Digital employee creation method and system based on artificial intelligence

Abstract

The invention relates to the technical field of digital employees, and discloses a digital employee creation method and system based on artificial intelligence, and the method comprises the steps: obtaining and analyzing post data, generating a digital employee portrait and a dynamic knowledge base for creating digital employees based on the post data, and creating the digital employees based on the digital employee portrait and the dynamic knowledge base. The system corresponds to the method. According to the method, the digital employee portrait including the skill map and the character feature model is generated through the post data, and the digital employee can dynamically adjust the skill weight based on the parameters in the character feature model by combining real-time updating of the dynamic knowledge base, so that deep cooperation of the skill and the character is realized; when a digital employee processes an instruction, the digital employee accurately calls a core skill and an associated skill, adapts to a personalized scene through character features, and meanwhile, depends on dynamic knowledge updating, the autonomous response and sustainable evolution ability of the digital employee to a complex business scene is enhanced, and the intelligent level and the actual business adaptation degree of the digital employee are effectively improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of digital employees, and particularly relates to a digital employee creation method and system based on artificial intelligence. BACKGROUND

[0002] In the prior art, the creation of digital employees focuses on the static configuration of skill characteristics, and the correlation between skill characteristics and personality characteristics in post data is insufficiently mined. Traditional methods often separate skill execution from personality characteristics, and skill weights are fixed, which makes it difficult to dynamically adjust the communication style and decision mode in the personality characteristic model. Meanwhile, the collaborative mechanism between the dynamic knowledge base and the personality characteristics is missing, which leads to poor skill calling and personality adaptation of digital employees when dealing with complex instructions, and the digital employees cannot realize personalized response by combining the communication style parameters and decision mode parameters, and cannot meet the demand for skill execution flexibility and personality matching degree in dynamic task scenarios.

[0003] A look board configuration method, device and equipment and storage medium are disclosed in Chinese patent application No. CN119376815A, a business processing method, device and equipment based on digital employees and storage medium are disclosed in Chinese patent application No. CN119597258A, and a dialogue robot construction method, system, device and storage medium are disclosed in Chinese patent application No. CN119621039A, all of which generate digital employees based on preset rules and fixed generation, which actually ignores the subjective judgment of the staff on the target post.

[0004] In view of the above, there is an urgent need for a new digital employee creation method based on artificial intelligence. SUMMARY

[0005] The application aims to provide a digital employee creation method and system based on artificial intelligence to solve the technical problems in the background art.

[0006] To achieve the above-mentioned purpose, the application discloses the following technical solutions:

[0007] In the first aspect, the application discloses a digital employee creation method based on artificial intelligence, which comprises the following steps:

[0008] Step 1: Obtain and analyze post data corresponding to a target post where a digital employee works, wherein the post data includes instruction characteristics, skill characteristics and personality characteristics, the instruction characteristics are used to represent instructions required to be processed by the target post, and the skill characteristics and the personality characteristics are used to represent skills and personality required to process the instructions;

[0009] Step two: generating a digital employee portrait for creating a digital employee based on the post data, the digital employee portrait including a skill map and a personality characteristic model, the skill map corresponding to the skill characteristics, and the personality characteristic model corresponding to the personality characteristics;

[0010] Step three: generating a dynamic knowledge base for creating a digital employee based on the post data and the digital employee portrait, the dynamic knowledge base being used to respond to the post data;

[0011] Step four: creating a digital employee based on the digital employee portrait and the dynamic knowledge base, the digital employee being configured to invoke skills, personality, and knowledge based on instructions of a target post to respond to the instructions.

[0012] As a preferred, the post data, in particular:

[0013] The historical operation log, cross-system interaction record, and user communication text corresponding to the instruction characteristics;

[0014] The professional knowledge graph, tool usage record, and task completion indicator corresponding to the skill characteristics;

[0015] The communication style label, decision-making tendency data, and emotional response mode corresponding to the personality characteristics.

