Working role simulation method, system and virtual robot based on virtual robot

By building virtual robots and simulating employee habits, the problems of insufficient flexibility and learning ability of virtual robots in work role simulation were solved, realizing efficient and personalized work role simulation, and improving user experience and enterprise efficiency.

CN118657495BActive Publication Date: 2024-11-19SHENZHEN AURORA TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411132402.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-19
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

In existing technologies, virtual robots lack flexibility and learning ability when simulating specific job roles, cannot effectively adapt to changes in workflows or differences in individual work habits, and fail to make full use of the experience and knowledge of existing employees, resulting in low efficiency and high costs.

Method used

By analyzing job role and skill information, a virtual robot is constructed and equipped with a skill package. Real-time terminal data is acquired, the habit data of the simulated object is analyzed, and a habit logic chain is constructed. This enables the virtual robot to imitate the employee's habits to perform tasks and adapt to changes in workflow through self-learning and evolution.

Benefits of technology

It improves work efficiency, reduces human error, provides personalized services, lowers long-term labor costs, promotes corporate innovation and competitiveness, and creates a positive work environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118657495B_ABST
    Figure CN118657495B_ABST
Patent Text Reader

Abstract

This application proposes a method, system and virtual robot for simulating work roles based on virtual robots. The method includes: selecting a simulation object; selecting a virtual robot and adding a skill software package; selecting replaceable work items, parsing software, determining permissions, and building an initial logical chain for the work items; obtaining terminal data through the virtual robot, and obtaining habit data of the simulation object from it; coupling the habit data to the initial logical chain to obtain a habit logical chain, granting permissions to the virtual robot, and allowing the virtual robot to imitate the habits of the simulation object according to the habit logical chain to execute the work items. This solution simulates the habits and workflow of specific simulation objects through virtual robots, imitates the decision-making mode, operation habits and preference settings of specific simulation objects, and provides highly personalized and customized services, thereby providing services that are more in line with personal style and improving user experience and satisfaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of role simulation, and in particular, to a work role simulation method and system based on a virtual robot, and a virtual robot. Background Art

[0002] With the rapid development of artificial intelligence technology, virtual robots are increasingly used in various industries, especially in simulating human work roles and performing specific work tasks. Traditionally, corporate organizations rely on manual labor to complete various complex and repetitive tasks, such as data analysis, customer service, production scheduling, etc. However, this method has problems such as low efficiency, high cost, and prone to errors. In addition, as business needs continue to change, the skill requirements for employees are also constantly increasing, resulting in long training cycles and poor adaptability.

[0003] In the existing technology, although there are some automation tools and robotic process automation solutions that attempt to solve the above problems, they are often limited to predefined rules and processes, lack flexibility and learning ability, and cannot effectively adapt to changes in workflows or differences in personal work habits. Furthermore, these systems often fail to fully utilize the experience and knowledge of existing employees when simulating specific job roles, which limits the effect and depth that automation can achieve.

[0004] Therefore, there is an urgent need for an innovative approach that can simulate specific job roles more accurately. Summary of the invention

[0005] Based on the problems existing in the prior art, this application provides a method, system and virtual robot for simulating work roles based on virtual robots. The specific scheme is as follows:

[0006] This application proposes a work role simulation method based on a virtual robot, including the following:

[0007] Select a specific simulation object under a certain job role, and analyze the role information, job responsibilities and skill information of the simulation object;

[0008] Selecting a virtual robot based on the role information and the job responsibilities, and adding a skill software package corresponding to the skill information to the virtual robot so that the virtual robot can call the skill software package to perform tasks;

[0009] Selecting a replaceable work item that the simulated object executes on the terminal from among the work responsibilities, parsing the execution process of the work item and the software involved, determining the authority required for the virtual robot to execute the work item, and constructing an initial logical chain of the work item based on the execution process;

[0010] In the process of the simulated object executing the work item, the terminal data of the simulated object when executing the work item at the terminal is obtained through the virtual robot, and project data related to the work item is screened out from the terminal data, and habit data of the simulated object is obtained by analyzing the project data;

[0011] The habit data is coupled to the initial logic chain to obtain a habit logic chain, and the virtual robot is given the same authority as the simulated object, so that the virtual robot can execute the work item according to the habit logic chain by imitating the habit of the simulated object.

[0012] In some specific embodiments, the virtual robot, when executing the work item, specifically includes:

[0013] When the requirements of the work item are the same as one or more requirements recorded in the project data, the virtual robot is made to repeat the execution directly according to the processing method recorded in the project data;

[0014] When the requirements of the work project are different from all the requirements recorded in the project data but are similar to one or more requirements, the virtual robot identifies the differences by comparing the requirements of the current work project with the features of similar requirements in the project data, and intelligently adjusts the corresponding links in the habitual logic chain based on the differences to achieve intelligent execution.

[0015] In some specific embodiments, when the requirements of a work project are neither the same as nor similar to all the requirements recorded in the project data, the virtual robot analyzes the requirements of the current work project, constructs a new initial logical chain, merges the habit data into the new initial logical chain to obtain a new habit logical chain, and executes the work project in accordance with the new habit logical chain, imitating the way the simulated object may execute when faced with new requirements.

[0016] In some specific embodiments, the virtual robot is given the permission to start background screen recording when the software is running, and the terminal data is obtained by recording the screen of the simulated object when the terminal executes the work item within a certain period of time;

[0017] Analyzing the terminal data frame by frame, and comparing whether there is a difference between two adjacent frames of images;

[0018] Mark the frame images with differences as changed frames, and find the changed areas in all changed frames;

[0019] Based on the running logic of the software, the operation behavior of the simulation object and its corresponding interface change are analyzed from the change area, and the project data of the time period is obtained after confirmation by the simulation object;

[0020] Summarize the project data of each time period, analyze the basis data of the simulated object's operation behavior according to the software's operating logic and the interface changes corresponding to the operation behavior, and obtain the habit data of the simulated object by combining the basis data and the corresponding operation behavior.

[0021] In some specific embodiments, the virtual robot is composed of an artificial virtual robot and one or more functional models, and the artificial virtual robot can call each functional model and select the functional model based on the skill information;

[0022] In a preset database, virtual robots divided by work roles are pre-stored. The role information of the virtual robots, including age, gender, and education level, can be customized and marked with skill labels of corresponding functional models; the basic skills required to complete the job responsibilities are determined, and based on the basic skills, virtual robots with corresponding skill labels are searched in the database.

