Task processing method and device
By employing feature engineering and machine learning to determine object suitability for tasks, the method automates the selection process, improving efficiency and reducing costs in task processing.
Patent Information
- Application Number
- CN202110601581.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-31
- Publication Date
- 2024-12-20
- Estimated Expiration
- 2041-05-31
AI Technical Summary
Existing task processing methods rely on manual selection of objects, leading to inefficient and ineffective task execution due to the lack of a suitable object for processing tasks.
A method and device that utilize feature engineering and machine learning to determine a classification label for each object based on historical data, allowing for the automatic selection of the most suitable object for a given task type, using trained classifiers and feature engineering processes such as illegal value processing, normalization, and dimensionality reduction.
This approach enhances task processing efficiency and effectiveness by accurately selecting the optimal object for task execution, reducing manual intervention and saving time and costs.
Smart Images
Figure CN113342518B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data and artificial intelligence technology, and in particular to a task processing method and device. Background Art
[0002] Various enterprises or organizations often use objects (e.g., computer hardware or software programs, etc.) to process tasks. When executing a task, it is necessary to select a suitable object to perform the task according to the task type. At present, tasks are performed by manually selecting suitable objects from a set of objects. However, the manual selection method is inefficient and depends on the experience of personnel. The selected object may not be the most suitable object for processing the task, resulting in low task processing efficiency and poor execution effect.
[0003] Currently, no effective solution has been proposed to the above problems. Summary of the invention
[0004] The embodiments of this specification provide a task processing method and device to solve the problems of low task processing efficiency and poor execution effect in the prior art.
[0005] An embodiment of the present specification provides a task processing method, including: receiving a task processing request, wherein the task processing request includes a target task type; obtaining historical task execution data and object attribute data corresponding to each object identifier in a target object identifier set; performing feature engineering processing on the historical task execution data and object attribute data to obtain feature data corresponding to each object identifier in the multiple object identifiers; determining a classification label corresponding to each object identifier based on the feature data corresponding to each object identifier; and selecting a target object identifier from the multiple object identifiers based on the classification label corresponding to each object identifier and the target task type, wherein the target object corresponding to the target object identifier is used to execute the target task.
[0006] In one embodiment, feature engineering processing includes at least one of the following: illegal value processing, missing value processing, normalization processing, derived feature generation, and dimensionality reduction processing.
[0007] In one embodiment, determining the classification label corresponding to each object identifier based on the feature data corresponding to each object identifier includes: inputting the feature data corresponding to each object identifier into a trained classifier to obtain the classification label corresponding to each object identifier.
[0008] In one embodiment, the classifier is trained in the following manner: obtaining a training sample set and a label set, wherein the training sample set includes feature data corresponding to each object in a plurality of objects, and the label set includes classification labels corresponding to each training sample in the training sample set; and constructing a classifier using the training sample set and the label set according to a preset machine learning algorithm.
[0009] In one embodiment, the preset machine learning algorithm includes a random forest algorithm or a gradient boosted decision tree algorithm.
[0010] In one embodiment, after receiving the task processing request, it also includes: obtaining a task object relationship table, wherein the task object relationship table records the correspondence between the task type and the object identification set; determining the target object identification set according to the target task type and the task object relationship table, and obtaining the target object identification set.
[0011] The embodiments of the present specification also provide a task processing device, including: a receiving module, used to receive a task processing request, wherein the task processing request includes a target task type; an acquisition module, used to obtain historical task execution data and object attribute data corresponding to each object identifier in a plurality of object identifiers in a target object identifier set; a feature engineering module, used to perform feature engineering processing on the historical task execution data and object attribute data to obtain feature data corresponding to each object identifier in a plurality of object identifiers; a determination module, used to determine a classification label corresponding to each object identifier based on the feature data corresponding to each object identifier; and a selection module, used to select a target object identifier from a plurality of object identifiers based on the classification label corresponding to each object identifier and the target task type, wherein the target object corresponding to the target object identifier is used to execute the target task.
[0012] An embodiment of the present specification also provides a computer device, including a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the task processing method described in any of the above embodiments when executing the instructions.
[0013] The embodiments of the present specification also provide a computer-readable storage medium on which computer instructions are stored. When the instructions are executed, the steps of the task processing method described in any of the above embodiments are implemented.
