresponding to the user device indicates that the position of the user device within the first time range is not within the coverage range.

[0084] In this embodiment, before updating the target user set, the second area range is first determined based on the coverage range of the target cell. The second area range may also be called the allowed-out range, which indicates an area range within a certain range within the coverage range of the target cell. It should be noted that the second area range is only Figure 2a The outdoor cell scenario shown in Figure 1 exists. Figure 2a As shown, based on the direction of the boundary of the target cell, the second setting value is extended toward the direction pointing to the target cell, and the determined boundary is used as the boundary of the second area range.

[0085] The user devices in the target user set are further updated based on the current location and trajectory prediction information of the user device. Among them, the trajectory prediction information indicates the possible movement trajectory of the user device within the first time range. The first time range is a future time range compared to the current time. For example, if the current time is 8:00 in the morning, the first time range may be 9:00-10:00 in the morning of the same day. Of course, the first time range in the embodiment of the present invention is not limited to the above examples, but may also be other values. For example, the duration of the first time range may be 3 hours, 10 hours, 24 hours, and so on. Optionally, the time granularity corresponding to the first time range is not limited to hours, but may also be minutes. For example, the first time range may be 1 minute, 15 minutes, and so on, which is not limited in this embodiment.

[0086] In some optional examples, if the current location of the user device belongs to the first area range, and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is within the coverage range, the user device is retained in the target user set. In this example, if the location of the user device at the current moment is within the first area range, but it is determined through the trajectory prediction information that the user device will reach the coverage range of the target device within the first time range, the user device (or the identifier of the user device) can be retained in the target user set, otherwise, the user device (or the identifier of the user device) is deleted from the target user set.

[0087] In some other optional examples, if the current location of the user device belongs to the second area range, and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is not within the coverage range, the user device is deleted from the target user set. In this example, if the location of the user device at the current moment is within the second area range, but it is determined through the trajectory prediction information that the user device will leave the coverage range of the target device within the first time range, the user device (or the identifier of the user device) can be deleted from the target user set, otherwise, the user device (or the identifier of the user device) is retained in the target user set.

[0088] In this embodiment, the trajectory prediction information of the user device within the first time range can be determined through the historical data of each user device. Optionally, the trajectory prediction information of the user device within the first time range can be determined based on the historical data of the user device using a Bayesian algorithm, or the trajectory prediction information of the user device within the first time range can be determined based on the historical data of the user device and a pre-trained machine learning model.

[0089] In some optional examples, the current position of the user device at the current moment can be input into the machine learning model to obtain the predicted position of the user device within a first time range of a preset time range from the current moment, and the preset position is used as the above-mentioned trajectory prediction information.

[0090] In other optional examples, the location data within a preset time range before the current moment can also be determined based on the historical data of the user device. The speed and direction of the user device at the current moment can be determined based on the location data within the preset time range before the current moment and the current position. The current location, speed, direction and other information of the user device at the current moment can be input into the machine learning model to obtain the predicted position of the user device within the first time range of the preset time range before the current moment, and the preset position is used as the above-mentioned trajectory prediction information.

[0091] In some optional embodiments of the present invention, determining the usage behavior data of at least one user device in the target user set in the first time range based on historical data includes: determining the historical usage data of the target application based on the historical data of any user device; the target application is any application that meets a preset condition; determining the historical usage probability of the target application being used in the first time range N days before the prediction date based on the historical usage data of the target application; N is a positive integer; determining the number of times the target application is used a preset number of time units before the first time range, and determining the inertial usage probability based on the preset number and the number; determining the probability of the target application being used in the first time range based on the historical usage probability and the inertial usage probability; when the probability is greater than a second threshold, marking the target application as being used in the first time range; determining the usage behavior data based on the target applications corresponding to all user devices in the target user set and marked as being used in the first time range.

