Intelligent training robot and training method

Abstract

The present application relates to the field of data processing technology, and further to an intelligent training robot and a training method. The intelligent training robot includes: a training module, which is configured to construct corresponding training content based on the Qwen large model and the input information of the police officer; an interactive training module, which is configured to construct the dialogue ability of the intelligent training robot based on the Qwen large model, so that the police officer can interact with the intelligent training robot; an evaluation module, which is configured to process the learning data of the police officer during the learning process and obtain the evaluation results of the police officer; the training module is also configured to customize training plans and course content for the police officer based on the evaluation results; the learning data includes the data when the police officer learns the training content and the data of interacting with the intelligent training robot. The intelligent training robot significantly improves the efficiency and effectiveness of training for police officers.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and further to an intelligent training robot and a training method. Background Art

[0002] At present, the traditional police training method relies on a large amount of physical teaching materials, dedicated venues and human resources, which involves cumbersome time management, including multiple stages such as course planning, teaching execution and effect evaluation. This traditional training method has reduced the efficiency and effectiveness of training. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides an intelligent training robot and a training method, which improve the efficiency and effectiveness of training.

[0004] In the first aspect, the present application provides an intelligent training robot, comprising: a training module, configured to construct corresponding training content based on the Qwen big model and the input information of the police officer; an interactive training module, configured to construct the dialogue capability of the intelligent training robot based on the Qwen big model, so that the police officer can interact with the intelligent training robot; an evaluation module, configured to process the learning data of the police officer during the learning process to obtain the evaluation result of the police officer; the training module is also configured to customize training plans and course content for the police officer based on the evaluation result; the learning data includes data when the police officer learns the training content and data of interacting with the intelligent training robot.

[0005] With the above intelligent training robots, police officers can receive personalized training content based on the Qwen large model through the training module, which not only improves the pertinence and efficiency of the training, but also ensures that the training content is closely connected with actual work needs. The introduction of the interactive training module enables police officers to interact with the intelligent training robot in real time. This interactive learning method not only enhances the fun of learning, but also improves the police officers' practical operation ability and problem-solving skills. The data processing function of the evaluation module can comprehensively analyze the learning data of the police officers and provide accurate evaluation results, so as to customize more accurate training plans and course content for each police officer. This data-driven personalized training method has significantly improved the efficiency and effectiveness of police training.

[0006] In one implementation, the evaluation module is also configured to collect the learning data of the police officer in real time, and analyze the learning data based on the Qwen big model, big data analysis and machine learning algorithm to determine the learning behavior of the police officer; the evaluation module is also configured to provide the police officer with corresponding learning resources based on the Qwen big model and the learning behavior.

[0007] In one implementation, the assessment module is further configured to conduct regular tests on the police officers to determine their competence levels; the assessment module is further configured to generate competence portraits of the police officers based on the configuration of the Qwen big model and the competence levels.

[0008] In one implementation, the training module is further configured to customize the training plan for the police officer based on the learning behavior and the ability level; the training module is further configured to generate the course content based on the training plan; the training module is further configured to adjust the course content in real time based on the Qwen big model and the learning progress of the police officer.

[0009] The above intelligent training robots, through the real-time data collection and analysis capabilities of the evaluation module, combined with big data analysis and machine learning algorithms, can accurately capture the learning behaviors and habits of police officers. This resource provision based on individual learning behavior ensures the personalization and efficiency of learning content. Regular testing and ability level assessment not only help the system generate ability portraits of police officers, but also provide a scientific basis for customized training plans. The training module can dynamically adjust the course content to ensure that the training keeps pace with the actual needs and progress of the police officers. This intelligent training system not only improves the efficiency of training, but also enhances the adaptability and pertinence of training and improves the user experience of police officers through real-time feedback and adjustments.

[0010] In one implementation, the interactive training module is further configured to perform natural language processing on the response data of the police officer during the interaction process, and extract key information from the response data; the interactive training module is further configured to compare the key information with the pre-stored answers, and generate a corresponding feedback report, so that the police officer can correct errors based on the feedback report.

