Resource scheduling method, device, computer equipment and storage medium

Abstract

The present application relates to a resource scheduling method, device, computer equipment and storage medium. It includes: obtaining a first scheduling request, determining whether the first scheduling request has produced a direct project according to a first decision tree model; when a direct project is produced and the predicted value of the project feedback result of the direct project is greater than a first threshold, determining the predicted value of the project feedback result of the first scheduling request to be the predicted value of the project feedback result of the produced direct project; when no direct project is produced or the predicted value of the project feedback result of the direct project produced by the scheduling request is not greater than the first threshold; determining whether the first scheduling request has produced an associated project, and if so, determining the predicted value of the project feedback result of the first scheduling request to be the predicted value of the project feedback result of the associated project; scheduling the target resource according to the predicted value of the project feedback result of each scheduling request in the target resource request queue. The use of this application can improve the utilization rate of the target resources.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a resource scheduling method, apparatus, computer equipment and storage medium. Background Art

[0002] When performing resource scheduling, the usual practice is: upon receiving a scheduling request, the required target resources are allocated to the scheduling request. When multiple scheduling requests are received, the required target resources are provided in sequence according to the order in which the scheduling requests are received.

[0003] Since different scheduling requests bring different benefits, some scheduling requests will produce direct projects, some scheduling requests will bring related projects, and the benefits brought are small, while some scheduling requests bring large benefits. When the number of scheduling requests is large and the target resources are limited, the method of scheduling target resources according to the order of scheduling requests cannot maximize the benefits of target resources. Therefore, how to improve the utilization rate of target resources is a technical problem that needs to be solved urgently. Summary of the invention

[0004] Based on this, it is necessary to provide a resource scheduling method, device, computer equipment, computer-readable storage medium and computer program product that can improve the utilization rate of target resources and obtain greater benefits in response to the above technical problems.

[0005] In a first aspect, the present application provides a resource scheduling method, comprising: the method comprising:

[0006] Acquire a first scheduling request from a target resource request queue; the target resource request queue includes multiple scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue;

[0007] Determining whether the first scheduling request produces a direct project according to a first decision tree;

[0008] When it is determined that the first scheduling request has produced a direct project, a predicted value of a project feedback result of the direct project produced by the first scheduling request is determined according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, the predicted value of the project feedback result of the direct project produced by the first scheduling request is used as the predicted value of the project feedback result of the first scheduling request;

[0009] When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold, determine whether the first scheduling request produces an associated project according to the third decision tree; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to the fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request;

[0010] The target resource is scheduled according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0011] The predicted value of the project feedback result may be the income of the project output, the profit brought, etc. It may be expressed by a specific numerical value or by a level, which is not limited here.

[0012] In one of the embodiments, the first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in a first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request produces a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing a direct project.

[0013] In one of the embodiments, the second decision tree is obtained by model training on multiple scheduling requests that have produced direct projects in historical data; the second decision tree has feature attributes in the second feature attribute set as nodes, the feature attributes corresponding to the terminal nodes of the second decision tree are project feedback results of direct projects produced by the scheduling requests, and the terminal nodes of the second decision tree include predicted values ​​of project feedback results of direct projects produced by the scheduling requests; the feature attributes in the second feature attribute set are feature attributes related to the project feedback results of direct projects produced by the scheduling requests.

[0014] In one of the embodiments, the third decision tree is obtained through model training of multiple scheduling requests that have not produced direct projects in historical data, or have produced direct projects and the project feedback results of the produced direct projects are not greater than the first threshold; the third decision tree has feature attributes in a third feature attribute set as nodes, the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0015] In one embodiment, the fourth decision tree is obtained through model training for scheduling requests that do not produce direct projects in historical data, or produce direct projects and the project feedback results of the direct projects produced are not greater than the first threshold, and simultaneously meet the production of associated projects; the fourth decision tree uses characteristic attributes in a fourth characteristic attribute set as nodes, the characteristic attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the characteristic attributes in the fourth characteristic attribute set are characteristic attributes related to the project feedback results of the associated project produced by the scheduling request.

