Virtual object role recommendation method and device, computer device, and storage medium
By acquiring the work transaction execution data of virtual objects, determining transaction requirement information and performing clustering, generating radar charts, and accurately recommending roles, the problem of resource waste and low efficiency caused by improper role selection in traditional methods is solved, and efficient virtual object role allocation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- KINGDEE SOFTWARE(CHINA) CO LTD
- Filing Date
- 2023-11-13
- Publication Date
- 2026-07-10
AI Technical Summary
In traditional methods, it is difficult to accurately select the roles of virtual objects by manually determining them, resulting in low efficiency and waste of resources in handling work tasks.
By acquiring work transaction execution data, determining transaction requirement information, performing clustering, generating radar charts, identifying target work transactions from clusters based on requirement information, and recommending appropriate roles.
It improves the efficiency of task processing, reduces resource waste, ensures that virtual objects perform high-demand tasks, and avoids low-demand resource waste.
Smart Images
Figure CN117668355B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer device, and storage medium for recommending roles for virtual objects. Background Technology
[0002] A virtual object is a virtual object used to perform certain tasks. It can be role-played and personified, and possesses the ability to act and analyze. For example, a digital employee is a type of virtual object. Enterprises can use digital employees to perform multiple business functions, helping real employees complete monotonous, repetitive, and time-consuming tasks, such as intelligent expense reimbursement.
[0003] Traditionally, virtual objects are assigned roles manually to perform tasks required by those roles. For example, employees assign digital employees positions to replace real employees. However, this manual role assignment method struggles to accurately identify the roles that truly require virtual objects, leading to inefficiency and resource waste. Summary of the Invention
[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for recommending virtual objects that can improve the efficiency of work tasks and reduce resource waste, in order to address the above-mentioned technical problems.
[0005] Firstly, this application provides a method for recommending roles for virtual objects, including:
[0006] Retrieve the execution data of each of the multiple work transactions;
[0007] Based on the execution data of each work transaction, determine the transaction requirement information of each work transaction.
[0008] Based on the transaction requirement information of each of the aforementioned tasks, the tasks are clustered to obtain multiple task clusters;
[0009] Based on the transaction requirement information corresponding to the transactions in each of the aforementioned transaction clusters, the target transaction cluster is determined from each of the aforementioned transaction clusters;
[0010] The roles corresponding to the work transactions in the target work transaction cluster are determined as the roles recommended for the virtual objects.
[0011] In one embodiment, the transaction requirement information includes the execution time interval of the work transaction;
[0012] The step of obtaining the execution data of the multiple work transactions includes:
[0013] According to a preset cycle, acquire the execution data of newly generated work transactions corresponding to multiple work transactions;
[0014] The step of determining the transaction requirement information for each work transaction based on the execution data corresponding to each work transaction includes:
[0015] For each work transaction, the execution time interval of the work transaction is determined based on the time interval between two consecutive acquisitions of the newly generated work transaction execution data.
[0016] In one embodiment, the work transaction execution data includes the number of times the work transaction is executed; the transaction requirement information includes the total number of times the work transaction is executed.
[0017] The step of determining the transaction requirement information for each work transaction based on the execution data corresponding to each work transaction includes:
[0018] For each task, the total number of executions of the task is determined based on the sum of the execution counts obtained within the target time window.
[0019] In one embodiment, the work transaction execution data further includes value quantification data for each execution of the work transaction; the transaction requirement information further includes total value quantification data for the work transaction.
[0020] The step of determining the transaction requirement information of each work transaction based on the execution data corresponding to each work transaction further includes:
[0021] For each work transaction, the total value quantification data of the work transaction is determined based on the total number of executions of the work transaction within the target time window and the value quantification data of each execution of the work transaction.
[0022] In one embodiment, determining the target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters includes:
[0023] A radar chart is generated based on the transaction requirement information corresponding to each of the work transactions in each of the aforementioned work transaction clusters; the data under each coordinate axis in the radar chart represent the transaction requirement information of each dimension; each of the aforementioned work transaction clusters corresponds to a radar graph in the radar chart;
[0024] Based on the distribution of each radar pattern in the radar pattern, the target task cluster is determined from each task cluster.
[0025] In one embodiment, the transaction requirement information includes at least one of the following: the execution time interval of the work transaction, the total number of executions, or the total value quantification data;
[0026] The step of determining the target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters includes:
[0027] Determine the target transaction requirement information corresponding to the cluster center of each of the aforementioned task clusters;
[0028] Determine the number of target conditions that the target transaction requirement information of each cluster center must satisfy;
[0029] The clusters of work transactions that meet the preset conditions are identified as the target work transaction clusters;
[0030] The target conditions include at least one of a first target condition, a second target condition, or a third target condition; the first target condition is that the execution time interval of the work transaction is less than or equal to a preset time interval threshold; the second target condition is that the total number of executions of the work transaction is greater than or equal to a preset number threshold; and the third target condition is that the total value quantification data of the work transaction is greater than or equal to a preset value threshold.
