Underwater robot dam body inspection virtual drilling scene recommendation method and system

Abstract

The invention relates to the technical field of underwater dam body inspection, and discloses an underwater robot dam body inspection virtual drilling scene recommendation method and system, and the method achieves the assessment of the underwater robot dam body inspection virtual drilling skill in a plurality of to-be-drilled scenes through combining an assessment attribute set and a drilling scene data set. According to the invention, the inspection capability of the underwater robot in different scenes can be clearly inspected, so that the drilling is more targeted, and the mastering conditions of drilling personnel on various skills in different scenes can be comprehensively understood. Furthermore, a plurality of skill examination and evaluation results are used to predict a non-drilling scene, the performance of the underwater robot in a new scene can be known in advance, a reference is provided for making a drilling plan, and the adaptability and foresight of the system are enhanced. And finally, the target recommendation scene is determined in combination with the real case attribute data set, the existing assessment result and the prediction result, and the actual situation and future requirements can be comprehensively considered, so that the recommended scene is more accurate and practical.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater dam body inspection, and in particular to a method and system for recommending virtual drill scenes for underwater robot dam body inspection. Background Art

[0002] With the development of underwater robot technology, underwater robots have begun to be used more and more in underwater dam inspection scenarios in recent years. At the same time, due to the complexity and high price of underwater robots, their operators need to undergo a lot of training before actual operations. However, due to the difficulty and high cost of actual underwater robot operations, operators usually need to be trained through virtual drills. However, at present, traditional virtual drills are mainly scored step by step according to fixed steps, and it is impossible to scientifically and comprehensively assess the various skills mastered by the drillers, as well as their decision-making and adaptability. At the same time, there are many drill scenarios, and drillers cannot quickly choose the drill scenario that suits them. The above factors reduce the efficiency of virtual drill training.

[0003] Existing technologies can only reflect whether the trainees have completed all the task points in a certain training scenario. There is no in-depth processing and analysis of the trainees' various skills. The trainees cannot intuitively understand their level of mastery of various skills. At the same time, the system cannot screen and recommend suitable training scenarios for each trainee based on the level of skill mastery of different trainees. Summary of the invention

[0004] In view of this, the present invention provides a method and system for recommending virtual rehearsal scenarios for underwater robot dam inspection, so as to solve the problem in the existing technology that trainees cannot intuitively understand their mastery of various skills, and the system cannot screen and recommend suitable rehearsal scenarios for each trainee according to the skill mastery of different trainees.

[0005] In a first aspect, the present invention provides a method for recommending a virtual training scenario for underwater robot dam inspection, which is used in an underwater robot virtual training system; the method comprises:

[0006] A real case attribute data set, an assessment attribute set and a plurality of drill scenario data sets of the scenarios to be drilled are obtained, and the real case attribute data set and the drill scenario data set are stored in a scenario attribute database in a structured storage manner and are associated with corresponding scenarios; based on the assessment attribute set, the drill scenario data set is used to conduct a skill assessment and evaluation of a virtual drill of an underwater robot dam body inspection in a plurality of scenarios to be drilled, and a plurality of skill assessment and evaluation results are obtained; based on the plurality of skill assessment and evaluation results, the assessment and evaluation conditions of the virtual drill skills of the underwater robot dam body inspection in a plurality of initial un-drilled scenarios are predicted, and a plurality of skill assessment and evaluation prediction results are obtained; based on the real case attribute data set, the plurality of skill assessment and evaluation results and the plurality of skill assessment and evaluation prediction results, a target recommended scenario for a virtual drill of an underwater robot dam body inspection is determined.

[0007] The method for recommending virtual drill scenes for underwater robot dam inspection provided by the present invention first obtains a real case attribute data set to truly reflect the actual situation in the underwater robot dam inspection, and the assessment attribute set can be assessed and evaluated from different capability dimensions, providing standards and frameworks for subsequent comprehensive evaluation. At the same time, by structured storage of the drill scene data set and associating it with the corresponding scene, different drill scenes can be quickly and accurately called and managed, providing rich scene resources for the virtual drill of underwater robot dam inspection, avoiding the time waste of repeatedly building scenes, and greatly improving the efficiency of drills. Secondly, combining the assessment attribute set and the drill scene data set to conduct the underwater robot dam inspection virtual drill skill assessment and evaluation in multiple scenes to be drilled, it can clearly test the inspection ability of the underwater robot in different scenes, making the drill more targeted, and then fully understand the mastery of various skills of the drill personnel in different scenes. Further, using multiple skill assessment and evaluation results to predict the un-drilled scenes, it is possible to understand the performance of the underwater robot in the new scene in advance, provide a reference for formulating the drill plan, and enhance the adaptability and foresight of the system. Finally, the target recommendation scenario is determined by combining the real case attribute data set, existing assessment results and prediction results, which can comprehensively consider the actual situation and future needs, making the recommended scenario more accurate and practical.

[0008] In an optional implementation, based on the assessment attribute set, the underwater robot dam body inspection virtual exercise skill assessment and evaluation is performed in multiple to-be-exercised scenarios using the exercise scenario data set, and multiple skill assessment and evaluation results are obtained, including:

[0009] The test matrix is ​​determined based on the assessment attribute set; the first assessment association matrix and the first scoring matrix of the scene to be drilled are obtained, the first assessment association matrix is ​​used to associate the drill assessment items with the drill skill assessment attributes, and the first scoring matrix is ​​used to record the score of each assessment item; based on the assessment attribute set, the test matrix, the first assessment association matrix and the first scoring matrix, the drill scene data set is used to conduct a virtual drill skill assessment and evaluation of the underwater robot dam body inspection in multiple scenes to be drilled, and multiple skill assessment and evaluation results are obtained.