[0016] As a preferred, the digital employee portrait, in particular:

[0017] The skill map includes core skills, associated skills, and corresponding skill weights; wherein the core skills and the associated skills are obtained by matching the instruction characteristics with the skill characteristics, and the skill weights are determined by the personality characteristic model;

[0018] The personality characteristic model is configured to determine the skill weights based on the communication style parameters, decision-making mode parameters, and emotional simulation parameters corresponding to the personality characteristics.

[0019] As a preferred, the dynamic knowledge base, in particular:

[0020] The basic business knowledge base stores standardized processes, industry standards, and common problem solving solutions related to the target post;

[0021] The knowledge update base is used to automatically expand knowledge nodes and associated relationships by real-time capturing of industry dynamic data and user feedback data;

[0022] The knowledge association graph is used to update the industry dynamic data and user feedback data captured by the knowledge update base to the basic business knowledge base based on the knowledge nodes and associated relationships expanded by the knowledge update base.

[0023] As preferred, the creation of the digital employee includes:

[0024] Based on the instruction features, the matched core skills and associated skills are extracted from the historical skill map;

[0025] The personality feature model is called to calculate the initial skill weights of the core skills and the associated skills by using the communication style parameters, the decision-making mode parameters and the emotional simulation parameters;

[0026] Based on the initial skill weights, an initial version of the skill map is generated, and the weight adjustment of the initial version of the skill map is performed in combination with the knowledge association relationship of the dynamic knowledge base to form an optimized skill map;

[0027] Through the personality feature model, the personality feature parameters are adjusted based on the optimized skill map to update the personality feature model;

[0028] Based on the updated personality feature model, the skill weights of the core skills and the associated skills are recalculated to form a final version of the skill map;

[0029] The final version of the skill map is associated with the dynamic knowledge base to construct a decision-making rule system of the digital employee;

[0030] Based on the decision-making rule system, the instruction response logic of the digital employee is configured to dynamically adjust the skill weights based on the parameters of the personality feature model after the creation of the digital employee, and to process the instructions according to the adjusted skill weights.

[0031] As preferred, based on the created digital employee, the method further includes:

[0032] Step four: task arrangement of the digital employee based on the dynamic knowledge base;

[0033] Step five: monitoring the work data of the digital employee corresponding to step three or step four, comparing the work data with the prediction data, and updating step three and step four based on the comparison result; wherein the work data is used to represent the processing of the digital employee to the instructions, and the prediction data is generated based on the adversarial sample.

[0034] As preferred, the task arrangement includes:

[0035] The dynamic knowledge base is optimized to generate a sub-task sequence that adapts to the skill map of the digital employee, and the sub-task sequence is determined based on the calling order of the knowledge in the dynamic knowledge base;

[0036] Based on the cross-system interface capability of the digital employee, the execution subject and the collaboration timing of each sub-task are allocated;

[0037] Adjust the task priority and resource allocation strategy in real time according to the update content of the dynamic knowledge base.

[0038] As preferred, the work data includes: task completion rate of digital employees, instruction response time, cross-system interaction error rate; knowledge calling accuracy of dynamic knowledge base, update delay time length; matching degree of skill characteristics in digital employee portrait and actual task demand, user acceptance of personality characteristics.

[0039] As preferred, the result updating steps three and four based on comparison include:

[0040] When the deviation between the work data and the prediction data exceeds a preset threshold, adjust the weight and association relationship of the knowledge nodes in the dynamic knowledge base;

[0041] Update the skill graph and personality characteristic model of the digital employee portrait based on the deviation;

[0042] Update the priority algorithm and cross-system collaboration strategy of the task arrangement based on the deviation.