[0016] In a second aspect, the present application further provides a resource scheduling device, comprising:

[0017] An acquisition module, configured to acquire a first scheduling request from a target resource request queue; the target resource request queue includes a plurality of scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue;

[0018] A first determination module is used to determine whether the first scheduling request produces a direct project according to a first decision tree.

[0019] a second determination module, configured to determine, when it is determined that the first scheduling request has produced a direct project, a predicted value of a project feedback result of the direct project produced by the first scheduling request according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, use the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request;

[0020] a third determination module, configured to determine whether the first scheduling request produces an associated project according to a third decision tree when it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to a fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request;

[0021] The scheduling module is used to schedule the target resource according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0022] In one of the embodiments, the first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in a first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request produces a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing a direct project.

[0023] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0024] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0025] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0026] The resource scheduling method, apparatus, computer equipment, storage medium and computer program product described above use a decision tree to determine the predicted value of the project feedback result of the direct project or associated project produced by the scheduling request. When the predicted value of the project feedback result of the direct project produced by the scheduling request is greater than a preset value, the predicted value of the project feedback result of the direct project is used as the predicted value of the project feedback result of the scheduling request; when the scheduling request does not produce a direct project, or when a direct project is produced but the predicted value of the project feedback result of the direct project is not greater than a preset value, the predicted value of the project feedback result of the associated project is used as the predicted value of the project feedback result of the scheduling request; finally, the target resources are scheduled according to the predicted value of the project feedback result of the scheduling request, which is conducive to improving the utilization rate of the target resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a resource scheduling method in one embodiment;

[0028] Figure 2 is a schematic diagram of a first decision tree in one embodiment;

[0029] Figure 3 is a structural block diagram of a resource scheduling device in one embodiment;

[0030] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction 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 are not used to limit the present application.

[0032] The resource scheduling method provided in the embodiment of the present application can schedule the target resources according to the project feedback results. The target resources can be one or more of hardware resources, software resources, and human resources. Specifically, Figure 1 As shown, a flowchart of a resource scheduling method is provided. The method is described by applying it to a terminal as an example. The terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. It should be noted that after providing target resource support for the scheduling request, some scheduling requests may produce direct projects, some scheduling requests may produce associated projects, and some scheduling requests may produce both direct projects and associated projects. When the project feedback result of the output direct project is greater than a preset value, the project feedback result of the direct project is used as the project feedback result of the scheduling request; when no direct project is output, or the project feedback result of the output direct project is not greater than a preset value, the project feedback result of the associated project is determined, and the project feedback result of the associated project is used as the project feedback result of the scheduling request. Finally, the target resource is scheduled according to the project feedback result of the scheduling request. For details, please refer to Figure 1 , this embodiment includes steps 101 to 106.

[0033] 101. Obtain a first scheduling request from a target resource request queue.

[0034] The target resource request queue includes multiple scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue. The target resource may be one or more of hardware resources, software resources, and human resources.

[0035] 102. Determine whether the first scheduling request produces a direct project according to the first decision tree.

[0036] In some possible implementations, the first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in the first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request has produced a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing direct projects.

[0037] Historical data includes scheduling requests that have been responded to by resource processing methods. Some of these call requests were assigned target resources, some were not assigned target resources, some scheduling requests produced direct projects, some produced related projects, and some did not produce either direct projects or related projects.

[0038] For ease of understanding, for example, if the target resource is scheduled in response to the first scheduling request, and the target resource is scheduled to the first scheduling request, the direct project produced is the project of selling chopsticks. If the scheduling request is supported by the target resource and no project of selling chopsticks is produced, but a project of selling spoons is produced, then the project of selling spoons is the associated project produced by the first scheduling request. In this example, the first characteristic attribute may include: the region where the scheduling request is located, the department that issued the scheduling request, the feedback result of the project produced by the scheduling request, the expected delivery time of the direct project produced, whether the scheduling request produces a direct project, whether the scheduling request produces an associated project, the project feedback result, etc.