[0010] The method for recommending virtual drill scenes for underwater robot dam inspection provided by the present invention has an assessment attribute set covering various key skill indicators, which can ensure the integrity and systematicness of the evaluation and avoid the limitations of single-dimensional evaluation. Further, the first assessment association matrix accurately associates the drill assessment items with the drill skill assessment attributes, so that each assessment item can clearly correspond to the specific skill requirements, which helps the evaluator to accurately judge the performance of the participants in different skills and provide a basis for targeted improvements. At the same time, the first scoring matrix is ​​used to record the score of each assessment item, so as to achieve a quantitative evaluation of the drill skills. Therefore, by determining the test matrix based on the assessment attribute set, and combining the first assessment association matrix and the first scoring matrix, the virtual drill skills of underwater robot dam inspection can be comprehensively evaluated from multiple dimensions. At the same time, the drill scene data set is used to perform assessment and evaluation in multiple scenes to be drilled, which enhances the adaptability and practicality of the technology. Different drill scenes can simulate various actual situations, test the coping ability of participants in different environments, and ensure that the evaluation results are more representative and reliable.

[0011] In an optional implementation, determining a test matrix based on the assessment attribute set includes:

[0012] Obtain the direct correlation between each assessment attribute in the assessment attribute set and determine the adjacency matrix. The assessment attributes are divided into primary attributes and secondary attributes; obtain the comprehensive relationship between each assessment attribute in the assessment attribute set and determine the reachable matrix; obtain the qualified status of each secondary attribute in the assessment attribute set and determine the cognitive structure; determine the test matrix based on the adjacency matrix, reachable matrix and cognitive structure.

[0013] The underwater robot dam inspection virtual drill scene recommendation method provided by the present invention can intuitively show the direct correlation between each assessment attribute in the assessment attribute set by determining the adjacency matrix. At the same time, after the assessment attributes are divided into primary attributes and secondary attributes, the direct correlation between attributes of different levels can be understood in a more hierarchical manner, which is convenient for targeted management and optimization. Further, determining the reachable matrix can obtain the comprehensive relationship between each assessment attribute in the assessment attribute set, which can not only understand the direct correlation, but also gain insight into the indirect impact path. Further, determining the cognitive structure can obtain the qualified status of each secondary attribute in the assessment attribute set, and then it can be specifically understood whether the performance of each secondary attribute in the current system is up to standard. Finally, combining the adjacency matrix, the reachable matrix and the cognitive structure to determine the test matrix can ensure that the test content is comprehensive, scientific and targeted. Therefore, by comprehensively considering the information provided by the three matrices, the key relationship between each assessment attribute can be covered, and the qualified status of the secondary attributes can be focused on.

[0014] In an optional implementation, based on multiple skill assessment results, the assessment and evaluation of the underwater robot dam body inspection virtual drill skills in multiple initial un-drilled scenarios are predicted to obtain multiple skill assessment prediction results, including:

[0015] A second assessment association matrix and a second score matrix are obtained for multiple initial un-rehearsed scenarios; based on multiple skill assessment evaluation results, the second assessment association matrix and the second score matrix, the assessment and evaluation conditions of the underwater robot dam body inspection virtual rehearsal skills in multiple initial un-rehearsed scenarios are predicted to obtain multiple skill assessment and evaluation prediction results.

[0016] The method for recommending underwater robot dam body inspection virtual rehearsal scenarios provided by the present invention uses multiple existing skill assessment results for prediction, fully utilizes existing data and experience, and can discover the potential laws and commonalities between different scenarios. At the same time, combined with the second assessment association matrix and the second scoring matrix, the analysis of unrehearsed scenarios can be further refined, improving the accuracy and reliability of the prediction. Therefore, by implementing the present invention, by combining multiple skill assessment results, the second assessment association matrix and the second scoring matrix to predict the assessment and evaluation conditions of multiple initial unrehearsed scenarios, the coverage of underwater robot dam body inspection virtual rehearsal skill evaluation can be greatly expanded.

[0017] In an optional implementation, based on a real case attribute data set, multiple skill assessment results, and multiple skill assessment prediction results, a target recommendation scenario for a virtual exercise of underwater robot dam inspection is determined, including:

[0018] Based on multiple skill assessment prediction results, multiple target unrehearsed scenarios are determined from multiple initial unrehearsed scenarios; based on a real case attribute data set, multiple scenario importance values ​​and multiple scenario similarity values ​​of the multiple target unrehearsed scenarios are calculated respectively; based on multiple skill assessment prediction results, multiple scenario importance values ​​and multiple scenario similarity values, target recommended scenarios for virtual rehearsals of underwater robot dam inspections are determined.

[0019] The method for recommending underwater robot dam body inspection virtual rehearsal scenarios provided by the present invention can make full use of the predicted results of multiple skill assessments and evaluations, and screen out multiple target unexercised scenarios with potential value and demand for further analysis. Further, by calculating multiple scene importance values ​​in combination with real case attribute data sets, the scenarios can be quantitatively evaluated from the perspective of practical application. At the same time, by calculating multiple scene similarity values ​​in combination with real case attribute data sets, it can help discover the similarities and correlations between different scenarios. Finally, by combining multiple skill assessment prediction results, multiple scene importance values ​​and multiple scene similarity values ​​to determine the target recommended scenarios for underwater robot dam body inspection virtual rehearsal, multiple factors can be comprehensively considered to obtain more scientific and reasonable recommendation results. Therefore, by implementing the present invention, both the predicted assessment and evaluation conditions are taken into account and the importance and similarity in practical applications are combined, which can better meet the actual recommendation needs.

