Training plan auxiliary generation method and device, electronic equipment and storage medium

Abstract

The invention provides a training plan auxiliary generation method and device, electronic equipment and a storage medium, and the method comprises the steps: determining target training plan information according to at least one of all levels of annual training plan information, all levels of monthly training plan information, task on-duty plan information and training plan related information; wherein each stage of annual training plan information comprises at least one of a training subject, training time, a training evaluation standard, a training stage and training posts; the monthly training plan information at each level comprises monthly training plan information of at least one of a training subject, training time, a training evaluation standard, a training stage and training posts. According to the method, the target training plan information comprises at least one of all levels of annual training plan information, all levels of monthly training plan information, task on-duty plan information and training plan related information, deep integration is carried out on multi-dimensional data, the data utilization rate is improved, and therefore the accuracy of training plan generation is improved, and the management efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of training plan generation technology, and in particular to a training plan generation-assisted method, apparatus, electronic device, and storage medium. Background Technology

[0002] In existing technologies, some military training systems adopt a modular design, but lack the ability to deeply integrate multi-dimensional data such as battlefield environment and combat readiness status. For example, combat training systems struggle to simulate the uncertainties and dynamic changes of a real battlefield, and physical training programs often ignore individual differences, leading to inconsistent training results.

[0003] Furthermore, with the application of technologies such as the Internet of Things, artificial intelligence, and virtual reality in the military field, the amount of training data (such as combat readiness parameters, personnel physiological indicators, and war simulation results) has exploded. However, problems such as low data utilization and outdated analysis methods have constrained the accuracy of training plans. Summary of the Invention

[0004] This invention provides a training plan-assisted generation method, apparatus, electronic device, and storage medium to address the deficiencies in training plan-assisted generation in the prior art.

[0005] This invention provides a training plan-assisted generation method, comprising the following steps: Based on the annual plan models at each level, annual training plan information for each level is generated; the annual training plan information for each level includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. Based on the monthly plan models at each level, monthly training plan information at each level is generated; the monthly training plan information at each level includes the training subjects, the training time, the training evaluation criteria, the training stage, and the monthly training plan information of at least one of the training positions. Based on the task duty plan model, generate task duty plan information; based on the training plan to assist in model generation, generate training plan-related information. The target training plan information is determined based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information.

[0006] According to a training plan-assisted generation method provided by the present invention, the training steps of the annual plan models at each level include: Obtain the initial annual plan models at all levels, the first sample data, and the labeled annual training plan information of the first sample data at all levels; the first sample data includes training outline data, training organization data of participating units, historical training data of trainees, and capability requirement data of participating units; The first sample data is input into the initial annual plan model at each level to obtain the predicted annual training plan information at each level output by the initial annual plan model at each level; Based on the differences between the predicted annual training plan information at each level and the labeled annual training plan information at each level, the initial annual plan model at each level is trained to obtain the annual plan model at each level.

[0007] According to a training plan-assisted generation method provided by the present invention, the training steps of the monthly plan models at each level include: Obtain the second sample data, as well as the corresponding monthly training plan information for the tags; the second sample data includes annual training plan information for each level of the sample, historical training data of trainees, and unit capability requirement data; The second sample data is input into the initial monthly planning model at each level to obtain the predicted monthly training plan information output by the initial monthly planning model at each level; Based on the predicted monthly training plan information and the labeled monthly training plan information, the initial monthly plan models at each level are trained to obtain the monthly plan models at each level.

[0008] According to a training plan-assisted generation method provided by the present invention, the training steps of the task duty plan model include: Obtain third sample data and the corresponding tag task duty plan information; the third sample data includes task attributes, unit personnel information, equipment resource data, strategy configuration information, and parameter configuration information; the task attributes include task level, task time, and task location. The third sample data is input into the initial task duty plan model to obtain the predicted task duty plan information output by the initial task duty plan model; Based on the predicted task duty schedule information and the labeled task duty schedule information, the initial task duty schedule model is trained to obtain the task duty schedule model.

[0009] According to a training plan generation method provided by the present invention, the training plan information includes training subjects, personnel composition, training time, evaluation criteria, and training stages.