[0023] In some specific embodiments, the process of acquiring the project data specifically includes:

[0024] Real-time monitoring of the terminal operation of the simulated object when executing a specific work item to obtain the terminal data, wherein the terminal operation includes keyboard input, mouse movement, click, and window management virtual robot program interaction;

[0025] Collecting the timestamp, sequence and frequency of each terminal operation to form a corresponding operation log, and incorporating the operation log into the terminal data;

[0026] Data directly related to the selected work item is screened out from the terminal data, and irrelevant data is eliminated through identification methods including keyword search, application identifier identification or specific operation mode identification to obtain project data.

[0027] In some specific embodiments, the process of acquiring the habit data specifically includes:

[0028] Analyze the project data using a pre-trained habit analysis model, perform cluster analysis on similar operations, and analyze the relevant operations in the time dimension using a preset long short-term memory network to obtain the habit pattern of the simulated object when executing the work project, wherein the habit pattern includes the time point of switching software on and off, the specific order of processing data, tool options, interface layout, and shortcut key usage;

[0029] Analyze the most common operation sequence of the simulated object when executing the work item based on the habit pattern, wherein the operation sequence includes the normal working sequence of the virtual object when executing the work item, and the decision-making mode and corresponding working sequence when facing anomalies;

[0030] The habit patterns and the operation sequences are summarized and encoded into a format parseable by a virtual robot to obtain the habit data.

[0031] In some specific embodiments, the role information includes the position, age, gender, and education level of the simulated object;

[0032] Said job duties include the daily tasks and responsibilities of the simulated subject;

[0033] The skill information includes the skills possessed by the simulated object, the skills required for the job role, and the skills that the simulated object wants to have but does not have;

[0034] The initial logic chain includes: the source of input data, data processing and analysis, decision-making logic, output result processing, and exception handling mechanism.

[0035] This application proposes a work role simulation system based on a virtual robot, including the following:

[0036] A role determination unit, used to select a specific simulation object under a certain work role, and analyze the role information, work responsibilities and skill information of the simulation object;

[0037] a model determination unit, configured to select a virtual robot based on the role information and the job responsibilities, and add a skill software package corresponding to the skill information to the virtual robot, so that the virtual robot can call the skill software package to perform a task;

[0038] A preprocessing unit, used to select a replaceable work item to be executed by the simulated object at the terminal in the work responsibility, analyze the execution process of the work item and the software involved, determine the authority required for the virtual robot to execute the work item, and construct an initial logical chain of the work item based on the execution process;

[0039] a data acquisition unit, configured to acquire, through the virtual robot, terminal data of the simulated object when the simulated object executes the work item at the terminal, filter out project data related to the work item from the terminal data, and acquire habit data of the simulated object by analyzing the project data;

[0040] The simulation unit is used to couple the habit data to the initial logic chain to obtain a habit logic chain, grant the virtual robot the same authority as the simulation object, and enable the virtual robot to perform the work item according to the habit logic chain by imitating the habit of the simulation object.

[0041] The present application proposes a virtual robot for implementing any of the above-mentioned work role simulation methods based on virtual robots.

[0042] Beneficial effects: This application proposes a method, system and virtual robot for simulating work roles based on virtual robots. The virtual robot simulates the habits and workflows of specific simulated objects, imitates the decision-making mode, operation habits and preference settings of specific simulated objects, and provides highly personalized and customized services, thereby providing services that are more in line with personal style and improving user experience and satisfaction. When simulating the execution of repetitive and rule-defined tasks, the virtual robot can accurately follow the habitual logic chain and complete the task quickly and accurately, which can greatly improve efficiency and reduce errors caused by human negligence or fatigue.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a flowchart of the work role simulation method of this application;

[0046] Figure 2 is a schematic diagram of the hierarchical relationship between the features of this application;

[0047] Figure 3 It is a schematic diagram of the virtual robot of the present application responding to different situations;

[0048] Figure 4 It is a schematic diagram of the work role simulation system module of this application.

[0049] Figure numerals: 1 - role determination unit; 2 - model determination unit; 3 - preprocessing unit; 4 - data acquisition unit; 5 - simulation unit. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] This application proposes a method for simulating work roles based on virtual robots. The virtual robot simulates the habits and workflow of a specific simulation object, imitates the decision-making mode, operation habits and preference settings of a specific simulation object, and provides highly personalized and customized services, thereby providing services that are more in line with personal style and improving user experience and satisfaction. The flowchart of the method for simulating work roles based on virtual robots is shown in the attached figure. Figure 1 The principle is shown in the attached Figure 2 The specific plan is as follows:

[0052] A method for simulating a work role based on a virtual robot, comprising the following steps:

[0053] 101. Select a specific simulation object under a certain work role, and analyze the role information, job responsibilities and skill information of the simulation object;

[0054] 102. Select a virtual robot based on the role information and job responsibilities, and add a skill software package corresponding to the skill information to the virtual robot, so that the virtual robot can call the skill software package to perform the task;

[0055] 103. Select a work item that can be replaced and executed by the simulated object at the terminal in the work responsibilities, analyze the execution process of the work item and the software involved, determine the permissions required for the virtual robot to execute the work item, and build an initial logical chain of the work item based on the execution process;

[0056] 104. In the process of the simulated object executing the work project, the terminal data of the simulated object when executing the work project at the terminal is obtained through the virtual robot, and the project data related to the work project is screened out from the terminal data, and the habit data of the simulated object is obtained by analyzing the project data;

[0057] 105. The habit data is coupled to the initial logic chain to obtain the habit logic chain, and the virtual robot is given the same authority as the simulated object, so that the virtual robot can execute the work item according to the habit logic chain by imitating the habit of the simulated object.

[0058] The work role simulation method of the present application applies a virtual robot to a specific simulation object under a specific work role to achieve simulation and enhancement of a specific role, and replaces the specific simulation object to perform related work items by imitating the habits and preferences of employees, providing more personalized services or products and enhancing user experience. It can not only reduce manual errors, improve work accuracy, accelerate the decision-making process, and significantly improve efficiency, but also reduce long-term labor costs, reduce dependence on manpower through automation, and help avoid costly mistakes. In addition. It can also promote the innovation and competitiveness of enterprises, while creating a more positive and productive working environment for employees.