[0043] In a second aspect, the present application discloses a digital employee creation system based on artificial intelligence, which is suitable for the digital employee creation method based on artificial intelligence as described above, and the system comprises:

[0044] A post data analysis module is configured to acquire and analyze post data corresponding to a target post of a digital employee, wherein the post data includes instruction characteristics, skill characteristics, and personality characteristics, the instruction characteristics are used to represent instructions required to be processed by the target post, and the skill characteristics and the personality characteristics are used to represent skills and personality required to process the instructions;

[0045] A digital employee portrait generation module is configured to generate a digital employee portrait for creating a digital employee based on the post data, wherein the digital employee portrait includes a skill graph and a personality characteristic model, the skill graph corresponds to the skill characteristics, and the personality characteristic model corresponds to the personality characteristics;

[0046] A dynamic knowledge base generation module is configured to generate a dynamic knowledge base for creating a digital employee based on the post data and the digital employee portrait, wherein the dynamic knowledge base is used to respond to the post data;

[0047] A digital employee creation module is configured to create a digital employee based on the digital employee portrait and the dynamic knowledge base, and the digital employee is configured to call skills, personality, and knowledge based on instructions of a target post to respond to the instructions.

[0048] Beneficial effects: the digital employee creation method and system based on artificial intelligence provided by the application generate a digital employee portrait including a skill map and a personality characteristic model through multi-dimensional analysis of post data, and combine a dynamic knowledge base real-time updating mechanism, so that the digital employee can dynamically adjust the skill weight based on the communication style, decision mode and other parameters in the personality characteristic model, realize the deep cooperation of skills and personality, and break through the limitation of the separation of skills and personality, so that the digital employee can accurately call core skills and associated skills when processing instructions, and can also adapt to personalized scenarios through personality characteristics, improve the flexibility and adaptability of task processing, and at the same time, rely on the dynamic knowledge updating mechanism to enhance the autonomous response and continuous evolution ability of the digital employee to complex business scenarios, effectively improve the intelligent level and actual business adaptability of the digital employee. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0050] Figure 1 The flowchart of the digital employee creation method based on artificial intelligence provided by the embodiments of the present application is shown in the figure.

[0051] Figure 2 The structural diagram of the digital employee creation system based on artificial intelligence provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0053] In this paper, the term "comprising" is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the elements defined by the statement "comprising" do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0054] In the creation of digital employees, it is usually set based on the basic rules of the target post, resulting in the solidification of digital employees. To solve this problem of solidification, the embodiment discloses a digital employee creation method based on artificial intelligence as shown in Figure 1 The method comprises the following steps:

[0055] Step one: obtaining and analyzing post data corresponding to the target post of the digital employee, the post data including instruction features, skill features and personality features, the instruction features being used to represent the instructions required to be processed by the target post, the skill features and the personality features being used to represent the skills and personality required to process the instructions;

[0056] Step two: generating a digital employee portrait for creating a digital employee based on the post data, the digital employee portrait including a skill map and a personality feature model, the skill map corresponding to the skill features, and the personality feature model corresponding to the personality features;

[0057] Step three: generating a dynamic knowledge base for creating a digital employee based on the post data and the digital employee portrait, the dynamic knowledge base being used to respond to the post data;

[0058] Step four: creating a digital employee based on the digital employee portrait and the dynamic knowledge base, the digital employee being configured to call skills, personality and knowledge based on the instructions of the target post to respond to the instructions.

[0059] Through the above, by deeply binding the skill features and the personality features, the digital employee can not only call core skills and associated skills, but also optimize the skill execution logic through the communication style, decision mode and other parameters in the personality feature model to realize the collaborative response of skills and personality. At the same time, combined with the real-time updating mechanism of the dynamic knowledge base, the digital employee can adaptively adjust the skill weight and execution strategy according to the personality features, improve the adaptability to complex scenarios, solve the mechanical response problem caused by the separation of skills and personality in the prior art, and enhance the scene adaptability and decision flexibility of the digital employee.