[0014] In an embodiment of the present specification, a task processing method is provided, which can receive a task processing request carrying a target task type, obtain historical task execution data and object attribute data corresponding to each object identifier in a target object identifier set, perform feature engineering processing on the historical task execution data and object attribute data, obtain feature data corresponding to each object identifier in the multiple object identifiers, determine the classification label corresponding to each object identifier based on the feature data corresponding to each object identifier, and select a target object identifier from the multiple object identifiers based on the classification label corresponding to each object identifier and the target task type, so as to use the target object corresponding to the target object identifier to execute the target task. In the above scheme, after receiving the task processing request, the feature data corresponding to each object identifier among the multiple object identifiers is obtained, and the classification label of each object identifier is determined according to the feature data corresponding to each object identifier. Since the feature data includes the historical task execution data and object attribute data of the object, the task execution capability of the object can be characterized, and the classification label of the object can be accurately determined based on the feature data; thereafter, the target object identifier for executing the target task can be determined according to the classification label and the task type, and then the target object corresponding to the target object identifier is used to execute the target task. There is no need to manually select the object based on experience, which is efficient and can effectively save time and labor costs, thereby improving the efficiency of task execution, improving the effect of task execution, and saving costs. The above scheme solves the technical problems of low efficiency and poor execution effect of existing task processing, and achieves the technical effect of effectively improving task processing efficiency, improving task execution effect, and saving costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The drawings described herein are used to provide a further understanding of this specification, constitute a part of this specification, and do not constitute a limitation of this specification. In the drawings:
[0016] Figure 1 A flowchart showing a task processing method in an embodiment of the present specification is shown;
[0017] Figure 2 A schematic diagram of a device for executing a task processing method in an embodiment of this specification is shown;
[0018] Figure 3 A flowchart showing a task processing method in an embodiment of the present specification is shown;
[0019] Figure 4 A schematic diagram of a task processing device in an embodiment of the present specification is shown;
[0020] Figure 5 A schematic diagram of a computer device in an embodiment of the present specification is shown. DETAILED DESCRIPTION
[0021] The principles and spirit of this specification will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement this specification, and are not intended to limit the scope of this specification in any way. On the contrary, these embodiments are provided to make this specification more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.
[0022] Those skilled in the art will appreciate that the embodiments of this specification may be implemented as a system, device, method, or computer program product. Therefore, this specification may be implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.
[0023] The embodiment of this specification provides a task processing method. In a scenario example of this specification, the task processing method can be applied to a device that performs a task, which can be a server or a server cluster. The device can receive a task processing request. The task processing request can be issued by a business terminal or by other devices. Among them, the task processing request can carry the target task type of the task to be performed. After receiving the task processing request, the device can respond to the task processing request and obtain historical task execution data and object attribute data corresponding to each object identifier in a plurality of object identifiers in a target object identifier set. Among them, the target object identifier set may include multiple object identifiers. Among them, the object may be a processor, a computer, a person or other hardware facility for performing the target task. The task may include services and products provided or recommended to users, or may include big data processing tasks, etc.
[0024] After obtaining the historical task execution data and object attribute data corresponding to each of the multiple object identifiers, feature engineering processing can be performed on the historical task execution data and the object attribute data to obtain the feature data corresponding to each of the multiple object identifiers. Afterwards, the classification label corresponding to each object identifier can be determined based on the feature data corresponding to each object identifier. Among them, the classification label corresponding to each object identifier can characterize the information related to the task type that the object corresponding to the object identifier is suitable for processing. After obtaining the classification label corresponding to each object identifier, the target object identifier can be selected from the multiple object identifiers based on the classification label corresponding to each object identifier and the target task type. The object corresponding to the target object identifier can be used to perform the target task.
[0025] Figure 1A flowchart of a task processing method in an embodiment of the present specification is shown. Although the present specification provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure described in the embodiments of the present specification and shown in the drawings. When the method or module structure is applied to an actual device or terminal product, it can be connected according to the method or module structure shown in the embodiments or drawings for sequential execution or parallel execution (for example, a parallel processor or a multi-threaded processing environment, or even a distributed processing environment).