[0059] Among them, virtual robots are built based on artificial virtual robots and combined with various schedulable functional models. The selection of functional models is based on the skill information and job responsibilities of the selected simulation object, such as data analysis model, text editing model, prediction model, etc. Based on advanced artificial virtual robots, deep learning and other functional models are integrated to achieve highly accurate simulation of specific work roles. Virtual robots use multi-layer neural network structures, especially convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM) or variants under the deep learning framework, such as Transformer models, to process complex nonlinear relationships and time series data. Virtual robots should have the ability to self-learn and evolve, and continuously learn from new data through online learning or incremental learning mechanisms to adapt to changes in work processes and updates to personal work habits.

[0060] In step 101, it is necessary to select a job role and parse relevant information to provide a basis for subsequent virtual robot selection and skill matching. The specific steps include the following: First, select a specific job role, such as "marketing manager", "data analyst", "human resources manager", "finance manager" and other specific job titles. Secondly, it is necessary to parse the role information, including job description, department, reporting relationship, etc. Next, it is necessary to clarify the job responsibilities of the simulated object, such as market research, advertising planning, customer relationship management, etc. Finally, according to the specific job responsibilities of the simulated object, determine the skill information required to complete the responsibilities, such as market analysis, creative writing, social media management, data analysis, etc.

[0061] It should be noted that a job role is a position, and the simulation object is a specific person with specific working habits. The virtual robot needs to imitate the simulation object, perform certain work tasks according to the working habits of the simulation object, and to a certain extent replace the simulation object to perform certain work tasks in order to reduce its workload.

[0062] Among them, role information is the basic description of the role. In addition to basic information such as the position, age, gender, and education of the simulated object, it also includes the position of the role in the organization, the relationship goals with other roles, the expected results of the role, and the criteria for successfully executing the role. Job responsibilities include the daily tasks and responsibilities of the simulated object, that is, the specific work that the role personnel need to complete every day or regularly, such as handling customer inquiries, data analysis, or financial reporting. In addition, job responsibilities are also related to measuring the success of the role, involving important indicators such as customer satisfaction, data accuracy, or the timeliness of financial reporting. Skill information includes the skills that the simulated object has, the skills required for the job role, and the skills that the simulated object wants to have but does not have. The specific knowledge and abilities required to perform specific job responsibilities are different, including both hard skills such as programming languages, the use of data analysis tools, and financial knowledge, as well as soft skills such as the ability to cooperate and communicate effectively with others, problem-solving skills, and the ability to adapt to changes.

[0063] Step 102 is about selecting a suitable virtual robot based on the characteristics of the selected job role and adding a specific skill package to it to ensure that the model is competent for the job responsibilities of the role. Based on the job responsibilities and skill requirements of the role, select the type of virtual robot that can handle the relevant tasks. For example, if the role involves a lot of data analysis and prediction, you may need to select a model with advanced data analysis and machine learning capabilities as a functional model. For another example, if the role involves content creation, etc., you may need a more intelligent text generation model as a functional model. When the role involves communicating with others, chatbots, sentiment analysis engines, etc. can be selected as functional models. Virtual robots can be customized and optimized according to the needs of specific job roles to improve efficiency, reduce errors, support decision-making, and provide users with a better service experience. With the continuous development of artificial intelligence technology, more virtual robots specifically for specific job roles may appear in the future to meet the increasingly complex and diverse workplace needs. In addition, it is necessary to establish an evaluation of virtual robots, including: evaluating the historical performance of the model on similar tasks, including accuracy, efficiency, and stability.

[0064] In some specific embodiments, virtual robots divided by work roles are pre-stored in a preset database. The role information of the virtual robots, including age, gender, and education, can be customized and marked with skill tags of corresponding functional models. In practical applications, the basic skills required to complete the job responsibilities are pre-determined, and virtual robots with corresponding skill tags are searched in the database based on the basic skills, so that enterprises or individuals can quickly find the most suitable virtual robots for specific tasks, reducing the time and cost of manual screening, and improving work efficiency. In the database, each virtual robot has its preset role information (such as age, gender, and education), which may be used for artificial intelligence applications in certain specific scenarios, such as role-playing when simulating user interaction. Each model is also assigned skill tags, which reflect the functions that the model can perform or the areas in which it is particularly good. When a job needs to be completed, the virtual robot with the corresponding skill tag in the database is queried according to the required skills. Database queries may be based on keyword searches, or more complex algorithms may be used to match the most suitable model, such as similarity scores.

[0065] For example, look for a data analyst job role that requires performing data cleaning, data exploratory analysis, and data visualization.

[0066] Defining skills: Data cleaning, statistical analysis, data visualization.

[0067] Database query: Search for virtual robots with the skill tags of "data cleaning", "statistical analysis", and "data visualization" in the preset database.

[0068] Selecting a model: Assume that the database returns three virtual robots A, B, and C, among which model B has the highest skill match.

[0069] Apply Model: Deploy Model B to perform the job responsibilities of a data analyst.

[0070] Exemplarily, when adding a skill package to a virtual robot, it specifically includes: clarifying what specific tasks the virtual robot needs to perform and the skills required to complete these tasks. For example, if the virtual robot is a model for data processing, it may require skills such as data cleaning, data conversion, statistical analysis, and machine learning algorithms. Secondly, according to the skill requirements, select the appropriate software package or library. For example, for data processing tasks, the following software packages may be required: Pandas: for data cleaning and conversion. NumPy: for numerical calculations. Scikit-learn: for machine learning algorithms. Matplotlib or Seaborn: for data visualization. After that, install the required software packages in the environment where the virtual robot runs through the package manager. At the same time, import the relevant software packages into the code of the virtual robot, encapsulate the code for executing specific skills into functions or methods, and the virtual robot can call these functions to complete the task, so that it can be better called when performing the task.

[0071] When choosing a software skill package, pay attention to selecting specific skills based on role information and job responsibilities, such as data analysis, programming, document processing, etc. And determine which skills are core and which are secondary to optimize resource allocation. In addition, choose a software package that is compatible with the virtual robot technology stack and ensure that the software package can fully cover the required skills.

[0072] Step 103 involves identifying specific work items that can be replaced by virtual robots in the selected job responsibilities, parsing the execution process of these items, determining the software permissions required by the virtual robot, and building an initial logical chain for project execution. Among them, the screening criteria for work items are highly repeatable, clear rules, and standardized workflows. For example, regular tasks such as daily data aggregation and weekly report generation, or tasks with fixed cycles. In addition, in actual applications, the complexity of the project should also be considered to ensure that the existing capabilities of the virtual robot are sufficient to handle it. Overly complex projects may require more advanced virtual robots or more customized development.