[0031] In one embodiment, obtaining the execution data of the multiple work transactions respectively includes:
[0032] The virtual object unit obtains the execution data of multiple work transactions corresponding to each work transaction from various business units through a pre-established interface.
[0033] Secondly, this application also provides a virtual object role recommendation device, comprising:
[0034] The data acquisition module is used to acquire the execution data of multiple work transactions.
[0035] The requirement information determination module is used to determine the transaction requirement information of each work transaction based on the execution data of each work transaction.
[0036] The clustering module is used to cluster each of the work transactions according to the transaction requirement information of each work transaction, so as to obtain multiple work transaction clusters;
[0037] The recommendation module is used to determine a target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters; and to determine the role corresponding to the work transactions in the target work transaction cluster as the role recommended for the virtual object.
[0038] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0039] Retrieve the execution data of each of the multiple work transactions;
[0040] Based on the execution data of each work transaction, determine the transaction requirement information of each work transaction.
[0041] Based on the transaction requirement information of each of the aforementioned tasks, the tasks are clustered to obtain multiple task clusters;
[0042] Based on the transaction requirement information corresponding to the transactions in each of the aforementioned transaction clusters, the target transaction cluster is determined from each of the aforementioned transaction clusters;
[0043] The roles corresponding to the work transactions in the target work transaction cluster are determined as the roles recommended for the virtual objects.
[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:
[0045] Retrieve the execution data of each of the multiple work transactions;
[0046] Based on the execution data of each work transaction, determine the transaction requirement information of each work transaction.
[0047] Based on the transaction requirement information of each of the aforementioned tasks, the tasks are clustered to obtain multiple task clusters;
[0048] Based on the transaction requirement information corresponding to the transactions in each of the aforementioned transaction clusters, the target transaction cluster is determined from each of the aforementioned transaction clusters;
[0049] The roles corresponding to the work transactions in the target work transaction cluster are determined as the roles recommended for the virtual objects.
[0050] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:
[0051] Retrieve the execution data of each of the multiple work transactions;
[0052] Based on the execution data of each work transaction, determine the transaction requirement information of each work transaction.
[0053] Based on the transaction requirement information of each of the aforementioned tasks, the tasks are clustered to obtain multiple task clusters;
[0054] Based on the transaction requirement information corresponding to the transactions in each of the aforementioned transaction clusters, the target transaction cluster is determined from each of the aforementioned transaction clusters;
[0055] The roles corresponding to the work transactions in the target work transaction cluster are determined as the roles recommended for the virtual objects.
[0056] The aforementioned method, apparatus, computer device, storage medium, and computer program product for recommending virtual objects acquire work transaction execution data corresponding to multiple work transactions. Based on the execution data for each work transaction, they determine the transaction requirement information for each work transaction. This transaction requirement information reflects the actual needs for each work transaction. Then, based on the transaction requirement information, they cluster the work transactions to obtain multiple work transaction clusters. Work transactions with similar transaction requirement information are grouped into the same cluster. Finally, based on the work transactions within each cluster, they determine the clusters that reflect the actual needs. The system identifies the target task cluster from various task clusters based on the task demand information. It then determines the roles corresponding to the tasks within the target task cluster as recommended roles for virtual objects. This allows for the identification of target task clusters to which high-demand tasks belong, enabling accurate role recommendations for these tasks. Virtual objects can then replace real employees in performing high-demand tasks, avoiding resource waste and low efficiency caused by improper role selection leading to virtual objects performing low-demand tasks. This improves task processing efficiency and reduces resource waste. Attached Figure Description
[0057] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0058] Figure 1 This is a diagram illustrating the application environment of a virtual object role recommendation method in one embodiment.
[0059] Figure 2 This is a flowchart illustrating a method for recommending virtual objects' roles in one embodiment.