[0011] The natural language processing capabilities of the interactive training module of the above intelligent training robots have greatly improved the interactivity and personalization of police training. By analyzing the police's response data in real time, the module can accurately extract key information and compare it with the pre-stored answer library to generate targeted feedback reports. This process not only improves the error correction efficiency of police officers, but also enhances their autonomous learning ability. Through this instant feedback mechanism, police officers can quickly identify and correct errors during training, thereby deepening their understanding of key concepts and operations. In addition, this intelligent interactive method based on the Qwen large model makes training more vivid and efficient, which helps to improve the learning motivation and participation of police officers. In the end, the introduction of this interactive training module not only optimized the training process, but also significantly improved the professional skills and practical capabilities of police officers.

[0012] In one implementation, the training module is configured to collect historical data of the call center and analyze the historical data based on natural language processing and machine learning algorithms; the training module is configured to automatically generate training content that meets the business needs of the call center based on the analysis results.

[0013] In one implementation, it also includes: a data processing module, configured to analyze the business needs of the intelligent training robot to determine the application scenarios and functional requirements of the Qwen big model; a download module, configured to download the Qwen big model that meets the requirements from the Qwen big model series based on the application scenarios and functional requirements of the Qwen big model.

[0014] In a second aspect, the present application also provides a training method, which is applied to any of the above-mentioned intelligent training robots, including: constructing corresponding training content based on the Qwen big model and the input information of the police officer; constructing the dialogue capability of the intelligent training robot based on the Qwen big model to enable the police officer to interact with the intelligent training robot; processing the learning data of the police officer during the learning process to obtain the evaluation results of the police officer; and customizing training plans and course content for the police officer based on the evaluation results.

[0015] In one implementation, it also includes: collecting the learning data of the police officer in real time, and analyzing the learning data based on the Qwen big model, big data analysis and machine learning algorithm to determine the learning behavior of the police officer; based on the Qwen big model and the learning behavior, providing the police officer with corresponding learning resources.

[0016] In one implementation, it also includes: conducting regular tests on the police officers to determine their ability levels; and generating ability portraits of the police officers based on the configuration of the Qwen big model and the ability levels.

[0017] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0018] 1. Police officers can receive personalized training content based on the Qwen large model through the training module, which not only improves the pertinence and efficiency of the training, but also ensures that the training content is closely connected with actual work needs. The introduction of the interactive training module enables police officers to interact with intelligent training robots in real time. This interactive learning method not only enhances the fun of learning, but also improves the police officers' practical operation ability and problem-solving skills. The data processing function of the evaluation module can comprehensively analyze the learning data of the police officers and provide accurate evaluation results, so as to customize more accurate training plans and course content for each police officer. This data-driven personalized training method has significantly improved the efficiency and effectiveness of police training.

[0019] 2. Through the real-time data collection and analysis capabilities of the evaluation module, combined with big data analysis and machine learning algorithms, the learning behaviors and habits of police officers can be accurately captured. This resource provision based on individual learning behavior ensures the personalization and efficiency of learning content. Regular testing and ability level assessment not only help the system generate ability portraits of police officers, but also provide a scientific basis for customized training plans. The training module can dynamically adjust the course content to ensure that the training keeps pace with the actual needs and progress of the police officers. This intelligent training system not only improves training efficiency, but also enhances the adaptability and pertinence of training and improves the user experience of police officers through real-time feedback and adjustments.

[0020] 3. The natural language processing capability of the interactive training module greatly improves the interactivity and personalization of police training. By analyzing the police's response data in real time, the module can accurately extract key information, compare it with the pre-stored answer library, and generate targeted feedback reports. This process not only improves the error correction efficiency of police officers, but also enhances their autonomous learning ability. Through this instant feedback mechanism, police officers can quickly identify and correct errors during training, thereby deepening their understanding of key concepts and operations. In addition, this intelligent interactive method based on the Qwen large model makes training more vivid and efficient, which helps to improve the learning motivation and participation of police officers. In the end, the introduction of this interactive training module not only optimizes the training process, but also significantly improves the professional skills and practical capabilities of police officers. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0022] Figure 1 A framework diagram of an intelligent training robot provided in an embodiment of the present application is shown;

[0023] Figure 2 A flow chart of a training method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0025] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0026] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] In this document, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0029] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

[0030] The Tongyi Qianwen (Qwen) large model is a series of large-scale language models and multimodal models developed by the Qwen team of Alibaba Group. These models are pre-trained on large-scale multilingual and multimodal data, and are later fine-tuned through high-quality data to be close to human preferences. The Qwen model has the capabilities of natural language understanding, text generation, visual understanding, audio understanding, etc., and can perform various tasks such as writing code, providing multilingual translation services, text polishing, role-playing dialogue, etc. The embodiment of the present application integrates the Qwen large model into the intelligent training robot. Through the built-in multiple modules of the intelligent training robot, the learning behavior and ability level of the police officers are analyzed, and training plans and course content are tailored for each police officer, which can achieve at least one of the following beneficial effects: improving the efficiency and effectiveness of training; or dynamically adjusting the course content according to the actual situation and learning progress of the police officers, improving the user experience of the police officers.