[0073] Break down the work project into a series of executable steps, such as data collection, data processing, decision making, and result output. Determine the software and tools used in each step, such as database query, specific office software, data processing scripts, etc. This part of the content can be summarized by the virtual robot and confirmed by the simulated object. If necessary, a flowchart or workflow diagram can be created to clearly show every link of the project from start to finish. After that, according to the workflow, determine which software or system resources the virtual robot needs to access to ensure that the virtual robot can perform the required operations, such as reading files, executing database queries, sending emails, etc. In step 103, you only need to confirm the required permissions, and grant permissions when the virtual robot actually starts to execute the work project to ensure data security. Regarding permission granting, the principle of least privilege must be followed.

[0074] In some specific embodiments, the initial logic chain includes: the source of input data, data processing and analysis, decision-making logic, output result processing, and exception handling mechanism. Regarding the design of the initial logic chain, based on the analysis of the workflow, the logic chain for the virtual robot to perform tasks is designed, that is, a series of instructions executed in a specific order. For steps that need to respond differently according to conditions, conditional branching logic is designed, such as "if data X exceeds threshold Y, then execute step Z". At the same time, an exception handling mechanism is constructed so that the virtual robot can pause, record errors, or try alternative solutions when encountering problems. When testing the initial logic chain, it is necessary to test each independent step to ensure that the virtual robot can execute correctly, and to test the entire logic chain to ensure that all steps are executed coherently without conflicts or omissions. At the same time, the execution efficiency of the virtual robot should be analyzed and the logic chain should be optimized, such as reducing unnecessary steps and improving algorithm performance.

[0075] The following are virtual robots corresponding to common job roles, skill requirements, software involved, and work items that can be replaced:

[0076] 1. Data Analyst

[0077] Virtual Robots: Automatic feature selection, anomaly detection, predictive modeling

[0078] Skills: Statistics, Data Visualization, Machine Learning Algorithms

[0079] Software: Python (Pandas, scikit-learn), R, Tableau, Power BI

[0080] Work items that can be replaced: data cleaning, basic data exploratory analysis, pattern recognition

[0081] 2. Customer Service Representative

[0082] Virtual robots: chatbots, speech recognition, sentiment analysis

[0083] Skills: Customer service, communication, problem solving

[0084] Software: Dialogflow, IBM Watson, Zendesk

[0085] Work items that can be replaced: FAQs, preliminary complaint handling, simple inquiries

[0086] 3. Financial accounting

[0087] Virtual robots: financial forecasting, automated auditing, compliance checks

[0088] Skills: accounting principles, tax knowledge, financial analysis

[0089] Software: SAP, Oracle, QuickBooks

[0090] Work items that can be replaced: Account classification, invoice processing, general report generation

[0091] 4. Physician Assistant

[0092] Virtual robots: medical image analysis, disease diagnosis assistance, patient medical record recording

[0093] Skills: Medical knowledge, patient care, health education

[0094] Software: DeepMind Health, IBM Watson for Oncology

[0095] Work that can be replaced: basic image reading, symptom analysis, electronic medical record organization

[0096] 5. Software Developer

[0097] Virtual robot: automatic code generation, error detection, code optimization suggestions

[0098] Skills: Programming languages, software architecture, testing

[0099] Software: GitHub Copilot, JetBrains Kite

[0100] Replaceable work items: code snippet generation, basic bug fixes, simple function implementation

[0101] 6. Human Resources Specialist

[0102] Virtual robots: resume screening, candidate assessment, employee satisfaction prediction

[0103] Skills: Recruitment strategy, interview skills, employee relations

[0104] Software: ZapRecruit, Mya Systems

[0105] Replaceable tasks: Preliminary resume screening, interview scheduling, and sending standardized emails

[0106] 7. Content Creators

[0107] Virtual robots: article writing, video editing, image generation

[0108] Skills: Creative Writing, Media Production, SEO

[0109] Software: Grammarly, Adobe Creative Suite, Midjourney AI

[0110] Possible work items: news release writing, basic graphic design, video clip editing

[0111] 8. Educators

[0112] Virtual robots: student performance prediction, personalized learning recommendations

[0113] Skills: pedagogy, curriculum design, student assessment

[0114] Software: Knewton, Edmentum

[0115] Replaceable work items: student progress tracking, basic feedback generation, course content recommendation

[0116] 9. Logistics and Supply Chain Manager

[0117] Virtual robots: inventory optimization, demand forecasting, transportation route planning

[0118] Skills: Supply chain management, logistics planning, data analysis

[0119] Software: Blue Yonder, SAP Ariba

[0120] Work items that can be replaced: Inventory level monitoring, transportation scheduling, supplier evaluation

[0121] 10. Marketing Expert

[0122] Virtual robots: customer segmentation, advertising optimization, market trend prediction

[0123] Skills: Market analysis, digital marketing, brand management

[0124] Software: Google Analytics, HubSpot, Salesforce Pardot

[0125] Work projects that can be replaced: market research, customer behavior analysis, advertising effect monitoring

[0126] Step 104 mainly involves collecting and understanding the work habits of the simulated objects by analyzing their behaviors when performing work items during the process of the simulated objects performing work items. The virtual robot records the operation data of the simulated objects on the terminal (such as a computer, workstation) in the background, which may include keyboard input, mouse clicks, application usage frequency, operation time, etc. From the large amount of terminal data collected, filter out the data directly related to the selected work item. This may involve identifying specific steps in the files, applications or workflows related to the project. Perform in-depth analysis on the filtered project data to identify the common operation patterns, preferences and habits of the simulated objects. For example, they may tend to use specific shortcut keys, perform tasks in a specific order, or perform certain operations at specific times.

[0127] In some specific embodiments, the process of acquiring project data specifically includes: real-time monitoring of the terminal operations of the simulated object when executing a specific work project to obtain terminal data, where the terminal operations include keyboard input, mouse movement, clicks, and window management virtual robot program interactions; collecting the timestamp, sequence, and frequency of each terminal operation to form a corresponding operation log, and incorporating the operation log into the terminal data; filtering out data directly related to the selected work project from the terminal data, and eliminating irrelevant data through identification methods including keyword search, application identifier identification, or specific operation mode identification to obtain project data.