[0026] Specifically, Figure 1 As shown, a task processing method provided in an embodiment of this specification may include the following steps:
[0027] Step S101: receiving a task processing request, wherein the task processing request includes a target task type.
[0028] The task processing method in this embodiment can be applied to a task processing device. The task processing device can be a server or a server cluster including multiple servers. The task processing device can receive a task processing request sent by a service terminal. The task processing request can include a target task type. For example, the target task type can include at least one of the following: data analysis, model building, model prediction, data collection, etc.
[0029] Step S102: acquiring historical task execution data and object attribute data corresponding to each object identification in a plurality of object identifications in the target object identification set.
[0030] In response to the received task processing request, the device may obtain historical task execution data and object attribute data corresponding to each of the multiple object identifiers in the target object identifier set.
[0031] In one embodiment, after receiving the task processing request, the task processing device may send a request to the data server, wherein the request includes multiple object identifiers in the target object identifier set. The data server may store historical task execution data and object attribute data corresponding to each of the multiple object identifiers. After receiving the request, the data server may return the historical task execution data and object attribute data corresponding to each of the multiple object identifiers in the target object identifier set to the task processing device.
[0032] In another embodiment, the memory of the task processing server may store a large number of historical task execution data and object attribute data of object identifiers. After receiving the task processing request, the historical task execution data and object attribute data corresponding to each object identifier in the target object identifier set may be read from the memory.
[0033] The historical task execution data may include information such as the historical task type, task execution time, and task execution result executed by the object corresponding to the object identifier in the past preset time period. The object attribute information may include attribute information of the object corresponding to the object identifier. For example, when the object is a computer, the object attribute information may include various parameters such as the CPU index, memory capacity, and system version of the computer.
[0034] Step S103, performing feature engineering processing on the historical task execution data and the object attribute data to obtain feature data corresponding to each of the multiple object identifiers.
[0035] After obtaining the historical task execution data and object attribute data corresponding to each object identifier, feature engineering processing can be performed on the historical task execution data and object attribute data corresponding to each object identifier to obtain feature data corresponding to each object identifier in multiple object identifiers. The feature data can be a feature vector.
[0036] Step S104: determining the classification label corresponding to each object identifier according to the feature data corresponding to each object identifier.
[0037] After obtaining the feature data corresponding to each object identifier, the classification label corresponding to each object identifier can be determined based on the feature data corresponding to each object identifier. For example, the feature data corresponding to each classification label in a plurality of classification labels may be stored in the task processing device. The distance or similarity between the feature data corresponding to each object identifier and the feature data corresponding to each classification label in a plurality of classification labels can be calculated. In one example, the classification label with the smallest distance or the highest similarity can be determined as the classification label corresponding to each object identifier. In another example, at least one classification label with a distance less than a preset threshold or a similarity higher than a preset threshold can be determined as the classification label corresponding to each object identifier. It will be appreciated by those skilled in the art that other methods may also be used to determine the classification label corresponding to each object identifier.
[0038] Step S105 , based on the classification labels and target task types corresponding to the object identifiers, a target object identifier is selected from the multiple object identifiers, wherein the target object corresponding to the target object identifier is used to perform the target task.
[0039] After obtaining the classification labels corresponding to each object identifier, a target object identifier can be selected from multiple object identifiers based on the classification labels corresponding to each object identifier and the target task type. After determining the target object identifier, the target object corresponding to the target object identifier can be used to perform the target task.
[0040] In the above embodiment, after receiving the task processing request, the task processing device can obtain the feature data corresponding to each object identifier among multiple object identifiers, and determine the classification label of each object identifier based on the feature data corresponding to each object identifier. Since the feature data includes the historical task execution data and object attribute data of the object, it can characterize the task execution capability of the object, and the classification label of the object can be accurately determined based on the feature data; thereafter, the target object identifier for executing the target task can be determined based on the classification label and the task type, and then the target object corresponding to the target object identifier can be used to execute the target task. There is no need to manually select objects based on experience, which is efficient and can effectively save time and labor costs, thereby improving task execution efficiency, improving task execution results, and saving costs.
[0041] In some embodiments of the present specification, feature engineering processing may include at least one of the following: illegal value processing, missing value processing, normalization processing, derived feature generation, and dimensionality reduction processing. In the above manner, feature data corresponding to each object identifier can be generated based on historical task execution data and object attribute data corresponding to each object identifier in the target object identifier set.