[0020] In an optional implementation, based on the real case attribute data set, multiple scene importance values ​​and multiple scene similarity values ​​of multiple target unexercised scenes are calculated respectively, including:

[0021] Calculate multiple attribute frequency weight values ​​and multiple attribute similarity values ​​of the real case attribute data set; calculate multiple scene importance values ​​based on multiple attribute frequency weight values; calculate multiple scene similarity values ​​using multiple attribute similarity values ​​based on expert experience and hierarchical analysis method.

[0022] The method for recommending virtual rehearsal scenarios for underwater robot dam inspection provided by the present invention calculates multiple attribute frequency weight values ​​of a real case attribute data set, and can quantify the importance of each attribute in the actual case. At the same time, calculating multiple attribute similarity values ​​can help determine the similarity between different scenarios at the attribute level. Further, by calculating multiple scene importance values ​​in combination with multiple attribute frequency weight values, the importance of each unrehearsed scenario for underwater robot dam inspection can be evaluated as a whole. Finally, when using multiple attribute similarity values ​​to calculate multiple scene similarity values, expert experience can provide an intuitive understanding and judgment of the scene, and the hierarchical analysis method can systematically handle the complex relationship between multiple attributes to ensure the accuracy and reliability of the similarity value.

[0023] In a second aspect, the present invention provides an underwater robot virtual rehearsal system for executing the underwater robot dam inspection virtual rehearsal scene recommendation method of the first aspect or any corresponding embodiment thereof; the system comprises: an underwater robot virtual rehearsal assessment module and a virtual rehearsal scene recommendation module.

[0024] The underwater robot virtual drill system provided by the present invention can comprehensively consider the actual situation and future needs through the underwater robot virtual drill assessment module and the virtual drill scenario recommendation module, and thus can more scientifically and reasonably determine the target recommended scenario for the underwater robot dam body inspection virtual drill.

[0025] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the method for recommending virtual rehearsal scenarios for underwater robot dam inspection according to the first aspect or any corresponding embodiment thereof.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for recommending a virtual rehearsal scenario for underwater robot dam inspection according to the first aspect or any corresponding embodiment thereof.

[0027] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for recommending virtual rehearsal scenarios for underwater robot dam inspection according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 is a structural block diagram of an underwater robot virtual drill system according to an embodiment of the present invention;

[0030] Figure 2 is a flow chart of a method for recommending a virtual drill scenario for underwater robot dam inspection according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of another method for recommending a virtual drill scenario for underwater robot dam inspection according to an embodiment of the present invention;

[0032] Figure 4 is a flow chart of another method for recommending a virtual drill scenario for underwater robot dam inspection according to an embodiment of the present invention;

[0033] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0035] The underwater robot virtual drill system allows underwater robot operators to conduct virtual drills anytime and anywhere to improve their drill skills. However, if the virtual drill system does not have a suitable assessment function, the drill operators will not be able to quickly obtain their mastery of various skills, and will not be able to quickly select the scene suitable for their drill from a variety of drill scenes according to their mastery of skills, thus limiting the effect of virtual drills.

[0036] Furthermore, most of the existing underwater robot virtual drill systems use virtual engines, such as Unity3D, UE, etc., to create drill simulation scenes with simple functions in the engine. The few systems with drill evaluation functions only complete tasks step by step in a certain scene, and gradually score them, and there is no drill scene recommendation function.

[0037] According to an embodiment of the present invention, an embodiment of a method for recommending virtual rehearsal scenarios for underwater robot dam inspection is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0038] In this embodiment, a method for recommending a virtual drill scene for underwater robot dam inspection is provided. Figure 1 The underwater robot virtual training system 1 shown; Figure 2 FIG. 4 is a flow chart of a method for recommending a virtual drill scene for underwater robot dam inspection according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0039] Step S201, obtaining a real case attribute data set, an assessment attribute set, and a plurality of drill scenario data sets of to-be-drilled scenarios.

[0040] Specifically, the real case attribute data set represents a representative set of attribute data extracted from actual underwater robot dam inspection cases, which may include underwater robot performance data, dam characteristic data, environmental data, inspection task execution data, etc. It can be obtained by installing various sensors on the underwater robot for real-time collection, or it can be obtained from a historical database.

[0041] The assessment attribute set represents a collection of attributes used to assess and evaluate the underwater robot dam body inspection virtual drill skills. In this embodiment, the underwater robot dam body inspection virtual drill skills of the drill personnel are assessed from four aspects: drill organization and scheduling capabilities, inspection task processing capabilities, emergency handling capabilities, and comprehensive management capabilities. Among them, the assessment attributes are divided into primary attributes and secondary attributes. When all the secondary attributes contained in each primary attribute are qualified, the drill personnel's primary attribute assessment is qualified. The assessment attribute settings in this embodiment are shown in Table 1 below:

[0042] Table 1. Assessment attributes

[0043]

[0044] The real case attribute data set and the drill scene data set are stored in the scene attribute database in a structured storage manner and are associated with the corresponding scene. Specifically, the real case attribute data set and the drill scene data set are structured and stored in numerical, symbolic, and entity types. Numerical types include water level height, water flow velocity, etc., symbolic types include weather conditions, water quality conditions, etc., and entity types include defect structures, which may include defect type, defect severity, defect location, etc. The scene feature attribute information is stored in the scene attribute database and associated with the corresponding scene.

