Resource scheduling method, device and equipment and computer storage medium

Abstract

The application discloses a resource scheduling method, device and equipment and a computer storage medium. The resource scheduling method comprises the following steps: obtaining a target performance index of a cell to be scheduled, wherein the target performance index comprises a wireless scene, a service model, cell load and channel quality; searching for a corresponding target fingerprint identifier from a fingerprint database according to the target performance index; matching a corresponding target scheduling factor combination according to the target fingerprint identifier; and scheduling resources of the cell to be scheduled according to the target scheduling factor combination. According to the embodiment of the application, the resource scheduling application can be classified from four dimensions of the wireless scene, the service model, the cell load and the channel quality, so that the resource scheduling application classification is more accurate, the resource scheduling is more accurate, and the resources can be fully utilized. Furthermore, the target scheduling factor combination of the cell to be scheduled can be directly matched from the fingerprint database according to the target fingerprint identifier, and the resources of the cell to be scheduled are scheduled, so that the resource scheduling efficiency is high.

Description

Technical Field

[0001] This application belongs to the field of wireless resource planning and optimization technology, and particularly relates to a resource scheduling method, apparatus, device and computer storage medium. Background Technology

[0002] As is well known, resource scheduling refers to the rational and effective adjustment, measurement, analysis, and use of various resources. Existing resource scheduling methods establish business control points according to different business types and user groups, and construct business request queues for resource scheduling. The allocation of resources among multiple queues can vary in size, and there are differences between queues. However, within a queue, resources are allocated equally according to the order of priority within the queue.

[0003] In existing resource scheduling methods, the number of classifications based on business type and user group is relatively small, and the classification of resource scheduling applications is not refined enough, which leads to the inability to fully utilize resources and low resource scheduling efficiency. Summary of the Invention

[0004] This application provides a resource scheduling method, apparatus, device, and computer storage medium to solve the technical problem that resource scheduling applications are not finely classified, resulting in insufficient resource utilization and low resource scheduling efficiency.

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

[0006] Obtain the target performance indicators of the cell to be scheduled. The target performance indicators include radio scenario, service model, cell load and channel quality. The radio scenario is used to indicate the radio signal propagation environment and the service model is used to indicate the traffic proportion of different service types.

[0007] Based on the target performance index, a target fingerprint identifier corresponding to the target performance index is retrieved from a pre-established fingerprint database. The fingerprint database includes a correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size for the corresponding business type.

[0008] Based on the target fingerprint identifier, match the corresponding target scheduling factor combination from the fingerprint database;

[0009] The resources of the cell to be scheduled are scheduled according to the target scheduling factor combination.

[0010] In one embodiment, before obtaining the target metrics of the cell to be scheduled, the method further includes:

[0011] Obtain sample metrics for sample cells, including sample performance metrics, which include wireless scenario, service model, cell load, and channel quality.

[0012] Based on the sample performance indicators, construct the fingerprint identifier of the sample cell;

[0013] The sample indicators are input into a preset neural network model to obtain the scheduling factor combination corresponding to the fingerprint identifier. The neural network model is trained based on the sample indicators and the scheduling factor combination.

[0014] A fingerprint database is established based on the correspondence between the fingerprint identifier and the scheduling factor combination.

[0015] In one embodiment, the sample metrics further include sample perception metrics, which include business success rate and business latency for different business types.

[0016] In one embodiment, before obtaining the target metrics of the cell to be scheduled, the method further includes:

[0017] Acquire at least one first perception indicator for a cell, the first perception indicator including service success rate and service latency for different service types;

[0018] Cells whose first perception index meets the preset conditions are identified as the cells to be scheduled.

[0019] In one embodiment, determining the cell that meets the preset conditions for the first sensing indicator as the cell to be scheduled includes:

[0020] If the success rate of the target service type is less than the preset first threshold corresponding to the target service type, or the service latency of the target service type is greater than the preset second threshold corresponding to the target service type, the target service type will be determined as a service type to be scheduled, and the target service type can be any service type.

[0021] Obtain the traffic of the service type to be scheduled;

[0022] Cells where the traffic of the service type to be scheduled is greater than a preset third threshold and the service success rate of the service type to be scheduled is less than a preset fourth threshold, or

[0023] Cells whose traffic for the service type to be scheduled is greater than a preset third threshold and whose service latency for the service type to be scheduled is greater than a preset fifth threshold are identified as the cells to be scheduled.

[0024] In one embodiment, scheduling the resources of the cell to be scheduled according to the target scheduling factor combination includes:

[0025] An execution script is generated based on the target scheduling factor combination;

[0026] The resources of the cell to be scheduled are scheduled according to the execution script.

[0027] In one embodiment, the scheduling factor combination includes a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor is used to characterize the resource scheduling size of a first service type, the second scheduling factor is used to characterize the resource scheduling size of a second service type, and the third scheduling factor is used to characterize the resource scheduling size of other service types besides the first and second service types.

[0028] In one embodiment, after scheduling the resources of the cell to be scheduled according to the target scheduling factor combination, the method further includes:

[0029] Obtain the second perception index after resource scheduling of the cell to be scheduled. The second perception index includes the service success rate and service latency of different service types.

[0030] Based on the second perception index, the resource scheduling result is obtained, which includes the resource scheduling result of the first business type, the resource scheduling result of the second business type, and the resource scheduling result of other business types besides the first and second business types.

[0031] Output the resource scheduling results.

[0032] Secondly, embodiments of this application provide a resource scheduling apparatus, the apparatus comprising:

[0033] The first acquisition module is used to acquire the target performance indicators of the cell to be scheduled. The target performance indicators include wireless scenario, service model, cell load and channel quality. The wireless scenario is used to indicate the wireless signal propagation environment and the service model is used to indicate the traffic proportion of different service types.

