Energy saving method, device, computer device and storage medium

Abstract

The application relates to an energy-saving method, device, computer equipment, storage medium and computer program product. The method comprises the following steps: when a preset energy-saving base station cell prediction condition is reached, obtaining each base station cell corresponding to a target energy-saving scene, main feature information corresponding to the target energy-saving scene, and user access information corresponding to each base station cell; inputting each base station cell, the main feature information corresponding to the target energy-saving scene, and the user access information corresponding to each base station cell into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result comprises a target base station cell; determining a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule; and performing energy-saving processing on the target base station cell according to the target energy-saving strategy. The method can improve communication quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to an energy saving method and device, computer equipment, storage medium and computer program product. BACKGROUND

[0002] A base station (Base Station), also known as a base station site or a base station device, is one of the key devices in a wireless communication network. The base station is used for communication and data transmission with mobile devices (such as mobile phones, wireless network cards, etc.), and realizes wireless communication coverage. The base station is a major power consumer in the mobile communication network of the 4th generation mobile communication technology (4G) and the 5th generation mobile communication technology (5G).

[0003] The current conventional energy saving method is to use the tidal effect of network load to save energy for all base stations. However, base station energy saving may have some impact on network coverage, causing network perception degradation. Therefore, the communication quality of the current conventional energy saving method is poor. SUMMARY

[0004] Therefore, it is necessary to provide an energy saving method, device, computer equipment, computer readable storage medium and computer program product capable of improving communication quality to solve the above technical problems.

[0005] In a first aspect, the present application provides an energy saving method. The method comprises:

[0006] When a preset energy saving base station cell prediction condition is reached, obtaining each base station cell corresponding to a target energy saving scenario, main feature information corresponding to the target energy saving scenario, and user access information corresponding to each base station cell;

[0007] Inputting each base station cell, main feature information corresponding to the target energy saving scenario, and user access information corresponding to each base station cell into a pre-trained energy saving base station cell prediction model to obtain an energy saving base station cell prediction result; the energy saving base station cell prediction result includes a target base station cell;

[0008] According to the target base station cell and a preset energy saving strategy determination rule, determining a target energy saving strategy;

[0009] According to the target energy saving strategy, performing energy saving processing on the target base station cell.

[0010] In one of the embodiments, the obtaining the base station cells corresponding to the target energy saving scenario, the subject feature information corresponding to the target energy saving scenario, and the user access information corresponding to each of the base station cells comprises:

[0011] obtaining the base station cells corresponding to the target energy saving scenario, the user access information corresponding to each of the base station cells, and the initial feature information corresponding to the target energy saving scenario;

[0012] for each target energy saving scenario, based on the preset subject feature index, analyzing the initial feature information corresponding to the base station cell, calculating the index feature information corresponding to the subject feature index, and obtaining the index feature information corresponding to the target energy saving scenario;

[0013] based on the initial feature information corresponding to the target energy saving scenario and the index feature information corresponding to the target energy saving scenario, constructing the subject feature information corresponding to the target energy saving scenario.

[0014] In one of the embodiments, the constructing the subject feature information corresponding to the target energy saving scenario based on the initial feature information corresponding to the target energy saving scenario and the index feature information corresponding to the target energy saving scenario comprises:

[0015] based on the subject feature index, determining the candidate feature information corresponding to the target energy saving scenario in the initial feature information corresponding to the target energy saving scenario;

[0016] constructing the subject feature information corresponding to the target energy saving scenario from the candidate feature information corresponding to the target energy saving scenario and the index feature information corresponding to the target energy saving scenario.

[0017] In one of the embodiments, the determining the target energy saving strategy according to the target base station cell and the preset energy saving strategy determination rule comprises:

[0018] for each target base station cell, in the preset mapping relationship between the base station cell and the energy saving mode, querying the target energy saving mode corresponding to the target base station cell, and obtaining the energy saving time period corresponding to the target base station cell;

[0019] based on the target energy saving mode corresponding to the target base station cell and the energy saving time period corresponding to the target base station cell, generating the energy saving sub-strategy corresponding to the target base station cell;

[0020] constructing the target energy saving strategy from the energy saving sub-strategies of each of the target base station cells.

[0021] In one of the embodiments, the method further comprises:

[0022] obtaining the historical traffic information of the target base station cell in a first historical time period;

[0023] determine, based on the historical traffic information and a preset traffic threshold, an energy-saving time period corresponding to the target base station cell in each time period.

[0024] In one of the embodiments, the method further comprises:

[0025] when a preset target energy-saving scenario determination condition is reached, obtaining historical network performance change trend information of each scenario in a second historical time period;

[0026] for each scenario, calculating target network performance change trend information of the scenario according to the historical network performance change trend information of the scenario;

[0027] determining, according to the target network performance change trend information of each scenario and a preset fluctuation threshold, a target energy-saving scenario in each scenario.

[0028] In one of the embodiments, the method further comprises:

[0029] when a preset model updating condition is reached, obtaining, in a time period from a current time to a target historical time, each sample base station cell corresponding to a sample target energy-saving scenario, subject feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, and energy-saving base station cell sample result of the sample target energy-saving scenario;

[0030] determining an updating data set based on each sample base station cell corresponding to the sample target energy-saving scenario, the user access sample information corresponding to each sample base station cell, the subject feature sample information corresponding to the sample target energy-saving scenario, and the energy-saving base station cell sample result;

[0031] training the energy-saving base station cell prediction model based on the updating data set to obtain a new energy-saving base station cell prediction model.

[0032] In a second aspect, the application further provides an energy-saving device. The device comprises:

[0033] a first obtaining module configured to, when a preset energy-saving base station cell prediction condition is reached, obtain each base station cell corresponding to a target energy-saving scenario, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell;

[0034] a prediction module configured to input each base station cell, the subject feature information corresponding to the target energy-saving scenario, and the user access information corresponding to each base station cell into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result comprises a target base station cell.

[0035] The first determining module is configured to determine a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule.