[0031] The following is explained with reference to the accompanying drawings:

[0032] Reference Figure 1 , which shows a framework diagram of an intelligent training robot provided by an embodiment of the present application. Figure 1 As shown, it includes a training module 100, an interactive training module 200, and an evaluation module 300. Among them, the training module 100 is configured to construct corresponding training content based on the Qwen large model and the input information of the police officer; the interactive training module 200 is configured to construct the dialogue capability of the intelligent training robot based on the Qwen large model, so that the police officer can interact with the intelligent training robot (or call center intelligent training robot); the evaluation module 300 is configured to process the learning data of the police officer in the learning process to obtain the evaluation results of the police officer; the training module 100 is also configured to customize the training plan and course content for the police officer based on the evaluation results; the learning data includes the data when the police officer learns the training content and the data interacting with the intelligent training robot.

[0033] The training module (or training content automatic generation module) 100 is configured to understand and analyze the police officer's input information based on the Qwen large model to obtain the training objectives and police officer's needs. By using the preset algorithms and rules, the relevant content related to the training objectives and police officer's needs is extracted from the knowledge base to generate the course outline and specific content (i.e. the corresponding training content). At the same time, it can also combine multimedia resources such as videos, recordings, pictures, etc. to further enrich the course content and form.

[0034] The interactive training module 200 interacts with police officers in real time through the intelligent training robot to provide a personalized training experience. For example, the interactive training module 200 builds the conversational capabilities of the intelligent training robot based on the Qwen large model. A variety of simulation scenarios and conversational tasks are designed for the intelligent training robot, so that police officers can choose corresponding simulation scenarios or conversational tasks to practice according to their needs. At the same time, the interactive training module 200 in the intelligent training robot can also provide real-time feedback and suggestions based on the police officers' answers and performance, thereby improving the efficiency and effectiveness of the police officers' training.

[0035] The evaluation module (or training effect intelligent evaluation module) 300 uses data analysis technology and machine learning algorithms to process and analyze the learning data of the police officers (the learning data can be the data when the police officers learn the training content, or the data when the police officers interact with the intelligent training robot). The learning effect of the police officers is quantitatively evaluated according to the evaluation indicators (such as accuracy, answer speed, participation, etc.) and an evaluation report and suggestions are generated. Then, the training module 100 can customize the training plan and course content for each police officer according to the evaluation results of the police officers.

[0036] In the embodiment of the present application, police officers can receive personalized training content based on the Qwen large model through the training module, which not only improves the pertinence and efficiency of the training, but also ensures that the training content is closely connected with actual work needs. The introduction of the interactive training module enables police officers to interact with intelligent training robots in real time. This interactive learning method not only enhances the fun of learning, but also improves the police officers' practical operation ability and problem-solving skills. The data processing function of the evaluation module can comprehensively analyze the learning data of the police officers and provide accurate evaluation results, so as to customize more accurate training plans and course content for each police officer. This data-driven personalized training method significantly improves the efficiency and effectiveness of police training.

[0037] In one embodiment of the present application, the evaluation module is also configured to collect the learning data of the police officers in real time, and analyze the learning data based on the Qwen big model, big data analysis and machine learning algorithms to determine the learning behavior of the police officers. The evaluation module is also configured to provide corresponding learning resources for the police officers based on the Qwen big model and learning behavior. The evaluation module is also configured to conduct regular tests on the police officers to determine the ability level of the police officers. The evaluation module is also configured to generate the ability portrait of the police officers based on the configuration of the Qwen big model and the ability level. The training module is also configured to customize training plans for police officers based on learning behavior and ability level. The training module is also configured to generate course content based on the training plan. The training module is also configured to adjust the course content in real time based on the Qwen big model and the learning progress of the police officers.