[0128] Among them, the virtual robot will monitor the operations of the simulated object on the terminal in real time when the simulated object executes the work project, including but not limited to keyboard input, mouse movement, clicks, windows opened or closed, applications and functions used, etc. Keyboard input: record every character typed, including shortcut key combinations. Mouse movement: track the movement trajectory of the mouse pointer. Click events: capture clicks and double clicks of the left mouse button, right mouse button, and scroll wheel. Window management: track the opening, closing, maximization, minimization, and switching of windows. Application interaction: record the startup, closing, menu selection, and function call of applications. Collect the timestamps, sequence, and frequency of these operations to form a detailed operation log. The timestamp is used to capture the exact time when the operation occurs; the sequence records the order of operations; and the frequency counts the number of repetitions of the same operation. This information is integrated into a detailed operation log and becomes part of the terminal data. Filter out data directly related to the selected work project from the large amount of terminal data collected. Specifically, it involves using keyword search, application identifiers, or specific operation modes to identify activities closely related to the project. Keyword search: find keywords or phrases related to the work project, such as project names, specific file paths, or commands. Application identifier identification: Use the application's unique identifier (such as process ID, software name) to identify which operations are related to the current work item. Specific operation mode identification: Analyze the operation sequence and identify the operation mode or process that is closely related to the work item, such as opening a specific folder, executing a series of commands, or adjusting the window layout. Eliminate operation data that is not related to the work item to reduce the complexity of analysis and improve efficiency.

[0129] In some embodiments, the process of acquiring habit data specifically includes: using a pre-trained habit analysis model to analyze project data, performing cluster analysis on similar operations, and combining a preset long short-term memory network to analyze related operations in the time dimension, to obtain the habit patterns of the simulated object when executing work projects, the habit patterns include the time points for switching software on and off, the specific order of processing data, tool options, interface layout, and shortcut key usage; based on the habit pattern analysis, the most common operation sequence of the simulated object when executing work projects, the operation sequence includes the normal working sequence of the virtual object when executing work projects, as well as the decision-making mode and corresponding working sequence when facing anomalies; summarizing the habit patterns and operation sequences, and encoding them into a format that can be parsed by the virtual robot to obtain habit data.

[0130] When performing data analysis, use data mining and machine learning techniques to identify the habitual patterns of simulation subjects when performing projects. For example, analyze at what point in time they tend to launch specific software, or the specific order in which they process data. At the same time, learn the preferences of simulation subjects when handling work projects, such as specific tool options, interface layout, or shortcut key usage. Cluster analysis is used to group similar operations together and identify recurring behavioral patterns of simulation subjects when performing work projects. For example, if the simulation subject always opens a browser and logs in to a specific website before starting a project, this sequence of actions will be clustered together as a habitual pattern. Long short-term memory network (LSTM) is a special type of recurrent neural network that is good at processing time series data and can remember long-term dependencies. When analyzing project data, LSTM is used to understand the time sequence of simulation subjects when performing operations and identify time-related habitual patterns. For example, LSTM can help identify the habit of simulation subjects opening email clients at a specific time every day, or performing data backup operations at a fixed time every week.

[0131] Habitual patterns include: the time to turn on and off software, such as opening the mailbox every morning and closing all work-related software before leaving work; the specific order of processing data, such as importing data first, then cleaning, then analyzing, and finally generating reports; tool options and interface layout, such as the tool configuration and work interface layout preferred by the simulation object; shortcut key usage. When identifying behavioral habits, identifying the most common operation sequence of the simulation object when performing work items helps the virtual robot learn the natural working order and abnormal working order of the workflow. Analyze the decision-making mode of the simulation object when facing choices, such as how to deal with data anomalies. Based on the acquisition of habitual patterns, further analyze the most common operation sequence of the simulation object when performing work items. This includes not only normal operating procedures, but also decision-making patterns and coping strategies when encountering abnormal situations. For example, if an error is found when importing data, the simulation object may have a fixed set of processing procedures, such as checking the data source, modifying the format, and trying to import again. All analyzed habitual patterns and operation sequences are summarized to form a comprehensive view, which will serve as the basis for virtual robot learning and imitation.

[0132] Finally, the collected habit data is converted into a structured form for the virtual robot to understand and apply. This may include encoding the habit data into a format that can be parsed by the model, such as a decision tree, rule set, or input to a neural network. The analyzed habit data is fed back to the virtual robot to optimize its execution logic chain to make it closer to the actual operating habits of the simulated object. In addition, the virtual robot is designed to be able to learn continuously and continuously improve its understanding of the simulated object's habits over time.

[0133] In some specific embodiments, the virtual robot is given the permission to start background screen recording when the software is running, and the terminal data is obtained by recording the screen of the simulated object when it executes the work item on the terminal within a certain period of time; the terminal data is analyzed frame by frame, and whether there is a difference between two adjacent frames; the frame images with differences are marked as change frames, and the change areas in all change frames are searched; based on the running logic of the software, the operation behavior of the simulated object and its corresponding interface changes are analyzed from the change area, and the project data of the time period is obtained after confirmation by the simulated object; the project data of each time period is summarized, and the basis data for the operation behavior of the simulated object is analyzed according to the running logic of the software and the interface changes corresponding to the operation behavior, and the habit data of the simulated object is obtained by combining the basis data and the corresponding operation behavior.

[0134] Specifically, the virtual robot needs to request background screen recording permissions from the operating system or application, which usually involves access to specific APIs. To configure the screen recording function in the virtual robot, you need to pre-set recording parameters, such as recording frequency, recording area, storage location, etc. At the same time, ensure that the use of screen recording permissions complies with data protection and privacy regulations. Start the screen recording within the preset time period, ensure that it covers the time period when the simulated object performs the work project, and store the screen recording data in a safe location for subsequent analysis. Convert the screen recording file into an analyzable format, use video editing software to capture the part of the work project execution, and remove irrelevant clips. Preliminarily watch the screen recording and manually mark key events and operations, such as start and end time, software used, operation sequence, etc. Read the screen recording file and analyze the image data frame by frame, which involves computer vision technology. Use computer vision and machine learning tools to automatically analyze the screen recording data to identify mouse tracks, keyboard heat maps, interface interactions, etc. For example, you can use OpenCV for image processing, or use deep learning models to identify operations on the screen. Compare two adjacent frames of images to identify the areas in the image that have changed, which is specifically achieved through pixel difference algorithms. Locate the image areas that have changed in the changed frames, which are often related to the operations of the simulated object. Based on the changes in the software's operating logic and interface elements, the simulation object's operation behavior, such as clicking a button, entering text, etc., is inferred. The common operation modes, preference settings, specific steps in the workflow, and behavioral habits at decision points of the simulation object are found through analysis tools. These changes may require confirmation or verification of the simulation object to ensure that the analyzed operation behavior is correct. Summarize the operation behavior and interface changes, and analyze the basis for the simulation object to make operations, such as the events responded to, the operation conditions triggered, etc. Through statistical and machine learning methods, the simulation object's habitual patterns, such as common operation sequences, preference settings, decision tendencies, etc., are identified. Integrating the basis data and operation behavior into the habit data of the simulation object requires building a data model or database to store and manage this information. Marking frames with differences as change frames helps to focus on analyzing the operation moments of the simulation object. Based on computer vision and behavior analysis, through screen recording and detailed data analysis, the virtual robot can more accurately capture the subtle habits of the simulation object when performing work items, so that it can be closer to human behavior when imitating, and improve the usability and acceptance of the automation system.