[0034] The lookup module is used to look up the target fingerprint identifier corresponding to the target performance indicator from a pre-established fingerprint database according to the target performance indicator. The fingerprint database includes the correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size of the corresponding business type.

[0035] The matching module is used to match the corresponding target scheduling factor combination from the fingerprint database based on the target fingerprint identifier;

[0036] The scheduling module is used to schedule the resources of the cell to be scheduled according to the target scheduling factor combination.

[0037] Thirdly, embodiments of this application provide an electronic device, the device comprising:

[0038] Processor and memory storing computer program instructions;

[0039] The processor implements the above-described method when executing the computer program instructions.

[0040] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the above-described method.

[0041] The resource scheduling method, apparatus, device, and computer storage medium of this application embodiment can obtain the target performance indicators of the cell to be scheduled. The target performance indicators include wireless scenario, service model, cell load, and channel quality. Based on the target performance indicators, the corresponding target fingerprint identifier is searched from a pre-established fingerprint database. Then, the corresponding target scheduling factor combination is matched according to the target fingerprint identifier. The resources of the cell to be scheduled are scheduled according to the target scheduling factor combination.

[0042] This application embodiment can retrieve the target fingerprint identifier from the fingerprint database based on four dimensions: wireless scenario, service model, cell load, and channel quality. This categorizes resource scheduling applications according to these four dimensions, resulting in more refined classification and more accurate resource scheduling, thus enabling fuller resource utilization. Furthermore, this application embodiment can also directly match the target scheduling factor combination of the cell to be scheduled from the fingerprint database based on the target fingerprint identifier, thereby scheduling the resources of the cell to be scheduled, resulting in high resource scheduling efficiency. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating a resource scheduling method provided in one embodiment of this application;

[0045] Figure 2 This is a partial flowchart of the resource scheduling method provided in the embodiments of this application;

[0046] Figure 3 This is a schematic diagram of the neural network model provided in the embodiments of this application;

[0047] Figure 4 This is another partial flowchart of the resource scheduling method provided in the embodiments of this application;

[0048] Figure 5 This is another partial flowchart of the resource scheduling method provided in the embodiments of this application;

[0049] Figure 6 This is a flowchart illustrating a scenario embodiment of the resource scheduling method provided in this application.

[0050] Figure 7 This is a schematic diagram of the structure of a resource scheduling device provided in another embodiment of this application;

[0051] Figure 8 This is a schematic diagram of the structure of an electronic device provided in another embodiment of this application. Detailed Implementation

[0052] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0053] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0054] To address the problems of the prior art, embodiments of this application provide a resource scheduling method, apparatus, device, and computer storage medium. The resource scheduling method provided in this application embodiment will be described first.

[0055] Figure 1A flowchart illustrating a resource scheduling method provided in one embodiment of this application is shown.

[0056] like Figure 1 As shown, the resource scheduling method provided in this application embodiment may include:

[0057] Step S101: Obtain the target performance indicators of the cell to be scheduled. The target performance indicators include wireless scenario, service model, cell load and channel quality. The wireless scenario is used to indicate the wireless signal propagation environment, and the service model is used to indicate the traffic proportion of different service types.

[0058] Step S102: Based on the target performance index, search for the target fingerprint identifier corresponding to the target performance index from the pre-established fingerprint database. The fingerprint database includes the correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size of the corresponding business type.

[0059] Step S103: Match the corresponding target scheduling factor combination from the fingerprint database based on the target fingerprint identifier;

[0060] Step S104: Schedule the resources of the cell to be scheduled according to the target scheduling factor combination.

[0061] In step S101, the cell to be scheduled can be a pre-determined cell that needs to be scheduled by resources. After the cell to be scheduled is determined, the target performance indicators of the cell to be scheduled can be obtained. The target performance indicators can include four dimensions: wireless scenario, service model, cell load and channel quality.

[0062] A wireless scenario can indicate the wireless signal propagation environment. Specifically, the wireless scenario can come from wireless network parameter data. In one example of this embodiment, the wireless scenario can mainly include 32 categories. Among these 32 categories, two can be selected as custom categories to facilitate system expansion.

[0063] For example, wireless scenarios can include villages, urban roads, high-rise residential areas, towns, low-rise residential areas, urban villages, universities, enterprises and institutions, highways, convention centers, primary and secondary schools, commercial centers, star-rated hotels, scenic spots, office buildings, industrial parks, government and military organs, hospitals, squares and parks, high-speed rail, subway, national and provincial highways, leisure and entertainment venues, suburban roads, ordinary railways, sports stadiums, railway stations, farmers' markets, long-distance bus stations, others, custom 1, and custom 2.

[0064] For ease of representation, wireless scenarios can be labeled, with each label indicating the corresponding wireless scenario. For example, "village" can correspond to label "1", urban roads can correspond to label "2", "high-rise residential area" can correspond to label "3", and so on.

[0065] A business model can be used to indicate the traffic share of different business types. These business types can include the first business type, which has low traffic consumption and high user perception, such as payment services; the second business type, which has high traffic consumption and low user perception, such as video viewing services; and other business types besides the first and second business types.

[0066] A business model can be defined according to the proportion of traffic for a particular business type in the total traffic for all business types.

[0067] In one example, the service model can be defined according to the traffic share of the first service type. That is, if two cells have the same traffic share of the first service type, they can be considered to belong to the same service model. Alternatively, the service model can be defined according to the traffic share of the second service type. That is, if two cells have the same traffic share of the second service type, they can be considered to belong to the same service model.