[0060] In view of the problem that the post data is often integrated generally or limited to certain fixed rules, without specific data carriers corresponding to the instruction features, the skill features and the personality features respectively, resulting in the fuzzy association logic of skills and personality, which is difficult to support the accurate call of the digital employee to the post data, the embodiment improves the data basis of the digital employee creation based on the accurate selection of the post data.

[0061] Specifically, the post data specifically includes:

[0062] The historical operation logs, cross-system interaction records and user communication texts corresponding to the instruction features;

[0063] The professional knowledge graph, tool usage records and task completion indicators corresponding to the skill features;

[0064] The personality characteristics correspond to the communication style label, decision-making tendency data, and emotional response mode.

[0065] Through the above, by clearly defining the specific data corresponding to the instruction characteristics, skill characteristics, and personality characteristics in the post data, a precise data basis is provided for the cooperation of the skill graph and the personality characteristic model. Through the above division, the association logic of skill characteristics and personality characteristics is clearer, ensuring that the skill calling and personality adaptation are more explicit during the subsequent creation of digital employees, and the utilization accuracy and scene adaptability of digital employees for post data are improved.

[0066] Existing digital employee creation is generally directly based on rules. These rules are a simple summary of actual employees when handling instructions, which leads to the creation of digital employees being fixed and flawed from the beginning. With the development of profiling technology, profiling employees on various target posts has become a reality. However, if profiling is only done from a skill perspective, the creative selection and application of skills by employees due to their personality are ignored. The specific manifestation is that digital employee profiling often separates skill characteristics and personality characteristics, and skill weights are determined only by static rules without dynamic adjustment in combination with communication style, decision-making mode, and other parameters in the personality characteristic model, leading to insufficient skill calling and personality adaptation, making it difficult to cope with personalized scenarios. To solve the above problems, the embodiment optimizes the profiling of digital employees through existing profiling technology, feature extraction technology, and machine learning technology.

[0067] Specifically, the digital employee profiling is as follows:

[0068] The skill graph includes core skills, associated skills, and corresponding skill weights. The core skills and associated skills are obtained based on matching skill characteristics from instruction characteristics, and the skill weights are determined by the personality characteristic model.

[0069] The personality characteristic model is configured to determine the skill weights based on the communication style parameters, decision-making mode parameters, and emotional simulation parameters corresponding to the personality characteristics.

[0070] Through the above, by clearly defining the matching logic of core skills and associated skills in the skill graph and the personality characteristic model dependency of skill weights, the skill calling of digital employees is deeply bound to personality characteristics. Compared with the design of skill and personality separation in the prior art, the skill weights in this scheme are dynamically determined by the communication style parameters, decision-making mode parameters, and emotional simulation parameters in the personality characteristic model, realizing a cooperative mechanism of skill execution and personality adaptation, allowing digital employees to flexibly adjust skill weights based on personality characteristic parameters when calling core skills and associated skills, ensuring the accuracy of skill calling and improving the individualization and flexibility of scene response through personality characteristic adaptation, solving the mechanical execution problem caused by the separation of skill and personality.

[0071] The knowledge base solves the problem of knowledge required by digital employees when processing instructions. The existing dynamic knowledge base often has problems such as loose association between the basic library and the updated data, lagging update, lack of linkage mechanism between knowledge node expansion and basic library update, and poor timeliness of knowledge response. To solve the above problems, the embodiment optimizes the knowledge base required by digital employees based on the existing knowledge base technology.

[0072] Specifically, the dynamic knowledge base, specifically:

[0073] The basic business knowledge base stores standardized processes, industry standards and common problem solving solutions related to target posts;

[0074] The knowledge update library is used to automatically expand knowledge nodes and associated relationships by real-time grabbing of industry dynamic data and user feedback data;

[0075] The knowledge association graph is used to update the industry dynamic data and user feedback data grabbed by the knowledge update library to the basic business knowledge base based on the knowledge nodes and associated relationships expanded by the knowledge update library.