[0039] For example, as shown in Table 1, it is data related to scheduling request in one embodiment.

[0040] Table 1

[0041]

[0042]

[0043] When training the scheduling request, the call data can be divided into training data and verification data according to a certain ratio. For example, the above 10 call data can be randomly divided into training data and verification data according to a ratio of 4:1. For example, the data numbered 2, 3, 4, 5, 6, 8, 9, and 10 are determined as training data, and the data numbered 1 and 7 are determined as verification data. The number of direct items produced by the scheduling request is used as the terminal node of the first decision tree.

[0044] The first decision tree can be Figure 2 According to Table 1 and Figure 2 It can be seen that the regions of the dispatch request include: City A, City B, City C. The departments that issued the dispatch request include: City A Branch, City A Branch; the expected output of the dispatch request (project feedback result) includes: below 10,000 level, below 50,000 level, below 100,000 level, below 1 million level, etc. The expected delivery time of the direct project output can be one month later, and the project feedback results include low, high, none, etc. It should be noted that the project feedback results can be described in terms of level or determined according to the specific output amount, which is not limited here.

[0045] 103. When it is determined that the first scheduling request has produced a direct project, the predicted value of the project feedback result of the direct project produced by the first scheduling request is determined according to the second decision tree; when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, the predicted value of the project feedback result of the direct project produced by the first scheduling request is used as the predicted value of the project feedback result of the first scheduling request.

[0046] In some possible implementations, the second decision tree is obtained by model training on multiple scheduling requests that produced direct projects in historical data; the second decision tree uses characteristic attributes in the second characteristic attribute set as nodes, the characteristic attributes corresponding to the terminal nodes of the second decision tree are the project feedback results of the direct projects produced by the scheduling requests, and the terminal nodes of the second decision tree include the predicted values ​​of the project feedback results of the direct projects produced by the scheduling requests; the characteristic attributes in the second characteristic attribute set are characteristic attributes related to the project feedback results of the direct projects produced by the scheduling requests.

[0047] For example, if the direct project produced by the first scheduling request is a project of selling chopsticks, the first threshold is 100,000. If the first scheduling request produces a direct project, and the predicted value of the direct project feedback result produced by the first scheduling request is determined to be 200,000 according to the second decision tree, then the predicted value of the project feedback result of the first scheduling request is 200,000.

[0048] 104. When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the direct project is not greater than the first threshold, determine whether the first scheduling request produces an associated project according to the third decision tree; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to the fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request.

[0049] In some possible implementations, the third decision tree is obtained through model training of multiple scheduling requests that have not produced direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than a first threshold; the third decision tree has feature attributes in the third feature attribute set as nodes, the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0050] In some possible implementations, the fourth decision tree is obtained through model training for historical data in which no direct project is produced, or direct projects are produced and the project feedback results of the direct projects produced are not greater than the first threshold, and multiple scheduling requests that simultaneously meet the output of associated projects are obtained; the fourth decision tree uses characteristic attributes in the fourth characteristic attribute set as nodes, the characteristic attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the characteristic attributes in the fourth characteristic attribute set are characteristic attributes related to the project feedback results of the associated project produced by the scheduling request.

[0051] 105. Schedule the target resource according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0052] It should be noted that, in some possible implementations, after obtaining the predicted value of the project feedback result of each scheduling request in the target request queue, the predicted values ​​can be sorted and displayed in order from large to small, and then the priority of the scheduling target resources can be determined according to the predicted values. The larger the predicted value, the higher the priority of the scheduling target resources. For example, the target resources are preferentially scheduled to the project corresponding to the scheduling request with the largest predicted value.

[0053] In some possible implementations, the level corresponding to the project can be determined based on the predicted value of the project feedback result of the scheduling request, and different levels (such as: extra high level, high level, medium level, low level, etc.) correspond to the predicted values ​​from high to low, and then the target resources are scheduled from high to low according to the levels.

[0054] It should be noted that, in some possible implementations, the project feedback results of the scheduling request may correspond to business opportunities of different levels, for example, the corresponding business opportunities may be at the 100,000 level, the 1 million level, or the 10 million level.