[0068] Cell load can be characterized by the utilization rate of the cell's downlink physical resource block (PRB). When the downlink PRB utilization rates of two cells are the same, the performance indicators of the cell load of the two cells can be considered to be the same.

[0069] Channel quality can be characterized by the cell downlink Channel Quality Indicator (CQI). When two cells have the same downlink CQI, the channel quality performance indicators of the two cells can be considered to be the same.

[0070] In step S102, a target fingerprint identifier corresponding to the target performance indicator can be retrieved from a pre-established fingerprint database. The fingerprint database can record multiple fingerprint identifiers, each corresponding to performance indicators across four dimensions: wireless scenario, service model, cell load, and channel quality. That is, the cells corresponding to each fingerprint identifier have essentially the same or similar performance indicators.

[0071] like Figure 2 As shown, the target performance index of the cell to be scheduled can be matched with the performance index corresponding to the fingerprint identifier in the fingerprint database to find the target fingerprint identifier corresponding to the target performance index.

[0072] For example, fingerprint A corresponds to wireless scenario 5, service model 35, cell load 24, and channel quality 7; fingerprint B corresponds to wireless scenario 8, service model 40, cell load 27, and channel quality 12; fingerprint C corresponds to wireless scenario 20, service model 29, cell load 27, and channel quality 7...

[0073] If the target performance metrics are: wireless scenario 5, service model 35, cell load 24, and channel quality 7, then fingerprint A can be used as the target fingerprint identifier; if the target performance metrics are: wireless scenario 8, service model 40, cell load 27, and channel quality 12, then fingerprint B can be used as the target fingerprint identifier...

[0074] The fingerprint database may also include a correspondence between fingerprint identifiers and scheduling factor combinations, whereby the scheduling factor combinations may include scheduling factors for at least one service type. For example, the scheduling factor combination may include scheduling factors for a first service type and scheduling factors for a second service type, wherein the scheduling factor for the first service type can be used to characterize the resource scheduling size for the first service type, and the scheduling factor for the second service type can be used to characterize the resource scheduling size for the second service type.

[0075] Each fingerprint identifier in the fingerprint database can correspond to a scheduling factor combination. For example, fingerprint A can correspond to scheduling factor combination A, fingerprint B can correspond to scheduling factor combination B, fingerprint C can correspond to scheduling factor combination C, and so on.

[0076] In step S103, the corresponding target scheduling factor combination can be matched from the fingerprint database based on the target fingerprint identifier. For example, when the target fingerprint identifier is fingerprint B, the scheduling factor combination B corresponding to fingerprint B can be used as the target scheduling factor combination.

[0077] In step S104, resources of the cell to be scheduled can be scheduled according to the target scheduling factor combination. The resource scheduling size for each service type may differ between different scheduling factor combinations, and the resources that different cells to be scheduled need to schedule are also different. Resources of the cell to be scheduled can be scheduled in a targeted manner according to the target scheduling factor combination matched from the fingerprint database.

[0078] The methods for scheduling resources in the cell to be scheduled can be as follows: First, the resources of the cell to be scheduled can be scheduled directly based on the resource scheduling size of different service types in the target scheduling factor combination. Second, an execution script can be generated based on the target scheduling factor combination, and then the resources of the cell to be scheduled can be scheduled according to the execution script.

[0079] like Figure 2As shown in the embodiments of this application, the resource scheduling method can obtain the target performance indicators of the cell to be scheduled. The target performance indicators include the radio scenario, service model, cell load and channel quality. Based on the target performance indicators, the corresponding target fingerprint identifier is searched from a pre-established fingerprint database. Then, the corresponding target scheduling factor combination is matched according to the target fingerprint identifier. The resources of the cell to be scheduled are scheduled according to the target scheduling factor combination.

[0080] The resource scheduling method provided in this application embodiment can find the target fingerprint identifier from the fingerprint database according to four dimensions: wireless scenario, service model, cell load, and channel quality. That is, the resource scheduling application is classified from four dimensions: wireless scenario, service model, cell load, and channel quality, so that the resource scheduling application classification is more refined, thereby making resource scheduling more accurate and making full use of resources.

[0081] The resource scheduling method provided in this application embodiment can also directly match the target scheduling factor combination of the cell to be scheduled from the fingerprint database based on the target fingerprint identifier, and schedule the resources of the cell to be scheduled, which has high resource scheduling efficiency.

[0082] Optionally, in order to effectively schedule the resources of the cell to be scheduled according to the target scheduling factor combination, in one embodiment, step S104, scheduling the resources of the cell to be scheduled according to the target scheduling factor combination, may include:

[0083] Execution scripts are generated based on combinations of target scheduling factors;

[0084] The resources of the cell to be scheduled are scheduled according to the execution script.

[0085] like Figure 2 As shown, in this embodiment, an execution script can be generated based on the target scheduling factor combination. The execution script can be an executable instruction, which can carry the resource scheduling size of each service type represented by the target scheduling factor combination. The resources of the cell to be scheduled can be scheduled according to the executable instruction.

[0086] Optionally, in order to quickly find the target scheduling factor combination corresponding to the cell to be scheduled, in one embodiment, before obtaining the target index of the cell to be scheduled, the resource scheduling method may further include:

[0087] Obtain sample metrics for the sample cells, including sample performance metrics, which include wireless scenario, service model, cell load, and channel quality.

[0088] Based on the sample performance indicators, construct the fingerprint identifier of the sample cell;

[0089] The sample indicators are input into a preset neural network model to obtain the scheduling factor combination corresponding to the fingerprint identifier. The neural network model is trained based on the sample indicators and the scheduling factor combination.

[0090] A fingerprint database is established based on the correspondence between fingerprint identifiers and scheduling factor combinations.