[0010] According to a training plan-assisted generation method provided by the present invention, the step of determining target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information further includes: Action recognition is performed on the training site video corresponding to the target training plan information to obtain action information; The training commands in the training site audio corresponding to the target training plan information are subjected to speech recognition to obtain text information; Based on the action information, assess the standardization of the trainees' actions in the target training plan information, and based on the text information, analyze the execution of the training commands, as well as evaluate the standardization and consistency of the training process.

[0011] According to a training plan generation method provided by the present invention, the method further includes: evaluating the standardization of trainees' movements in the target training plan information based on the movement information, analyzing the execution of training commands based on the text information, and evaluating the standardization and consistency of the training process; and then further including: Emotion recognition is performed based on the action information and the text information to obtain the emotion recognition result; Based on the emotion recognition results, adjust the target training plan information.

[0012] The present invention also provides a training plan auxiliary generation device, comprising the following units: The first generation unit is used to generate annual training plan information for each level based on the annual plan model at each level; the annual training plan information for each level includes annual training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions; The second generation unit is used to generate monthly training plan information at each level based on the monthly plan model at each level; the monthly training plan information at each level includes monthly training plan information of at least one of the training subjects, the training time, the training evaluation criteria, the training stage, and the training positions; The third generation unit is used to generate task duty plan information based on the task duty plan model and to generate training plan-related information based on the training plan to assist the generation model. The determining unit is used to determine target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the training plan-assisted generation method as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the training plan-assisted generation method as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the training plan-assisted generation method as described above.

[0016] The training plan generation method, apparatus, electronic device, and storage medium provided by this invention determine target training plan information based on at least one of the following: annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information. The annual training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. The monthly training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. This method, by deeply integrating multi-dimensional data—including annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information—improves the accuracy of training plan generation, management efficiency, and user experience. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is one of the flowcharts of the training plan-assisted generation method provided by the present invention.

[0019] Figure 2 This is the second flowchart of the training plan-assisted generation method provided by the present invention.

[0020] Figure 3 This is a schematic diagram of the training plan auxiliary generation device provided by the present invention.

[0021] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0023] The terms "first," "second," etc., used in this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and that the objects distinguished by "first," "second," etc., are generally of the same class.

[0024] Figure 1 This is one of the flowcharts illustrating the training plan-assisted generation method provided by the present invention. Figure 2 This is the second flowchart of the training plan-assisted generation method provided by the present invention, as shown below. Figure 1 , Figure 2 As shown, the method includes steps 110, 120, 130 and 140.

[0025] Step 110: Generate annual training plan information for each level based on the annual plan model for each level; the annual training plan information for each level includes annual training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions.

[0026] Specifically, annual training plan information for each level can be generated based on the annual plan model at each level. This information includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions.

[0027] The annual plan models at each level can be random forest models, or LSTM (Long Short-Term Memory) networks, etc., and the embodiments of the present invention do not specifically limit them.

[0028] Here, the annual training plan information at all levels is a structured training plan data set with an annual time granularity, used to comprehensively describe the training tasks that units at all levels (such as theater commands, services, brigades, regiments, or battalions / companies) must complete or prioritize in the next calendar year. Training subjects refer to the specific content of the training tasks. Training subjects can include basic training subjects, specialized training subjects, and comprehensive exercise subjects, such as tactical exercises, live-fire shooting, and emergency mobilization. This embodiment of the invention does not specifically limit these. Training time refers to the execution time arrangement of the training tasks, which can be a specific date, cycle, or phase division. Training evaluation standards refer to quantitative or qualitative indicators for measuring training effectiveness. For example, a hit rate of 90% or higher in shooting training is excellent, and 80%-89% is good. Training phases are divided according to the progress of the training tasks, usually progressing according to difficulty or objectives. Participating positions refer to the positions of personnel involved in the training tasks. For example, participating positions can include command positions, operational positions, and support positions.