[0135] The terminal data collected in step 104 covers a variety of behavioral traces of the simulated object when executing the work project. The comprehensive collection of these data helps the virtual robot to more accurately analyze and understand the habits of the simulated object. In some specific embodiments, the terminal data includes: the timestamp triggered by the terminal input device and the instructions sent, the log file of the software, the editing of the file and its timestamp, and the access record of the website. The logging function of the operating system or a third-party log collection tool can be used to automatically record the above-mentioned types of activities. Special desktop monitoring software can also be used to comprehensively track and record all activities of the simulated object on the terminal. Record the timestamp of each keyboard stroke and mouse action, including keystrokes, scrolling, clicking, etc., and the corresponding action instructions. These data can reveal the operation rhythm, preferences and efficiency of the simulated object. Collect the log files generated when the software is running. These files record the running status, error messages, function calls, etc. of the software, which helps to understand the specific operations and problems in the use of the software. Record the timestamps of operations such as creation, editing, and saving of files, as well as the specific changes made. This is very important for understanding the workflow and decision-making process, especially when the work involves document or code editing. Collect website access records, including access time, browsed pages, dwell time, etc. This can be helpful in analyzing the online behavior of the person being simulated, especially for job roles that require web research or documentation.

[0136] Step 105 is about integrating the habit data collected and analyzed previously into the execution logic of the virtual robot so that the virtual robot can imitate the habits of the simulated object to execute the work project. In step 104, the habit data of the simulated object when executing the work project has been collected and analyzed, including the operation sequence, preference settings, decision-making mode, etc. In this step, it is necessary to convert these habit data into a logical chain that the virtual robot can understand and execute. Specifically, it includes: mapping habits to logical chains: converting the habitual behavior of the simulated object into the logical instructions of the virtual robot. For example, if the simulated object always executes a certain function immediately after opening a certain software, then in the logical chain of the virtual robot, these two steps should be closely connected. Constructing a decision tree or state machine: Based on the habit data, construct a decision tree or state machine, which will guide the virtual robot to make the same or similar decisions as the simulated object when encountering similar situations. List all permissions required by the simulated object when executing the work project, including but not limited to file access, network connection, application control, etc. In the operating environment of the virtual robot, assign the same permissions to the virtual robot as the simulated object to ensure that it can access all necessary resources. In addition, it is necessary to ensure that the execution environment of the virtual robot is consistent with the working environment of the simulated object, including software version, data source, workspace configuration, etc. Start the virtual robot and let it start executing the work item according to the customary logic chain. The virtual robot should be able to independently handle the work item, including data collection, processing, decision-making and result output.

[0137] When a virtual robot executes a work item, there are three main situations: when it encounters a completely matching requirement, when it encounters a similar but not completely identical requirement, and when it encounters a requirement that is neither identical nor similar. The handling measures are as follows: Figure 3 shown.

[0138] In some embodiments, when the virtual robot is executing a work project, specifically, when the requirements of the work project are the same as one or more requirements recorded in the project data, the virtual robot is directly caused to repeat the execution according to the processing method recorded in the project data. When the requirements of the work project are different from all the requirements recorded in the project data, but are similar to one or more requirements, the virtual robot is caused to identify the differences by comparing the requirements of the current work project with the features of similar requirements in the project data, and intelligently adjust the corresponding links in the habit logic chain based on the differences to achieve intelligent execution. Exemplarily, a memory library or knowledge graph is established to record various requirements and solutions that have been processed in the past. When encountering the same requirements, the virtual robot can directly refer to the processing method in this knowledge base without recalculation or analysis.

[0139] When the work project requirements faced by the virtual robot are completely consistent with one or more requirements recorded in the project data it stores, the robot will take the most direct action path - that is, repeat the execution according to the existing processing methods in the project data. In this case, the virtual robot does not need additional calculations or decisions, because it has mastered the correct process of how to handle such requirements in past learning or programming. For example, if the project data records the complete process of processing invoices, including the steps of receiving, verifying, entering the system, paying and archiving, then when a new invoice processing request arrives and its requirements are completely consistent with the records, the virtual robot will automatically execute according to this process without human intervention.

[0140] When the work item requirements encountered by the virtual robot are not exactly the same as all the requirements recorded in the project data, but are similar to some of them, it will not simply refuse to execute or blindly apply the old processing methods, but will enter a more complex intelligent decision-making process. First, the virtual robot will compare the requirements of the current work item with the characteristics of similar requirements in the project data and identify the differences between the two. For example, if the previous invoice processing cases were all for domestic suppliers, and the current requirement is to process an invoice for an international supplier, then the attribute "international" is the difference. Next, based on the identified differences, the virtual robot will intelligently adjust the corresponding links in its habitual logic chain to more appropriately execute the current work item. The habitual logic chain is a series of organized steps followed by the virtual robot when performing tasks, which can change dynamically according to specific circumstances.

[0141] For example, an advanced similarity assessment algorithm (such as a natural language processing model based on deep learning) is used to identify and compare the similarity between current requirements and historical requirements. Key features such as keywords, process steps, target results, etc. are extracted from the requirements, and then compared with the requirements features stored in the knowledge base to identify similarities. A special intelligent adjustment module is designed that can automatically adjust the existing logic chain according to the identified differences, including parameter fine-tuning, process modification, or introduction of new decision nodes.

[0142] In the above example, the virtual robot might intelligently adjust its processing flow, such as adding currency conversion, considering international tax regulations, using different payment methods, etc. to ensure that the task is completed accurately even when processing international supplier invoices.