[0091] In this embodiment, sample indicators of sample cells can be obtained, which may include sample performance indicators in four dimensions: wireless scenario, service model, cell load, and channel quality.

[0092] As mentioned above, in some examples, wireless scenarios can include 32 main scenarios: villages, urban roads, high-rise residential areas, towns, low-rise residential areas, urban villages, universities, enterprises and institutions, highways, convention centers, primary and secondary schools, commercial centers, star-rated hotels, scenic spots, office buildings, industrial parks, party and government organs, hospitals, squares and parks, high-speed rail, subway, national and provincial highways, leisure and entertainment venues, suburban roads, ordinary railways, sports stadiums, railway stations, farmers' markets, long-distance bus stations, others, custom 1, and custom 2, which correspond to values ​​of (1, 2, 3, ..., 32).

[0093] To facilitate understanding, the business model is illustrated using the traffic share of the first business type as an example. The traffic share of the first business type ranges from 0 to 100, and the business model can be represented as N1 = ROUNDDOWN(traffic share of the first business type / 2, 0), that is, the value of business model N1 can be [0, 50].

[0094] The ROUNDDOWN function rounds numbers closer to zero in the direction of decreasing absolute value.

[0095] The cell load can be expressed as N2 = ROUNDDOWN (cell downlink PRB utilization rate % / 2, 0), that is, the cell load N2 can take the value of [0, 50].

[0096] Channel quality can be expressed as N3 = ROUNDDOWN(Cell Average Downlink CQI, 0), that is, the value of channel quality N3 can be [0, 15].

[0097] Fingerprint identifiers for sample cells can be constructed based on sample performance metrics. Each sample performance metric of a sample cell can correspond to a fingerprint identifier, meaning that each fingerprint indicates that the cells have essentially the same or similar wireless performance.

[0098] By inputting sample metrics into a pre-defined neural network model, the combination of scheduling factors corresponding to the fingerprint identifier can be obtained. Specifically, the values ​​of wireless scenario, service model, cell load, and channel quality can be input into the pre-defined neural network model to train and obtain the combination of scheduling factors.

[0099] The preset neural network model can be a back-propagation network (BP network). The BP network can be trained with sample data to continuously adjust the network weights and thresholds so that the error function decreases along the negative gradient direction and approaches the desired output.

[0100] Specifically, the input layer, hidden layer, and output layer of a BP network can use a sigmoid transfer function. Through the reverse transmission function By continuously adjusting the network weights and thresholds, the error function is minimized, where t i For the desired output, o i This is the computational output of the network.

[0101] For ease of explanation, in some examples, the neural network toolbox in MATLAB software can be used to train the neural network. The specific training steps are as follows:

[0102] After normalizing the training sample data, it can be input into the neural network. For example, the values ​​of wireless scenario, service model, cell load and channel quality can be input into the neural network.

[0103] Define the activation functions for the hidden and output layers of the neural network. The activation function for the hidden layer can be the hyperbolic tangent sigmoid transfer function (tansig function), and the activation function for the output layer can be the sigmoid transfer function (logsig function). The training function of the neural network can be the momentum and adaptive lrBP gradient decreasing training function (traingdx function), and the performance function of the neural network can be the mean squared error function (mse function).

[0104] First, you can set the number of neurons in the hidden layer, for example, initially set to 4. Then, set the network parameters, including the number of epochs (10,000), the expected error (goal) (0.00000001), and the learning rate (lr) (0.01). After setting the parameters, start training the neural network model.

[0105] A fingerprint database can be established based on the correspondence between fingerprint identifiers and scheduling factor combinations. Specifically, fingerprint identifiers can be constructed based on sample performance indicators from the sample metrics, while scheduling factor combinations can be trained by inputting the sample metrics into a neural network model. Therefore, the scheduling factor combinations trained on the sample metrics can be used as the scheduling factor combinations corresponding to the fingerprint identifiers constructed from the sample performance indicators. A fingerprint database is then established based on this correspondence between fingerprint identifiers and scheduling factor combinations.

[0106] For example, in the fingerprint database, fingerprint A corresponds to scheduling factor combination A; fingerprint B corresponds to scheduling factor combination B; fingerprint C corresponds to scheduling factor combination C... fingerprint N corresponds to scheduling factor combination N.

[0107] In this embodiment, a fingerprint identifier can be constructed for a sample cell, and then the sample indicators of the sample cell can be input into a neural network to train and obtain the scheduling factor combination corresponding to the fingerprint identifier. Based on the correspondence between the fingerprint identifier and the scheduling factor combination, a fingerprint database is established.

[0108] In the subsequent resource scheduling process, the target fingerprint identifier corresponding to the cell to be scheduled can be directly found in the fingerprint database. The corresponding target scheduling factor combination can then be matched based on the target fingerprint identifier. The resources of the cell to be scheduled can then be scheduled according to the target scheduling factor combination, which effectively improves the quality and efficiency of resource scheduling based on the scheduling factor combination.

[0109] Optionally, in order to enable the scheduling factor combination to schedule cell resources more accurately, in one embodiment, the scheduling factor combination may include a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor is used to characterize the resource scheduling size of a first service type, the second scheduling factor is used to characterize the resource scheduling size of a second service type, and the third scheduling factor is used to characterize the resource scheduling size of other service types besides the first and second service types.

[0110] In this embodiment, the scheduling factor combination may include a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor can characterize the resource scheduling size of a first service type, the second scheduling factor can characterize the resource scheduling size of a second service type, and the third scheduling factor can characterize the resource scheduling size of other service types besides the first and second service types. Different values ​​can represent the differences between resource scheduling sizes.