[0029] Step 120: Generate monthly training plan information for each level based on the monthly plan model at each level; the monthly training plan information for each level includes monthly training plan information for at least one of the training subjects, the training time, the training evaluation criteria, the training stage, and the training positions.

[0030] Specifically, monthly training plan information at each level can be generated based on the monthly plan model at each level. Here, the monthly training plan information at each level includes monthly training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions.

[0031] The monthly planning models at each level can be random forest models, LSTM models, etc., and this embodiment of the invention does not specifically limit them.

[0032] Here, the monthly training plan information at each level refers to a set of structured training plan data with a calendar month as the time granularity, which is used to refine the annual training tasks month by month and implement them into specific execution units.

[0033] Step 130: Generate task duty plan information based on the task duty plan model, and generate training plan related information based on the training plan-assisted model generation.

[0034] Specifically, task duty schedule information can be generated based on the task duty schedule model. The task duty schedule model can be a random forest model, an LSTM model, etc., and this embodiment of the invention does not specifically limit it.

[0035] Here, training plan-related information refers to the structured data set output by the model, with a single training activity as the smallest granularity, which is used to directly guide training implementation and evaluation, and is generated with the help of the training plan. Training plan-related information includes training subjects, personnel composition, training time, evaluation criteria, and training phases.

[0036] The training plan-assisted generation model can be a random forest model or an LSTM model, etc., and this embodiment of the invention does not specifically limit it.

[0037] Here, based on the training plan generation function of the training plan-assisted generation model, it can automatically generate training plan-related information such as training subjects, personnel composition, training time, evaluation criteria, and training stages according to information such as training objectives and participating units, around the training outline, and combined with the training history data of a certain unit. Through scene version management, time series model parameter configuration, model parameter optimization, simulation result management, and automatic system optimization, it assists in plan formulation and improves the rationality of training plans.

[0038] Step 140: Determine the target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and the training plan related information.

[0039] Specifically, after obtaining annual training plan information, monthly training plan information, task duty plan information, and training plan-related information at all levels, the target training plan information can be determined based on at least one of these information. That is, the target training plan information can be determined based on annual and monthly training plan information, task duty plan information and the aforementioned training plan-related information, or a combination of all three. This embodiment of the invention does not specifically limit the determination of these methods.

[0040] The method provided in this invention can be applied to a training plan generation system, which supports dynamic expansion and can be flexibly adjusted according to different business scenarios. Through a plug-in mechanism, the system can be developed independently of the main system and integrated with it through a standard interface. Furthermore, the data service management in the training plan generation system provides an API (Application Programming Interface), allowing users or third-party developers to access system data programmatically, further enhancing the system's flexibility and scalability.

[0041] The method provided in this invention determines target training plan information based on at least one of the following: annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information. The annual training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. The monthly training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. This method, by deeply integrating multi-dimensional data—including annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information—improves data utilization, thereby enhancing the accuracy of training plan generation, management efficiency, and user experience.

[0042] Based on the above embodiments, the training steps of the annual plan models at each level include: Step 210: Obtain the initial annual plan models at all levels, the first sample data, and the labeled annual training plan information of the first sample data at all levels; the first sample data includes training outline data, training organization data of participating units, historical training data of participating personnel, and capability requirement data of participating units. Step 220: Input the first sample data into the initial annual plan model at each level to obtain the predicted annual training plan information at each level output by the initial annual plan model at each level; Step 230: Based on the difference between the predicted annual training plan information at each level and the labeled annual training plan information at each level, train the initial annual plan model at each level to obtain the annual plan model at each level.

[0043] Specifically, to obtain better models for annual plans at all levels, training can be performed based on the following steps: First, obtain the initial annual plan models at all levels, the first sample data, and the labeled annual training plan information of the first sample data at all levels. The first sample data includes training outline data, training organization data of participating units, historical training data of trainees, and capability requirement data of participating units.

[0044] Here, the initial annual plan model at each level can be a random forest model or an LSTM model, etc., and the embodiments of the present invention do not specifically limit it.

[0045] The parameters of the initial annual plan models at each level can be preset or randomly generated; this embodiment of the invention does not impose specific limitations on this.