[0143] In some embodiments, when the requirements of a work project are neither the same nor similar to all the requirements recorded in the project data, the virtual robot analyzes the requirements of the current work project, constructs a new initial logic chain, merges the habit data into the new initial logic chain to obtain a new habit logic chain, and executes the work project in accordance with the new habit logic chain in a manner that imitates the simulated object in the face of new requirements. Exemplarily, an expert system is integrated into the virtual robot, which contains the knowledge and experience of domain experts and is used to guide the virtual robot's decision-making process when facing unknown requirements. Using machine learning and reinforcement learning techniques, the virtual robot can learn the best solution to new requirements through trial and error. Use a large amount of historical data to train the model so that it can recognize patterns and regularities to better respond to new requirements.

[0144] When the work project requirements encountered by the virtual robot are neither the same nor similar to all the requirements recorded in the project data, it means that the robot is facing an unprecedented challenge and needs to demonstrate a high degree of autonomy and innovation to deal with new situations. The virtual robot will first deeply analyze the requirements of the current work project and understand the core elements and goals of the task. The analysis of requirements specifically includes: Requirements interpretation: Parsing the work project requirements document and extracting key information, such as task objectives, data types involved, and expected output formats. Environmental perception: Identifying the applications, tools, and data sources required to execute the work project. Feasibility assessment: Determine whether the work project can be completed with existing skills and resources, or whether additional skill packages or data support are needed.

[0145] After understanding the requirements of the work item, the virtual robot will begin to build a new initial logic chain, which is the basic framework for executing the new task. This process may include: Task decomposition: decomposing the work item into a series of smaller, manageable subtasks. Process design: designing the order and method of completing these subtasks to form a preliminary execution process. Decision making: determining the decision points that may be encountered during the execution process and the corresponding processing strategies.

[0146] The virtual robot then merges the previously acquired data related to the simulated object's habits into a new initial logic chain in order to mimic the simulated object's possible behavior when faced with new requirements. First, the habit patterns are embedded into key nodes of the logic chain, such as specific tool options, interface layout, and shortcut key usage. Second, the decision-making patterns of the simulated object when faced with choices are incorporated into the logic chain to guide the robot to make decisions under uncertainty. Through the above steps, the virtual robot constructs a new habit logic chain, which is an execution plan that combines the new task requirements and the simulated object's habits. This logic chain not only includes the steps to complete the task, but also incorporates the simulated object's habits and preferences when dealing with similar or different situations. Finally, the virtual robot executes the work item according to the new habit logic chain, mimicking the execution method that the simulated object may take when faced with new requirements.

[0147] After the virtual robot starts to execute the work project, its execution needs to be monitored to ensure that it can accurately imitate the habits of the simulated object and optimize according to the actual situation. Collect data on the virtual robot during the execution process, including execution time, error rate, resource consumption, etc. Based on the monitoring data, analyze the execution efficiency and accuracy of the virtual robot, identify any deviations or deficiencies, and make necessary adjustments and optimizations to the habit logic chain. In some embodiments, it also includes: collecting feedback from actual users or stakeholders to understand whether the performance of the virtual robot meets expectations and whether there is room for improvement. Then, based on the feedback, iteratively improve the virtual robot and continuously optimize the habit logic chain to make it more in line with the habits and workflow of the simulated object.

[0148] This application proposes a work role simulation system based on a virtual robot, which systematizes the above-mentioned work role simulation method based on a virtual robot to make it more practical. A module schematic diagram of a work role simulation system based on a virtual robot is shown in the attached figure. Figure 4 The specific plan is as follows:

[0149] A work role simulation system based on a virtual robot, comprising:

[0150] The role determination unit 1 is used to select a specific simulation object under a certain work role and analyze the role information, work responsibilities and skill information of the simulation object;

[0151] Model determination unit 2, used to select a virtual robot based on role information and job responsibilities, and add a skill software package corresponding to the skill information to the virtual robot, so that the virtual robot can call the skill software package to perform tasks;

[0152] The preprocessing unit 3 is used to select a work item that can be replaced and executed by the simulated object at the terminal in the work responsibilities, analyze the execution process of the work item and the software involved, determine the permissions required for the virtual robot to execute the work item, and build an initial logical chain of the work item based on the execution process;

[0153] The data acquisition unit 4 is used to acquire the terminal data of the simulated object when the simulated object executes the work project at the terminal through the virtual robot, and to filter out the project data related to the work project from the terminal data, and to acquire the habit data of the simulated object by analyzing the project data;

[0154] The simulation unit 5 is used to couple the habit data to the initial logic chain to obtain the habit logic chain, and to grant the virtual robot the same authority as the simulation object, so that the virtual robot can execute the work item according to the habit logic chain by imitating the habits of the simulation object.

[0155] The present application proposes a virtual robot for implementing any of the above-mentioned work role simulation methods based on virtual robots.

[0156] The present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method for simulating a work role based on a virtual robot. A method for simulating a work role based on a virtual robot is applied to a computer program product for easy execution.

[0157] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for simulating a work role based on a virtual robot as described above.

[0158] The computer storage medium of the present application may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. The present application applies a method for simulating a work role based on a virtual robot to a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the clothing simulation method provided by the present application are implemented, which is simple and fast, easy to store, and not easy to lose.

[0159] This application proposes a method, system and virtual robot for simulating work roles based on virtual robots. The virtual robot simulates the habits and workflow of specific simulated objects, imitates the decision-making mode, operation habits and preference settings of specific simulated objects, and provides highly personalized and customized services, thereby providing services that are more in line with personal style and improving user experience and satisfaction. When simulating the execution of repetitive and rule-defined tasks, the virtual robot can accurately follow the habitual logic chain and complete the task quickly and accurately, which can greatly improve efficiency and reduce errors caused by human negligence or fatigue.

[0160] Those skilled in the art should understand that the modules of the present application described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by program codes executable by a computer system, so that they can be stored in a storage system and executed by the computing system, 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. Thus, the present application is not limited to any specific combination of hardware and software.

[0161] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

[0162] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.