[0045] Step S202, based on the assessment attribute set, using the exercise scenario data set to conduct an underwater robot dam body inspection virtual exercise skill assessment in multiple to-be-exercised scenarios, and obtain multiple skill assessment results.

[0046] Specifically, the acquired drill scene data set can be used to conduct virtual drills of underwater robot dam inspections in multiple scenes to be drilled, and each assessment attribute in each drill process can be evaluated against the multiple assessment attributes and evaluation criteria contained in the assessment attribute set described in step S101 to obtain corresponding multiple skill assessment evaluation results that reflect the drill personnel's mastery of each drill assessment skill.

[0047] Step S203, based on the multiple skill assessment results, predict the assessment of the underwater robot dam body inspection virtual drill skills in multiple initial un-drilled scenarios to obtain multiple skill assessment prediction results.

[0048] Specifically, by combining the multiple skill assessment results of the rehearsed scenarios to predict the assessment and evaluation of the underwater robot dam inspection virtual rehearsal skills in multiple initial uncooked scenarios, the skill assessment status in multiple initial uncooked scenarios can be understood in advance, so as to carry out targeted preparation and training, thereby reducing unnecessary waste of rehearsal time and resources and improving rehearsal efficiency.

[0049] Exemplarily, a prediction model between the skill assessment results and the scene features can be established by selecting appropriate machine learning algorithms, such as regression analysis, decision trees, neural networks, etc. The existing assessment results are used as training data, the scene features are input, and the corresponding skill assessment values ​​are output. Furthermore, the features of the initial unexercised scene can be input into the trained prediction model to obtain multiple skill assessment prediction results. Among them, the prediction model can be trained using the training data, and the parameters of the model can be continuously adjusted to minimize the prediction error. Methods such as cross-validation can be used to evaluate the performance of the model, and to adjust the parameters and optimize the model.

[0050] Step S204, based on the real case attribute data set, multiple skill assessment results and multiple skill assessment prediction results, determine the target recommended scenario for the underwater robot dam inspection virtual drill.

[0051] Specifically, by analyzing the real case attribute data set, we can obtain the structural characteristics of different dam bodies, the problems encountered in actual inspections and their solutions, the impact of environmental factors on inspections, etc. By analyzing multiple skill assessment results, we can understand the strengths and weaknesses of drill personnel in different drill scenarios. By analyzing multiple skill assessment prediction results, we can understand the situations that may occur in unexercised scenarios.

[0052] Therefore, by combining the real case attribute data set, multiple skill assessment results and multiple skill assessment prediction results, more suitable and representative training scenarios for underwater robot dam inspection virtual training can be recommended to trainees or operators in a more comprehensive and accurate manner.

[0053] Furthermore, determining the target recommended scenarios can provide a clear direction for planning the virtual drills of underwater robot dam inspections, and then the drill time and resource allocation can be reasonably arranged according to the recommended scenarios to improve the effectiveness and efficiency of the drills.

[0054] The method for recommending virtual drill scenarios for underwater robot dam inspection provided in this embodiment first obtains a real case attribute data set to truly reflect the actual situation of underwater robot dam inspection, and the assessment attribute set can be assessed and evaluated from different capability dimensions, providing standards and frameworks for subsequent comprehensive evaluation. At the same time, by structured storage of drill scenario data sets and associating with corresponding scenarios, different drill scenarios can be quickly and accurately called and managed, providing rich scene resources for underwater robot dam inspection virtual drills, avoiding the time waste of repeatedly building scenes, and greatly improving the efficiency of drills. Secondly, combining the assessment attribute set and the drill scenario data set to conduct underwater robot dam inspection virtual drill skill assessment and evaluation in multiple scenes to be drilled, it is possible to clearly test the inspection ability of underwater robots in different scenes, making the drill more targeted, and then fully understand the mastery of various skills of drill personnel in different scenes. Further, using multiple skill assessment and evaluation results to predict unexercised scenes can understand the performance of underwater robots in new scenes in advance, provide reference for formulating drill plans, and enhance the adaptability and foresight of the system. Finally, the target recommendation scenario is determined by combining the real case attribute data set, existing assessment results and prediction results, which can comprehensively consider the actual situation and future needs, making the recommended scenario more accurate and practical.

[0055] In this embodiment, a method for recommending a virtual drill scene for underwater robot dam inspection is provided. Figure 1 The underwater robot virtual training system 1 shown; Figure 3 FIG. 4 is a flow chart of a method for recommending a virtual drill scene for underwater robot dam inspection according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0056] Step S301, obtain a real case attribute data set, an assessment attribute set, and a plurality of drill scenario data sets for the scenarios to be drilled. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0057] Step S302, based on the assessment attribute set, using the exercise scenario data set to conduct an underwater robot dam body inspection virtual exercise skill assessment in multiple to-be-exercised scenarios, and obtain multiple skill assessment results.

[0058] Specifically, the above step S302 includes:

[0059] Step S3021, determining a test matrix based on the assessment attribute set.

[0060] Specifically, the test matrix may include an adjacency matrix, a reachability matrix, and a cognitive structure.