[0036] The processing module is configured to perform energy-saving processing on the target base station cell according to the target energy-saving strategy.

[0037] In one of the embodiments, the first obtaining module is specifically configured to:

[0038] obtain each base station cell corresponding to a target energy-saving scenario, user access information corresponding to each base station cell, and initial feature information corresponding to the target energy-saving scenario;

[0039] For each target energy-saving scenario, based on a preset main feature index, the initial feature information corresponding to the base station cell is analyzed, index feature information corresponding to the main feature index is calculated, and index feature information corresponding to the target energy-saving scenario is obtained.

[0040] Based on the initial feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario, main feature information corresponding to the target energy-saving scenario is constructed.

[0041] In one of the embodiments, the first obtaining module is specifically configured to:

[0042] Based on the main feature index, the candidate feature information corresponding to the target energy-saving scenario is determined in the initial feature information corresponding to the target energy-saving scenario.

[0043] The candidate feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario are used to construct the main feature information corresponding to the target energy-saving scenario.

[0044] In one of the embodiments, the first determining module is specifically configured to:

[0045] For each target base station cell, a target energy-saving mode corresponding to the target base station cell is queried in a preset mapping relationship between base station cells and energy-saving modes, and an energy-saving time period corresponding to the target base station cell is obtained.

[0046] Based on the target energy-saving mode corresponding to the target base station cell and the energy-saving time period corresponding to the target base station cell, an energy-saving sub-strategy corresponding to the target base station cell is generated.

[0047] The energy-saving sub-strategies of the target base station cells are used to constitute a target energy-saving strategy.

[0048] In one of the embodiments, the apparatus further comprises:

[0049] a second obtaining module, configured to obtain historical traffic information of the target base station cell in a first historical period;

[0050] a second determining module, configured to determine an energy-saving period corresponding to the target base station cell in each period based on the historical traffic information and a preset traffic threshold.

[0051] In one of the embodiments, the apparatus further includes:

[0052] a third obtaining module, configured to obtain historical network performance trend information of each scenario in a second historical period when a preset target energy-saving scenario determination condition is reached;

[0053] a calculating module, configured to calculate target network performance trend information of each scenario according to the historical network performance trend information of the scenario;

[0054] a third determining module, configured to determine a target energy-saving scenario from each of the scenarios according to the target network performance trend information of the scenario and a preset fluctuation threshold.

[0055] In one of the embodiments, the apparatus further includes:

[0056] a fourth obtaining module, configured to obtain, when a preset model updating condition is reached, sample target energy-saving scenario corresponding sample base station cells in a period from a current time to a target historical time, main feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each of the sample base station cells, and energy-saving base station cell sample results of the sample target energy-saving scenario;

[0057] a fourth determining module, configured to determine an updated data set based on the sample target energy-saving scenario corresponding sample base station cells, the user access sample information corresponding to each of the sample base station cells, the main feature sample information corresponding to the sample target energy-saving scenario, and the energy-saving base station cell sample results.

[0058] a training module, configured to train the energy-saving base station cell prediction model based on the updated data set to obtain a new energy-saving base station cell prediction model.

[0059] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the first aspect when executing the computer program.

[0060] In a fourth aspect, the present application also provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps of the first aspect.

[0061] In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program, and the computer program, when executed by a processor, implements the steps of the first aspect.

[0062] The energy saving method, device, computer device, storage medium and computer program product described above, when the preset energy saving base station cell prediction condition is reached, obtain each base station cell corresponding to a target energy saving scenario, main feature information corresponding to the target energy saving scenario, and user access information corresponding to each base station cell; input each base station cell, the main feature information corresponding to the target energy saving scenario, and the user access information corresponding to each base station cell into a pre-trained energy saving base station cell prediction model to obtain an energy saving base station cell prediction result; the energy saving base station cell prediction result comprises a target base station cell; determine a target energy saving strategy according to the target base station cell and a preset energy saving strategy determination rule; and perform energy saving processing on the target base station cell according to the target energy saving strategy. In this way, when the preset energy saving base station cell prediction condition is reached, the target base station cell with small influence on network communication of users and low user dependence degree is periodically predicted based on the base station cell corresponding to the target energy saving scenario, the main feature information corresponding to the target energy saving scenario, the user access information corresponding to the base station cell, and the energy saving base station cell prediction model, and only the target base station cell corresponding to the target energy saving scenario is subjected to energy saving processing, which has small influence on network perception degradation and small influence on communication quality, and the communication quality is good. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 A flowchart of an energy saving method in an embodiment;

[0064] Figure 2 A flowchart of a step of obtaining each base station cell corresponding to a target energy saving scenario, main feature information corresponding to the target energy saving scenario, and user access information corresponding to each base station cell in an embodiment;

[0065] Figure 3 A flowchart of a step of constructing main feature information corresponding to a target energy saving scenario in an embodiment;

[0066] Figure 4 A flowchart of a step of determining a target energy saving strategy in an embodiment;

[0067] Figure 5 A flowchart of a step of determining an energy saving period in an embodiment;

[0068] Figure 6 a flowchart of a process for determining a target energy-saving scenario in an embodiment;

[0069] Figure 7 a flowchart of a process for an energy-saving method in another embodiment;

[0070] Figure 8 a block diagram of an energy-saving device in an embodiment;

[0071] Figure 9 an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0072] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0073] In an embodiment, as shown in Figure 1 an energy-saving method is provided, and the embodiment is exemplified by the method applied to a terminal. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction of the terminal and the server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle-mounted device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server can be realized by an independent server or a server cluster composed of multiple servers.

[0074] In the embodiment, the method includes the following steps:

[0075] In step 101, when a preset energy-saving base station cell prediction condition is reached, each base station cell corresponding to a target energy-saving scenario, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell are obtained.