[0076] Through the above, by constructing the cooperative mechanism of the basic business knowledge base, the knowledge update library and the knowledge association graph, the new knowledge is realized to be included in the basic library in real time, the knowledge node association is strengthened, the problems of knowledge update lag and weak association in the prior art are solved, and the response efficiency of the dynamic knowledge base to post data is improved, thereby providing real-time and accurate knowledge support for digital employees.

[0077] Under the condition that the creation of digital employees lacks the association between skills and personality, the embodiment introduces skill weight calculation to realize dynamic adjustment of skills combined with personality characteristic parameters, improve the skill calling and personality adaptation, and optimize the response to personalized scenarios.

[0078] Specifically, the creation of digital employees includes:

[0079] Based on the instruction characteristics, the matching core skills and associated skills are extracted from the historical skill graph;

[0080] The personality characteristic model is called, and the initial skill weight of the core skills and associated skills is calculated by using the communication style parameter, the decision mode parameter and the emotion simulation parameter;

[0081] Based on the initial skill weight, an initial version of the skill graph is generated, and the weight of the initial version of the skill graph is adjusted based on the knowledge association relationship of the dynamic knowledge base to form an optimized skill graph;

[0082] The personality characteristic parameters are adjusted based on the optimized skill graph by the personality characteristic model, and the personality characteristic model is updated;

[0083] recompute the skill weights of the core skills and the associated skills based on the updated personality characteristic model, to form a final version of the skill map;

[0084] associate map the final version of the skill map with the dynamic knowledge base, to construct a decision rule system of the digital employee;

[0085] based on the decision rule system, configure the instruction response logic of the digital employee, so that the digital employee dynamically adjusts the skill weights based on the parameters of the personality characteristic model after being created, and processes the instructions according to the adjusted skill weights.

[0086] By the above, by deeply binding the creation of the digital employee with the personality characteristic model, the weight calculation of the core skills and the associated skills directly relies on personality parameters such as communication style and decision mode, realizing real-time collaboration of skill calling and personality characteristics. When dynamically adjusting the skill weights, the skill execution logic is optimized in combination with the personality characteristic model parameters, solving the problem of insufficient scene adaptability caused by the separation of skills and personality, and improving the flexibility and accuracy of the digital employee in personalized task processing.

[0087] For the deployment problem of the created digital employee, the existing technology is generally deployed separately, which is not conducive to the continuous development of instructions, and lacks an updating mechanism, resulting in the need for periodic updating of the digital employee in the background after going online, thereby constraining the application of the digital employee. To solve this problem, the present embodiment uses the calling order of knowledge and the existing GAN adversarial network generation technology to arrange tasks and adaptively update multiple digital employees.

[0088] Specifically, based on the created digital employee, the method further includes:

[0089] Step four: task arrangement of the digital employee based on the dynamic knowledge base;

[0090] Step five: monitor the work data of the digital employee corresponding to step three or step four, compare the work data with the prediction data, and update step three and step four based on the comparison result; wherein the work data is used to represent the processing of the digital employee to the instructions, and the prediction data is generated based on the adversarial sample.

[0091] By the above, through the closed-loop design of task arrangement and work data monitoring, the digital employee task processing is dynamically adapted to the skill and knowledge base of the digital employee. The prediction data based on the adversarial sample generation is compared with the work data, the skill map optimization and knowledge base updating are accurately performed, the collaborative evolution ability of tasks, skills and knowledge is strengthened, and the adaptability and autonomous evolution efficiency of the digital employee to complex scenes are improved.

[0092] In the prior art, even if there is task arrangement, it often ignores the adaptability of dynamic knowledge base and skill map, the sub-task allocation does not combine the cross-system interface capability of digital employees, and lacks real-time adjustment mechanism, resulting in low task execution efficiency and unreasonable resource allocation. To solve this problem, the embodiment determines the rules of task arrangement based on the calling sequence of knowledge in the dynamic knowledge base,

[0093] Specifically, the task arrangement includes:

[0094] Optimizing the dynamic knowledge base to generate a sub-task sequence adapted to the skill map of the digital employee, the sub-task sequence being determined based on the calling sequence of knowledge in the dynamic knowledge base;

[0095] Based on the cross-system interface capability of the digital employee, the execution subject and collaboration timing of each sub-task are allocated;

[0096] Real-time adjustment of task priority and resource allocation strategy according to the update content of the dynamic knowledge base.