[0092] In this embodiment, the usage of the application by the user device is predicted based on the historical data of each user device in the target user set, so as to obtain the usage behavior data of the user device in the first time range. Exemplarily, the historical data of each user device can be historical detailed data. The historical data may include the following information: the start time and end time of the service, the service type (such as phone, short message, application, etc.); if the service type is an application, the historical data may also include an application identifier (used to uniquely indicate the application), traffic usage information of the application, etc. In this embodiment, the target application can be determined based on the historical data of each user device in the target user set, and the target application is any application that meets the preset conditions.

[0093] For example, the target application that meets the preset condition may be an application that has been used more than once in the N days before the prediction date (i.e., the N days before the current date) and has a usage flow exceeding a preset flow threshold. The preset flow threshold may be, for example, 10,000 bits. Of course, the value of the preset flow threshold is not limited to the above example.

[0094] In some optional embodiments, the method further includes: determining a first parameter based on historical usage data of the target application, wherein the first parameter is a parameter used to calculate a historical usage probability of the target application.

[0095] In some optional embodiments of the present invention, determining the first parameter based on the historical usage data of the target application includes: counting the first probability of the target day appearing when the target application has been used only once in the N+n days to the 2 days before the prediction day; n is a positive integer; counting the number of times the target application has been used in the first M time units before the day before the prediction day, and determining a first ratio based on the number; M is a positive integer; determining a process probability based on the first probability and the first ratio, and when the process probability is greater than a third threshold, marking the target application as predicted use within a preset time range of the day before the prediction day; determining the prediction accuracy of the target application marked as predicted use using the historical usage data of the day before the prediction day corresponding to the target application, and counting the prediction accuracy of the target application corresponding to the day before the prediction day; determining the first parameter based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than a fourth threshold; the first parameter represents the number of consecutive days in other consecutive historical prediction days adjacent to the prediction day with a prediction accuracy greater than the fourth threshold.

[0096] In this embodiment, historical usage data of the user device corresponding to the target application program N+n days before the prediction day is obtained. The prediction day may be the day of the current moment, and as time goes by, each day may be used as the prediction day, or each day before the current moment may be used as the prediction day corresponding to the current moment, so as to determine the first parameter.

[0097] In this embodiment, the above-mentioned first parameter can be recorded as D. The value of D is related to the process probability determined based on the above-mentioned first probability and the first ratio. The process probability can be understood as the probability of using the target application in the prediction time range of the previous day based on the usage from the previous N+n days to the previous 2 days of the prediction day. If the process probability is greater than the third threshold, the target application can be marked for predicted use.

[0098] Specifically, the first probability alpha' can be expressed as: alpha'=1 / (N+n-1); the first ratio beta' can be expressed as beta'=b' / M; wherein b' represents the number of times the target application has been used in the first M time units of the day before the forecast day; the time unit can be a preset time length, which can be 1 hour, or other time lengths, which are not limited in this embodiment. In this embodiment, the first probability and the first ratio can be weighted summed to obtain the process probability.

[0099] Exemplarily, the determination method of the process probability P' may satisfy the following expression:

[0100] P'=w×alpha'+(1-w)×beta'(1)

[0101] Wherein, w is a weight coefficient. In some optional embodiments, the value of w is a preset fixed value. In other optional embodiments, the value of w can also be obtained through a machine learning model, and optionally, the machine learning model can be a neural network model + a genetic algorithm model.

[0102] Furthermore, when the determined process probability is greater than a third threshold, the target application may be marked as predicted to be used within a preset time range one day before the prediction day; and combined with the actual usage of the target application within the preset time range one day before the prediction day, it may be determined whether the prediction for the application is correct; if the target application is actually used within the preset time range one day before the prediction day, it may be determined that the prediction is correct; and if the target application is actually not used within the preset time range one day before the prediction day, it may be determined that the prediction is wrong; and further, for the target application, statistics may be made on whether the prediction corresponding to each user device one day before the prediction day is correct, specifically the number of correct predictions may be counted, and the ratio between the number of correct predictions and the total number of predictions corresponding to each user device may be taken as the prediction accuracy rate corresponding to the target application one day before the prediction day.