[0055] When performing target resource scheduling, the priority of target resource scheduling can be adaptively adjusted according to the expected completion time of the project. For example, if the forecast values ​​corresponding to Project A and Project B are the same, and if the date on which Project A expects to receive target resource support is closer to the current date than the date on which Project B expects to receive target resource support, then the target resources can be scheduled to Project A first.

[0056] It should be noted that when training historical data to obtain a decision tree, the historical data that meets the training conditions can be divided into a training set and a validation set according to a certain ratio (for example, a ratio of 2 to 1), and the decision tree model is trained with the training set and the validation set to obtain a decision tree.

[0057] In some possible implementations, a scheduling request that does not produce either a direct project or an associated project may not be allocated a target resource during resource scheduling.

[0058] The technical solution provided by this embodiment uses a decision tree to determine the predicted value of the project feedback result of the direct project or the associated project produced by the scheduling request. When the predicted value of the project feedback result of the direct project produced by the scheduling request is greater than a preset value, the predicted value of the project feedback result of the direct project is used as the predicted value of the project feedback result of the scheduling request; when the scheduling request does not produce a direct project, or when a direct project is produced but the predicted value of the project feedback result of the direct project is not greater than a preset value, the predicted value of the project feedback result of the associated project is used as the predicted value of the project feedback result of the scheduling request; finally, the target resources are scheduled according to the predicted value of the project feedback result of the scheduling request, which is conducive to improving the utilization rate of the target resources.

[0059] Based on the same inventive concept, the embodiment of the present application also provides a resource scheduling device for implementing the resource scheduling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the resource scheduling device embodiment provided below can refer to the limitations of the resource scheduling method above, and will not be repeated here.

[0060] In one embodiment, Figure 3 As shown, a resource scheduling device 300 is provided, comprising: an acquisition module 301, a first determination module 302, a second determination module 303, a third determination module 304 and a scheduling module 305, wherein:

[0061] The acquisition module 301 is used to acquire a first scheduling request from a target resource request queue.

[0062] The target resource request queue includes multiple scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue. The target resource can be one or more of hardware resources, software resources, and human resources.

[0063] The first determination module 302 is used to determine whether the first scheduling request produces a direct project according to the first decision tree.

[0064] In some possible implementations, the first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in the first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request has produced a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing direct projects.

[0065] For ease of understanding, for example, if the target resource is scheduled in response to the first scheduling request, and the target resource is scheduled to the first scheduling request, the direct project produced is the project of selling chopsticks. If the scheduling request is supported by the target resource and no project of selling chopsticks is produced, but a project of selling spoons is produced, then the project of selling spoons is the associated project produced by the first scheduling request. In this example, the first characteristic attribute may include: the region where the scheduling request is located, the department that issued the scheduling request, the feedback result of the project produced by the scheduling request, the expected delivery time of the direct project produced, whether the scheduling request produces a direct project, whether the scheduling request produces an associated project, the project feedback result, etc.

[0066] The second determination module 303, when determining that the first scheduling request has produced a direct project, determines the predicted value of the project feedback result of the direct project produced by the first scheduling request according to the second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, uses the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request.

[0067] In some possible implementations, the second decision tree is obtained by model training on multiple scheduling requests that produced direct projects in historical data; the second decision tree uses characteristic attributes in the second characteristic attribute set as nodes, the characteristic attributes corresponding to the terminal nodes of the second decision tree are the project feedback results of the direct projects produced by the scheduling requests, and the terminal nodes of the second decision tree include the predicted values ​​of the project feedback results of the direct projects produced by the scheduling requests; the characteristic attributes in the second characteristic attribute set are characteristic attributes related to the project feedback results of the direct projects produced by the scheduling requests.

[0068] For example, if the direct project produced by the first scheduling request is a project of selling chopsticks, the first threshold is 100,000, if the predicted value of the direct project produced by the first scheduling request is 1, and the predicted value of the direct project feedback result produced by the first scheduling request is determined to be 200,000 according to the second decision tree, then the predicted value of the project feedback result of the first scheduling request is 200,000.