[0061] Among them, the adjacency matrix is ​​used to describe the direct correlation between each assessment attribute; the reachability matrix is ​​used to describe the comprehensive relationship between each assessment attribute; and the cognitive structure is used to record the mastery of the secondary attributes of the drill personnel.

[0062] Therefore, the corresponding test matrix can be determined in combination with the obtained assessment attribute set.

[0063] In some optional implementations, the above step S3021 includes:

[0064] Step a1, obtaining the direct correlation between each assessment attribute in the assessment attribute set and determining the adjacency matrix.

[0065] Step a2, obtaining the comprehensive relationship between each assessment attribute in the assessment attribute set and determining the reachable matrix.

[0066] Step a3, obtaining the qualification status of each secondary attribute in the assessment attribute set and determining the cognitive structure.

[0067] Step a4, determining the test matrix based on the adjacency matrix, the reachability matrix and the cognitive structure.

[0068] Specifically, the adjacency matrix can be determined by obtaining the direct correlation between each assessment attribute in the assessment attribute set. If there is a direct correlation between each assessment attribute, the corresponding position in the adjacency matrix is ​​recorded as "1", otherwise it is recorded as "0".

[0069] The adjacency matrix is ​​usually a two-dimensional matrix with the number of rows and columns equal to the number of assessment attributes. For example, if there are five assessment attributes, the adjacency matrix is ​​a 5×5 matrix. If assessment attribute A is directly related to assessment attribute B, then the position in row A and column B and row B and column A of the matrix is ​​recorded as "1".

[0070] Furthermore, the reachability matrix can be determined by obtaining the comprehensive relationship between each assessment attribute in the assessment attribute set. If there is a direct, indirect or self-association between each assessment attribute, the corresponding position of the adjacency matrix is ​​recorded as "1", otherwise it is recorded as "0".

[0071] Furthermore, the cognitive structure is used to record the mastery of the secondary attributes of the drill personnel. The ideal response model can be used for recording. If the corresponding assessment attribute is qualified, it is recorded as "1", which means mastery. Otherwise, it is recorded as "0", which means not mastered. This binary recording method is concise and clear, and is convenient for statistics and analysis.

[0072] Furthermore, through the records of "1" and "0", it is possible to intuitively see which aspects the trainees have mastered and which aspects need further improvement.

[0073] Finally, the corresponding test matrix can be determined by combining the obtained adjacency matrix, reachability matrix and cognitive structure.

[0074] Step S3022, obtaining a first assessment correlation matrix and a first score matrix of the scenario to be practiced.

[0075] Among them, the first assessment association matrix is ​​used to associate the drill assessment items with the drill skill assessment attributes; the first score matrix is ​​used to record the score of each assessment item.

[0076] In this embodiment, the drill assessment items are set as shown in Table 2 below:

[0077] Table 2: Exercise Assessment Items

[0078]

[0079] In an optional embodiment, the first assessment correlation matrix is ​​shown in Table 3 below:

[0080] Table 3. First assessment correlation matrix

[0081]

[0082] Step S3023, based on the assessment attribute set, the test matrix, the first assessment association matrix and the first score matrix, the exercise scenario data set is used to conduct an underwater robot dam body inspection virtual exercise skill assessment in multiple to-be-exercised scenarios to obtain multiple skill assessment results.

[0083] Specifically, when the underwater robot dam inspection virtual drill skill assessment is conducted in multiple drill scenarios using the drill scenario data set, the drill personnel's mastery of various drill assessment skills can be obtained by combining the assessment attribute set, the test matrix, the first assessment association matrix, and the first score matrix, that is, multiple skill assessment results can be obtained:

[0084] [α 11 α 12 α 13 α 21 α 22 α 23 α 24 α 25 α 26 α 31 α 32 α 33 α 41 α 42 ].

[0085] In an optional embodiment, a drill project includes a combination of several assessment items. For example, the assessment items of drill project A include 1 equipment scheduling work, 2 hoisting operations, 5 precision inspections, and 3 detailed inspections. The drill personnel qualifiedly completed 1 equipment scheduling work, 1 hoisting operation project, 4 precision inspections, and 3 detailed inspections in drill project A. The score percentage is 82% of the total project assessment workload and the number of completed tasks. The corresponding assessment correlation matrix of the obtained assessment skill mastery is [-,-,1,0.5,-,-,0.8,0.8,1,-,-,-,-,-], that is, the operating equipment scheduling ability scores 1 point, the robot hoisting ability scores 0.5 points, the defect recognition ability scores 0.8 points, the defect detection ability scores 0.8 points, the defect and obstacle handling ability scores 1 point, and no other points.

[0086] Step S303, based on the multiple skill assessment results, predict the assessment of the underwater robot dam body inspection virtual drill skills in multiple initial un-drilled scenarios to obtain multiple skill assessment prediction results.

[0087] Specifically, the above step S303 includes:

[0088] Step S3031, obtaining a second assessment association matrix and a second score matrix for a plurality of initial un-exercised scenarios.

[0089] Specifically, the specific description of the second assessment association matrix and the second scoring matrix can refer to the description of the first assessment association matrix and the first scoring matrix in step S3022, which will not be repeated here.

[0090] Step S3032, based on multiple skill assessment results, the second assessment association matrix and the second score matrix, predict the assessment and evaluation of the underwater robot dam inspection virtual drill skills in multiple initial un-drilled scenarios to obtain multiple skill assessment prediction results.