[0060] Figure 3 This is a schematic diagram illustrating the data structure of transaction requirement information in one embodiment;
[0061] Figure 4 This is a schematic diagram of the clustering method in one embodiment;
[0062] Figure 5 This is a schematic diagram of the clustering results in one embodiment;
[0063] Figure 6 This is a schematic diagram of a radar chart in one embodiment;
[0064] Figure 7 This is a schematic diagram of the overall process of a virtual object role recommendation method in one embodiment;
[0065] Figure 8 A structural block diagram of a virtual object role recommendation device in one embodiment;
[0066] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0067] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0068] The virtual object role recommendation method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, the virtual object unit 102 can communicate with each business unit 104. The virtual object unit 102 can obtain work transaction execution data corresponding to multiple work transactions from each business unit 104, and then execute the virtual object role recommendation method in each embodiment of this application. The virtual object unit 102 and each business unit 104 can belong to the same system or different systems. The virtual object unit 102 and each business unit 104 can be deployed on the same server or different servers.
[0069] In some embodiments, such as Figure 2 As shown, a method for recommending roles for virtual objects is provided, which can be applied to... Figure 1 The following steps are used as an example to illustrate the concept of virtual object unit 102, including steps 202 to 210. Wherein:
[0070] Step 202: Obtain the execution data of the work transactions corresponding to the multiple work transactions.
[0071] Work tasks are the work-related items that employees perform during their workdays. Employees include virtual objects and real employees. Each work task is performed by an employee with a corresponding role. Work task execution data is the data generated after an employee completes a work task. A virtual object is a virtual object used to perform certain tasks. For example, a virtual object can be a digital employee used to perform work tasks for the company. The role of a virtual object indicates which work task(s) the virtual object is responsible for handling. For example, the role of a virtual object can refer to the position of the real employee that the virtual object represents.
[0072] In some embodiments, work transactions can be business transactions processed by the system, such as expense reimbursement approval, leave approval, cash disbursement or budgeting, etc.
[0073] In some embodiments, the work transaction execution data may include at least one of the following: the number of executions corresponding to the work transaction, the number of successful executions, the number of failed executions, or the value quantification data for each execution of the work transaction. Here, the value quantification data for each execution of the work transaction refers to data that quantifies the value generated by each execution of the work transaction.
[0074] In some embodiments, the value quantification of each work transaction can be the human resource cost required to perform each work transaction.
[0075] In some embodiments, a virtual object unit can obtain execution data for multiple work transactions corresponding to various business units. A business unit is a unit within a business system used by an enterprise to manage and process business operations. For example, a business system may include at least one of an office automation (OA) system, a financial management system, or an enterprise resource planning (ERP) system. The virtual object unit can obtain execution data for multiple work transactions corresponding to each business unit within that business unit.
[0076] In some embodiments, task execution data is distributed across various business units within different business systems. A virtual object unit can obtain task execution data corresponding to multiple tasks from each business unit within those systems. For example, a business unit may include a quality inspection unit or an accounting unit.
[0077] In some embodiments, the virtual object unit can periodically obtain work transaction execution data corresponding to multiple work transactions from various business units according to a preset period. In other embodiments, the business units can report newly generated work transaction execution data to the virtual object unit after each generation of work transaction execution data.
[0078] In some embodiments, after obtaining the work transaction execution data, the virtual object unit may first preprocess the work transaction execution data, and then execute step 204 based on the preprocessed work transaction execution data.
[0079] In some embodiments, preprocessing may include at least one of data deduplication, missing value handling, or outlier handling. Data deduplication involves removing duplicates based on the primary key of the data table. Missing value handling involves deleting data rows in the data table that contain missing field values. Outlier handling involves deleting data rows in the data table where the data type of a field value is inconsistent with the data type of the field item.
[0080] Step 204: Determine the transaction requirement information for each task based on the execution data of each task.
[0081] Among them, transaction demand information is information used to reflect the actual demand for work transactions.
[0082] In some embodiments, transaction demand information may include at least one of the following: execution time interval of a work transaction, total number of executions, or total value quantification data. The execution time interval of a work transaction is the time interval between two consecutive executions of that work transaction. The total number of executions of a work transaction is the total number of times that work transaction is executed within a target time window. The total value quantification data of a work transaction is the sum of the value quantification data of all work transactions executed within the target time window. The target time window is a statistical time window used to calculate the transaction demand information.
[0083] Figure 3 The diagram illustrates the execution time interval, total number of executions, and total value quantification data for each task.
[0084] It is understandable that the execution time interval, total number of executions, and total value of work tasks can all reflect the actual demand for these tasks. A shorter execution time interval indicates a higher level of actual demand for the task. A higher total number of executions also indicates a higher level of actual demand for the task. Finally, a higher total value indicates a higher level of actual demand for the task.
[0085] In some embodiments, the virtual object unit can determine the execution time interval of a work transaction based on the time interval between two consecutive acquisitions of newly generated work transaction execution data for that work transaction.