[0097] Through the above, by optimizing the dynamic knowledge base to generate a sub-task sequence adapted to the skill map, and allocating the execution subject based on the cross-system interface capability, precise matching of tasks and skills is achieved. Real-time adjustment of priority according to the knowledge base update improves task processing flexibility and resource utilization, solves the problem of disconnection between task arrangement and skills and knowledge in the prior art, and strengthens the collaborative execution capability of digital employees.

[0098] In the embodiment, specifically, the work data includes: task completion rate, instruction response time, cross-system interaction error rate of the digital employee; knowledge calling accuracy, update delay time length of the dynamic knowledge base; matching degree of skill characteristics in the digital employee portrait and actual task demand, user acceptance of personality characteristics.

[0099] Through the above, the collection content of the work data is provided, which provides a technical basis for the generation of prediction data, thereby providing a data basis for the comparison of work data and prediction data.

[0100] The deviation processing of work data and prediction data often adjusts the knowledge base or task strategy in isolation, without updating the skill map and personality characteristic model of the digital employee in linkage, resulting in fragmented adjustment and insufficient collaboration. To solve this problem, the embodiment uses existing data processing technologies, such as data fitting to determine a threshold, to analyze and utilize the work data and prediction data.

[0101] Specifically, the updating steps three and four based on the comparison result include:

[0102] When the deviation between the work data and the prediction data exceeds the preset threshold, the weight and the association relationship of the knowledge node in the dynamic knowledge base are adjusted;

[0103] Updating the skill graph and personality characteristic model of the digital employee portrait based on bias;

[0104] Updating the priority algorithm of task scheduling and cross-system collaboration strategy based on bias.

[0105] Through the above, the collaborative updating of the dynamic knowledge base, digital employee portrait and task scheduling triggered by bias realizes the closed loop of data bias, skill personality optimization and task strategy adjustment. It not only ensures the adaptation of knowledge node weight and skill graph, but also synchronously optimizes the skill execution logic through the personality characteristic model, solves the problem of isolated adjustment in the prior art, and improves the collaborative response ability and execution precision of digital employees to dynamic scenarios.

[0106] The second aspect of the embodiment discloses an artificial intelligence-based digital employee creation system as shown in Figure 2 The system is applicable to the artificial intelligence-based digital employee creation method described above, and the system comprises:

[0107] A post data analysis module acquires and analyzes post data corresponding to a target post worked by the digital employee, the post data including instruction characteristics, skill characteristics and personality characteristics, the instruction characteristics being used to represent instructions required to be processed by the target post, and the skill characteristics and personality characteristics being used to represent skills and personality required to process the instructions;

[0108] A digital employee portrait generation module generates a digital employee portrait for creating the digital employee based on the post data, the digital employee portrait including a skill graph and a personality characteristic model, the skill graph corresponding to the skill characteristics, and the personality characteristic model corresponding to the personality characteristics;

[0109] A dynamic knowledge base generation module generates a dynamic knowledge base for creating the digital employee based on the post data and the digital employee portrait, the dynamic knowledge base being used to respond to the post data;

[0110] A digital employee creation module creates the digital employee based on the digital employee portrait and the dynamic knowledge base, the digital employee being configured to invoke skills, personality and knowledge based on instructions of the target post to respond to the instructions.

[0111] It should be noted that the artificial intelligence-based digital employee creation system of the embodiment corresponds to the artificial intelligence-based digital employee creation method described above. Therefore, the contents not specifically described in the artificial intelligence-based digital employee creation system of the embodiment can be, but are not limited to, functional definitions, working principles and technical effects, and can all refer to the descriptions in the artificial intelligence-based digital employee creation method described above. This text will not be repeated here.