[0038] The evaluation module collects various learning data generated by police officers on the intelligent training robot in real time, such as learning time, click rate, completion rate, accuracy rate, etc., and sends these data to the Qwen big model for recording. At the same time, the data generated by the police officers through the interaction with the intelligent training robot through the interactive training module (such as information such as police officers' feedback, preferences and interests) will also be captured by the Qwen big model. Through the Qwen big model, big data analysis and machine learning algorithms, these learning data are deeply analyzed and processed to determine the learning behavior of the police officers (for example, including but not limited to the learning habits, interest preferences, learning speed, points of interest, difficulties and weaknesses of the police officers). Based on the learning behavior of the police officers and the Qwen big model, the evaluation module recommends appropriate learning resources, learning paths and learning methods to the police officers.

[0039] Furthermore, the assessment module is also configured to conduct regular tests on police officers to determine their competence levels. The Qwen big model is used to conduct in-depth analysis of the test results to accurately assess the competence levels of police officers in various aspects. The Qwen big model can comprehensively judge the competence levels and development potential of police officers based on their answers, reaction speed, etc. Based on the assessment results, a detailed competence profile is generated for each police officer, including strengths, weaknesses, potential and other aspects.

[0040] Furthermore, the training module is also configured to customize training plans for police officers based on learning behavior and ability levels. The training plan includes key elements such as learning objectives, learning paths, and learning schedules to ensure that police officers can complete learning tasks efficiently and orderly. At the same time, the training module is also configured to generate course content based on the training plan. For example, the training module designs personalized course content for police officers through the Qwen big model and the police officers' interests and learning needs. By combining the course content with the actual needs of the police officers, the Qwen big model can stimulate the learning interest and motivation of the police officers. In addition, the Qwen big model will also recommend suitable learning resources for the fire department based on the learning progress and ability level of the police officers. These resources include course videos, simulated test questions, etc., which can improve the learning effect of the police officers. In addition, the training module can also use the Qwen big model and the actual learning situation and learning progress of the police officers to dynamically adjust the course content to ensure that the police officers can master the knowledge they have learned smoothly. During the training of police officers, the Qwen big model can monitor the learning situation of the police officers in real time, and adjust and optimize the course content in real time based on the feedback and performance of the police officers.

[0041] The embodiment of the present application can accurately capture the learning behaviors and habits of police officers through the real-time data collection and analysis capabilities of the evaluation module, combined with big data analysis and machine learning algorithms. This resource provision based on individual learning behavior ensures the personalization and efficiency of the learning content. Regular testing and ability level assessments not only help the system generate ability portraits of police officers, but also provide a scientific basis for customized training plans. The training module can dynamically adjust the course content to ensure that the training keeps pace with the actual needs and progress of the police officers. This intelligent training system not only improves the efficiency of training, but also enhances the adaptability and pertinence of training and improves the user experience of police officers through real-time feedback and adjustments.

[0042] In one embodiment of the present application, the interactive training module is further configured to perform natural language processing on the response data of the police officers during the interaction process, and extract key information from the response data; the interactive training module is further configured to compare the key information with the pre-stored answers, and generate a corresponding feedback report, so that the police officers can correct errors based on the feedback report.

[0043] During the training process, the police officers submit their reply data to the intelligent training robot. The intelligent training robot receives the police officers' reply data in real time (the reply data can be input in the form of text or voice. The FunASR multi-functional speech recognition toolkit is used. FunASR can convert voice signals into text, and it also supports overseas corpora and uses Whisper for real-time speech transcription). The interactive training module uses the Qwen large model to perform natural language processing on the reply data (the Qwen large model uses its natural language processing capabilities and deep learning capabilities to perform semantic analysis, grammar checking, logical judgment and other aspects of the police officers' answers) to extract key information from the reply data. The interactive training module compares the key information with the correct answer to evaluate the accuracy and completeness of the police officers' replies (the evaluation process is essentially a real-time evaluation of the police officers' skills, knowledge, etc. through the Qwen large model). Then, a detailed feedback report and suggestions are generated based on the evaluation results. The intelligent training robot displays the feedback report and suggestions to the police officers in real time. The feedback report includes the correctness of the reply, the cause of the error, and suggestions for improvement. The police officers can find and correct problems in a timely manner based on the feedback report. At the same time, police officers can submit revised answers multiple times until they reach a satisfactory result.