[0091] Specifically, based on the trainees' mastery of various drill assessment skills, combined with the assessment correlation matrix and score matrix of the assessment scenarios that have not been rehearsed, the trainees' scores in the virtual drill scenarios that have not been rehearsed can be predicted, and the expected score percentage can be calculated to obtain multiple skill assessment prediction results.

[0092] For example, the assessment items of drill project B include 1 engineering vehicle dispatching work, 1 operating personnel dispatching work, 1 equipment dispatching work, 2 lifting and lowering operation projects, 1 lifting and lowering operation, 5 precision inspections, and 6 detailed inspections. Given the personnel skill mastery matrix [-,-,1,0.5,-,-,0.8,0.8,1,-,-,-,-,-], it is predicted that the personnel will be able to complete 1 equipment dispatching work, 0.5 lifting and lowering operations (expected value), 4 precision inspections, and 6 detailed inspections in drill project B. The predicted score percentage is 68%.

[0093] Step S304: Determine the target recommended scenario for the underwater robot dam inspection virtual exercise based on the real case attribute data set, multiple skill assessment results and multiple skill assessment prediction results. Figure 1 Step S204 of the illustrated embodiment will not be described in detail here.

[0094] The method for recommending underwater robot dam inspection virtual drill scenarios provided in this embodiment can comprehensively evaluate the underwater robot dam inspection virtual drill skills from multiple dimensions by determining the test matrix based on the assessment attribute set and combining the first assessment association matrix and the first score matrix. At the same time, the adaptability and practicality of the technology are enhanced by using the drill scenario data set to conduct assessments in multiple scenarios to be drilled. Different drill scenarios can simulate various actual situations, test the participants' coping capabilities in different environments, and ensure that the evaluation results are more representative and reliable. Further, by combining multiple skill assessment results, the second assessment association matrix and the second score matrix to predict the assessment and evaluation of multiple initial unexercised scenarios, the coverage of the underwater robot dam inspection virtual drill skill evaluation can be greatly expanded. Finally, the target recommendation scenario is determined by combining the real case attribute data set, the existing assessment and evaluation results and the prediction results, which can comprehensively consider the actual situation and future needs, making the recommended scenario more accurate and practical.

[0095] In this embodiment, a method for recommending a virtual drill scene for underwater robot dam inspection is provided. Figure 1 The underwater robot virtual training system 1 shown; Figure 4 FIG. 4 is a flow chart of a method for recommending a virtual drill scene for underwater robot dam inspection according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0096] Step S401, obtain a real case attribute data set, an assessment attribute set, and a plurality of drill scenario data sets for the scenarios to be drilled. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0097] Step S402: Based on the assessment attribute set, the training scenario data set is used to conduct a virtual training skill assessment of the underwater robot dam inspection in multiple training scenarios to obtain multiple skill assessment results. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0098] Step S403, based on the multiple skill assessment results, predict the assessment of the underwater robot dam inspection virtual drill skills in multiple initial unexercised scenarios to obtain multiple skill assessment prediction results. Figure 3 Step S303 of the illustrated embodiment will not be described in detail here.

[0099] Step S404, based on the real case attribute data set, multiple skill assessment results and multiple skill assessment prediction results, determine the target recommended scenario for the underwater robot dam inspection virtual drill.

[0100] Specifically, the above step S404 includes:

[0101] Step S4041, based on the multiple skill assessment prediction results, determine multiple target unrehearsed scenarios from multiple initial unrehearsed scenarios.

[0102] Specifically, multiple initial unrehearsed scenarios can be sorted from low to high according to the predicted score ratio of the current practitioner in the corresponding scenario, that is, the skill assessment prediction result, and the rehearsal scenarios with predicted score ratios between [50%, 70%] are preferentially selected as the corresponding target unrehearsed scenarios.

[0103] Step S4042, based on the real case attribute data set, calculate multiple scene importance values ​​and multiple scene similarity values ​​of multiple target unexercised scenes respectively.

[0104] Specifically, multiple scene importance values ​​can evaluate the importance of each unexercised scene for the underwater robot dam inspection as a whole; multiple scene similarity values ​​can help determine the rules and commonalities between similar scenes.

[0105] In some optional implementations, the above step S4042 includes:

[0106] Step b1, calculating multiple attribute frequency weight values ​​and multiple attribute similarity values ​​of the real case attribute data set.

[0107] Specifically, the real operation case attribute values ​​are extracted from the real case attribute data set. For example, for a specific real operation case, it is determined that the dam type is a concrete dam, the dam height is a specific value, the water flow velocity is within a certain range, etc.

[0108] Furthermore, the frequency weight of each attribute value in the real job case is calculated. The higher the weight, the more important the attribute is:

[0109] (1) Count the number of times each attribute value appears in all real operation cases. For example, count how many cases are concrete dams, how many cases have dam heights within a specific range, etc.

[0110] (2) Calculate the frequency of each attribute value, that is, the number of times the attribute value appears divided by the total number of real job cases.

[0111] (3) Normalize the frequency of each attribute value so that the sum of the frequencies of all attribute values ​​is 1.

[0112] (4) The normalized frequency is the frequency weight of the attribute value. The higher the weight, the more important the attribute value is in the real operation case.

[0113] Furthermore, the scene attribute data is divided into digital type, symbol type, and entity type, and the similarity of each attribute value is calculated respectively, among which the entity type sub-attribute can be divided into digital type and symbol type. The numerical attribute can be regarded as two points. The farther the calculated distance is, the lower the similarity is, and vice versa. The symbolic attribute determines the similarity value by comparing whether the symbol value is the same.