[0111] To facilitate understanding, let's take a combination of scheduling factors with a value of 1000 as an example. The first scheduling factor can have a value range of [0, 1000], the second scheduling factor can have a value range of [0, 1000], and the third scheduling factor can also have a value range of [0, 1000]. The sum of the specific values ​​of the first, second, and third scheduling factors can be 1000, and the step size for adjusting these values ​​can be set based on empirical values, for example, a step size of 10.

[0112] For example, the combination of scheduling factors can be a combination of the first scheduling factor being 280, the second scheduling factor being 650, and the third scheduling factor being 70; it can also be a combination of the first scheduling factor being 350, the second scheduling factor being 350, and the third scheduling factor being 300; or it can be a combination of the first scheduling factor being 450, the second scheduling factor being 550, and the third scheduling factor being 0, etc.

[0113] Optionally, in order to make the combination of scheduling factors corresponding to the fingerprint identifier more accurate, in one embodiment, the sample indicators may also include sample perception indicators, which include the business success rate and business latency of different business types.

[0114] In this embodiment, the sample metrics may also include sample perception metrics, which may include the business success rate and business latency for different business types. In some examples, the business success rate (%) can be [0, 100], and the business latency (ms) can be [0, 300].

[0115] For example, sample perception metrics may include the first service success rate and first service latency for the first service type, and the second service success rate and second service latency for the second service type. Sample perception metrics may also include the third service success rate and third service latency for other service types besides the first and second service types.

[0116] For ease of understanding, taking the sample perception indicators including the first service success rate, the first service latency, the second service success rate, and the second service latency as an example, in this embodiment, the first service success rate, the first service latency, the second service success rate, and the second service latency can also be input into the neural network model to make the training-obtained combination of scheduling factors more accurate, thereby ensuring the accuracy of resource scheduling.

[0117] In a specific scenario example, such as Figure 3 As shown, the number of nodes in the input layer of the neural network model can be set to 8, which can be used to input the wireless scenario, service model, cell load, channel quality, first service success rate, first service delay, second service success rate, and second service delay, respectively. The number of neurons in the hidden layer can be set to 4, and the number of nodes in the output layer can be set to 3, which can be used to output the first scheduling factor, the second scheduling factor, and the third scheduling factor, respectively.

[0118] For example, the input sample indicator data can be shown in the table below:

[0119]

[0120]

[0121] By inputting different sample index data into the neural network model, different combinations of scheduling factors can be trained.

[0122] Optionally, in order to determine the cell to be scheduled from multiple cells, in one embodiment, before obtaining the target index of the cell to be scheduled, the resource scheduling method may further include:

[0123] Acquire at least one first perception indicator for a cell, including service success rate and service latency for different service types;

[0124] Cells that meet the preset conditions for the first perception indicator are identified as cells to be scheduled.

[0125] In this embodiment, at least one first perception indicator of a cell is obtained. The first perception indicator may include the service success rate and service latency of different service types. Specifically, the first perception indicator may include the first service success rate and first service latency of a first service type, the second service success rate and second service latency of a second service type, and the third service success rate and third service latency of other service types besides the first and second service types.

[0126] After obtaining the first perception indicator, the first perception indicator can be compared with preset conditions. If the first perception indicator meets the preset conditions, the cell with the first perception indicator can be identified as a cell to be scheduled.

[0127] The preset conditions can be set according to the actual situation. For example, the preset conditions can be set to any business success rate being less than a preset success rate threshold or any business latency being greater than a preset latency threshold.

[0128] In a specific example, the preset success rate threshold can be 90%. When the success rate of the first service, the second service, or the third service of a cell is less than 90%, the cell can be identified as a cell to be scheduled. Alternatively, the preset latency threshold can be 150ms. When the latency of the first service, the second service, or the third service of a cell is greater than 150ms, the cell can be identified as a cell to be scheduled.

[0129] For example, preset conditions can be set such that the success rate of each business type is less than the preset success rate threshold corresponding to that business type, or the business latency of each business type is greater than the preset latency threshold corresponding to that business type.

[0130] In a specific example, the preset success rate threshold for the first service type can be 95%, the preset success rate threshold for the second service type can be 90%, and the preset success rate threshold for other service types can be 85%. When the success rate of the first service in a cell is less than 95%, or the success rate of the second service is less than 90%, or the success rate of the third service is less than 85%, the cell can be identified as a cell to be scheduled.

[0131] Alternatively, the preset latency threshold for the first service type can be 120ms, the preset latency threshold for the second service type can be 130ms, and the preset latency threshold for other service types can be 150ms. When the latency of the first service in a cell is greater than 120ms, or the latency of the second service is greater than 130ms, or the latency of the third service is greater than 150ms, the cell can be identified as a cell to be scheduled.

[0132] Optionally, to make the identified cells to be scheduled more accurate, in one embodiment, cells that meet the preset conditions for the first sensing index are identified as cells to be scheduled, which may include:

[0133] If the success rate of the target business type is less than the preset first threshold corresponding to the target business type, or the business latency of the target business type is greater than the preset second threshold corresponding to the target business type, the target business type will be determined as the business type to be scheduled. The target business type can be any business type.

[0134] Obtain traffic for the service type to be scheduled;

[0135] Cells where the traffic of the service type to be scheduled exceeds a preset third threshold and the service success rate of the service type to be scheduled is less than a preset fourth threshold, or

[0136] Cells whose traffic for the service type to be scheduled exceeds a preset third threshold and whose service latency for the service type to be scheduled exceeds a preset fifth threshold are identified as cells to be scheduled.