[0076] In the embodiments of the present application, when the preset energy-saving base station cell prediction condition is reached, the terminal determines each base station cell corresponding to the target energy-saving scenario. Then, the terminal obtains each base station cell corresponding to the target energy-saving scenario, the subject feature information corresponding to the target energy-saving scenario, and the user access information corresponding to each base station cell. The energy-saving base station cell prediction condition is used to measure whether to start energy-saving base station cell prediction. The energy-saving base station cell prediction condition can be a time condition. For example, the energy-saving base station cell prediction condition can be that the time reaches a certain time point of the day, that is, the energy-saving base station cell prediction is performed once a day. The target energy-saving scenario is a scenario for energy saving, which can be an office scenario, a residence, a large shopping mall, etc. A sector is a geographical area covered by a single antenna of a base station, which can be considered that one antenna corresponds to one sector. A base station using a single omnidirectional antenna has only one sector; a base station using a directional antenna generally has three sectors. The capacity of the base station can be improved by increasing the sectors. The base station cell is a logical concept under the sector, and multiple base station cells can be defined under a sector based on different carrier frequencies and scrambling codes, that is, multiple base station cells can correspond to one sector. One target energy-saving scenario corresponds to multiple base station cells. The subject feature information is used to represent the scenario characteristics and the crowd characteristics of the target energy-saving scenario. The subject feature information includes the scenario characteristic information of the target energy-saving scenario and the group characteristic information of the users in the target energy-saving scenario. The subject feature information can include: the enterprise size of the office scenario, the enterprise type of the office scenario, the average unit price of the housing in the residential community, the community type of the residential community, the housing rent ratio of the residential community, and the WIFI package usage ratio of the residential community households. The user access information is the network access information of the user. The enterprise type can include functional departments. The community type can include village residential communities. The user access information can include: uplink and downlink traffic, uplink and downlink physical resource block (Physical Resource Block, PRB) utilization rate, uplink and downlink radio resource control protocol (Radio Resource Control, RRC) connection number, and base station cell engineering parameter information. The base station cell engineering parameter information can include: indoor and outdoor labels, community latitude and longitude, community name, and community direction angle.

[0077] In step 102, each base station cell, the subject feature information corresponding to the target energy-saving scenario, and the user access information corresponding to each base station cell are input into the pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result.

[0078] The energy-saving base station cell prediction result includes a target base station cell.

[0079] In the embodiment of the present application, the terminal inputs the subject feature information corresponding to each base station cell and the target energy saving scenario, the user access information corresponding to each base station cell into the pre-trained energy saving base station cell prediction model to obtain an energy saving base station cell prediction result. The energy saving base station cell prediction model can be a machine learning model or a deep learning model. For example, the energy saving base station cell prediction model can be a fully connected neural network. The energy saving base station cell prediction result is a prediction result of the base station cell for energy saving processing. The energy saving base station cell prediction result can include each base station cell and the energy saving base station cell grade corresponding to each base station cell, or only the target base station cell. The energy saving base station cell grade is used to represent the priority of each base station cell for energy saving processing.

[0080] In step 103, the target energy saving strategy is determined according to the target base station cell and the preset energy saving strategy determination rule.

[0081] In the embodiment of the present application, the terminal determines the target energy saving strategy according to the target base station cell and the preset energy saving strategy determination rule. The target energy saving strategy is a strategy for energy saving processing of the base station cell. The target energy saving strategy can include an energy saving processing object, and can also include an energy saving processing time and an energy saving processing mode.

[0082] In one example, the terminal takes the target base station cell as the energy saving processing object to obtain the target energy saving strategy.

[0083] In step 104, the target base station cell is subjected to energy saving processing according to the target energy saving strategy.

[0084] In the embodiment of the present application, the terminal subjects the target base station cell to energy saving processing according to the target energy saving strategy.

[0085] In one example, for each target base station cell, the terminal subjects the target base station cell to energy saving processing according to the target energy saving strategy at the energy saving processing time corresponding to the target base station cell and by using the energy saving processing mode corresponding to the target base station cell.

[0086] In the energy-saving method, when the preset energy-saving base station cell prediction condition is reached, the base stations and cells corresponding to the target energy-saving scene, the main feature information corresponding to the target energy-saving scene, and the user access information corresponding to each base station cell are obtained; the base stations and cells corresponding to the target energy-saving scene, the main feature information corresponding to the target energy-saving scene, and the user access information corresponding to each base station cell are input into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result includes a target base station cell; a target energy-saving strategy is determined according to the target base station cell and a preset energy-saving strategy determination rule; and the target base station cell is subjected to energy-saving processing according to the target energy-saving strategy. In this way, when the preset energy-saving base station cell prediction condition is reached, the target base station cell with small influence on network communication of users and low user dependence is periodically and dynamically predicted based on the base stations and cells corresponding to the target energy-saving scene, the main feature information corresponding to the target energy-saving scene, the user access information corresponding to each base station cell, and the energy-saving base station cell prediction model, and only the target base station cell corresponding to the target energy-saving scene is subjected to energy-saving processing, thereby causing small network perception degradation and small influence on communication quality, and good communication quality. Moreover, the target base station cell is dynamically predicted, the energy-saving effect of the energy-saving processing on the target base station cell is ensured to be real-time optimal, and the communication quality is further improved. Furthermore, the target base station cell corresponding to the target energy-saving scene is subjected to energy-saving processing, the key energy-saving scene is further subdivided, and the optimal cost-effective energy-saving base station cell is screened, which can improve the accuracy of energy-saving processing operation and further improve the communication quality. Moreover, the energy-saving base station cell prediction model pre-trained by the method is used to predict the target base station cell of the target energy-saving scene, the model is an artificial intelligence (AI) model constructed by scene features and user group features of the key scene, the neural network is applied to the determination of the base station energy-saving strategy for the first time, the target base station cell corresponding to the target energy-saving scene can be subjected to energy-saving processing, and the risk of user experience decline and user complaints caused by energy-saving can be maximally avoided.