[0046] Here, the training syllabus data includes elements such as training policies, course outlines, training objectives, class hour allocation, assessment standards, and required facilities, equipment, and instructor qualifications, serving as the basis for formulating annual plans. The training organization data of participating units reflects structured information about the unit's ability to organize training, such as the number of staff, the number of existing instructors / inspectors, training venue capacity, historical training completion rates, and training support conditions.

[0047] Historical training data of trainees refers to the quantitative performance of an individual or group during past training cycles.

[0048] After obtaining the first sample data, data preprocessing can be performed on the first sample data. Data preprocessing may include data cleaning, missing value handling, and data integration, etc., and the embodiments of the present invention do not specifically limit this.

[0049] After obtaining the first sample data, the first sample data can be input into the initial annual planning model at each level to obtain the predicted annual training plan information at each level output by the initial annual planning model at each level.

[0050] After outputting the predicted annual training plan information for each level based on the initial annual plan model for each level, the first loss can be determined based on the difference between the predicted annual training plan information for each level and the labeled annual training plan information for each level. Based on the first loss, the initial annual plan model for each level is trained, and the initial annual plan model for each level after training is used as the annual plan model for each level.

[0051] Here, training the initial annual plan models at all levels includes automatically optimizing the weights of the initial annual plan models at all levels, etc., and this embodiment of the invention does not specifically limit this.

[0052] Understandably, the greater the difference between the predicted annual training plan information and the labeled annual training plan information, the greater the first loss; conversely, the smaller the difference between the predicted annual training plan information and the labeled annual training plan information, the smaller the first loss.

[0053] Based on the above embodiments, the training steps of the monthly planning models at each level include: Step 310: Obtain the second sample data and the corresponding monthly training plan information for the tags; the second sample data includes annual training plan information for each level of the sample, historical training data of trainees, and unit capability requirement data; Step 320: Input the second sample data into the initial monthly planning model at each level to obtain the predicted monthly training plan information output by the initial monthly planning model at each level; Step 330: Based on the predicted monthly training plan information and the labeled monthly training plan information, train the initial monthly plan models at each level to obtain the monthly plan models at each level.

[0054] Specifically, to obtain better monthly plan models at all levels, training can be performed based on the following steps: First, acquire the second sample data and the corresponding monthly training plan information. The second sample data includes annual training plan information at all levels, historical training data of trainees, and unit capability requirements data. Here, historical training data refers to records of various training activities participated in by trainees in the past, including training subjects, training time, training results, training evaluations, and training feedback. Unit capability requirements data refers to the capabilities that the unit needs to improve or maintain in the current and future period, including combat capabilities, support capabilities, and command and control capabilities.

[0055] After obtaining the second sample data, it can be input into the initial monthly planning models at each level to obtain the predicted monthly training plan information output by the initial monthly planning models at each level.

[0056] After obtaining the predicted monthly training plan information, the initial monthly plan models at each level can be trained based on the predicted monthly training plan information and the labeled monthly training plan information to obtain the monthly plan models at each level.

[0057] The method provided in this invention obtains second sample data and corresponding label-based monthly training plan information. The second sample data includes annual training plan information at each level, historical training data of trainees, and unit capability requirement data. This second sample data is then input into initial monthly plan models at each level to obtain predicted monthly training plan information output by the initial models. Finally, based on the predicted and label-based monthly training plan information, the initial monthly plan models at each level are trained to obtain monthly plan models at each level. This method assists in plan formulation, satisfying both annual training plan requirements and the actual training situation of the unit, thus improving the scientific rigor and effectiveness of monthly training plans at each level.

[0058] Based on the above embodiments, the training steps of the task duty schedule model include: Step 410: Obtain the third sample data and the corresponding tag task duty plan information; the third sample data includes task attributes, unit personnel information, equipment resource data, strategy configuration information, and parameter configuration information; the task attributes include task level, task time, and task location. Step 420: Input the third sample data into the initial task duty plan model to obtain the predicted task duty plan information output by the initial task duty plan model; Step 430: Based on the predicted task duty plan information and the labeled task duty plan information, train the initial task duty plan model to obtain the task duty plan model.