[0137] like Figure 4 As shown, in this embodiment, the service types to be scheduled in the cell can be determined first. That is, if the service success rate of any service type is less than the preset first threshold corresponding to the service type, or the service latency of any service type is greater than the preset second threshold corresponding to the service type, the service type can be determined as the service type to be scheduled.

[0138] The preset first threshold and the preset second threshold can be set based on empirical values. Specifically, the perception index baseline of the cell can be associated with the cell identifier, and the perception index baseline can include the preset first threshold and the preset second threshold.

[0139] In some examples, the cell identifier can be represented using an ECI code, which consists of a base station ID and a location service ID, and is a unique identifier for the cell. Based on the cell identifier, a baseline of sensing metrics for the cell can be associated with empirical values.

[0140] For example, if the preset first threshold for the first service type of the cell under the cell identifier can be 95%, the preset first threshold for the second service type can be 90%, and the preset first threshold for other service types can be 85%, and the actual success rate of the first service obtained by the cell is 92%, the success rate of the second service is 95%, and the success rate of the third service is 86%, then the first service type can be used as the service type to be scheduled.

[0141] For example, the preset second threshold for the first service type of the cell under this cell identifier can be 120ms, the preset second threshold for the second service type can be 130ms, and the preset second threshold for other service types can be 150ms. However, if the actual latency of the first service obtained by the cell is 120ms, the latency of the second service is 150ms, and the latency of the third service is 140ms, then the second service type can be used as the service type to be scheduled.

[0142] In some examples, the success rate and latency of various service types in a cell can be presented in the form of charts, making it easier to determine the service types to be scheduled in a timely manner.

[0143] Obtain traffic for the service type to be scheduled. For example, when the first service type of a cell is determined to be the service type to be scheduled, the average daily traffic of the first service type of the cell can be obtained as the traffic for the service type to be scheduled.

[0144] Cells whose traffic for the type of service to be scheduled exceeds a preset third threshold and whose service success rate for the type of service to be scheduled is less than a preset fourth threshold, or whose traffic for the type of service to be scheduled exceeds a preset third threshold and whose service latency for the type of service to be scheduled exceeds a preset fifth threshold, can be identified as cells to be scheduled.

[0145] The preset third, fourth, and fifth thresholds can be set according to actual conditions. In some examples, the preset third threshold can be set to 0.5GB, the preset fourth threshold can be set to 90%, and the preset fifth threshold can be set to 150ms.

[0146] In this example, a cell can be identified as a cell to be scheduled if the traffic of the service type to be scheduled in the cell is greater than 0.5GB and the service success rate of the service type to be scheduled is less than 90%, or if the traffic of the service type to be scheduled in the cell is greater than 0.5GB and the service latency of the service type to be scheduled is greater than 150ms.

[0147] For example, if the service type to be scheduled is the first service type, and cell A has an average daily traffic of 0.6GB for the first service type, a success rate of 92%, and a latency of 120ms, then cell A is not a cell to be scheduled. If cell B has an average daily traffic of 0.6GB for the first service type, a success rate of 89%, and a latency of 120ms, then cell B is a cell to be scheduled. If cell C has an average daily traffic of 0.6GB for the first service type, a success rate of 92%, and a latency of 151ms, then cell C is a cell to be scheduled.

[0148] Optionally, in order to monitor the results of resource scheduling, in one embodiment, after scheduling the resources of the cell to be scheduled according to the target scheduling factor combination, the resource scheduling method may further include:

[0149] Obtain the second perception index after resource scheduling of the cell to be scheduled. The second perception index includes the service success rate and service latency of different service types.

[0150] Based on the second perception indicator, the resource scheduling results are obtained. The resource scheduling results include the resource scheduling results of the first business type, the resource scheduling results of the second business type, and the resource scheduling results of other business types besides the first and second business types.

[0151] Output resource scheduling results.

[0152] like Figure 5 As shown in this embodiment, after the resources of the cell to be scheduled are processed according to the target scheduling factor combination, a second perception index after the resource scheduling of the cell to be scheduled can be obtained. The second perception index may include the service success rate and service latency of different service types after resource scheduling.

[0153] Resource scheduling results can be obtained based on the second perception index. For example, the resource scheduling results can be obtained by comparing the second perception index after resource scheduling with the perception index before resource scheduling of the cell to be scheduled.

[0154] Specifically, the success rate and latency of each business type can be compared one by one to obtain the resource scheduling results of the first business type, the second business type, and other business types besides the first and second business types.

[0155] For example, in a specific instance, the resource scheduling result for the first service type can be represented as a 5% increase in the success rate of the first service and a 20% decrease in the latency of the first service.

[0156] For example, the resource scheduling result can be obtained by comparing the second perception index after resource scheduling with the baseline perception index of the cell to be scheduled. Specifically, the service success rate and service latency of each service type can be compared with the perception baseline corresponding to that service type.

[0157] For example, in a specific instance, the resource scheduling result of the first service type can be represented as the first service success rate and the first service latency load and the first service perceived baseline.

[0158] Output resource scheduling results, such as in the form of charts or text, and display these results. Specifically, the results can be displayed as charts on the interface, or they can be transmitted to a management device so that administrators can view them on the management device.

[0159] The management devices include, but are not limited to, electronic devices such as mobile phones, tablets, and laptops.

[0160] To facilitate understanding of the resource scheduling method provided in the above embodiments, the following describes the above express delivery storage method using a specific scenario embodiment. Figure 6 A flowchart illustrating a scenario embodiment of the above resource scheduling method is shown.

[0161] like Figure 6 As shown, at least one first perception indicator of a cell can be obtained, and the type of service to be scheduled can be determined based on the first perception indicator. Specifically, as mentioned above, service types with a service success rate lower than a preset first threshold corresponding to the service type, or service latency greater than a preset second threshold corresponding to the service type, can be determined as service types to be scheduled.