[0086] In some embodiments, the virtual object unit can standardize the transaction requirement information for each dimension separately, and then execute step 206 based on the standardized transaction requirement information. In some embodiments, the standardization process can be a process of transforming transaction requirement information under the same dimension into data that follows a normal distribution. Data that follows a normal distribution refers to data with a mean of 0 and a standard deviation of 1. The formula for standardization is as follows:
[0087]
[0088] Where x represents the data before standardization, x' represents the data after standardization, μ represents the mean of transaction demand information under the same dimension, and σ represents the standard deviation of transaction demand information under the same dimension.
[0089] Step 206: Cluster each task according to its task requirements information to obtain multiple task clusters.
[0090] Clustering of each task refers to dividing each task into multiple task clusters so that each task cluster contains the processing of at least one task.
[0091] In some embodiments, the K-means clustering algorithm can be used for clustering.
[0092] In some embodiments, the virtual object unit can randomly select work transactions that meet the preset number of clusters from each work transaction as initial cluster centers. These initial cluster centers are then used as the current cluster centers in the first iteration. Based on the distance between the transaction requirement information corresponding to each work transaction and the transaction requirement information corresponding to each current cluster center, each work transaction is assigned to the current cluster corresponding to its current cluster center. Then, based on the transaction requirement information of each work transaction in each current cluster, the cluster centers of each current cluster are redefined and used as the current cluster centers in the next iteration. The unit then returns to execute the steps of assigning each work transaction to the current cluster corresponding to its current cluster based on the distance between the transaction requirement information corresponding to each work transaction and the transaction requirement information corresponding to each current cluster center, and subsequent steps, to iteratively perform clustering until the iteration stopping condition is met, resulting in multiple work transaction clusters. The cluster centers redefined based on the transaction requirement information of each work transaction in each work transaction cluster are then used as the cluster centers of the work transaction clusters.
[0093] The distance between the transaction requirement information corresponding to each work task and the transaction requirement information corresponding to each current cluster center refers to the spatial distance of the multi-dimensional data formed by the transaction requirement information of each dimension. For example... Figure 4 As shown, clustering is performed based on the spatial distance of transaction demand information in three dimensions: execution time interval, total number of executions, and total value quantification data. The figure schematically shows the clustering results when the preset number of clusters is 6, and each transaction is divided into 6 transaction clusters.
[0094] like Figure 5 As shown, this diagram schematically illustrates the execution time interval, total number of executions, and total value quantification data corresponding to the cluster centers of each work task cluster obtained by clustering, as well as the number of work tasks in each work task cluster.
[0095] Step 208: Determine the target work transaction cluster from each work transaction cluster based on the transaction requirement information corresponding to the work transactions in each work transaction cluster.
[0096] In some embodiments, the number of target job transaction clusters can be one or more.
[0097] In some embodiments, the virtual object unit can generate, based on the transaction requirement information corresponding to each transaction in each transaction cluster, such as... Figure 6The radar chart is shown. In some embodiments, the virtual object unit can output the radar chart to a terminal for display. The user can select from various task clusters based on the distribution of radar patterns in the displayed radar chart. The terminal can respond to the user's selection operation by sending a selection command to the virtual object unit. The virtual object unit can respond to the selection command sent by the terminal by determining the task cluster selected by the user as the target task cluster. In other embodiments, the virtual object unit can determine the target task cluster from various task clusters based on the distribution of radar patterns in the radar chart.
[0098] In other embodiments, the virtual object unit can determine the target transaction requirement information corresponding to the cluster center of each work transaction cluster, compare the target transaction requirement information of each dimension with the target threshold corresponding to that dimension, and determine the target work transaction cluster from each work transaction cluster based on the comparison results.
[0099] Step 210: Determine the roles corresponding to the work transactions in the target work transaction cluster as the roles recommended for the virtual object.
[0100] In some embodiments, the virtual object unit may determine the roles corresponding to all or part of the work transactions in the target work transaction cluster as the roles recommended for the virtual object.
[0101] In some embodiments, the virtual object unit outputs recommended roles for the virtual object to the terminal for display, providing a reference for users when setting roles for the virtual object. Users can select a target role from the recommended roles and assign it to the virtual object. In response to the user's selection, the terminal can send a role setting instruction to the virtual object unit. The virtual object unit can then assign the selected target role to the virtual object, enabling the virtual object to execute the corresponding work transaction within the business unit through an interface.