[0042] In some embodiments of the present specification, determining the classification label corresponding to each object identifier according to the feature data corresponding to each object identifier may include: inputting the feature data corresponding to each object identifier into a trained classifier to obtain the classification label corresponding to each object identifier. By inputting the feature data into the trained classifier, the classification label corresponding to each object identifier can be accurately and quickly obtained, thereby improving the efficiency and accuracy of task processing and saving costs.
[0043] In some embodiments of the present specification, a classifier can be trained in the following manner: obtaining a training sample set and a label set, wherein the training sample set includes feature data corresponding to each object in a plurality of objects, and the label set includes classification labels corresponding to each training sample in the training sample set; and constructing a classifier using the training sample set and the label set according to a preset machine learning algorithm.
[0044] The classifier can be trained by the task processing device, or it can be trained by other servers and then sent to the task processing device. You can first obtain a training sample set and a label set. Among them, the training sample set may include feature data corresponding to each object in a plurality of objects. You can first collect historical task execution data and object attribute data of each object in a plurality of objects. You can perform feature engineering processing on the historical task execution data and object attribute data of each object in a plurality of objects to obtain feature data of each object. The label set may include classification labels corresponding to each training sample. A classifier can be constructed using the training sample set and the label set according to a preset machine learning algorithm. In the above manner, a classifier for determining the classification label of an object can be constructed.
[0045] In some embodiments of the present specification, the preset machine learning algorithm may include a random forest algorithm or a gradient boosted decision tree algorithm. Since the classification label of the object may include more than two categories, a machine learning algorithm that supports multiple classifications may be used, including but not limited to a random forest algorithm and a gradient boosted decision tree algorithm. In the above manner, the object can be classified into one of the multiple classification labels.
[0046] In some embodiments of the present specification, after receiving a task processing request, it may also include: obtaining a task object relationship table, wherein the task object relationship table records the correspondence between task types and object identification sets; determining a target object identification set based on the target task type and the task object relationship table, and obtaining the target object identification set.
[0047] Specifically, after receiving the task processing request, the task processing device can obtain the task object relationship table. The object relationship table records the correspondence between the task type and the object identification set. The task processing device can determine the target object identification set corresponding to the target task type from the task object relationship table according to the target task type, and obtain the target object identification set. That is, each task type can correspond to an object identification set, that is, a set of object identifications suitable for processing the task type. Afterwards, the most suitable object is selected from the target object identification set to perform the task. By first obtaining the target object identification set, the selection range can be narrowed, the amount of data processing can be reduced, and computing resources can be saved.
[0048] In some embodiments of the present specification, a preset correspondence table may be stored in the task processing device. The preset correspondence table may include a correspondence between a classification label and a task type. A classification label corresponding to a target type may be selected from the preset correspondence table, and an object identifier corresponding to the classification label may be determined as a target object identifier. In the above manner, the target object identifier may be determined based on the classification label corresponding to each object identifier and the target task type.
[0049] The above method is described below in conjunction with a specific embodiment. However, it should be noted that the specific embodiment is only for better illustrating the present specification and does not constitute an improper limitation on the present specification.
[0050] Please refer to Figure 2 and Figure 3 , Figure 2 A schematic diagram of a device for executing the task processing method in this specific embodiment is shown. Figure 3 A flowchart of a task processing method in an embodiment of the present specification is shown.
[0051] like Figure 2 As shown, the device may include: a task control module 201, a data acquisition and machine learning module 202, a user interaction module 203, and a network bus 204. The modules are connected via the network bus 204 to achieve mutual communication.
[0052] The task control module 201 can be used to: (1) establish or update the model: when the model administrator deems it necessary, issue a modeling instruction to the data collection and machine learning module 202 to complete the re-modeling; (2) determine the employee position labels: receive the employee list sent by the user interaction module 203; issue an instruction to the data collection and machine learning module 202 to collect the data of the employees in the list and determine the employee position labels using the latest model; and send the employee position labels to the user interaction module 203 for display.