[0112] To sum up, the artificial intelligence-based digital employee creation method and system of the embodiment generates a digital employee portrait including a skill map and a personality characteristic model through multi-dimensional analysis of post data, and combines a dynamic knowledge base real-time updating mechanism, so that the digital employee can dynamically adjust the skill weight based on the communication style, decision mode and other parameters in the personality characteristic model, realize the deep cooperation of skills and personality, and break through the limitation of the separation of skills and personality, so that the digital employee can accurately call core skills and associated skills when processing instructions, and adapt to personalized scenarios through personality characteristics, improve the flexibility and adaptability of task processing, and at the same time, rely on the dynamic knowledge updating mechanism to enhance the autonomous response and continuous evolution capability of the digital employee to complex business scenarios, effectively improve the intelligent level and actual business adaptability of the digital employee.

[0113] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be realized in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be realized in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be instructed by a computer program to relevant hardware. In implementation, the above program can be stored in a computer readable storage medium or transmitted as one or more instructions or codes on a computer readable storage medium. The computer readable storage medium includes computer storage medium and communication medium, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium accessible by a computer. The computer readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer.

[0114] Finally, it should be noted that: the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent replacements to some technical features, as long as they are within the spirit and principles of the present application. Any modification, equivalent replacement, improvement, etc. made shall be included in the protection scope of the present application.

Claims

1. A method for creating digital employees based on artificial intelligence, characterized in that: The method includes: Step 1: Acquire and analyze job data corresponding to the target job position of the digital employee, the job data including instruction characteristics, skill characteristics, and personality characteristics. The instruction characteristics are used to characterize the instructions that the target job needs to process, and the skill characteristics and personality characteristics are used to characterize the skills and personality required to process the instructions. Step 2: Generate a digital employee profile for creating a digital employee based on the job data, wherein the digital employee profile includes a skill profile and a personality trait model, wherein the skill profile corresponds to the skill trait, and the personality trait model corresponds to the personality trait; Step 3: Generate a dynamic knowledge base for creating digital employees based on the job data and the digital employee portrait, wherein the dynamic knowledge base is used to respond to the job data; Step 4: Create a digital employee based on the digital employee portrait and the dynamic knowledge base, and configure the digital employee to call skills, personality and knowledge based on the instructions of the target position to respond to the instructions.

2. The method for creating a digital employee based on artificial intelligence according to claim 1, characterized in that: The position data are specifically: Historical operation logs, cross-system interaction records, and user communication texts corresponding to the command features; Professional knowledge maps, tool usage records, and task completion indicators corresponding to the skill characteristics; The communication style labels, decision-making tendency data and emotional response patterns corresponding to the personality traits.

3. The method for creating digital employees based on artificial intelligence according to claim 1, characterized in that: The digital employee portrait is specifically: The skill map includes core skills, related skills, and corresponding skill weights; wherein the core skills and the related skills are obtained by matching the instruction features with the skill features, and the skill weights are determined by the personality trait model; The personality trait model is configured to determine the skill weight based on a communication style parameter, a decision-making mode parameter, and an emotion simulation parameter corresponding to the personality trait.

4. The method for creating a digital employee based on artificial intelligence according to claim 1, characterized in that: The dynamic knowledge base is specifically: Basic business knowledge base, which stores standardized processes, industry specifications, and solutions to common problems related to the target position; Knowledge update library, used to capture industry dynamic data and user feedback data in real time, and automatically expand knowledge nodes and related relationships; The knowledge association graph is used to update the industry dynamic data and user feedback data captured in real time by the knowledge update library to the basic business knowledge library based on the knowledge nodes and association relationships expanded by the knowledge update library.