[0069] The third determination module 304 is used to determine whether the first scheduling request produces an associated project according to the third decision tree when it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to the fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request;

[0070] In some possible implementations, the third decision tree is obtained through model training of multiple scheduling requests that have not produced direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than a first threshold; the third decision tree has feature attributes in the third feature attribute set as nodes, the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0071] In some possible implementations, the fourth decision tree is obtained through model training for historical data in which no direct project is produced, or direct projects are produced and the project feedback results of the direct projects produced are not greater than the first threshold, and multiple scheduling requests that simultaneously meet the output of associated projects are obtained; the fourth decision tree uses characteristic attributes in the fourth characteristic attribute set as nodes, the characteristic attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the characteristic attributes in the fourth characteristic attribute set are characteristic attributes related to the project feedback results of the associated project produced by the scheduling request.

[0072] The scheduling module 305 is used to schedule the target resource according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0073] The technical solution provided by this embodiment uses a decision tree to determine the predicted value of the project feedback result of the direct project or the associated project produced by the scheduling request. When the predicted value of the project feedback result of the direct project produced by the scheduling request is greater than a preset value, the predicted value of the project feedback result of the direct project is used as the predicted value of the project feedback result of the scheduling request; when the scheduling request does not produce a direct project, or when a direct project is produced but the predicted value of the project feedback result of the direct project is not greater than a preset value, the predicted value of the project feedback result of the associated project is used as the predicted value of the project feedback result of the scheduling request; finally, the target resources are scheduled according to the predicted value of the project feedback result of the scheduling request, which is conducive to improving the utilization rate of the target resources.

[0074] Each module in the resource scheduling device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0075] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. 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 operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a resource scheduling method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0076] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0077] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining a first scheduling request from a target resource request queue. Determining whether the first scheduling request produces a direct project according to a first decision tree. When it is determined that the first scheduling request produces a direct project, determining the predicted value of the project feedback result of the direct project produced by the first scheduling request according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, using the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold, determining whether the first scheduling request produces an associated project according to a third decision tree; when it is determined that the first scheduling request produces an associated project, determining the predicted value of the project feedback result of the associated project produced by the first scheduling request according to a fourth decision tree, and using the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. The target resource is scheduled according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0078] The target resource request queue includes multiple scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue. The target resource can be one or more of hardware resources, software resources, and human resources.

[0079] In one embodiment, the processor also implements the following steps when executing the computer program: a first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in a first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request has produced a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing direct projects.

[0080] In one embodiment, the processor further implements the following steps when executing the computer program: a second decision tree is obtained by model training on multiple scheduling requests that have produced direct projects in historical data; the second decision tree has feature attributes in the second feature attribute set as nodes, and the feature attributes corresponding to the terminal nodes of the second decision tree are the project feedback results of the scheduling requests, and the terminal nodes of the second decision tree include predicted values ​​of the project feedback results of the direct projects produced by the scheduling requests; the feature attributes in the second feature attribute set are feature attributes related to the project feedback results of the direct projects produced by the scheduling requests.

[0081] In one embodiment, when the processor executes the computer program, the following steps are also implemented: a decision tree is obtained by training a model for multiple scheduling requests that have no direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than a first threshold; a third decision tree is composed of feature attributes in a third feature attribute set as nodes, and the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0082] In one embodiment, when the processor executes the computer program, the following steps are also implemented: a fourth decision tree is obtained by performing model training on historical data in which no direct project is produced, or a direct project is produced and the project feedback result of the direct project is not greater than a first threshold, and multiple scheduling requests that simultaneously meet the output of associated projects are obtained; the fourth decision tree has feature attributes in the fourth feature attribute set as nodes, the feature attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the feature attributes in the fourth feature attribute set are feature attributes related to the project feedback result of the associated project produced by the scheduling request.