[0053] The data collection and machine learning module 202 can be used to: (1) perform modeling according to the instructions of the task control module 201. The modeling process includes data collection, feature engineering and machine learning, and store the modeling results; (2) based on the employee list sent by the task control module 201, collect employee work behavior data and basic information data and process them into the input format of the model, use the stored latest model to determine the employee position label, and return it to the task control module 201.
[0054] The user interaction module 203 can be used to: (1) allow the user to input a list of employees whose job labels need to be determined and send it to the task control module 201; (2) receive the employee job label results from the task control module 201 and display them to the user.
[0055] like Figure 3 As shown, the execution process of the task processing method includes the following steps:
[0056] Step S301: Modeling and storing employee position labels.
[0057] Complete the modeling and storage of employee position labels according to user instructions, as follows:
[0058] The task control module 201 issues modeling instructions to the data acquisition and machine learning module 202 according to user instructions;
[0059] The data collection and machine learning module 202 performs data collection after receiving the modeling instruction. The collected data specifically includes employee work behavior data, employee basic information data, and employee job tags. Among them: employee work behavior data includes the system name and number of times the employee logs into the company's various IT systems during the observation period (for example, one quarter), which is collected from the logs of each IT system and is a feature variable for machine learning; employee basic information data includes the employee's age, length of service, length of service in the company, job title, job level, professional and technical qualifications, highest academic degree, highest academic major, etc. at the end of the observation period (for example, the end of a quarter), which is collected from the human resources management system and is a feature variable for machine learning; employee job tags are employee job tags determined through manual surveys, which are collected from the human resources management system and are target variables for machine learning.
[0060] The data collection and machine learning module 202 performs feature engineering processing on the collected employee data, including but not limited to illegal value processing, missing value processing, normalization processing, derivative feature generation, dimensionality reduction and final wide table generation.
[0061] The data collection and machine learning module 202 performs machine learning based on the wide table. Machine learning can use a variety of algorithms and compare them according to certain standards to select the best model. Since there are generally multiple job labels (large enterprises will have dozens), it is necessary to select a machine learning algorithm that supports multiple classifications, including but not limited to RF (random forest), GBDT (gradient boosted decision tree) and other algorithms. Business departments are generally most concerned about the accuracy of job labels, so the accuracy can be used as a criterion for model selection.
[0062] The data collection and machine learning module 202 stores the modeling results on the server for subsequent determination of employee job tags.
[0063] Step S302 , receiving a list of employees whose job tags need to be determined. The user interaction module 203 may receive the list of employees whose job tags need to be determined by the user and send it to the task control module 201 .
[0064] Step S303, using the latest model to determine the employee job labels for the employee list input by the user. Specifically, the task control module 201 forwards the employee list that needs to determine the job labels to the data collection and machine learning module 202; after receiving the employee list, the data collection and machine learning module 202 performs the following processing: collects the data of the employees on the list, and the data range includes the employee work behavior data and employee basic information data as described above; performs feature engineering processing, including but not limited to illegal value processing, missing value processing, normalization processing, derived feature generation, dimensionality reduction and final wide table generation; inputs the wide table format data into the latest model, and outputs the employee job label data; the data collection and machine learning module 202 sends the label result data to the task control module 201.
[0065] Step S304: Return the employee position label to the user.
[0066] The task control module 201 sends the label result data to the user interaction module 203, and the user interaction module 203 displays it to the user.
[0067] The method provided in the above specific embodiment can generate employee job labels based on machine learning, which can overcome the defect of high cost of determining employee job labels by existing manual survey methods. By collecting employee work behavior data and employee basic information data for machine learning modeling, employee job labels can be automatically determined, which greatly improves work efficiency and saves human resource management costs.
[0068] Based on the same inventive concept, a task processing device is also provided in the embodiments of this specification, as described in the following embodiments. Since the principle of solving the problem by the task processing device is similar to that of the task processing method, the implementation of the task processing device can refer to the implementation of the task processing method, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Figure 4 is a structural block diagram of a task processing device according to an embodiment of this specification, such as Figure 4 As shown, it includes: a receiving module 401, an acquisition module 402, a feature engineering module 403, a determination module 404 and a selection module 405. The structure is described below.
[0069] The receiving module 401 is used to receive a task processing request, wherein the task processing request includes a target task type.