[0103] The first parameter is further determined based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day. Exemplarily, the number of days of other consecutive historical prediction days whose prediction accuracy is greater than a fourth threshold is counted, and the number of days can be used as the first parameter. The fourth threshold is a preset value, and the fourth threshold can be, for example, 35%, of course, this embodiment is not limited to the above example.

[0104] In one example, the following Table 1 shows the statistics of an application, where the first column of data indicates whether the application is actually used, 1 indicates that the application is actually used, and 0 indicates that the application is actually not used. The second column of data indicates the total number of tests of the application 10 days before the prediction date, specifically the total number of tests that the application was actually used 10 days before the prediction date and the total number of tests that the application was actually not used 10 days before the prediction date. The third column indicates the i-th day before the prediction date, and according to different values ​​of i, it can represent the 1st to 10 days before the prediction date; the fourth column of data indicates the number of tests of the application that the corresponding application is actually used or not actually used, corresponding to the statistics of the i-th day before the prediction date; the fifth column of data is the number of applications predicted to be used on the i-th day before the prediction date; the sixth column of data indicates the prediction accuracy. It can be understood that, through the statistical data shown in Table 1, for example, if the fourth threshold is assumed to be 35%, the number of consecutive days corresponding to other historical prediction days adjacent to the prediction date with a prediction accuracy greater than 35% can be determined. If the prediction accuracy of the first 5 consecutive days adjacent to the prediction date is greater than 35%, the above-mentioned first parameter D can be determined to be 5.

[0105] Table 1

[0106]

[0107]

[0108] In some optional embodiments, determining the historical usage probability of the target application being used in the first time range N days before the prediction date based on the historical usage data of the target application includes: determining the historical usage probability of the target application being used in the first time range N days before the prediction date based on a first parameter.

[0109] In some optional embodiments of the present invention, determining the historical usage probability of the target application being used in the first time range N days before the prediction date based on the first parameter includes: determining a second probability of the target application being used in the first time range of each of the N days before the prediction date; wherein, if the target date is within the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0110]

[0111] If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0112] A=R; where factor is a preset value;

[0113] The second probabilities corresponding to each day are summed up, and the sum result is used as the historical usage probability.

[0114] Exemplarily, the historical usage probability alpha can be expressed as: Among them, A i represents the second probability corresponding to the first i days among the first N days.

[0115] Further, based on the number of times the target application is used a preset number of time units before the first time range, the inertial usage probability is determined based on the preset number and the number of times.

[0116] For example, if the number of times the target application is used in the previous M moments is b, the inertial use probability beta can be expressed as: beta=b / M.

[0117] In some optional embodiments of the present invention, determining the probability of the target application being used in the first time range based on the historical usage probability and the inertial usage probability includes: performing weighted sum processing on the historical usage probability and the inertial usage probability to obtain the probability of the target application being used in the first time range.

[0118] Exemplarily, the probability P of the target application being used in the first time range can be expressed as:

[0119] P = w × alpha + (1-w) × beta (3)

[0120] Among them, w is the weight coefficient, alpha is the historical usage probability, and beta is the inertial usage probability.

[0121] When the above probability P is greater than the second threshold, the target application can be marked as being used within the first time range, and the target application marked as being used can be used as an application that is expected to be used by the user device within the first time range, so that the target applications corresponding to all user devices in the target user set can be counted, and the information of the target applications marked as being used within the first time range can be counted as the above usage behavior data.

[0122] For example, the above process can refer to Figure 3 As shown, including:

[0123] Step 201: Obtain the data details of the target application program used by the user devices in the target user set in the recent N+n days, wherein the data details of the N+n days are the data details of the N+n days before the current day; N and n are both positive integers.

[0124] Step 202: Count the probability (ie, first probability) of the target day appearing when the target application is used only once in the N+n to 2 days before the prediction day, and record this probability as alpha'=1 / (N+n-1).

[0125] Step 203: Count the number of times b' the target application has been used in the first M time units of the day before the forecast day, and calculate a first ratio beta'=b' / M, where M is a positive integer.