[0162] In some specific examples, the type of service to be scheduled can also be determined based on the first perception indicator and a preset business perception baseline or a preset perception weekly granularity indicator. The preset business perception baseline and the preset perception weekly granularity indicator can be set based on empirical values.

[0163] Specifically, business types whose first perception index is worse than the preset business perception baseline, or whose perception weekly granularity index is worse than the preset index by more than 15%, can be identified as business types to be scheduled.

[0164] In some specific examples, the first perception indicators can also be automatically presented in charts to facilitate the quick identification of the types of services to be scheduled.

[0165] After determining the type of service to be scheduled, the cells to be scheduled can be identified based on the service success rate and latency of that service type. The target performance metrics of the cells to be scheduled are then obtained, and the target fingerprint identifier is retrieved from the fingerprint database based on these metrics.

[0166] Next, target scheduling factor combinations are matched from the fingerprint database based on the target fingerprint identifier, an execution script is generated based on the target scheduling factor combinations, and then the resources of the cell to be scheduled are scheduled according to the execution script.

[0167] After resource scheduling, the second perception index of the cell to be scheduled is obtained. Based on the second perception index, the resource scheduling results of each service type can be obtained, and the resource scheduling results can be presented in the form of charts.

[0168] Based on the resource scheduling method provided in the above embodiments, this application also provides an embodiment of a resource scheduling device.

[0169] Figure 7 A schematic diagram of the structure of a resource scheduling device provided in another embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0170] Reference Figure 7 The resource scheduling device may include:

[0171] The first acquisition module 701 can be used to acquire the target performance indicators of the cell to be scheduled. The target performance indicators include wireless scenario, service model, cell load and channel quality. The wireless scenario is used to indicate the wireless signal propagation environment, and the service model is used to indicate the traffic proportion of different service types.

[0172] The lookup module 702 can be used to look up the target fingerprint identifier corresponding to the target performance indicator from a pre-established fingerprint database according to the target performance indicator. The fingerprint database includes the correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size of the corresponding business type.

[0173] The matching module 703 can be used to match the corresponding target scheduling factor combination from the fingerprint database based on the target fingerprint identifier;

[0174] The scheduling module 704 can be used to schedule the resources of the cell to be scheduled according to the target scheduling factor combination.

[0175] Optionally, in one embodiment, the resource scheduling apparatus may further include:

[0176] The second acquisition module can be used to acquire sample indicators of sample cells. The sample indicators include sample performance indicators, which include wireless scenario, service model, cell load and channel quality.

[0177] The building module can be used to construct fingerprint identifiers for sample cells based on sample performance indicators;

[0178] The training module can be used to input sample indicators into a preset neural network model to obtain the scheduling factor combination corresponding to the fingerprint identifier. The neural network model is trained based on the sample indicators and the scheduling factor combination.

[0179] The module can be used to build a fingerprint database based on the correspondence between fingerprint identifiers and scheduling factor combinations.

[0180] Optionally, in one embodiment, the sample metrics may also include sample perception metrics, which may include business success rate and business latency for different business types.

[0181] Optionally, in one embodiment, the resource scheduling apparatus may further include:

[0182] The third acquisition module can be used to acquire at least one first perception indicator of a cell. The first perception indicator includes the service success rate and service latency of different service types.

[0183] The determination module can be used to identify cells that meet the preset conditions for the first perception indicator as cells to be scheduled.

[0184] Optionally, in one embodiment, the determining module may include:

[0185] The first determining unit can be used to determine the target business type as the business type to be scheduled when the business success rate of the target business type is less than the preset first threshold corresponding to the target business type, or the business latency of the target business type is greater than the preset second threshold corresponding to the target business type. The target business type can be any business type.

[0186] The acquisition unit can be used to acquire traffic of the service type to be scheduled;

[0187] The second determining unit can be used to identify cells where the traffic of the service type to be scheduled is greater than a preset third threshold and the service success rate of the service type to be scheduled is less than a preset fourth threshold, or

[0188] Cells whose traffic for the service type to be scheduled exceeds a preset third threshold and whose service latency for the service type to be scheduled exceeds a preset fifth threshold are identified as cells to be scheduled.

[0189] Optionally, in one embodiment, the scheduling module 704 may include:

[0190] The generation unit can be used to generate execution scripts based on a combination of target scheduling factors;

[0191] The scheduling unit can be used to schedule the resources of the cell to be scheduled according to the execution script.

[0192] Optionally, in one embodiment, the scheduling factor combination includes a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor is used to characterize the resource scheduling size of a first service type, the second scheduling factor is used to characterize the resource scheduling size of a second service type, and the third scheduling factor is used to characterize the resource scheduling size of other service types besides the first and second service types.

[0193] Optionally, in one embodiment, the resource scheduling apparatus may further include:

[0194] The fourth acquisition module can be used to acquire the second perception indicators after the resource scheduling of the cell to be scheduled. The second perception indicators include the service success rate and service latency of different service types.

[0195] The module can be used to obtain resource scheduling results based on the second perception indicator. The resource scheduling results include resource scheduling results for the first business type, resource scheduling results for the second business type, and resource scheduling results for other business types besides the first and second business types.

[0196] The output module can be used to output resource scheduling results.

[0197] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application, and are devices corresponding to the above-mentioned resource scheduling method. All implementation methods in the above-mentioned method embodiments are applicable to the embodiments of this device. For details on its specific functions and the technical effects it brings, please refer to the method embodiment section, which will not be repeated here.

[0198] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0199] Figure 8 A schematic diagram of the hardware structure of an electronic device provided in yet another embodiment of this application is shown.