[0044] Furthermore, a large amount of historical police response data and correct answer data can be used to train the Qwen model. By adjusting model parameters and optimizing algorithms, the accuracy of the Qwen model's assessment of police responses can be improved.

[0045] The natural language processing capability of the interactive training module in the embodiment of the present application greatly improves the interactivity and personalization of police training. By analyzing the police's response data in real time, the module can accurately extract key information, compare it with the pre-stored answer library, and generate targeted feedback reports. This process not only improves the error correction efficiency of police officers, but also enhances their autonomous learning ability. Through this instant feedback mechanism, police officers can quickly identify and correct errors during training, thereby deepening their understanding of key concepts and operations. In addition, this intelligent interactive method based on the Qwen large model makes training more vivid and efficient, and helps to improve the learning motivation and participation of police officers. In the end, the introduction of this interactive training module not only optimized the training process, but also significantly improved the professional skills and practical capabilities of police officers.

[0046] In one embodiment of the present application, the training module is configured to collect historical data of the call center and analyze the historical data based on natural language processing and machine learning algorithms; the training module is configured to automatically generate training content that meets the business needs of the call center based on the analysis results.

[0047] The training module collects historical data of the call center, including customer feedback, agent performance, common problems, etc. Natural language processing (NLP) and machine learning (ML) technologies are used to analyze historical data and extract key information and patterns from historical data. Based on the analysis results, training content that meets the business needs of the call center is automatically generated. Including training course outlines, teaching materials, case analysis, simulated dialogues, etc. The training module can also optimize and adjust the automatically generated training content according to the actual needs and feedback of police officers to ensure the accuracy, practicality and readability of the training content. Among them, the training content that meets the business needs of the call center includes various business processes of the call center, such as receiving calls, handling calls, information recording, information transmission, etc., which can cultivate good communication skills and adaptability of police officers so that they can communicate effectively with callers and other departments in emergency situations; it also includes simulating various emergency situations to train police officers on how to quickly judge the level of the alarm, take corresponding measures, coordinate relevant departments, etc.; it also includes simulating different types of alarm situations and letting police officers perform police operations, including information transmission, coordination of resources, on-site disposal, etc.; it also includes selecting typical cases of receiving and dispatching calls for analysis so that police officers can understand the handling methods and techniques in different situations.

[0048] In one embodiment of the present application, refer to the attached Figure 1 , further comprising: a data processing module 400 and a downloading module 500. The data processing module 400 is configured to analyze the business requirements of the intelligent training robot to determine the application scenarios and functional requirements of the Qwen large model; the downloading module 500 is configured to download the Qwen large model that meets the requirements from the Qwen large model series based on the application scenarios and functional requirements of the Qwen large model.

[0049] The data processing module 400 shares the business requirements of the intelligent training robot (business requirements include training content, interaction methods, user groups, etc.) to determine the application scenarios and functional requirements of the Qwen large model. The download module 500 downloads the Qwen large model that meets the requirements from the Qwen large model series based on the application scenarios and functional requirements of the Qwen large model (the Qwen large model version Qwen2.5-7B / 72B is selected in the embodiment of the present application). At the same time, the Qwen large model is configured to ensure that the Qwen large model file is complete and the version of the Qwen large model is compatible with the system of the intelligent training robot. The specific configuration process is to configure high-performance computing resources to meet the operating requirements of the Qwen large model. Install necessary software such as Python, transformers library, etc. to load and use the Qwen large model. Use the AutoModelForCausalLM and AutoTokenizer classes in the transformers library to load the Qwen large model and the supporting word segmenter. Build a dialogue system based on the Qwen large model to achieve natural interaction with call center police officers. Design a dialogue process, including opening remarks, question answering, skill demonstration and other links. According to the training needs of the call center, customize the training content, including business knowledge, communication skills, FAQs, etc. Use Qwen big model to generate or optimize training materials, such as conversation scripts, simulation scenarios, etc.

[0050] Furthermore, the Qwen model was integrated into the API service of the intelligent training robot to achieve remote access and integration. The API interface was designed to allow call center police officers to interact with the Qwen model through HTTP requests. The intelligent training robot integrated with the Qwen model was deployed to the call center. The police officers were organized to conduct training and testing to ensure that they were familiar with and used the new training system.