[0087] In one embodiment, as shown in FIG. 2, the specific process of obtaining the base stations and cells corresponding to the target energy-saving scene, the main feature information corresponding to the target energy-saving scene, and the user access information corresponding to each base station cell includes the following steps: Figure 2

[0088] Step 201, obtaining the base stations and cells corresponding to the target energy-saving scene, the user access information corresponding to each base station cell, and the initial feature information corresponding to the target energy-saving scene.

[0089] ​In the embodiment of the present application, the terminal acquires each base station cell corresponding to a target energy saving scenario, user access information corresponding to each base station cell, and initial characteristic information corresponding to the target energy saving scenario. The initial characteristic information is characteristic information that can be directly collected for the target energy saving scenario. For example, the initial characteristic information can be the total number of residential cell houses, the number of residential cell houses for self-use, and the number of residential cell houses for rent.

[0090] In step 202, for each target energy saving scenario, the initial characteristic information corresponding to the base station cell is analyzed based on a preset subject characteristic index, the index characteristic information corresponding to the subject characteristic index is calculated, and the index characteristic information corresponding to the target energy saving scenario is obtained.

[0091] In the embodiment of the present application, for each target energy saving scenario, the terminal analyzes the initial characteristic information corresponding to the base station cell based on a preset subject characteristic index, calculates the index characteristic information corresponding to the subject characteristic index, and obtains the index characteristic information corresponding to the target energy saving scenario. The subject characteristic index is an index used to represent the group characteristics of users in the target energy saving scenario. The index characteristic information is information used to represent the subject characteristic index of the target energy saving scenario. For example, the subject characteristic index is the residential cell house self-use ratio, and the index characteristic information is that the residential cell house self-use ratio of the target energy saving scenario A is 63%.

[0092] In step 203, the subject characteristic information corresponding to the target energy saving scenario is constructed based on the initial characteristic information corresponding to the target energy saving scenario and the index characteristic information corresponding to the target energy saving scenario.

[0093] In the embodiment of the present application, the terminal constructs the subject characteristic information corresponding to the target energy saving scenario based on the initial characteristic information corresponding to the target energy saving scenario and the index characteristic information corresponding to the target energy saving scenario.

[0094] In one example, the terminal constructs the subject characteristic information corresponding to the target energy saving scenario by using the initial characteristic information corresponding to the target energy saving scenario and the index characteristic information corresponding to the target energy saving scenario.

[0095] In the energy saving method, the target energy saving scene corresponding to each base station cell, the user access information corresponding to each base station cell, and the initial feature information corresponding to the target energy saving scene are obtained; for each target energy saving scene, the initial feature information corresponding to the base station cell is analyzed based on the preset main feature index, the index feature information corresponding to the main feature index is calculated, and the index feature information corresponding to the target energy saving scene is obtained; and the main feature information corresponding to the target energy saving scene is constructed based on the initial feature information corresponding to the target energy saving scene and the index feature information corresponding to the target energy saving scene. In this way, the target energy saving scene corresponding to each base station cell and the user access information corresponding to each base station cell are directly obtained, the initial feature information corresponding to the target energy saving scene is obtained first, then the index feature information corresponding to the main feature index is calculated based on the initial feature information, and the main feature information corresponding to the target energy saving scene is constructed based on the initial feature information and the index feature information, so that the main feature information corresponding to the target energy saving scene not only includes the basic main feature that can be directly obtained, but also includes the derived index feature that is analyzed and calculated based on the basic main feature and the preset main feature index, the main feature information corresponding to the target energy saving scene is more comprehensive and rich, can more accurately reflect the scene feature and the user group feature, can improve the prediction accuracy of the target base station cell, further reduces the influence degree on the communication quality, and further improves the communication quality.

[0096] In one embodiment, as shown in FIG. 10, the specific process of constructing the main feature information corresponding to the target energy saving scene based on the initial feature information corresponding to the target energy saving scene and the index feature information corresponding to the target energy saving scene includes the following steps: Figure 3

[0097] Step 301, based on the main feature index, determining the candidate feature information corresponding to the target energy saving scene in the initial feature information corresponding to the target energy saving scene.

[0098] In the embodiment of the present application, the terminal determines the candidate feature information corresponding to the target energy saving scene that meets the preset feature information screening condition in the initial feature information corresponding to the target energy saving scene based on the main feature index.

[0099] In one example, the terminal determines the used initial feature information for calculating the main feature index in the initial feature information corresponding to the target energy saving scene based on the main feature index. Then, the terminal removes the used initial feature information in the initial feature information corresponding to the target energy saving scene to obtain unused initial feature information. Then, the terminal takes the unused initial feature information in the initial feature information corresponding to the target energy saving scene as the candidate feature information corresponding to the target energy saving scene.

[0100] ​In step 302, the candidate feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario are constructed into the main feature information corresponding to the target energy-saving scenario.

[0101] In the embodiment of the present application, the terminal constructs the main feature information corresponding to the target energy-saving scenario from the candidate feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario.

[0102] In one example, the terminal constructs the main feature information corresponding to the target energy-saving scenario from the candidate feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario.

[0103] In the above energy-saving method, the candidate feature information corresponding to the target energy-saving scenario is determined from the initial feature information corresponding to the target energy-saving scenario based on the main feature index, and the main feature information corresponding to the target energy-saving scenario is constructed from the candidate feature information corresponding to the target energy-saving scenario and the index feature information corresponding to the target energy-saving scenario. In this way, the candidate feature information is selected from the initial feature information based on the main feature index, and the main feature information corresponding to the target energy-saving scenario is constructed from the candidate feature information and the index feature information. The main feature information does not include redundant process information, so that the main feature information corresponding to the target energy-saving scenario is more accurate, which can more accurately reflect the scene features and user group features, further improve the prediction accuracy of the target base station cell, further reduce the degree of influence on the communication quality, and further improve the communication quality.

[0104] In one embodiment, as shown in Figure 4 According to the target base station cell and the preset energy-saving strategy determination rule, the target energy-saving strategy is determined, which includes:

[0105] In step 401, for each target base station cell, the target energy-saving mode corresponding to the target base station cell is queried in the preset mapping relationship between the base station cell and the energy-saving mode, and the energy-saving period corresponding to the target base station cell is obtained.