[0200] The device may include a processor 801 and a memory 802 storing computer program instructions.

[0201] When processor 801 executes a computer program, it implements the steps in any of the above method embodiments.

[0202] For example, a computer program can be divided into one or more modules / units, one or more of which are stored in memory 802 and executed by processor 801 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the device.

[0203] Specifically, the processor 801 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0204] Memory 802 may include mass storage for data or instructions. For example, and not limitingly, memory 802 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 802 may include removable or non-removable (or fixed) media. Where appropriate, memory 802 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 802 is non-volatile solid-state memory.

[0205] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0206] The processor 801 implements any of the methods described above by reading and executing computer program instructions stored in the memory 802.

[0207] In one example, the electronic device may also include a communication interface 803 and a bus 810. The processor 801, memory 802, and communication interface 803 are connected via the bus 810 and communicate with each other.

[0208] The communication interface 803 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0209] Bus 810 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 810 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0210] Furthermore, in conjunction with the methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods in the above embodiments.

[0211] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0212] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer grids such as the Internet, intranets, etc.

[0213] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0214] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0215] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A resource scheduling method, characterized in that, include: Obtain the target performance indicators of the cell to be scheduled. The target performance indicators include radio scenario, service model, cell load and channel quality. The radio scenario is used to indicate the radio signal propagation environment and the service model is used to indicate the traffic proportion of different service types. Based on the target performance index, a target fingerprint identifier corresponding to the target performance index is retrieved from a pre-established fingerprint database. The fingerprint database includes a correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size for the corresponding business type. Based on the target fingerprint identifier, a corresponding target scheduling factor combination is matched from the fingerprint database. The scheduling factor combination includes a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor is used to characterize the resource scheduling size of a first service type, the second scheduling factor is used to characterize the resource scheduling size of a second service type, and the third scheduling factor is used to characterize the resource scheduling size of other service types besides the first and second service types. The resources of the cell to be scheduled are scheduled according to the target scheduling factor combination.

2. The method according to claim 1, characterized in that, Before obtaining the target metrics of the cell to be scheduled, the method further includes: Obtain sample metrics for sample cells, including sample performance metrics, which include wireless scenario, service model, cell load, and channel quality. Based on the sample performance indicators, construct the fingerprint identifier of the sample cell; The sample indicators are input into a preset neural network model to obtain the scheduling factor combination corresponding to the fingerprint identifier. The neural network model is trained based on the sample indicators and the scheduling factor combination. A fingerprint database is established based on the correspondence between the fingerprint identifier and the scheduling factor combination.

3. The method according to claim 2, characterized in that, The sample metrics also include sample perception metrics, which include business success rate and business latency for different business types.

4. The method according to claim 1, characterized in that, Before obtaining the target metrics of the cell to be scheduled, the method further includes: Acquire at least one first perception indicator for a cell, the first perception indicator including service success rate and service latency for different service types; Cells whose first perception index meets the preset conditions are identified as the cells to be scheduled.

5. The method according to claim 4, characterized in that, The step of determining cells that meet the preset conditions for the first perception index as the cells to be scheduled includes: If the success rate of the target service type is less than the preset first threshold corresponding to the target service type, or the service latency of the target service type is greater than the preset second threshold corresponding to the target service type, the target service type will be determined as a service type to be scheduled, and the target service type can be any service type. Obtain the traffic of the service type to be scheduled; Cells where the traffic of the service type to be scheduled is greater than a preset third threshold and the service success rate of the service type to be scheduled is less than a preset fourth threshold, or Cells whose traffic for the service type to be scheduled is greater than a preset third threshold and whose service latency for the service type to be scheduled is greater than a preset fifth threshold are identified as the cells to be scheduled.

6. The method according to claim 1, characterized in that, The step of scheduling resources of the cell to be scheduled according to the target scheduling factor combination includes: An execution script is generated based on the aforementioned combination of target scheduling factors; The resources of the cell to be scheduled are scheduled according to the execution script.

7. The method according to claim 1, characterized in that, After scheduling the resources of the cell to be scheduled according to the target scheduling factor combination, the method further includes: Obtain the second perception index after resource scheduling of the cell to be scheduled, the second perception index including the service success rate and service latency of different service types; Based on the second perception index, the resource scheduling result is obtained, which includes the resource scheduling result of the first business type, the resource scheduling result of the second business type, and the resource scheduling result of other business types besides the first and second business types. Output the resource scheduling results.

8. A resource scheduling device, characterized in that, The device includes: The first acquisition module is used to acquire the target performance indicators of the cell to be scheduled. The target performance indicators include wireless scenario, service model, cell load and channel quality. The wireless scenario is used to indicate the wireless signal propagation environment and the service model is used to indicate the traffic proportion of different service types. The lookup module is used to look up the target fingerprint identifier corresponding to the target performance indicator from a pre-established fingerprint database according to the target performance indicator. The fingerprint database includes the correspondence between fingerprint identifiers and scheduling factor combinations. The scheduling factor combination includes at least one scheduling factor for a business type. The scheduling factor is used to characterize the resource scheduling size of the corresponding business type. The matching module is used to match a corresponding target scheduling factor combination from the fingerprint database based on the target fingerprint identifier. The scheduling factor combination includes a first scheduling factor, a second scheduling factor, and a third scheduling factor. The first scheduling factor is used to characterize the resource scheduling size of a first service type, the second scheduling factor is used to characterize the resource scheduling size of a second service type, and the third scheduling factor is used to characterize the resource scheduling size of other service types besides the first and second service types. The scheduling module is used to schedule the resources of the cell to be scheduled according to the target scheduling factor combination.

9. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method as described in any one of claims 1-7.

Images