Claims

1. A method for simulating a work role based on a virtual robot, characterized in that: These include: Select a specific simulation object under a certain job role, and analyze the role information, job responsibilities and skill information of the simulation object; Selecting a virtual robot based on the role information and the job responsibilities, and adding a skill software package corresponding to the skill information to the virtual robot so that the virtual robot can call the skill software package to perform tasks; Selecting a replaceable work item that the simulated object executes at the terminal from the work responsibilities, parsing the execution process of the work item and the software involved, determining the authority required for the virtual robot to execute the work item, and constructing an initial logical chain of the work item based on the execution process; In the process of the simulated object executing the work item, the terminal data of the simulated object when executing the work item at the terminal is obtained through the virtual robot, and project data related to the work item is screened out from the terminal data, and habit data of the simulated object is obtained by analyzing the project data; The habit data is coupled to the initial logic chain to obtain a habit logic chain, and the virtual robot is given the same authority as the simulated object, so that the virtual robot imitates the habit of the simulated object according to the habit logic chain to perform the work item; When the requirements of the work project are neither the same nor similar to all the requirements recorded in the project data, the virtual robot analyzes the requirements of the current work project, constructs a new initial logic chain, merges the habit data into the new initial logic chain to obtain a new habit logic chain, and executes the work project in a manner that the simulated object may execute when facing new requirements according to the new habit logic chain; The virtual robot, when executing the work item, specifically includes: When the requirements of the work item are the same as one or more requirements recorded in the project data, the virtual robot is made to repeat the execution directly according to the processing method recorded in the project data; When the requirements of the work project are different from all the requirements recorded in the project data but are similar to one or more requirements, the virtual robot identifies the differences by comparing the requirements of the current work project with the features of similar requirements in the project data, and intelligently adjusts the corresponding links in the habitual logic chain based on the differences to achieve intelligent execution.

2. The work role simulation method according to claim 1, characterized in that: Granting the virtual robot the authority to start background screen recording when the software is running, and obtaining terminal data by recording the screen of the simulated object when it executes the work item at the terminal within a certain period of time; Analyzing the terminal data frame by frame, and comparing whether there is a difference between two adjacent frames of images; Mark the frame images with differences as changed frames, and find the changed areas in all changed frames; Based on the running logic of the software, the operation behavior of the simulation object and its corresponding interface change are analyzed from the change area, and the project data of the time period is obtained after confirmation by the simulation object; Summarize the project data of each time period, analyze the basis data of the simulated object's operation behavior according to the software's operating logic and the interface changes corresponding to the operation behavior, and obtain the habit data of the simulated object by combining the basis data and the corresponding operation behavior.

3. The work role simulation method according to claim 1, characterized in that: The virtual robot is composed of an artificial virtual robot and one or more functional models, and the artificial virtual robot can call each functional model and select the functional model based on the skill information; In a preset database, virtual robots divided by work roles are pre-stored. The role information of the virtual robots, including age, gender, and education level, can be customized and marked with skill labels of corresponding functional models; the basic skills required to complete the job responsibilities are determined, and based on the basic skills, virtual robots with corresponding skill labels are searched in the database.

4. The work role simulation method according to claim 1, characterized in that: The process of obtaining the project data specifically includes: Real-time monitoring of the terminal operation of the simulated object when executing a specific work item to obtain the terminal data, wherein the terminal operation includes keyboard input, mouse movement, click, and window management virtual robot program interaction; Collecting the timestamp, sequence and frequency of each terminal operation to form a corresponding operation log, and incorporating the operation log into the terminal data; Data directly related to the selected work item is screened out from the terminal data, and irrelevant data is eliminated through identification methods including keyword search, application identifier identification or specific operation mode identification to obtain project data.

5. The work role simulation method according to claim 1, characterized in that: The process of acquiring the habit data specifically includes: Analyze the project data using a pre-trained habit analysis model, perform cluster analysis on similar operations, and analyze the relevant operations in the time dimension using a preset long short-term memory network to obtain the habit pattern of the simulated object when executing the work project, wherein the habit pattern includes the time point of switching software on and off, the specific order of processing data, tool options, interface layout, and shortcut key usage; Analyze the most common operation sequence of the simulated object when executing the work item based on the habit pattern, wherein the operation sequence includes the normal working sequence of the virtual object when executing the work item, and the decision-making mode and corresponding working sequence when facing anomalies; The habit patterns and the operation sequences are summarized and encoded into a format parseable by a virtual robot to obtain the habit data.

6. The work role simulation method according to claim 1, characterized in that: The role information includes the position, age, gender, and education level of the simulated object; Said job duties include the daily tasks and responsibilities of the simulated subject; The skill information includes the skills possessed by the simulated object, the skills required for the job role, and the skills that the simulated object wants to have but does not have; The initial logic chain includes: the source of input data, data processing and analysis, decision-making logic, output result processing, and exception handling mechanism.

7. A work role simulation system based on a virtual robot, characterized in that: These include: A role determination unit, used to select a specific simulation object under a certain work role, and analyze the role information, work responsibilities and skill information of the simulation object; a model determination unit, configured to select a virtual robot based on the role information and the job responsibilities, and add a skill software package corresponding to the skill information to the virtual robot, so that the virtual robot can call the skill software package to perform a task; A preprocessing unit, used to select a replaceable work item to be executed by the simulated object at the terminal in the work responsibility, analyze the execution process of the work item and the software involved, determine the authority required for the virtual robot to execute the work item, and construct an initial logical chain of the work item based on the execution process; a data acquisition unit, configured to acquire, through the virtual robot, terminal data of the simulated object when the simulated object executes the work item at the terminal, filter out project data related to the work item from the terminal data, and acquire habit data of the simulated object by analyzing the project data; A simulation unit, used for coupling the habit data to the initial logic chain to obtain a habit logic chain, giving the virtual robot the same authority as the simulation object, so that the virtual robot can perform the work item according to the habit logic chain by imitating the habit of the simulation object; When the requirements of the work project are neither the same nor similar to all the requirements recorded in the project data, the virtual robot analyzes the requirements of the current work project, constructs a new initial logic chain, merges the habit data into the new initial logic chain to obtain a new habit logic chain, and executes the work project in a manner that the simulated object may execute when facing new requirements according to the new habit logic chain; The virtual robot, when executing the work item, specifically includes: When the requirements of the work item are the same as one or more requirements recorded in the project data, the virtual robot is made to repeat the execution directly according to the processing method recorded in the project data; When the requirements of the work project are different from all the requirements recorded in the project data but are similar to one or more requirements, the virtual robot identifies the differences by comparing the requirements of the current work project with the features of similar requirements in the project data, and intelligently adjusts the corresponding links in the habitual logic chain based on the differences to achieve intelligent execution.

8. A virtual robot, characterized in that: Used to implement the work role simulation method based on a virtual robot as described in any one of claims 1-6.