[0114] Step b2, calculating multiple scene importance values ​​based on multiple attribute frequency weight values.

[0115] Specifically, the presence or absence of each attribute value in the drill scenario is counted, and the weighted sum of the scenario attribute values ​​is calculated: if a certain attribute value exists in the scenario, the frequency weight of the attribute value is added to the sum; if it does not exist, it is not added. For example, for the target un-drilled scenario A, if the concrete dam attribute value exists in the scenario, and the frequency weight of the concrete dam attribute value is 0.4, then 0.4 is added to the weighted sum of scenario A.

[0116] Furthermore, normalization is performed and the importance value of each scene is calculated: the weighted sum of all target unexercised scenes is normalized so that the sum of the importance values ​​of all scenes is 1. The normalized weighted sum is the importance value of each scene. The higher the importance value, the greater the importance of the scene in the underwater robot dam inspection.

[0117] In an optional example, the real operation case is decomposed into the operation tasks and their times in the assessment item table. For example, if there are n real operation cases in total, and there are n1 times of precision inspection, then the weight of precision inspection is For the drill scenario C, the precision inspection work occurs n1' times, and its weighted value is calculated as I1=k1*n1'. The weighted values ​​of all the work that occurs in the drill scenario C are summed up to obtain its importance value.

[0118] Step b3, based on expert experience and analytic hierarchy process, multiple attribute similarity values ​​are used to calculate multiple scene similarity values.

[0119] Specifically, combined with expert scoring, the analytic hierarchy process is used to set the weight of each attribute value in the similarity calculation, and the weighted sum is taken to calculate the similarity of the exercise scenarios.

[0120] In an optional embodiment, the weight set K of each scenario factor and the attribute set S of the exercise scenario A are obtained by combining experts and other methods. A , the attribute set S of the drill scene B B , the difference equation of a certain attribute of the exercise scenario A / B is shown in the following relationship:

[0121]

[0122] Where: S A [x] represents the value of a certain attribute in the exercise scenario A; S B [x] represents the value of a certain attribute in exercise scenario B;

[0123] Furthermore, the similarity equation of the exercise scenario A / B is shown in the following relationship:

[0124] f(n)=∑K*f(S A ,S B )

[0125] Where: f(n) represents the similarity value of the drill scenario A / B.

[0126] Step S4043, based on multiple skill assessment prediction results, multiple scene importance values ​​and multiple scene similarity values, determine the target recommended scene for the underwater robot dam inspection virtual drill.

[0127] Specifically, the target recommended scenario for the virtual drill of underwater robot dam inspection is determined by comprehensively considering multiple skill assessment prediction results, multiple scenario importance values ​​and multiple scenario similarity values. This can comprehensively consider multiple factors, taking into account both the predicted assessment situation and the importance and similarity in actual applications, thereby making the obtained target recommended scenario more scientific, reasonable and representative.

[0128] The method for recommending underwater robot dam inspection virtual rehearsal scenarios provided in this embodiment makes full use of the predicted results of multiple skill assessments and evaluations, and screens out multiple target unexercised scenarios with potential value and demand for further analysis. Further, by calculating multiple scene importance values ​​in combination with real case attribute data sets, the scenarios can be quantitatively evaluated from the perspective of practical application. At the same time, by calculating multiple scene similarity values ​​in combination with real case attribute data sets, it can help discover the similarities and correlations between different scenarios. Finally, by combining multiple skill assessment prediction results, multiple scene importance values ​​and multiple scene similarity values ​​to determine the target recommended scenarios for underwater robot dam inspection virtual rehearsal, multiple factors can be comprehensively considered to obtain more scientific and reasonable recommendation results. Therefore, by implementing the present invention, both the predicted assessment and evaluation conditions are taken into account and the importance and similarity in practical applications are combined, which can better meet the actual recommendation needs.

[0129] In this embodiment, a virtual training system for an underwater robot is provided. Figure 1 As shown, the underwater robot virtual drill system 1 includes: an underwater robot virtual drill assessment module 11 and a virtual drill scene recommendation module 12.

[0130] Specifically, the underwater robot virtual drill assessment module 11 is used to perform underwater robot dam body inspection virtual drill skill assessment. The specific process can refer to the above steps S301 to S302, which will not be repeated here.

[0131] Further, the virtual drill scenario recommendation module 12 is used to determine a target recommended scenario for the underwater robot dam body inspection virtual drill. The specific process can refer to the description of the above steps S403 to S404, which will not be repeated here.

[0132] The underwater robot virtual drill system provided in this embodiment can comprehensively consider the actual situation and future needs through the underwater robot virtual drill assessment module and the virtual drill scene recommendation module, and can thus more scientifically and reasonably determine the target recommended scene for the underwater robot dam inspection virtual drill. Therefore, by implementing the present invention, the problem that most of the existing underwater robot virtual drill systems use virtual engines such as Unity3D, UE, etc., and create drill simulation scenes with simple functions in the engine is solved. The few systems with drill evaluation functions only complete tasks step by step in a certain scene, and gradually score them, and there is no drill scene recommendation function.

[0133] In one example, a method for evaluating and recommending virtual drills for underwater robot dam inspections is provided, which is used to analyze and calculate the degree of mastery of various skills demonstrated by drill personnel in the drill, so that the drill personnel can understand their own strengths and weaknesses. At the same time, based on the degree of mastery of various skills, suitable drill scenarios are analyzed and recommended to the drill personnel.