[0059] Specifically, to obtain a better task duty schedule model, it can be trained based on the following steps: First, obtain the third sample data and the corresponding tag task duty plan information. The third sample data includes task attributes, unit personnel information, equipment resource data, strategy configuration information and parameter configuration information. The task attributes include task level, task time and task location.

[0060] Here, the "task duty schedule information" refers to the planned information that needs to be completed during the duty period for a specific task, including the specific arrangements of the duty tasks, personnel allocation, equipment usage plans, duty schedules, and emergency response measures. Task level refers to the importance and urgency of the task, usually divided into high, medium, and low levels. A high task level indicates that the task is very critical and needs to be prioritized; a low task level indicates that the task is relatively minor and can be handled if resources allow. Task time refers to the start and end times of the task, used to determine the duration of the task. The accuracy of the task time is crucial for resource allocation and planning. Task location refers to the specific geographical location of the task execution, such as a specific area, location, or facility. The task location determines the allocation of resources and the deployment of personnel.

[0061] Here, equipment resource data refers to information about the equipment and resources required to perform the task. This data can include equipment name, equipment status, equipment quantity, and equipment performance parameters. Equipment name refers to the name or model of the equipment, such as communication equipment, transportation vehicles, or weaponry. Equipment status refers to the current state of the equipment, such as normal, under maintenance, or standby. Equipment quantity refers to the number of available devices, used to assess resource adequacy. Equipment performance parameters refer to the technical parameters of the equipment, such as power, speed, and capacity, used to assess whether they meet the task requirements.

[0062] Here, strategy configuration information refers to the strategies and rules established for task execution. Strategy configuration information may include task priority strategies, resource allocation strategies, emergency response strategies, and security strategies, etc., which are not specifically limited in this embodiment of the invention. Task priority strategies determine the rules for the order in which tasks are executed, such as executing high-priority tasks first. Resource allocation strategies determine the rules for how personnel and equipment resources are allocated, such as on-demand allocation or proportional allocation. Emergency response strategies refer to the measures taken to deal with unexpected situations during task execution, such as fault handling and personnel replacement. Security strategies ensure security measures during task execution, such as confidentiality requirements and operating procedures.

[0063] Parameter configuration information refers to the specific parameters and configurations set for task execution. Parameter configuration information may include task parameters, system parameters, environment parameters, and operation parameters, etc. This embodiment of the invention does not impose specific limitations on this.

[0064] After obtaining the third sample data, it can be input into the initial task duty plan model to obtain the predicted task duty plan information output by the initial task duty plan model. The predicted task duty plan information may include duty alert level, duty personnel grouping and deployment, duty equipment, and other task duty plan related information; however, this embodiment of the invention does not specifically limit this information.

[0065] After obtaining the predicted task duty schedule information, the initial task duty schedule model can be trained based on the predicted task duty schedule information and the labeled task duty schedule information to obtain the task duty schedule model.

[0066] Understandably, the task duty plan generation function based on the task duty plan model can automatically generate task duty plan information such as duty alert level, duty personnel grouping and deployment, and duty equipment through business object management, version management, parameter configuration and strategy configuration, based on key information such as task level, time and location, combined with data such as unit personnel and equipment capabilities, thereby assisting in plan formulation and improving the rationality of task duty plans.

[0067] Based on the above embodiments, step 140 further includes: Step 141: Perform motion recognition on the training site video corresponding to the target training plan information to obtain motion information; Step 142: Perform speech recognition on the training commands in the training site audio corresponding to the target training plan information to obtain text information; Step 143: Based on the action information, evaluate the standardization of the trainees' actions in the target training plan information, and based on the text information, analyze the execution of the training commands, and evaluate the standardization and consistency of the training process.

[0068] Specifically, considering that there may be unsuitable situations after the target training plan information is determined, the target training plan information can be evaluated.

[0069] Here, action recognition can be performed on the training site video corresponding to the target training plan information to obtain action information. Action recognition can use Two-Stream CNN (Two-Stream Convolutional Neural Network) or TSN (Temporal Segment Networks), etc. This embodiment of the invention does not make specific limitations on this.