[0102] like Figure 7 The diagram illustrates the overall flow of the virtual object role recommendation method in the above embodiments. First, the work transaction execution data undergoes data preprocessing, including handling missing values and cleaning outliers. Then, feature engineering is performed, extracting features from the preprocessed work transaction execution data to obtain transaction requirement information, which is then standardized to obtain standardized transaction requirement information. Next, model training and prediction are performed, using the K-means clustering algorithm to cluster each work transaction based on the transaction requirement information. Finally, analysis and decision-making are based on the clustering results, determining the target work transaction cluster and identifying the roles corresponding to the work transactions within that cluster as the recommended roles for virtual objects.
[0103] The aforementioned method for recommending virtual objects involves obtaining execution data for multiple work tasks, determining the transaction requirements for each task based on this data, and then clustering the tasks according to these requirements. This results in multiple task clusters, grouping tasks with similar requirements into the same cluster. Finally, based on the actual requirements of the tasks within each cluster, a target task cluster is determined and grouped together. The roles corresponding to work tasks within a cluster are determined by recommending roles to virtual objects. This allows for the identification of target work task clusters to which high-demand tasks belong, enabling accurate role recommendations for these tasks. Virtual objects can then replace real employees in performing high-demand tasks, avoiding resource waste and low efficiency caused by improper role selection leading to virtual objects performing low-demand tasks. This improves efficiency and reduces resource waste, concentrating limited resources on high-demand roles to achieve cost reduction and efficiency improvement. Furthermore, recommending high-demand roles can serve as a crucial basis for enterprise digital transformation.
[0104] In some embodiments, the transaction requirement information includes the execution time interval of the work transaction; obtaining the work transaction execution data corresponding to multiple work transactions respectively includes: obtaining the newly generated work transaction execution data corresponding to multiple work transactions according to a preset period; determining the transaction requirement information of each work transaction based on the work transaction execution data corresponding to each work transaction respectively includes: for each work transaction, determining the execution time interval of the work transaction based on the time interval between two adjacent acquisitions of the newly generated work transaction execution data of the work transaction.
[0105] The preset period can be set according to actual needs. For example, the preset period can be 5 minutes, that is, every 5 minutes, the execution data of newly generated work transactions corresponding to multiple work transactions are obtained.
[0106] It is understandable that, since the virtual object unit actively acquires the work transaction execution data according to a preset cycle in this embodiment, there are two possibilities in each cycle: acquisition and non-acquisition. Therefore, the time interval between two adjacent acquisitions can be used to approximate the execution time interval of the work transaction.
[0107] In some embodiments, the virtual object unit may determine the execution time interval of a work transaction based on the average of the time intervals between two consecutive acquisitions of newly generated work transaction execution data.
[0108] In the above embodiments, according to a preset period, newly generated work transaction execution data corresponding to multiple work transactions are obtained. For each work transaction, the execution time interval of the work transaction is determined based on the time interval between two adjacent acquisitions of newly generated work transaction execution data, which can efficiently determine the execution time interval of the work transaction.
[0109] In some embodiments, the work transaction execution data includes the number of executions corresponding to the work transaction; the transaction requirement information includes the total number of executions of the work transaction; and the transaction requirement information of each work transaction is determined based on the work transaction execution data corresponding to each work transaction, including: for each work transaction, determining the total number of executions of the work transaction based on the sum of the number of executions of the work transactions obtained within the target time window.
[0110] It is understandable that the work transaction execution data includes the number of times each work transaction was executed.
[0111] In some embodiments, the virtual object unit can determine the total number of executions of a work transaction within a target time window based on the sum of the execution counts of each work transaction obtained in previous instances within the target time window.
[0112] In the above embodiments, for each work transaction, the total number of executions of the work transaction is determined based on the sum of the execution counts of the work transactions obtained within the target time window, which can efficiently and accurately determine the total number of executions of the work transaction.
[0113] In some embodiments, the work transaction execution data also includes the value quantification data of each execution of the work transaction; the transaction requirement information also includes the total value quantification data of the work transaction; the transaction requirement information of each work transaction is determined based on the work transaction execution data corresponding to each work transaction, and further includes: for each work transaction, determining the total value quantification data of the work transaction based on the total number of executions of the work transaction within the target time window and the value quantification data of each execution of the work transaction.
[0114] In some embodiments, when the value quantification data for each execution of the same work transaction is the same, the virtual object unit can determine the total value quantification data for each work transaction based on the product of the total number of executions of the work transaction within the target time window and the value quantification data for each execution of the work transaction. For example, assuming that for the work transaction of leave approval, the value quantification data for each approved leave application (i.e., each execution of the work transaction) is 10 yuan, and a total of 80 applications were approved (i.e., the leave approval work transaction was executed 80 times), then the total value quantification data for the leave approval work transaction is 800 yuan (i.e., 80 applications multiplied by 10 yuan).