[0106] In the embodiment of the present application, for each target base station cell, the terminal queries the target energy-saving mode corresponding to the target base station cell in the preset mapping relationship between the base station cell and the energy-saving mode. Then, the terminal obtains the energy-saving period corresponding to the target base station cell. The energy-saving mode is a mode or means for energy-saving processing of the base station cell, also known as the energy-saving processing mode. The energy-saving mode can include a deep energy-saving mode and a shallow energy-saving mode. The energy-saving period is the time for energy-saving processing of the base station cell, also known as the energy-saving processing time. The energy-saving period can be one or more periods. Different base station cells can correspond to the same energy-saving mode and the same energy-saving period, or different energy-saving modes and different energy-saving periods.

[0107] At step 402, the terminal generates the energy saving sub-strategy corresponding to the target base station cell based on the target energy saving mode corresponding to the target base station cell and the energy saving period corresponding to the target base station cell.

[0108] In the embodiments of the present application, the terminal generates the energy saving sub-strategy corresponding to the target base station cell based on the target energy saving mode corresponding to the target base station cell and the energy saving period corresponding to the target base station cell.

[0109] In one example, the terminal constitutes the target base station cell, the target energy saving mode corresponding to the target base station cell and the energy saving period corresponding to the target base station cell into the energy saving sub-strategy corresponding to the target base station cell.

[0110] At step 403, the terminal constitutes the energy saving sub-strategies of the target base station cells into the target energy saving strategy.

[0111] In the embodiments of the present application, the terminal constitutes the energy saving sub-strategies of the target base station cells into the target energy saving strategy.

[0112] In the energy saving method, for each target base station cell, the target energy saving mode corresponding to the target base station cell is queried in the preset mapping relationship between base station cells and energy saving modes, and the energy saving period corresponding to the target base station cell is obtained; the energy saving sub-strategy corresponding to the target base station cell is generated based on the target energy saving mode corresponding to the target base station cell and the energy saving period corresponding to the target base station cell; and the energy saving sub-strategies of the target base station cells are constituted into the target energy saving strategy. In this way, based on the preset mapping relationship, the target energy saving mode corresponding to each target base station cell is queried, and the energy saving period corresponding to each target base station cell is obtained to constitute the target energy saving strategy, so that the target energy saving strategy not only includes energy saving processing objects, but also includes different energy saving processing modes and different energy saving processing times corresponding to different energy saving processing objects, which is more in line with the actual situation that the target base station cells have different self conditions, the energy saving processing operation is more accurate, the degree of influence on the communication quality is further reduced, and the communication quality is further improved.

[0113] In one embodiment, as shown in Figure 5 the energy saving method further includes the following steps:

[0114] At step 501, the terminal obtains the historical traffic information of the target base station cell in a first historical period.

[0115] In the embodiment of the present application, the terminal obtains historical traffic information of the target base station cell in a first historical period. The first historical period is related to the energy-saving base station cell prediction condition. When the energy-saving base station cell prediction condition is to reach a certain time point of each day, i.e., the energy-saving base station cell prediction is performed every day, the first historical period can be the day before the prediction time, or the same day of the last month (e.g., October 10) or the same day of the last week (e.g., Wednesday of last week). The historical traffic information includes time and traffic corresponding to the time.

[0116] In step 502, the energy-saving period corresponding to the target base station cell is determined in each period based on the historical traffic information and a preset traffic threshold.

[0117] In the embodiment of the present application, the terminal determines the energy-saving period corresponding to the target base station cell in each period based on the historical traffic information and a preset traffic threshold. The traffic threshold can be a fixed value or a variable value. Different base station cells can correspond to different traffic thresholds.

[0118] In one example, the terminal determines, based on the historical traffic information, a period in which the traffic is less than or equal to a preset traffic threshold as the energy-saving period corresponding to the target base station cell.

[0119] In the above energy-saving method, the historical traffic information of the target base station cell in a first historical period is obtained, and the energy-saving period corresponding to the target base station cell is determined in each period based on the historical traffic information and a preset traffic threshold. In this way, the energy-saving period corresponding to the target base station cell is determined in each period based on the historical traffic information of the target base station cell in the first historical period and the preset traffic threshold. Different first historical periods correspond to different prediction times, and the corresponding energy-saving period also changes accordingly, which is more in line with the actual situation. The real-time performance of the energy-saving period determination is better, and the energy-saving period determination is more accurate. The accuracy of the energy-saving processing operation is further improved, the degree of influence on the communication quality is further reduced, and the communication quality is further improved.

[0120] In one embodiment, as shown in Figure 6 the energy-saving method further includes the following steps:

[0121] In step 601, when a preset target energy-saving scenario determination condition is reached, historical network performance change trend information of each scenario in a second historical period is obtained.

[0122] In the embodiment of the present application, when the preset target energy saving scene determination condition is reached, the terminal obtains historical network performance change trend information of each scene in a second historical period. The target energy saving scene determination condition is used to measure whether to start determining the target energy saving scene. The target energy saving scene determination condition can be a time condition. For example, the target energy saving scene determination condition can be that the time reaches a certain time point every week, that is, the target energy saving scene determination is performed once every week. The second historical period is related to the target energy saving scene determination condition. When the target energy saving scene determination condition is that the time reaches a certain time point every week, that is, the target energy saving scene determination is performed once every week, the second historical period can be the previous week of the prediction time. The historical network performance change trend information is used to represent the change trend of the historical network performance. The historical network performance change trend information can be historical network key performance indication (KPI) fluctuation trend information.

[0123] In step 602, for each scene, target network performance change trend information of the scene is calculated according to the historical network performance change trend information of the scene.

[0124] In the embodiment of the present application, for each scene, the terminal calculates target network performance change trend information of the scene according to historical network performance change trend information of the scene.