[0126] Step 204: Calculate the process probability based on the first probability and the first ratio; when the process probability is greater than a third threshold, mark it as predicted use.

[0127] Wherein, the process probability P'=w×alpha'+(1-w)×beta', when P'>p1 (the third threshold), it is marked as prediction use.

[0128] Step 205: Determine whether the mark is correct based on the actual usage data of the target application, count the prediction accuracy of the target application, and determine the first parameter D based on the prediction accuracy.

[0129] Among them, the first parameter is determined based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than the fourth threshold; it can be understood that if the prediction accuracy for 5 consecutive days is greater than the fourth threshold, the first parameter D=5 can be determined.

[0130] Step 206: Determine the second probability that the target application is used in the first time range of each of the N days before the prediction date, sum the second probabilities corresponding to each day, and use the sum as the historical usage probability.

[0131] If the target date is within the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0132]

[0133] If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0134] A=R; where factor is a preset value;

[0135] Then the historical usage probability alpha can be expressed as: Among them, A i represents the second probability corresponding to the first i days among the first N days.

[0136] Step 207: Determine that the number of times the target application is used M times before the prediction date is b, then the inertial use probability beta can be expressed as: beta = b / M.

[0137] The number of times the target application is used M times before the predicted date may also be determined through historical data.

[0138] Step 208: Perform weighted sum processing based on the historical usage probability and the inertial usage probability to obtain the probability that the target application is used in the first time range.

[0139] Among them, the probability P of the target application being used in the first time range can be expressed as:

[0140] P = w × alpha + (1-w) × beta

[0141] In some optional embodiments of the present invention, for user devices in the target user set, the probability of the target application being used in the first time range may be determined for each user device, or the probability of the target application being used in the first time range may be determined for a group of user devices; wherein the group of user devices may be multiple user devices with the same user profile. It is understood that the probability of multiple user devices in a group of user devices using the same service is greater than a preset value.

[0142] In this embodiment, after determining that the target application is used in the first time range, the average usage traffic of the target application marked as being used can be determined based on the historical data of the user device (the average usage traffic corresponding to each user device can be calculated separately, or the average usage traffic can be calculated for a group of user devices belonging to the same user profile), and the average usage traffic of all user devices in the target user set within the first time range, corresponding to the target application marked as being used, is counted, and the above-mentioned average usage traffic is added up to obtain the expected traffic demand within the first time range.

[0143] Further, when the estimated traffic demand exceeds the first threshold, the specific network parameters are controlled to be activated. Optionally, the specific network parameters may include at least one of the following: cell parameters, channels, symbols, subframes, mode parameters, etc. Exemplarily, the control to activate the specific network parameters may include activating a specific cell, or activating a specific channel, a specific symbol, etc., or activating a specific cell in deep sleep, etc.

[0144] In some optional embodiments of the present invention, the method may further include: when the predicted traffic demand is lower than another threshold, controlling to deactivate the specific network parameter.

[0145] The technical solution of the embodiment of the present invention, on the one hand, first determines the target user, and then determines the users and applications that may use the cell resources in the future based on the historical data of the target user, thereby realizing the prediction of the traffic demand in the future, so that specific network parameters can be activated based on the prediction results to activate resources before the resources of the cell are insufficient to provide services to the user, avoiding the lag problem caused by the user first accessing, then monitoring, and then activating in the related scheme, while taking into account the operating cost and improving the user experience. On the other hand, the historical usage probability in the embodiment of the present invention is determined according to different parameters obtained from different historical times or historical usage situations, without the need to use complex and time-consuming deep learning algorithms.