[0070] Furthermore, the training commands in the training audio corresponding to the target training plan information can be recognized by speech to obtain text information. The speech recognition can use 3D ResNet, or Wav2Vec 2.0, etc. The embodiments of the present invention do not specifically limit this.

[0071] After obtaining the action information, the accuracy of the trainees' actions in the target training plan information can be evaluated based on the action information, and the execution of training commands can be analyzed based on the text information, as well as the standardization and consistency of the training process can be assessed.

[0072] Here, "action standardization" refers to the accuracy, standardization, and consistency of the actions performed by trainees. Assessing the action standardization of trainees based on action information can employ methods based on keypoint detection or action classification models; this embodiment of the invention does not specifically limit the methods used.

[0073] Analyzing the execution of training commands based on textual information allows us to check their accuracy, completeness, and timeliness; for example, whether commands are issued in the prescribed order and at the prescribed time. Furthermore, natural language processing techniques can be used to semantically understand the training command text, assessing its clarity and instructiveness.

[0074] Based on the above embodiments, step 143 further includes: Step 1431: Perform emotion recognition based on the action information and the text information to obtain the emotion recognition result; Step 1432: Adjust the target training plan information based on the emotion recognition results.

[0075] Specifically, emotion recognition can be performed based on action information and text information to obtain emotion recognition results. Here, emotion recognition of action information can be based on the amplitude, speed, and rhythm of the action. For example, a larger amplitude of action may indicate excitement or tension, while a smaller amplitude of action may indicate relaxation or fatigue; a faster speed of action may indicate tension or urgency, while a slower speed of action may indicate relaxation or fatigue; an irregular rhythm of action may indicate emotional instability, while a regular rhythm of action may indicate emotional stability.

[0076] Here, emotion recognition of text information relies on keyword analysis and semantic understanding, etc., and the embodiments of the present invention do not specifically limit this.

[0077] After obtaining the emotion recognition results, the training plan information can be adjusted based on these results. For example, if the emotion recognition results show that the trainees are in a positive mood, the training intensity or difficulty can be appropriately increased to further improve the training effect. Conversely, if the emotion recognition results show that the trainees are in a negative mood, the training intensity or difficulty can be appropriately reduced, and encouragement and incentive measures can be increased to help the trainees adjust their emotions.

[0078] The training plan auxiliary generation device provided by the present invention is described below. The training plan auxiliary generation device described below and the training plan auxiliary generation method described above can be referred to in correspondence.

[0079] Based on any of the above embodiments, the present invention provides a training plan auxiliary generation device. Figure 3This is a schematic diagram of the training plan auxiliary generation device provided by the present invention, as shown below. Figure 3 As shown, the device includes: The first generation unit 310 is used to generate annual training plan information for each level based on the annual plan model for each level; the annual training plan information for each level includes annual training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and training positions; The second generation unit 320 is used to generate monthly training plan information at each level according to the monthly plan model at each level; the monthly training plan information at each level includes monthly training plan information of at least one of the training subjects, the training time, the training evaluation criteria, the training stage, and the training positions; The third generation unit 330 is used to generate task duty plan information based on the task duty plan model and to generate training plan-related information based on the training plan to assist the generation model. The determining unit 340 is used to determine the target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and the training plan related information.

[0080] The apparatus provided in this invention determines target training plan information based on at least one of the following: annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information. The annual training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. The monthly training plan information at all levels includes at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. This method, by deeply integrating multi-dimensional data—including at least one of annual training plan information at all levels, monthly training plan information at all levels, task duty plan information, and training plan-related information—improves the accuracy of training plan generation, management efficiency, and user experience.

[0081] Based on any of the above embodiments, a first training unit is further included, wherein the first training unit is specifically used for: Obtain the initial annual plan models at all levels, the first sample data, and the labeled annual training plan information of the first sample data at all levels; the first sample data includes training outline data, training organization data of participating units, historical training data of trainees, and capability requirement data of participating units; The first sample data is input into the initial annual plan model at each level to obtain the predicted annual training plan information at each level output by the initial annual plan model at each level; Based on the differences between the predicted annual training plan information at each level and the labeled annual training plan information at each level, the initial annual plan model at each level is trained to obtain the annual plan model at each level.