[0083] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: a first scheduling request is obtained from a target resource request queue. Determine whether the first scheduling request produces a direct project according to a first decision tree. When it is determined that the first scheduling request produces a direct project, determine the predicted value of the project feedback result of the direct project produced by the first scheduling request according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, use the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold, determine whether the first scheduling request produces an associated project according to a third decision tree; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to a fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. The target resource is scheduled according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

[0084] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a first decision tree is obtained through model training for multiple scheduling requests; the first decision tree is composed of feature attributes in a first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is the number of direct projects produced by the scheduling request, and the end node of the first decision tree includes a predicted value of the number of direct projects produced by the scheduling request; the feature attributes in the first feature attribute set are feature attributes related to the number of direct projects produced by the scheduling request.

[0085] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a second decision tree is obtained by model training on multiple scheduling requests that have produced direct projects in historical data; the second decision tree has feature attributes in the second feature attribute set as nodes, and the feature attributes corresponding to the end nodes of the second decision tree are project feedback results of direct projects produced by the scheduling requests, and the end nodes of the second decision tree include predicted values ​​of project feedback results of direct projects produced by the scheduling requests; the feature attributes in the second feature attribute set are feature attributes related to the project feedback results of direct projects produced by the scheduling requests.

[0086] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a decision tree is obtained by training a model for multiple scheduling requests that have no direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than a first threshold; a third decision tree is composed of feature attributes in a third feature attribute set as nodes, and the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0087] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a fourth decision tree is obtained by performing model training on historical data in which no direct project is produced, or a direct project is produced and the project feedback result of the direct project is not greater than a first threshold, and multiple scheduling requests that simultaneously meet the production of associated projects are obtained; the fourth decision tree has feature attributes in the fourth feature attribute set as nodes, the feature attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the feature attributes in the fourth feature attribute set are feature attributes related to the project feedback result of the associated project produced by the scheduling request.

[0088] In one embodiment, a computer program product is provided, including a computer program, which obtains a first scheduling request from a target resource request queue. Determine whether the first scheduling request produces a direct project according to a first decision tree. When it is determined that the first scheduling request produces a direct project, determine the predicted value of the project feedback result of the direct project produced by the first scheduling request according to the second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, use the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold, determine whether the first scheduling request produces an associated project according to a third decision tree; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to a fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request. Schedule the target resource according to the predicted value of the project feedback result of each scheduling request in the target resource request queue.

[0089] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a first decision tree is obtained by model training for multiple scheduling requests in the example data; the first decision tree is composed of feature attributes in the first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is the number of direct projects produced by the scheduling request, and the end node of the first decision tree includes the predicted value of the number of direct projects produced by the scheduling request; the feature attributes in the first feature attribute set are feature attributes related to the number of direct projects produced by the scheduling request.

[0090] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a second decision tree is obtained by model training on multiple scheduling requests that have produced direct projects in historical data; the second decision tree has feature attributes in the second feature attribute set as nodes, and the feature attributes corresponding to the end nodes of the second decision tree are project feedback results of direct projects produced by the scheduling requests, and the end nodes of the second decision tree include predicted values ​​of project feedback results of direct projects produced by the scheduling requests; the feature attributes in the second feature attribute set are feature attributes related to the project feedback results of direct projects produced by the scheduling requests.

[0091] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a decision tree is obtained by training a model for multiple scheduling requests that have no direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than a first threshold; a third decision tree is composed of feature attributes in a third feature attribute set as nodes, and the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

[0092] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a fourth decision tree is obtained by performing model training on historical data in which no direct project is produced, or a direct project is produced and the project feedback result of the direct project is not greater than a first threshold, and multiple scheduling requests that simultaneously meet the production of associated projects are obtained; the fourth decision tree has feature attributes in the fourth feature attribute set as nodes, the feature attribute corresponding to the terminal node of the fourth decision tree is the project feedback result of the scheduling request, and the terminal node of the fourth decision tree includes the predicted value of the project feedback result of the associated project produced by the scheduling request; the feature attributes in the fourth feature attribute set are feature attributes related to the project feedback result of the associated project produced by the scheduling request.