[0146] The embodiment of the present invention also provides an information processing device. Figure 4 Schematic diagram of the structure of the information processing device according to an embodiment of the present invention; Figure 4 As shown, the device includes: a first determining unit 11, a second determining unit 12, a third determining unit 13 and a control unit 14; wherein,

[0147] The first determining unit 11 is used to determine a target user set associated with the coverage of the target cell; the target user set includes at least one user equipment;

[0148] The second determination unit 12 is used to determine the usage behavior data of at least one user device in the target user set within a first time range based on the historical data; the usage behavior data includes data of the application program that is expected to be used by the user device within the first time range;

[0149] The third determining unit 13 is used to determine the estimated traffic demand within the first time range based on the usage behavior data of the at least one user equipment;

[0150] The control unit 14 is configured to control activation of a specific network parameter when the estimated traffic demand determined by the third determination unit 13 exceeds a first threshold.

[0151] In some optional embodiments of the present invention, the first determination unit 11 is used to determine the coverage range of the target cell, and determine a first area range based on the coverage range; the first area range is an area range outside the coverage range and at a first set value away from the boundary of the coverage range, or the first area range is an area range corresponding to a cell that is continuous with the target cell; obtain the current position of each user device, and determine the target user set based on the current position of each user device; the current position of the user equipment in the target user set will be within the coverage range or within the first area range.

[0152] In some optional embodiments of the present invention, the first determination unit 11 is used to obtain the current position of each user device in the target user set, determine the trajectory prediction information of each user device within a first time range based on the current position and historical data of each user device, and update the target user set based on the current position of the user device and the trajectory prediction information corresponding to the user device.

[0153] In some optional embodiments of the present invention, the first determination unit 11 is used to retain the user device in the target user set when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is within the coverage range; or, when the current location of the user device belongs to the first area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is not within the coverage range, delete the user device from the target user set; or, determine a second area range based on the coverage range; the second area range is an area range within the coverage range and a second set value away from the boundary of the coverage range; when the current location of the user device belongs to the second area range and the trajectory prediction information corresponding to the user device indicates that the location of the user device within the first time range is not within the coverage range, delete the user device from the target user set.

[0154] In some optional embodiments of the present invention, the second determination unit 12 is used to determine the historical usage data of the target application based on the historical data of any user device; the target application is any application that meets the preset conditions; based on the historical usage data of the target application, determine the historical usage probability of the target application being used in the first time range N days before the prediction date; N is a positive integer; determine the number of times the target application is used a preset number of time units before the first time range, and determine the inertial usage probability based on the preset number and the number; determine the probability of the target application being used in the first time range based on the historical usage probability and the inertial usage probability; when the probability is greater than a second threshold, mark the target application as being used in the first time range; determine the usage behavior data based on the target applications corresponding to all user devices in the target user set, which are marked as being used in the first time range.

[0155] In some optional embodiments of the present invention, the second determination unit 12 is further used to determine a first parameter based on the historical usage data of the target application; specifically, it is used to count the first probability of the target day appearing when the target application has only been used once in the N+n days to the 2 days before the prediction day; n is a positive integer; count the number of times the target application has been used in the first M time units before the day before the prediction day, and determine a first ratio based on the number; M is a positive integer; determine a process probability based on the first probability and the first ratio, and when the process probability is greater than a third threshold, mark the target application as predicted use within a preset time range of the day before the prediction day; determine the prediction accuracy of the target application marked as predicted use using the historical usage data of the day before the prediction day corresponding to the target application, and count the prediction accuracy of the target application corresponding to the day before the prediction day; determine the first parameter based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than a fourth threshold; the first parameter represents the number of consecutive days in other consecutive historical prediction days adjacent to the prediction day with a prediction accuracy greater than the fourth threshold.

[0156] In some optional embodiments of the present invention, the second determination unit 12 is further used to determine the historical usage probability of the target application being used in the first time range of the previous N days based on the first parameter; specifically, to determine the second probability of the target application being used in the first time range of each day of the previous N days; wherein, if the target day is within the date range corresponding to the first parameter, the second probability corresponding to the target day is expressed as:

[0157]

[0158] If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as:

[0159] A=R; where factor is a preset value;

[0160] The second probabilities corresponding to each day are summed up, and the sum result is used as the historical usage probability.

[0161] In some optional embodiments of the present invention, the second determining unit 12 is configured to perform weighted sum processing on the historical use probability and the inertial use probability to obtain the probability of the application being used in the first time range.