[0082] Based on any of the above embodiments, a second training unit is further included, the second training unit being specifically used for: Obtain the second sample data, as well as the corresponding monthly training plan information for the tags; the second sample data includes annual training plan information for each level of the sample, historical training data of trainees, and unit capability requirement data; The second sample data is input into the initial monthly planning model at each level to obtain the predicted monthly training plan information output by the initial monthly planning model at each level; Based on the predicted monthly training plan information and the labeled monthly training plan information, the initial monthly plan models at each level are trained to obtain the monthly plan models at each level.

[0083] Based on any of the above embodiments, a third training unit is further included, wherein the third training unit is specifically used for: Obtain third sample data and the corresponding tag task duty plan information; the third sample data includes task attributes, unit personnel information, equipment resource data, strategy configuration information, and parameter configuration information; the task attributes include task level, task time, and task location. The third sample data is input into the initial task duty plan model to obtain the predicted task duty plan information output by the initial task duty plan model; Based on the predicted task duty schedule information and the labeled task duty schedule information, the initial task duty schedule model is trained to obtain the task duty schedule model.

[0084] Based on any of the above embodiments, the training plan information includes training subjects, personnel composition, training time, evaluation criteria, and training phases.

[0085] Based on any of the above embodiments, an evaluation unit is further included, wherein the evaluation unit is specifically used for: Action recognition is performed on the training site video corresponding to the target training plan information to obtain action information; The training commands in the training site audio corresponding to the target training plan information are subjected to speech recognition to obtain text information; Based on the action information, assess the standardization of the trainees' actions in the target training plan information, and based on the text information, analyze the execution of the training commands, as well as evaluate the standardization and consistency of the training process.

[0086] Based on any of the above embodiments, an emotion recognition unit is further included, wherein the emotion recognition unit is specifically used for: Emotion recognition is performed based on the action information and the text information to obtain the emotion recognition result; Based on the emotion recognition results, adjust the target training plan information.

[0087] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communications bus 440. The processor 410 can call logic instructions in the memory 430 to execute a training plan-assisted generation method. This method includes: generating annual training plan information for each level based on annual plan models at each level; the annual training plan information includes at least one of the following: training subjects, training time, training evaluation criteria, training stages, and participating positions; generating monthly training plan information for each level based on monthly plan models at each level; the monthly training plan information includes at least one of the following: training subjects, training time, training evaluation criteria, training stages, and participating positions; generating task duty plan information based on a task duty plan model; generating training plan-related information based on a training plan-assisted generation model; and determining target training plan information based on at least one of the annual training plan information, the monthly training plan information, the task duty plan information, and the training plan-related information.

[0088] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the training plan-assisted generation method provided by the above methods. The method includes: generating annual training plan information at each level according to annual plan models at each level; the annual training plan information at each level includes annual training plan information of at least one of training subjects, training time, training evaluation criteria, training stages, and training positions; generating monthly training plan information at each level according to monthly plan models at each level; the monthly training plan information at each level includes monthly training plan information of at least one of training subjects, training time, training evaluation criteria, training stages, and training positions; generating task duty plan information according to a task duty plan model; generating training plan-related information according to a training plan-assisted generation model; and determining target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and the training plan-related information.

[0090] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the training plan-assisted generation method provided by the above methods. This method includes: generating annual training plan information at various levels based on annual plan models at various levels; the annual training plan information at various levels includes annual training plan information of at least one of training subjects, training time, training evaluation criteria, training stages, and training positions; generating monthly training plan information at various levels based on monthly plan models at various levels; the monthly training plan information at various levels includes monthly training plan information of at least one of the training subjects, training time, training evaluation criteria, training stages, and training positions; generating task duty plan information based on a task duty plan model; generating training plan-related information based on a training plan-assisted generation model; and determining target training plan information based on at least one of the annual training plan information at various levels, the monthly training plan information at various levels, the task duty plan information, and the training plan-related information.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A training plan-assisted generation method, characterized in that, include: Based on the annual plan models at each level, generate annual training plan information for each level; The annual training plan information at each level includes information on at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. Based on the monthly plan models at each level, generate monthly training plan information at each level; The monthly training plan information at each level includes monthly training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions; Based on the task duty plan model, generate task duty plan information; based on the training plan to assist in model generation, generate training plan-related information. The target training plan information is determined based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information.