[0070] The acquisition module 402 is used to acquire historical task execution data and object attribute data corresponding to each object identification in a plurality of object identifications in the target object identification set.
[0071] The feature engineering module 403 is used to perform feature engineering processing on the historical task execution data and the object attribute data to obtain feature data corresponding to each object identifier in the multiple object identifiers.
[0072] The determination module 404 is used to determine the classification label corresponding to each object identification according to the feature data corresponding to each object identification.
[0073] The selection module 405 is used to select a target object identifier from multiple object identifiers based on the classification labels and target task types corresponding to the object identifiers, wherein the target object corresponding to the target object identifier is used to perform the target task.
[0074] In some embodiments of the present specification, feature engineering processing may include at least one of the following: illegal value processing, missing value processing, normalization processing, derivative feature generation, and dimensionality reduction processing.
[0075] In some embodiments of the present specification, the determination module may be used to: input feature data corresponding to each object identifier into a trained classifier to obtain a classification label corresponding to each object identifier.
[0076] In some embodiments of the present specification, a classifier can be trained in the following manner: obtaining a training sample set and a label set, wherein the training sample set includes feature data corresponding to each object in a plurality of objects, and the label set includes classification labels corresponding to each training sample in the training sample set; and constructing a classifier using the training sample set and the label set according to a preset machine learning algorithm.
[0077] In some embodiments of the present specification, the preset machine learning algorithm may include a random forest algorithm or a gradient boosting decision tree algorithm.
[0078] In some embodiments of the present specification, the acquisition module can also be used to: after receiving a task processing request, obtain a task object relationship table, wherein the task object relationship table records the correspondence between the task type and the object identification set; determine the target object identification set based on the target task type and the task object relationship table, and obtain the target object identification set.
[0079] From the above description, it can be seen that the embodiments of this specification achieve the following technical effects: after receiving a task processing request, the feature data corresponding to each object identifier in multiple object identifiers is obtained, and the classification label of each object identifier is determined according to the feature data corresponding to each object identifier. Since the feature data includes the historical task execution data and object attribute data of the object, the task execution capability of the object can be characterized, and the classification label of the object can be accurately determined based on the feature data; thereafter, the target object identifier for executing the target task can be determined according to the classification label and the task type, and then the target object corresponding to the target object identifier is used to execute the target task, without the need to manually select the object based on experience, which is highly efficient and can effectively save time and labor costs, thereby improving the efficiency of task execution, improving the effect of task execution, and saving costs. The above scheme solves the technical problems of low efficiency and poor execution effect of existing task processing, and achieves the technical effects of effectively improving task processing efficiency, improving task execution effect, and saving costs.
[0080] This specification also provides a computer device, which can be found in Figure 5 The computer device structure diagram of the task processing method provided by the embodiment of this specification is shown, and the computer device may specifically include an input device 51, a processor 52, and a memory 53. Among them, the memory 53 is used to store processor executable instructions. When the processor 52 executes the instructions, the steps of the task processing method described in any of the above embodiments are implemented.
[0081] In this embodiment, the input device may specifically be one of the main devices for information exchange between the user and the computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input the original data and the program for processing these numbers into the computer. The input device can also obtain and receive data transmitted from other modules, units, and devices. The processor can be implemented in any appropriate manner. For example, the processor can take the form of a computer-readable medium, a logic gate, a switch, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, etc., such as a microprocessor or a processor and a computer-readable program code (such as software or firmware) that can be executed by the (micro) processor. The memory may specifically be a memory device used to store information in modern information technology. The memory may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function without a physical form is also called a memory, such as a RAM, a FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, a TF card, etc.
[0082] In this embodiment, the functions and effects specifically realized by the computer device can be explained in comparison with other embodiments and will not be described in detail here.
[0083] A computer storage medium based on the task processing method is also provided in the implementation mode of this specification. The computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the task processing method described in any of the above embodiments are implemented.
[0084] In this embodiment, the storage medium includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD) or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.
[0085] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer storage medium can be explained in comparison with other embodiments and will not be repeated here.
[0086] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of this specification can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of this specification are not limited to any specific combination of hardware and software.