[0051] Reference Figure 2 , which shows a flow chart of a training method provided by an embodiment of the present application. Figure 2 As shown, the training method is applied to the intelligent training robot in the above embodiment, including:

[0052] S200, based on the Qwen large model and the input information of the police officers, builds the corresponding training content;

[0053] S210, builds the conversational capabilities of the intelligent training robot based on the Qwen large model to enable police officers to interact with the intelligent training robot;

[0054] S220, processing the learning data of the police officers during the learning process to obtain the evaluation results of the police officers;

[0055] S230, customize training plans and course content for police officers based on the evaluation results.

[0056] The details of the embodiments of the present application have been described in the aforementioned embodiments and will not be repeated here.

[0057] In one embodiment of the present application, it also includes: collecting the learning data of police officers in real time, and analyzing the learning data based on the Qwen big model, big data analysis and machine learning algorithm to determine the learning behavior of the police officers; based on the Qwen big model and learning behavior, providing corresponding learning resources for the police officers.

[0058] In one embodiment of the present application, it also includes: conducting regular tests on police officers to determine their ability levels; and generating ability portraits of police officers based on the configuration and ability levels of the Qwen big model.

[0059] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent training robot, characterized in that: include: The training module is configured to construct corresponding training content based on the Qwen big model and the input information of the police officers; An interactive training module, configured to construct the conversation capability of the intelligent training robot based on the Qwen large model, so that the police officer can interact with the intelligent training robot; An evaluation module, configured to process the learning data of the police officer during the learning process to obtain an evaluation result of the police officer; The training module is further configured to customize a training plan and course content for the police officer based on the evaluation results; The learning data includes data when the police officer learns the training content and data of interacting with the intelligent training robot.

2. The intelligent training robot according to claim 1, characterized in that: The evaluation module is further configured to collect the learning data of the police officer in real time, and analyze the learning data based on the Qwen big model, big data analysis and machine learning algorithm to determine the learning behavior of the police officer; The evaluation module is also configured to provide corresponding learning resources for the police officer based on the Qwen big model and the learning behavior.

3. The intelligent training robot according to claim 2, characterized in that: The assessment module is further configured to perform periodic tests on the police officer to determine the officer's competency level; The assessment module is also configured to generate a capability profile of the police officer based on the configuration of the Qwen big model and the capability level.

4. The intelligent training robot according to claim 3, characterized in that: The training module is further configured to customize the training plan for the police officer based on the learning behavior and the ability level; The training module is further configured to generate the course content based on the training plan; The training module is also configured to adjust the course content in real time based on the Qwen big model and the learning progress of the police officer.

5. The intelligent training robot according to any one of claims 1 to 4, characterized in that: The interactive training module is further configured to perform natural language processing on the response data of the police officer during the interaction process, and extract key information from the response data; The interactive training module is also configured to compare the key information with pre-stored answers and generate a corresponding feedback report so that the police officer can correct errors based on the feedback report.

6. The intelligent training robot according to claim 1, characterized in that: The training module is configured to collect historical data of the call center and analyze the historical data based on natural language processing and machine learning algorithms; The training module is configured to automatically generate training content that meets the business needs of the call center based on the analysis results.

7. The intelligent training robot according to claim 1, characterized in that: Also includes: A data processing module is configured to analyze the business requirements of the intelligent training robot to determine the application scenarios and functional requirements of the Qwen large model; The download module is configured to download the Qwen big model that meets the requirements from the Qwen big model series based on the application scenario and functional requirements of the Qwen big model.

8. A training method, characterized in that: The intelligent training robot applied to any one of claims 1 to 7 comprises: Based on the Qwen big model and the input information of the police officers, build corresponding training content; Constructing the conversation capability of the intelligent training robot based on the Qwen big model so that the police officer can interact with the intelligent training robot; Processing the learning data of the police officer during the learning process to obtain an evaluation result of the police officer; A training plan and course content are customized for the police officer based on the assessment results.

9. The training method according to claim 8, characterized in that: Also includes: Collect the learning data of the police officers in real time, and analyze the learning data based on the Qwen big model, big data analysis and machine learning algorithm to determine the learning behavior of the police officers; Based on the Qwen big model and the learning behavior, corresponding learning resources are provided for the police officers.

10. The training method according to claim 9, characterized in that: Also includes: Conducting periodic testing of said officers to determine the competency level of said officers; Based on the configuration of the Qwen big model and the capability level, a capability profile of the police officer is generated.

Images