[0125] In one example, the target base station cell prediction is performed once every day. The historical network performance change trend information includes historical network performance change trend sub-information corresponding to each day. For each scene, the terminal calculates historical daily average network performance change trend information of the scene according to historical network performance change trend sub-information of the scene on each day. Then, the terminal takes the historical daily average network performance change trend information of the scene as the target network performance change trend information of the scene.

[0126] In one example, the target base station cell prediction is performed once every day. The historical network performance change trend information includes historical network performance change trend sub-information corresponding to each day. For each scene, the terminal calculates historical daily average network performance change trend information of the scene according to historical network performance change trend sub-information of the scene on each day. Then, the terminal takes the historical daily average network performance change trend information of the scene as the target network performance change trend information of the scene.

[0127] In step 603, the target energy saving scene is determined in each scene according to the target network performance change trend information of each scene and a preset fluctuation threshold.

[0128] In the embodiments of the present application, the terminal calculates the fluctuation value of each scene according to the target network performance change trend information of each scene. Then, the terminal determines the target energy-saving scene in each scene according to the fluctuation value of each scene and the preset fluctuation threshold. The fluctuation threshold can be a fixed value or a variable value. Different base station cells can correspond to different fluctuation thresholds.

[0129] In one example, for each scene, the terminal determines the peak and the valley of the scene according to the target network performance change trend information of the scene. Then, the terminal calculates the fluctuation value of the scene according to the network performance value corresponding to the peak and the network performance value corresponding to the valley. Then, the terminal regards the scene whose fluctuation value is greater than the preset fluctuation threshold as the target energy-saving scene.

[0130] In the above energy-saving method, when the preset target energy-saving scene determination condition is reached, the historical network performance change trend information of each scene in a second historical time period is obtained; for each scene, the target network performance change trend information of the scene is calculated according to the historical network performance change trend information of the scene; and the target energy-saving scene is determined in each scene according to the target network performance change trend information of each scene and the preset fluctuation threshold. In this way, based on the historical network performance change trend information, the target network performance change trend information is calculated, and then the scene with large network performance fluctuation is regarded as the target energy-saving scene according to the target network performance change trend information. The target energy-saving scene is updated regularly, which is more in line with the actual situation that the scene situation changes over time, has better real-time performance in determining the target energy-saving scene, is more accurate, further improves the prediction accuracy of the target base station cell, further reduces the degree of influence on the communication quality, and further improves the communication quality.

[0131] In one embodiment, as shown in FIG. 7, the energy-saving method further includes the following steps: Figure 7

[0132] Step 701, when the preset model update condition is reached, the sample target energy-saving scene corresponding to each sample base station cell in a time period from the current time to the target historical time, the subject feature sample information corresponding to the sample target energy-saving scene, the user access sample information corresponding to each sample base station cell, and the energy-saving base station cell sample result of the sample target energy-saving scene are obtained.

[0133] ​In the embodiment of the present application, when the preset model updating condition is reached, the terminal obtains each sample base station cell corresponding to a sample target energy-saving scenario, subject feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, and energy-saving base station cell sample result of the sample target energy-saving scenario in a time period from the current time to a target historical time. The model updating condition is used to measure whether to update the energy-saving base station cell prediction model. The model updating condition can be a time condition. For example, the model updating condition can be that the time reaches a certain time point of each month, that is, the energy-saving base station cell prediction model is updated once a month. The target historical time is related to the model updating condition. When the model updating condition is that the time reaches a certain time point of each month, the target historical time can be the time point of the last month. The sample target energy-saving scenario is similar to the target energy-saving scenario. The sample base station cell is similar to the base station cell. The subject feature sample information is similar to the subject feature information. The user access sample information is similar to the user access information. The energy-saving base station cell sample result is similar to the energy-saving base station cell prediction result.

[0134] In step 702, based on each sample base station cell corresponding to a sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, subject feature sample information corresponding to the sample target energy-saving scenario, and energy-saving base station cell sample result, an update data set is determined.

[0135] In the embodiment of the present application, the terminal determines an update data set based on each sample base station cell corresponding to a sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, subject feature sample information corresponding to the sample target energy-saving scenario, and energy-saving base station cell sample result.

[0136] In one example, the terminal constitutes each sample base station cell corresponding to a sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, subject feature sample information corresponding to the sample target energy-saving scenario, and energy-saving base station cell sample result into an update data set.

[0137] In one example, for each sample target energy-saving scenario, the terminal constitutes each sample base station cell corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, subject feature sample information corresponding to the sample target energy-saving scenario, and energy-saving base station cell sample result corresponding to the sample target energy-saving scenario into a candidate sample corresponding to the sample target energy-saving scenario. Then, the terminal determines a target sample satisfying a preset sample screening condition from the candidate samples. Then, the terminal constitutes each target sample into an update data set.

[0138] In step 703, based on the update data set, the energy-saving base station cell prediction model is trained to obtain a new energy-saving base station cell prediction model.

[0139] In the embodiment of the present application, the terminal trains the energy-saving base station cell prediction model based on the update data set to obtain a new energy-saving base station cell prediction model. In the process of model training, the terminal can calculate the training error by using the mean square error. The terminal can train the model by using the forward propagation method.

[0140] In the above energy-saving method, when the preset model update condition is reached, each sample base station cell corresponding to a sample target energy-saving scenario, subject feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, and energy-saving base station cell sample results of the sample target energy-saving scenario are obtained within a time period from the current time to the target historical time. The update data set is determined based on each sample base station cell corresponding to the sample target energy-saving scenario, the user access sample information corresponding to each sample base station cell, the subject feature sample information corresponding to the sample target energy-saving scenario, and the energy-saving base station cell sample results. The energy-saving base station cell prediction model is trained based on the update data set to obtain a new energy-saving base station cell prediction model. In this way, based on the newly added historical data, the sample and the update data set are updated regularly, the energy-saving base station cell prediction model is trained regularly, the continuous update of the energy-saving base station cell prediction model is realized, the self-learning and self-adaptive capabilities of the neural network are fully utilized, the model update and self-learning are continuously completed online, the real-time accuracy of the energy-saving base station cell prediction model is ensured, the accuracy of the target base station cell prediction is further improved, the degree of influence on the communication quality is further reduced, and the communication quality is further improved.