2. The training plan-assisted generation method according to claim 1, characterized in that, The training steps for the annual plan models at each level include: Obtain the initial annual plan models at all levels, the first sample data, and the labeled annual training plan information of the first sample data at all levels; the first sample data includes training outline data, training organization data of participating units, historical training data of participating personnel, and capability requirement data of participating units; The first sample data is input into the initial annual plan model at each level to obtain the predicted annual training plan information at each level output by the initial annual plan model at each level; Based on the differences between the predicted annual training plan information at each level and the labeled annual training plan information at each level, the initial annual plan model at each level is trained to obtain the annual plan model at each level.

3. The training plan-assisted generation method according to claim 1, characterized in that, The training steps for the monthly planning models at each level include: Obtain the second sample data, as well as the corresponding monthly training plan information for the tags; the second sample data includes annual training plan information for each level of the sample, historical training data of trainees, and unit capability requirement data; The second sample data is input into the initial monthly planning model at each level to obtain the predicted monthly training plan information output by the initial monthly planning model at each level; Based on the predicted monthly training plan information and the labeled monthly training plan information, the initial monthly plan models at each level are trained to obtain the monthly plan models at each level.

4. The training plan-assisted generation method according to any one of claims 1 to 3, characterized in that, The training steps of the task duty schedule model include: Obtain third sample data and the corresponding tag task duty plan information; the third sample data includes task attributes, unit personnel information, equipment resource data, strategy configuration information, and parameter configuration information; the task attributes include task level, task time, and task location. The third sample data is input into the initial task duty plan model to obtain the predicted task duty plan information output by the initial task duty plan model; Based on the predicted task duty schedule information and the labeled task duty schedule information, the initial task duty schedule model is trained to obtain the task duty schedule model.

5. The training plan-assisted generation method according to any one of claims 1 to 3, characterized in that, The training plan includes information on training subjects, personnel composition, training time, evaluation criteria, and training phases.

6. The training plan-assisted generation method according to any one of claims 1 to 3, characterized in that, The step of determining the target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information further includes: Action recognition is performed on the training site video corresponding to the target training plan information to obtain action information; The training commands in the training site audio corresponding to the target training plan information are subjected to speech recognition to obtain text information; Based on the action information, assess the standardization of the trainees' actions in the target training plan information, and based on the text information, analyze the execution of the training commands, as well as evaluate the standardization and consistency of the training process.

7. The training plan-assisted generation method according to claim 6, characterized in that, The process of evaluating the standardization of trainees' movements in the target training plan information based on the movement information, analyzing the execution of training commands based on the text information, and evaluating the standardization and consistency of the training process, further includes: Emotion recognition is performed based on the action information and the text information to obtain the emotion recognition result; Based on the emotion recognition results, adjust the target training plan information.

8. A training plan-aided generation device, characterized in that, include: The first generation unit is used to generate annual training plan information for each level based on the annual plan model at each level. The annual training plan information at each level includes information on at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions. The second generation unit is used to generate monthly training plan information for each level based on the monthly plan model at each level. The monthly training plan information at each level includes monthly training plan information for at least one of the following: training subjects, training time, training evaluation standards, training stages, and participating positions; The third generation unit is used to generate task duty plan information based on the task duty plan model and to generate training plan-related information based on the training plan to assist the generation model. The determining unit is used to determine target training plan information based on at least one of the annual training plan information at each level, the monthly training plan information at each level, the task duty plan information, and training plan-related information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the training plan-assisted generation method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the training plan-assisted generation method as described in any one of claims 1 to 7.

Images