[0115] In other embodiments, when the value quantification data of the same work transaction is different each time it is executed, the virtual object unit can determine the total value quantification data of the work transaction for each work transaction based on the sum of the value quantification data of each work transaction executed within the target time window.
[0116] In the above embodiments, for each work transaction, the total value quantification data of the work transaction is determined based on the total number of executions of the work transaction within the target time window and the value quantification data of each execution of the work transaction, which can efficiently and accurately determine the total value quantification data of the work transaction.
[0117] In some embodiments, determining a target work transaction cluster from each work transaction cluster based on the transaction requirement information corresponding to the work transactions in each work transaction cluster includes: generating a radar chart based on the transaction requirement information corresponding to each work transaction in each work transaction cluster; the data under each coordinate axis in the radar chart represents the transaction requirement information of each dimension; each work transaction cluster corresponds to a radar graphic in the radar chart; and determining the target work transaction cluster from each work transaction cluster based on the distribution of each radar graphic in the radar chart.
[0118] In some embodiments, the virtual object unit can map the work transactions in each work transaction cluster to a radar chart based on the transaction requirement information corresponding to each work transaction in each work transaction cluster. For each work transaction cluster, a radar chart corresponding to that work transaction cluster is generated based on the points corresponding to each work transaction in the radar chart.
[0119] In some embodiments, such as Figure 6 As shown, when the transaction requirement information includes the execution time interval, total number of executions, and total value quantification data of the work transaction, the data under each coordinate axis in the radar chart represent the execution time interval, total number of executions, and total value quantification data, respectively. Figure 6Different line types were used to show the radar patterns corresponding to each task cluster in the radar chart. The spaces enclosed by the different line types are the radar patterns corresponding to each task cluster.
[0120] In the above embodiments, a radar chart is generated based on the transaction demand information corresponding to each transaction in each transaction cluster. This chart can accurately reflect the distribution trend of transaction demand information in each dimension of the transactions in each transaction cluster. Then, based on the distribution of each radar chart, the target transaction cluster can be accurately determined from each transaction cluster. This allows for accurate recommendation of roles corresponding to transactions with high demand, reducing resource waste.
[0121] In some embodiments, the transaction requirement information includes at least one of the following: the execution time interval of the work transaction, the total number of executions, or the total value quantification data. Based on the transaction requirement information corresponding to the work transactions in each work transaction cluster, a target work transaction cluster is determined from each work transaction cluster. This includes: determining the target transaction requirement information corresponding to the cluster center of each work transaction cluster; determining the number of target conditions satisfied by the target transaction requirement information of each cluster center; and determining the work transaction cluster whose number of conditions meets a preset condition number as the target work transaction cluster. The target conditions include at least one of a first target condition, a second target condition, or a third target condition; the first target condition is that the execution time interval of the work transaction is less than or equal to a preset time interval threshold; the second target condition is that the total number of executions of the work transaction is greater than or equal to a preset number threshold; and the third target condition is that the total value quantification data of the work transaction is greater than or equal to a preset value threshold.
[0122] In some embodiments, the virtual object unit can compare the execution time interval corresponding to each cluster center with a preset time interval threshold, the total number of executions with a preset number of executions threshold, and the total value quantification data with a preset value threshold to determine the number of target conditions satisfied by the target transaction requirement information of each cluster center.
[0123] In some embodiments, the number of preset conditions can be any one of "greater than or equal to 1", "greater than or equal to 2", or "greater than or equal to 3". For example, assuming the number of preset conditions is "greater than or equal to 2", then the cluster of work transactions with a number of conditions greater than or equal to 2 is determined as the target work transaction cluster. That is, the cluster of work transactions whose information in at least two dimensions of the transaction requirement information satisfies the target conditions of the corresponding dimensions is determined as the target work transaction cluster.
[0124] In the above embodiments, the transaction requirement information of each dimension is compared with the corresponding threshold to determine the number of conditions satisfied by the cluster center of each work transaction cluster. This enables accurate determination of which work transaction clusters are identified as target work transaction clusters, accurate role recommendation, and reduced resource waste.
[0125] In some embodiments, obtaining the execution data of multiple work transactions respectively includes: the virtual object unit obtaining the execution data of multiple work transactions respectively from each business unit through a pre-established interface.
[0126] In some embodiments, the virtual object unit can predefine the various parameters that the interface needs to transmit, and each business unit implements the interface according to the defined parameters. Each parameter is used to fill in the work transaction execution data for each dimension.
[0127] In the above embodiments, the virtual object unit obtains the execution data of multiple work transactions corresponding to each work transaction from each business unit through a pre-established interface, which enables the virtual object unit to efficiently obtain the execution data of work transactions from each business unit.