[0093] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0094] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A resource scheduling method, characterized in that: The method comprises: Acquire a first scheduling request from a target resource request queue; the target resource request queue includes multiple scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue; Determining whether the first scheduling request produces a direct project according to a first decision tree; When it is determined that the first scheduling request has produced a direct project, a predicted value of a project feedback result of the direct project produced by the first scheduling request is determined according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, the predicted value of the project feedback result of the direct project produced by the first scheduling request is used as the predicted value of the project feedback result of the first scheduling request; When it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold, determine whether the first scheduling request produces an associated project according to the third decision tree; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to the fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request; The target resource is scheduled according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

2. The method according to claim 1, characterized in that The first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in the first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request produces a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing direct projects.

3. The method according to claim 1, characterized in that The second decision tree is obtained by model training on multiple scheduling requests that have produced direct projects in historical data; the second decision tree uses feature attributes in the second feature attribute set as nodes, the feature attributes corresponding to the terminal nodes of the second decision tree are the project feedback results of the direct projects produced by the scheduling requests, and the terminal nodes of the second decision tree include the predicted values ​​of the project feedback results of the direct projects produced by the scheduling requests; the feature attributes in the second feature attribute set are feature attributes related to the project feedback results of the direct projects produced by the scheduling requests.

4. The method according to claim 1, characterized in that: The third decision tree is obtained through model training on multiple scheduling requests that have not produced direct projects in historical data, or have produced direct projects and the project feedback results of the direct projects produced are not greater than the first threshold; the third decision tree has feature attributes in a third feature attribute set as nodes, the feature attribute corresponding to the end node of the third decision tree is whether the scheduling request has produced associated projects, and the feature attributes in the third feature attribute set are feature attributes related to the scheduling request producing associated projects.

5. The method according to claim 4, characterized in that The fourth decision tree is obtained through model training for scheduling requests that do not produce direct projects in historical data, or produce direct projects and the project feedback results of the direct projects produced are not greater than the first threshold, and simultaneously meet the production of related projects; the fourth decision tree uses the characteristic attributes in the fourth characteristic attribute set as nodes, the characteristic attributes corresponding to the terminal nodes of the fourth decision tree are the project feedback results of the scheduling requests, and the terminal nodes of the fourth decision tree include the predicted values ​​of the project feedback results of the related projects produced by the scheduling requests; the characteristic attributes in the fourth characteristic attribute set are characteristic attributes related to the project feedback results of the related projects produced by the scheduling requests.

6. A resource scheduling device, characterized in that: include: An acquisition module, used for acquiring a first scheduling request from a target resource request queue; The target resource request queue includes a plurality of scheduling requests, and the first scheduling request is any scheduling request in the target resource request queue; A first determination module is used to determine whether the first scheduling request produces a direct project according to a first decision tree. a second determination module, configured to determine, when it is determined that the first scheduling request has produced a direct project, a predicted value of a project feedback result of the direct project produced by the first scheduling request according to a second decision tree, and when the predicted value of the project feedback result of the direct project produced by the first scheduling request is greater than a first threshold, use the predicted value of the project feedback result of the direct project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request; a third determination module, configured to determine whether the first scheduling request produces an associated project according to a third decision tree when it is determined that the first scheduling request does not produce a direct project, or when it is determined that the first scheduling request produces a direct project and the predicted value of the project feedback result of the produced direct project is not greater than the first threshold; when it is determined that the first scheduling request produces an associated project, determine the predicted value of the project feedback result of the associated project produced by the first scheduling request according to a fourth decision tree, and use the predicted value of the project feedback result of the associated project produced by the first scheduling request as the predicted value of the project feedback result of the first scheduling request; The scheduling module is used to schedule the target resource according to the predicted value of the item feedback result of each scheduling request in the target resource request queue.

7. The device according to claim 6, characterized in that The first decision tree is obtained by model training on multiple scheduling requests in historical data; the first decision tree is composed of feature attributes in the first feature attribute set as nodes; the feature attribute corresponding to the end node of the first decision tree is whether the scheduling request produces a direct project; the feature attributes in the first feature attribute set are feature attributes related to the scheduling request producing direct projects.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images