[0141] In one embodiment, the training process of the energy-saving base station cell prediction model includes: obtaining each sample base station cell corresponding to a sample target energy-saving scenario, subject feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, and energy-saving base station cell sample results of the sample target energy-saving scenario within a third historical period; determining a target data set based on each sample base station cell corresponding to the sample target energy-saving scenario, the user access sample information corresponding to each sample base station cell, the subject feature sample information corresponding to the sample target energy-saving scenario, and the energy-saving base station cell sample results; and training a target neural network based on the target data set to obtain the energy-saving base station cell prediction model. It can be understood that the specific process of training the energy-saving base station cell prediction model is similar to the specific process of updating the energy-saving base station cell prediction model.

[0142] In one embodiment, the terminal regularly collects user access information of base station cells corresponding to different target energy-saving scenarios (office, residence, shopping mall, etc.). Then, the terminal fuses these user access information into a sample set L1={(c i , t i , s i , p i , v i, w i ,..., o i )}. Wherein, c i , t i , s i , p i , v i , w i , o i are different user access information. Then, the terminal carries out data arrangement and merging of the user access information of the base station cell corresponding to the target energy-saving scene collected by the terminal into feature data available for model training, and meanwhile, the terminal eliminates outliers and fills in missing values. Then, the terminal further derives the source data to increase new derived features in the sample. The derived features include but are not limited to high residential area with high self-occupancy ratio, village-in-city residential area and high-WIFI package usage ratio area. Then, the terminal puts the new derived features into the sample set to obtain a new sample set L2={(c i , t i , s i , p i , v i , w i , l i ,..., o i )}. Wherein, l i is a new derived feature. The new sample set L2 contains sample feature information. The terminal selects a fully connected neural network as the energy-saving base station cell prediction model, and adds a feature ratio in the energy-saving base station cell prediction model. When processing sample feature information, the energy-saving base station cell prediction model performs feature vector normalization processing on the sample feature information, and converts the sample feature information into a matrix normalized data vector table. The feature vector normalization processing includes One-Hot Encoding, data standardization and normalization. In this way, the user data is preprocessed into group features and converted into a series of matrix normalized data vector tables, which can realize lossless dynamic expression of group features. Then, the terminal trains the energy-saving base station cell prediction model based on the sample set L2. During training, the terminal calculates the training error by using the mean square error, and obtains the training result and model optimization of the multi-scene target base station cell by using the forward propagation method, including vector optimization, sample precision screening, network adjustment and parameter adjustment. Then, the terminal periodically inputs the feature information of each target energy-saving scene into the trained energy-saving base station cell prediction model to update the energy-saving base station cell prediction model. In this way, the energy-saving base station cell prediction model is optimized online, and the base station energy-saving strategy is dynamically optimized.

[0143] It should be understood that although each step in the flowchart involved in the embodiments described above is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiments of the present application also provide an energy-saving device for implementing the energy-saving method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more energy-saving device embodiments provided below can refer to the limitations of the energy-saving method described above, which will not be repeated here.

[0145] In one embodiment, as shown in Figure 8 An energy-saving device 800 is provided, comprising: a first acquisition module 810, a prediction module 820, a first determination module 830, and a processing module 840, wherein:

[0146] The first acquisition module 810 is configured to acquire each base station cell corresponding to a target energy-saving scenario, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell when a preset energy-saving base station cell prediction condition is reached.

[0147] The prediction module 820 is configured to input each base station cell, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result includes a target base station cell.

[0148] The first determination module 830 is configured to determine a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule.

[0149] The processing module 840 is configured to perform energy-saving processing on the target base station cell according to the target energy-saving strategy.

[0150] Optionally, the first acquisition module 810 is specifically configured to:

[0151] acquire each base station cell corresponding to a target energy saving scenario, user access information corresponding to each base station cell, and initial feature information corresponding to the target energy saving scenario;

[0152] For each target energy saving scenario, based on a preset main feature index, analyze the initial feature information corresponding to the base station cell, calculate the index feature information corresponding to the main feature index, and obtain the index feature information corresponding to the target energy saving scenario;

[0153] Based on the initial feature information corresponding to the target energy saving scenario and the index feature information corresponding to the target energy saving scenario, the main feature information corresponding to the target energy saving scenario is constructed.

[0154] Optionally, the first acquisition module 810 is specifically configured to:

[0155] Based on the main feature index, determine the candidate feature information corresponding to the target energy saving scenario in the initial feature information corresponding to the target energy saving scenario;

[0156] The candidate feature information corresponding to the target energy saving scenario and the index feature information corresponding to the target energy saving scenario are constructed to obtain the main feature information corresponding to the target energy saving scenario.

[0157] Optionally, the first determination module 830 is specifically configured to:

[0158] For each target base station cell, in a preset mapping relationship between base station cells and energy saving modes, query the target energy saving mode corresponding to the target base station cell, and acquire the energy saving period corresponding to the target base station cell;

[0159] Based on the target energy saving mode corresponding to the target base station cell and the energy saving period corresponding to the target base station cell, generate the energy saving sub-strategy corresponding to the target base station cell;

[0160] The energy saving sub-strategies of each target base station cell are constructed to form a target energy saving strategy.

[0161] Optionally, the device 800 further includes:

[0162] The second acquisition module is configured to acquire historical traffic information of the target base station cell in a first historical period;

[0163] The second determination module is configured to determine the energy saving period corresponding to the target base station cell in each period based on the historical traffic information and a preset traffic threshold.

[0164] Optionally, the device 800 further includes:

[0165] The third obtaining module is configured to obtain historical network performance change trend information of each scene in a second historical period when a preset target energy-saving scene determination condition is reached.

[0166] The calculating module is configured to calculate target network performance change trend information of each scene according to the historical network performance change trend information of the scene.