[0087] It should be understood that the above description is for illustration and not for limitation. Many embodiments and many applications beyond the examples provided will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this specification should not be determined with reference to the above description, but should be determined with reference to the preceding claims and the full scope of equivalents to which these claims belong.
[0088] The above description is only the preferred embodiment of this specification and is not intended to limit this specification. For those skilled in the art, the embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included in the protection scope of this specification.
Claims
1. A task processing method, characterized in that: include: receiving a task processing request, wherein the task processing request includes a target task type; Acquire historical task execution data and object attribute data corresponding to each of the multiple object identifiers in the target object identifier set; the historical task execution data includes the historical task type, task execution time and task execution result executed by the object corresponding to the object identifier within a historical preset time period; Performing feature engineering processing on the historical task execution data and the object attribute data to obtain feature data corresponding to each of the multiple object identifiers; Determining, according to the feature data corresponding to each object identifier, a classification label corresponding to each object identifier; Based on the classification labels corresponding to the object identifiers and the target task type, a target object identifier is selected from the multiple object identifiers, wherein the target object corresponding to the target object identifier is used to perform the target task; After receiving the task processing request, it also includes: Obtaining a task object relationship table, wherein the task object relationship table records the correspondence between task types and object identification sets; Determine a target object identification set according to the target task type and the task object relationship table, and obtain the target object identification set; Wherein, determining the classification label corresponding to each object identifier according to the feature data corresponding to each object identifier includes: Calculate the distance or similarity between the feature data corresponding to each object identifier and the feature data corresponding to each classification label in the plurality of classification labels; The classification label with the smallest distance or the highest similarity is determined as the classification label corresponding to each object identifier; or at least one classification label with a distance less than a preset threshold or a similarity higher than a preset threshold is determined as the classification label corresponding to each object identifier.
2. The method according to claim 1, characterized in that The feature engineering process includes at least one of the following: illegal value processing, missing value processing, normalization processing, derived feature generation, and dimensionality reduction processing.
3. The method according to claim 1, characterized in that Determining, according to the feature data corresponding to each object identifier, a classification label corresponding to each object identifier, including: The feature data corresponding to each object identification is input into a trained classifier to obtain a classification label corresponding to each object identification.
4. The method according to claim 3, characterized in that The classifier is trained in the following way: Acquire a training sample set and a label set, wherein the training sample set includes feature data corresponding to each object in a plurality of objects, and the label set includes a classification label corresponding to each training sample in the training sample set; According to a preset machine learning algorithm, a classifier is constructed using the training sample set and the label set.
5. The method according to claim 4, characterized in that The preset machine learning algorithm includes a random forest algorithm or a gradient enhanced decision tree algorithm.
6. A task processing device, characterized in that: include: A receiving module, configured to receive a task processing request, wherein the task processing request includes a target task type; An acquisition module, used to acquire historical task execution data and object attribute data corresponding to each of the multiple object identifiers in the target object identifier set; the historical task execution data includes the historical task type, task execution time and task execution result executed by the object corresponding to the object identifier within a historical preset time period; A feature engineering module, used to perform feature engineering processing on the historical task execution data and the object attribute data to obtain feature data corresponding to each of the multiple object identifiers; A determination module, used to determine the classification label corresponding to each object identifier according to the feature data corresponding to each object identifier; A selection module, configured to select a target object identifier from the plurality of object identifiers based on the classification labels corresponding to the object identifiers and the target task type, wherein the target object corresponding to the target object identifier is used to perform the target task; The acquisition module is further specifically used for: after receiving the task processing request, acquiring a task object relationship table, wherein the task object relationship table records the correspondence between the task type and the object identification set; determining the target object identification set according to the target task type and the task object relationship table, and acquiring the target object identification set; The determination module is specifically used to: calculate the distance or similarity between the feature data corresponding to each object identifier and the feature data corresponding to each classification label among the multiple classification labels; determine the classification label with the smallest distance or the highest similarity as the classification label corresponding to each object identifier; or determine at least one classification label with a distance less than a preset threshold or a similarity higher than a preset threshold as the classification label corresponding to each object identifier.
7. The device according to claim 6, characterized in that The determination module is specifically used for: The feature data corresponding to each object identification is input into a trained classifier to obtain a classification label corresponding to each object identification.
8. A computer device, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the instructions.
9. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.