[0128] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0129] Based on the same inventive concept, this application also provides a virtual object role recommendation apparatus for implementing the virtual object role recommendation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more virtual object role recommendation apparatus embodiments provided below can be found in the limitations of the virtual object role recommendation method described above, and will not be repeated here.
[0130] In some embodiments, such as Figure 8 As shown, a virtual object role recommendation device 800 is provided, including: a data acquisition module 802, a demand information determination module 804, a clustering module 806, and a recommendation module 808, wherein:
[0131] The data acquisition module 802 is used to acquire the execution data of multiple work transactions.
[0132] The requirement information determination module 804 is used to determine the transaction requirement information of each work transaction based on the execution data of each work transaction.
[0133] Clustering module 806 is used to cluster each task according to the task requirement information of each task, and obtain multiple task clusters.
[0134] The recommendation module 808 is used to determine the target work transaction cluster from each work transaction cluster based on the transaction requirement information corresponding to the work transactions in each work transaction cluster; and to determine the role corresponding to the work transactions in the target work transaction cluster as the role recommended for the virtual object.
[0135] In some embodiments, the transaction requirement information includes the execution time interval of the work transaction. The data acquisition module 802 is further configured to acquire newly generated work transaction execution data corresponding to multiple work transactions according to a preset period. The requirement information determination module 804 is further configured to determine the execution time interval of each work transaction based on the time interval between two consecutive acquisitions of newly generated work transaction execution data.
[0136] In some embodiments, the work transaction execution data includes the number of executions corresponding to the work transaction; the transaction requirement information includes the total number of executions of the work transaction. The requirement information determination module 804 is further configured to determine the total number of executions of each work transaction based on the sum of the number of executions corresponding to the work transactions obtained within the target time window.
[0137] In some embodiments, the work transaction execution data further includes value quantification data for each execution of the work transaction; the transaction demand information further includes total value quantification data for the work transaction. The demand information determination module 804 is also used to determine the total value quantification data for each work transaction based on the total number of executions of the work transaction within the target time window and the value quantification data for each execution of the work transaction.
[0138] In some embodiments, the recommendation module 808 is further configured to generate a radar chart based on the transaction requirement information corresponding to each transaction in each transaction cluster; the data under each coordinate axis in the radar chart represent the transaction requirement information of each dimension; each transaction cluster corresponds to a radar graphic in the radar chart; and the target transaction cluster is determined from each transaction cluster based on the distribution of each radar graphic in the radar chart.
[0139] In some embodiments, the transaction requirement information includes at least one of the execution time interval of the work transaction, the total number of executions, or the total value quantification data. The recommendation module 808 is further configured to: determine the target transaction requirement information corresponding to the cluster center of each work transaction cluster; determine the number of target conditions satisfied by the target transaction requirement information of each cluster center; and determine the work transaction clusters whose number of conditions meets a preset condition number as target work transaction clusters; wherein the target conditions include at least one of a first target condition, a second target condition, or a third target condition; the first target condition is that the execution time interval of the work transaction is less than or equal to a preset time interval threshold; the second target condition is that the total number of executions of the work transaction is greater than or equal to a preset number threshold; and the third target condition is that the total value quantification data of the work transaction is greater than or equal to a preset value threshold.
[0140] In some embodiments, the data acquisition module 802 is further configured to acquire work transaction execution data corresponding to multiple work transactions from each business unit through a pre-established interface.
[0141] The aforementioned virtual object role recommendation device acquires execution data for multiple work tasks, determines the task requirements for each task based on this data, and identifies the actual needs for each task. Then, it clusters the tasks based on these requirements, grouping tasks with similar requirements into the same cluster. Finally, based on the actual needs reflected in the task requirements within each cluster, it identifies a target task cluster and determines the roles corresponding to the tasks in that cluster as recommended roles for the virtual object. This method accurately identifies target task clusters for tasks with high demand, allowing virtual objects to replace real employees in performing these high-demand tasks. This avoids resource waste and low efficiency caused by improper role selection leading to virtual objects performing low-demand tasks, thus improving overall task processing efficiency and reducing resource waste.
[0142] The various modules in the aforementioned virtual object role recommendation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0143] In some embodiments, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data for task execution. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a virtual object role recommendation method.
[0144] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0145] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0146] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.
[0147] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0149] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.