5. The method for creating digital employees based on artificial intelligence according to claim 3, characterized in that: The creation of the digital workforce includes: Based on the instruction features, extracting matching core skills and related skills from the historical skill map; Invoking the personality trait model, and using the communication style parameter, the decision-making mode parameter, and the emotion simulation parameter, calculating the initial skill weights of the core skill and the associated skills; An initial version of the skill map is generated based on the initial skill weights, and the weights of the initial version of the skill map are adjusted in combination with the knowledge associations in the dynamic knowledge base to form an optimized skill map; Through the personality trait model, the personality trait parameters are adjusted based on the optimized skill map, and the personality trait model is updated; Recalculate the skill weights of core skills and related skills based on the updated personality trait model to form the final version of the skill map; Map the final version of the skills map to the dynamic knowledge base to build a decision-making rule system for digital employees; Based on the decision rule system, the instruction response logic of the digital employee is configured so that after the digital employee is created, the skill weight is dynamically adjusted based on the parameters of the personality characteristic model, and instructions are processed according to the adjusted skill weight.

6. The method for creating digital employees based on artificial intelligence according to claim 1, characterized in that: Based on the created digital employee, the method further includes: Step 4: Arrange tasks for the digital employee based on the dynamic knowledge base; Step 5: Monitor the work data of the digital employee corresponding to step 3 or step 4, compare the work data with the predicted data, and update steps 3 and 4 based on the comparison results; wherein, the work data is used to characterize the digital employee's processing of the instructions, and the predicted data is generated based on the adversarial sample.

7. The method for creating a digital employee based on artificial intelligence according to claim 6, characterized in that: The task arrangement includes: Optimizing the dynamic knowledge base to generate a subtask sequence adapted to the skill map of the digital employee, wherein the subtask sequence is determined based on the order in which the knowledge in the dynamic knowledge base is called; Based on the cross-system interface capabilities of digital employees, assign the execution entities and collaboration timing of each subtask; The task priorities and resource allocation strategies are adjusted in real time according to the updated content of the dynamic knowledge base.

8. The method for creating digital employees based on artificial intelligence according to claim 6, characterized in that: The work data includes: the task completion rate, instruction response time, and cross-system interaction error rate of digital employees; the knowledge call accuracy and update delay time of the dynamic knowledge base; the matching degree between the skill characteristics in the digital employee portrait and the actual task requirements, and the user acceptance of personality characteristics.

9. The method for creating digital employees based on artificial intelligence according to claim 7, characterized in that: The updating of step 3 and step 4 based on the comparison result includes: When the deviation between the working data and the predicted data exceeds a preset threshold, adjusting the weights and associations of the knowledge nodes in the dynamic knowledge base; updating the skill map and personality trait model of the digital employee portrait based on the deviation; The priority algorithm and cross-system collaboration strategy of the task scheduling are updated based on the deviation.

10. An artificial intelligence-based digital employee creation system, which is applicable to the artificial intelligence-based digital employee creation method according to any one of claims 1 to 9, characterized in that: The system includes: a position data analysis module, which acquires and analyzes position data corresponding to the target position of the digital employee, wherein the position data includes instruction characteristics, skill characteristics, and personality characteristics. The instruction characteristics are used to characterize the instructions that the target position needs to process, and the skill characteristics and personality characteristics are used to characterize the skills and personality required to process the instructions. a digital employee portrait generation module, which generates a digital employee portrait for creating a digital employee based on the job data, wherein the digital employee portrait includes a skill map and a personality trait model, wherein the skill map corresponds to the skill trait, and the personality trait model corresponds to the personality trait; A dynamic knowledge base generation module generates a dynamic knowledge base for creating a digital employee based on the job data and the digital employee portrait, wherein the dynamic knowledge base is used to respond to the job data; A digital employee creation module creates a digital employee based on the digital employee portrait and the dynamic knowledge base, wherein the digital employee is configured to call skills, personality and knowledge based on instructions of the target position to respond to the instructions.

Images