[0167] The third determining module is configured to determine a target energy-saving scene in each scene according to the target network performance change trend information of each scene and a preset fluctuation threshold.

[0168] Optionally, the apparatus 800 further includes:

[0169] The fourth obtaining module is configured to obtain, when a preset model updating condition is reached, each sample base station cell corresponding to a sample target energy-saving scene from a current time to a target historical time, main feature sample information corresponding to the sample target energy-saving scene, user access sample information corresponding to each sample base station cell, and an energy-saving base station cell sample result of the sample target energy-saving scene.

[0170] The fourth determining module is configured to determine an updating data set based on each sample base station cell corresponding to the sample target energy-saving scene, the user access sample information corresponding to each sample base station cell, the main feature sample information corresponding to the sample target energy-saving scene, and the energy-saving base station cell sample result.

[0171] The training module is configured to train the energy-saving base station cell prediction model based on the updating data set to obtain a new energy-saving base station cell prediction model.

[0172] Each module in the energy-saving apparatus can be realized by software, hardware, and a combination thereof in whole or in part. Each module can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to each module.

[0173] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 9The computer device shown in the figure includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize an energy saving method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0174] Those skilled in the art can understand that, Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0175] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the above method embodiments.

[0176] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the above method embodiments.

[0177] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in each of the above method embodiments.

[0178] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of the country and region.

[0179] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of each method can be included. In the embodiments provided in the present application, any reference to memory, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0180] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0181] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. An energy saving method, characterized by, The method comprises: When a preset energy-saving base station cell prediction condition is reached, obtaining each base station cell corresponding to a target energy-saving scene, main feature information corresponding to the target energy-saving scene, and user access information corresponding to each base station cell; inputting each base station cell, main feature information corresponding to the target energy-saving scene, and user access information corresponding to each base station cell into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result comprises a target base station cell; determining a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule; performing energy-saving processing on the target base station cell according to the target energy-saving strategy; The method further comprises: when a preset target energy-saving scene determination condition is reached, obtaining historical network performance trend information of each scene in a second historical period; For each scene, target network performance trend information of the scene is calculated according to the historical network performance trend information of the scene; According to the target network performance trend information of each scene and a preset fluctuation threshold, the target energy-saving scene is determined in each scene.

2. The method of claim 1, wherein, The obtaining of each base station cell corresponding to a target energy-saving scene, main feature information corresponding to the target energy-saving scene, and user access information corresponding to each base station cell comprises: obtaining each base station cell corresponding to a target energy-saving scene, user access information corresponding to each base station cell, and initial feature information corresponding to the target energy-saving scene; For each target energy-saving scene, the initial feature information corresponding to the base station cell is analyzed based on a preset main feature index, the index feature information corresponding to the main feature index is calculated, and the index feature information corresponding to the target energy-saving scene is obtained; The main feature information corresponding to the target energy-saving scene is constructed based on the initial feature information corresponding to the target energy-saving scene and the index feature information corresponding to the target energy-saving scene.

3. The method of claim 2, wherein, The construction of the main feature information corresponding to the target energy-saving scene based on the initial feature information corresponding to the target energy-saving scene and the index feature information corresponding to the target energy-saving scene comprises: determining candidate feature information corresponding to the target energy-saving scene in the initial feature information corresponding to the target energy-saving scene based on the main feature index; The main feature information corresponding to the target energy-saving scene is constructed based on the candidate feature information corresponding to the target energy-saving scene and the index feature information corresponding to the target energy-saving scene.

4. The method of claim 1, wherein, The determination of a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule comprises: For each target base station cell, a target energy-saving mode corresponding to the target base station cell is queried in a preset mapping relationship between base station cells and energy-saving modes, and an energy-saving period corresponding to the target base station cell is obtained; a target energy-saving mode corresponding to the target base station cell and an energy-saving period corresponding to the target base station cell are used to generate an energy-saving sub-strategy corresponding to the target base station cell; The energy-saving sub-strategies of each target base station cell are combined to form a target energy-saving strategy.

5. The method of claim 4, wherein, The method further comprises: acquiring historical traffic information of the target base station cell in a first historical period; determining an energy-saving period corresponding to the target base station cell in each period based on the historical traffic information and a preset traffic threshold.

6. The method of claim 1, wherein, The method further comprises: when a preset model updating condition is reached, acquiring each sample base station cell corresponding to a sample target energy-saving scenario, subject feature sample information corresponding to the sample target energy-saving scenario, user access sample information corresponding to each sample base station cell, and energy-saving base station cell sample results of the sample target energy-saving scenario in a time period from a current time to a target historical time; determining an update data set based on each sample base station cell corresponding to the sample target energy-saving scenario, the user access sample information corresponding to each sample base station cell, the subject feature sample information corresponding to the sample target energy-saving scenario, and the energy-saving base station cell sample results; training the energy-saving base station cell prediction model based on the update data set to obtain a new energy-saving base station cell prediction model.

7. An energy saving device characterized by, The device comprises: a first acquisition module configured to acquire each base station cell corresponding to a target energy-saving scenario, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell when a preset energy-saving base station cell prediction condition is reached; a prediction module configured to input each base station cell, subject feature information corresponding to the target energy-saving scenario, and user access information corresponding to each base station cell into a pre-trained energy-saving base station cell prediction model to obtain an energy-saving base station cell prediction result; the energy-saving base station cell prediction result comprises a target base station cell; a first determination module configured to determine a target energy-saving strategy according to the target base station cell and a preset energy-saving strategy determination rule; a processing module configured to perform energy-saving processing on the target base station cell according to the target energy-saving strategy; The device further comprises: a third acquisition module configured to acquire historical network performance trend information of each scenario in a second historical period when a preset target energy-saving scenario determination condition is reached; a calculation module configured to calculate target network performance trend information of each scenario according to the historical network performance trend information of the scenario for each scenario; a third determination module configured to determine the target energy-saving scenario among each scenario according to the target network performance trend information of each scenario and a preset fluctuation threshold.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images