[0162] In the embodiment of the present invention, the first determination unit 11, the second determination unit 12, the third determination unit 13 and the control unit 14 in the device can be implemented by a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit 14 (MCU) or a programmable gate array (FPGA) in practical applications.

[0163] It should be noted that: when the information processing device provided in the above embodiment performs information processing, only the division of the above program modules is used as an example. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the information processing device provided in the above embodiment and the information processing method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0164] The embodiment of the present invention further provides a network device, Figure 5 FIG. 1 is a schematic diagram of the hardware structure of the network device according to an embodiment of the present invention. Figure 5 As shown, the network device includes a memory 22, a processor 21, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the program, the steps of the information processing method described in the embodiment of the present invention are implemented.

[0165] Optionally, the network device further includes a network interface 23. It is understood that the various components in the network device can be coupled together via a bus system 24. It is understood that the bus system 24 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 24 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 5 Various buses are labeled as bus system 24 .

[0166] It can be understood that the memory 22 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 22 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0167] The method disclosed in the above embodiment of the present invention can be applied to the processor 21, or implemented by the processor 21. The processor 21 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 21 or the instruction in the form of software. The above processor 21 can be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 21 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 22. The processor 21 reads the information in the memory 22 and completes the steps of the above method in combination with its hardware.

[0168] In an exemplary embodiment, the network device may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), FPGA, general purpose processor, controller, MCU, microprocessor, or other electronic components to execute the aforementioned method.

[0169] In an exemplary embodiment, the present invention also provides a computer-readable storage medium, such as a memory 22 including a computer program, and the computer program can be executed by a processor 21 of a network device to complete the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM; or it can be various devices including one or any combination of the above memories.

[0170] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the information processing method described in the embodiment of the present invention are implemented.

[0171] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0172] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0173] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0175] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0176] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0177] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, disks or optical disks.

[0178] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0179] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An information processing method, characterized in that: The method comprises: Determine a target user set associated with the coverage of the target cell; the target user set includes at least one user equipment; Determine usage behavior data of at least one user device in the target user set within a first time range based on historical data; the usage behavior data includes data of an application program that is expected to be used by the user device within the first time range; Determining an estimated traffic demand within the first time range based on the usage behavior data of the at least one user device; When determining that the estimated traffic demand exceeds a first threshold, controlling activation of a specific network parameter; The determining, based on historical data, usage behavior data of at least one user device in the target user set within a first time range includes: Determining historical usage data of a target application based on historical data of any user device; the target application is any application that meets a preset condition; Determine, based on the historical usage data of the target application, the historical usage probability that the target application is used in the first time range N days before the prediction date; N is a positive integer; Determine the number of times the target application is used a preset number of time units before the first time range, and determine an inertial use probability based on the preset number and the number of times; determining a probability that the target application is used in the first time range based on the historical use probability and the inertial use probability; When the probability is greater than a second threshold, marking the target application as being used within the first time range; The usage behavior data is determined based on target applications corresponding to all user devices in the target user set that are marked as being used within the first time range.

2. The method according to claim 1, characterized in that The determining of a target user set associated with the coverage of the target cell includes: Determine the coverage range of the target cell, and determine a first area range based on the coverage range; the first area range is an area range outside the coverage range and at a first set value from the boundary of the coverage range, or the first area range is an area range corresponding to a cell that is continuous with the coverage of the target cell; The current location of each user equipment is obtained, and the target user set is determined based on the current location of each user equipment; the current location of the user equipment in the target user set will be within the coverage area or within the first area.

3. The method according to claim 2, characterized in that The method further comprises: The target user set is updated based on the current position of each user device and the trajectory prediction information corresponding to the user device.