[0151] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for recommending roles for virtual objects, characterized in that, The method includes: Retrieve the execution data of each of the multiple work transactions; Based on the execution data of each work transaction, determine the transaction requirement information of each work transaction. Based on the transaction requirement information of each of the aforementioned tasks, the tasks are clustered to obtain multiple task clusters; Based on the transaction requirement information corresponding to the transactions in each of the aforementioned transaction clusters, the target transaction cluster is determined from each of the aforementioned transaction clusters; The roles corresponding to the work transactions in the target work transaction cluster are determined as the roles recommended for the virtual objects; The transaction requirement information includes at least one of the following: the execution time interval of the work transaction, the total number of executions, or the total value quantification data; The step of determining the target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters includes: Determine the target transaction requirement information corresponding to the cluster center of each of the aforementioned task clusters; determine the number of target conditions satisfied by the target transaction requirement information of each cluster center; and determine the task clusters whose number of conditions meets the preset number of conditions as target task clusters. The target conditions include at least one of a first target condition, a second target condition, or a third target condition; the first target condition is that the execution time interval of the work transaction is less than or equal to a preset time interval threshold; the second target condition is that the total number of executions of the work transaction is greater than or equal to a preset number threshold; and the third target condition is that the total value quantification data of the work transaction is greater than or equal to a preset value threshold.
2. The method according to claim 1, characterized in that, The transaction requirement information includes the execution time interval of the work transaction; The step of obtaining the execution data of the multiple work transactions includes: According to a preset cycle, acquire the execution data of newly generated work transactions corresponding to multiple work transactions; The step of determining the transaction requirement information for each work transaction based on the execution data corresponding to each work transaction includes: For each work transaction, the execution time interval of the work transaction is determined based on the time interval between two consecutive acquisitions of the newly generated work transaction execution data.
3. The method according to claim 1, characterized in that, The task execution data includes the number of times the task is executed; the task requirement information includes the total number of times the task is executed. The step of determining the transaction requirement information for each work transaction based on the execution data corresponding to each work transaction includes: For each task, the total number of executions of the task is determined based on the sum of the execution counts obtained within the target time window.
4. The method according to claim 3, characterized in that, The work transaction execution data also includes value quantification data for each execution of the work transaction; the transaction requirement information also includes total value quantification data for the work transaction. The step of determining the transaction requirement information of each work transaction based on the execution data corresponding to each work transaction further includes: For each work transaction, the total value quantification data of the work transaction is determined based on the total number of executions of the work transaction within the target time window and the value quantification data of each execution of the work transaction.
5. The method according to claim 1, characterized in that, The step of determining the target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters includes: A radar chart is generated based on the transaction requirement information corresponding to each of the work transactions in each of the aforementioned work transaction clusters; the data under each coordinate axis in the radar chart represent the transaction requirement information of each dimension; each of the aforementioned work transaction clusters corresponds to a radar graph in the radar chart; Based on the distribution of each radar pattern in the radar pattern, the target task cluster is determined from each task cluster.
6. The method according to claim 1, characterized in that, The work transaction execution data includes at least one of the following: the number of executions corresponding to the work transaction, the number of successful executions, the number of failed executions, or the value quantification data of each execution of the work transaction; Among them, the value quantification data for each execution of a work task refers to the data after quantifying the value generated by each execution of a work task.
7. The method according to any one of claims 1 to 6, characterized in that, The step of obtaining the execution data of the multiple work transactions includes: The virtual object unit obtains the execution data of multiple work transactions corresponding to each work transaction from various business units through a pre-established interface.
8. A virtual object role recommendation device, characterized in that, The device includes: The data acquisition module is used to acquire the execution data of multiple work transactions. The requirement information determination module is used to determine the transaction requirement information of each work transaction based on the execution data of each work transaction. The clustering module is used to cluster each of the work transactions according to the transaction requirement information of each work transaction, so as to obtain multiple work transaction clusters; The recommendation module is used to determine a target work transaction cluster from each of the work transaction clusters based on the transaction requirement information corresponding to the work transactions in each of the work transaction clusters; and to determine the roles corresponding to the work transactions in the target work transaction clusters as recommended roles for virtual objects. The transaction requirement information includes at least one of the following: the execution time interval of the work transaction, the total number of executions, or the total value quantification data; The recommendation module is also used to determine the target transaction requirement information corresponding to the cluster center of each task cluster; determine the number of target conditions satisfied by the target transaction requirement information of each cluster center; and determine the task clusters whose number of conditions meets the preset number of conditions as target task clusters. The target conditions include at least one of a first target condition, a second target condition, or a third target condition; the first target condition is that the execution time interval of the work transaction is less than or equal to a preset time interval threshold; the second target condition is that the total number of executions of the work transaction is greater than or equal to a preset number threshold; and the third target condition is that the total value quantification data of the work transaction is greater than or equal to a preset value threshold.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.
11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.