4. The method according to claim 3, characterized in that The updating of the target user set based on the current location of the user equipment and the trajectory prediction information corresponding to the user equipment includes: When the current location of the user equipment belongs to the first area range and the trajectory prediction information corresponding to the user equipment indicates that the location of the user equipment within the first time range is within the coverage range, retaining the user equipment in the target user set; or, When the current location of the user equipment belongs to the first area range and the trajectory prediction information corresponding to the user equipment indicates that the location of the user equipment within the first time range is not within the coverage range, deleting the user equipment from the target user set; or, A second area range is determined based on the coverage range; the second area range is an area range within the coverage range and at a second set value away from the boundary of the coverage range; when the current position of the user device belongs to the second area range and the trajectory prediction information corresponding to the user device indicates that the position of the user device within the first time range is not within the coverage range, the user device is deleted from the target user set.

5. The method according to claim 1, characterized in that The method further includes: determining a first parameter based on historical usage data of the target application; the first parameter is denoted as D; The determining the first parameter based on the historical usage data of the target application comprises: Count the first probability of the target day appearing when the target application has been used only once from N+n days to 2 days before the prediction day; n is a positive integer; Counting the number of times the target application has been used in the first M time units of the day before the predicted day, and determining a first ratio based on the number of times; M is a positive integer; Determine a process probability based on the first probability and the first ratio, and when the process probability is greater than a third threshold, mark the target application as being used for prediction within a preset time range of one day before the prediction day; Determine the prediction accuracy of the target application marked as predicted use by using the historical usage data of the target application corresponding to the day before the prediction day, and count the prediction accuracy of the target application corresponding to the day before the prediction day; The first parameter is determined based on the prediction accuracy corresponding to other consecutive historical prediction days adjacent to the prediction day; wherein the prediction accuracy corresponding to the other consecutive prediction days are all greater than a fourth threshold; the first parameter represents the number of consecutive days among other consecutive historical prediction days adjacent to the prediction day whose prediction accuracy is greater than the fourth threshold.

6. The method according to claim 5, characterized in that The determining, based on the historical usage data of the target application, the historical usage probability that the target application is used in the first time range N days before the prediction date, comprises: determining, based on the first parameter, the historical usage probability that the target application is used in the first time range N days before the prediction date; The determining, based on the first parameter, the historical usage probability of the target application being used in the first time range N days before the prediction date includes: Determine a second probability that the target application is used in the first time range of each of the N days before the prediction date; wherein, if the target date is within the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as: If the target date is outside the date range corresponding to the first parameter, the second probability corresponding to the target date is expressed as: A=R; where ;factor is a preset value; The second probabilities corresponding to each day are summed up, and the sum result is used as the historical usage probability.

7. The method according to claim 1, characterized in that The determining, based on the historical usage probability and the inertial usage probability, the probability that the target application is used in the first time range includes: The historical usage probability and the habitual usage probability are weighted and summed to obtain the probability that the target application is used in the first time range.

8. An information processing device, characterized in that: The device comprises: a first determining unit, a second determining unit, a third determining unit and a control unit; wherein, The first determining unit is used to determine a target user set associated with the coverage of the target cell; the target user set includes at least one user equipment; The second determination unit is used to determine, based on historical data, usage behavior data of at least one user device in the target user set within a first time range; the usage behavior data includes data on the expected use of an application by the user device within the first time range; The third determining unit is used to determine the expected traffic demand within the first time range based on the usage behavior data of the at least one user equipment; The control unit is configured to control activation of a specific network parameter when determining that the estimated traffic demand determined by the third determination unit exceeds a first threshold; The second determination unit is used to determine the historical usage data of the target application based on the historical data of any user device; the target application is any application that meets the preset conditions; based on the historical usage data of the target application, determine the historical usage probability of the target application being used in the first time range N days before the prediction date; N is a positive integer; determine the number of times the target application is used a preset number of time units before the first time range, and determine the inertial usage probability based on the preset number and the number; determine the probability of the target application being used in the first time range based on the historical usage probability and the inertial usage probability; when the probability is greater than a second threshold, mark the target application as being used in the first time range; determine the usage behavior data based on the target applications corresponding to all user devices in the target user set, which are marked as being used in the first time range.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A network device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.