[0134] The following is an example to illustrate the entire technical solution:

[0135] The attribute data of each case and scene are stored in a structured manner, divided into numerical type, symbol type, and entity type. Numerical types include water level height, water flow speed, etc., symbol types include weather conditions, water quality conditions, etc., and entity types include defect structures, including defect type, defect severity, defect location, etc. The scene feature attribute information is stored in the scene attribute database and associated with the corresponding scene.

[0136] The underwater robot virtual drill assessment module includes:

[0137] Determine the assessment attributes. The underwater robot virtual drill assessment module assesses the drill personnel's drill skills from four aspects: drill organization and scheduling capabilities, inspection task processing capabilities, emergency handling capabilities, and comprehensive management capabilities. Among them, the assessment attributes are divided into primary attributes and secondary attributes. When all secondary attributes contained in each primary attribute are qualified, the drill personnel's primary attribute assessment is qualified. The assessment attribute settings of this embodiment are shown in Table 1.

[0138] Determine the test matrix. The test matrix includes the adjacency matrix, the reachability matrix, and the cognitive structure. The adjacency matrix is ​​used to describe the direct relationship between the assessment attributes. If there is a direct relationship between the attributes, the corresponding position in the matrix is ​​recorded as "1", otherwise it is recorded as "0"; the reachability matrix is ​​used to describe the comprehensive relationship between the assessment attributes. If there is a direct, indirect or self-relationship between the two attributes, the corresponding position in the matrix is ​​recorded as "1", otherwise it is recorded as "0"; the cognitive structure is used to record the mastery of the secondary attributes of the drill personnel. Using the ideal response model, if the corresponding assessment attribute is qualified, it is recorded as "1", that is, mastered, otherwise it is recorded as "0", which means not mastered.

[0139] The underwater robot virtual drill assessment module designs an assessment association matrix and a scoring matrix, wherein the assessment association matrix (Q matrix) is used to associate the drill assessment items with the drill skill assessment attributes. The assessment items in this embodiment are set as shown in Table 2.

[0140] The score matrix is ​​used to record the score of each assessment item. The underwater robot virtual exercise assessment module obtains the drill personnel's mastery of various exercise assessment skills through specific assessment attributes, test matrix, score matrix and assessment association matrix.

[0141] The mastery of assessment skills can be obtained by analyzing the score percentage of the drill assessment items.

[0142] For example, a drill project includes a combination of assessment items. For example, the assessment items of drill project A include 1 equipment scheduling work, 2 hoisting operations, 5 precision inspections, and 3 detailed inspections. The drill personnel qualifiedly completed 1 equipment scheduling work, 1 hoisting operation, 4 precision inspections, and 3 detailed inspections in drill project A. The score percentage is 82% of the total project assessment workload and the number of completed tasks. The corresponding assessment correlation matrix of the assessment skill mastery is [-,-,1,0.5,-,-,0.8,0.8,1,-,-,-,-,-], that is, the equipment scheduling ability scores 1 point, the robot hoisting ability scores 0.5 point, the defect recognition ability scores 0.8 point, the defect detection ability scores 0.8 point, the defect and obstacle handling ability scores 1 point, and no other points.

[0143] Recommended modules for virtual drill scenarios include:

[0144] According to the drill personnel's mastery of various drill assessment skills obtained in the underwater robot virtual drill assessment module, combined with the assessment correlation matrix and score matrix of the assessment scenario that has not been drilled, the drill personnel's score in the virtual drill scenario that has not been drilled is predicted, and the expected score percentage is calculated;

[0145] For example, the assessment items of exercise project B include 1 engineering vehicle dispatching work, 1 operating personnel dispatching work, 1 equipment dispatching work, 2 lifting and lowering operation projects, 1 lifting and lowering operation, 5 precision inspections and 6 detailed inspections. Given the personnel skill mastery matrix [-,-,1,0.5,-,-,0.8,0.8,1,-,-,-,-,-], it is predicted that the personnel will be able to complete 1 equipment dispatching work, 0.5 lifting and lowering operations (expected value), 4 precision inspections and 6 detailed inspections in exercise project B. The predicted score percentage is 68%.

[0146] Sort the drill scenarios from low to high according to the predicted score ratio of the current drill personnel in the corresponding scenario, and give priority to screening the drill scenarios with predicted score ratios between [50%, 70%];

[0147] In the calculation of the importance of the drill scene, the attribute values ​​of the real operation cases are first extracted, and the frequency weights of each attribute value in the real operation cases are calculated. The higher the weight, the higher the attribute importance. Then, the presence or absence of each attribute value in the drill scene is counted. Finally, the weighted sum of the scene attribute values ​​is calculated and normalized to calculate the importance value of each scene.

[0148] Decompose the real work cases into the work tasks and their times in the assessment item table. For example, if there are n real work cases in total, and there are n1 times of precision inspection, then the weight of precision inspection is For the drill scenario C, the precision inspection work occurs n1' times, and its weighted value is calculated as I1=k1*n1'. The weighted values ​​of all the work that occurs in the drill scenario C are summed up to obtain its importance value.

[0149] In the calculation of the similarity of the drill scenes, the scene attribute data is divided into digital, symbolic, and entity types, and the similarity of each attribute value is calculated respectively. The entity type sub-attribute can be divided into digital and symbolic types. Numerical attributes can be regarded as two points. The farther the calculated distance is, the lower the similarity is, and vice versa. Symbolic attributes determine the similarity by comparing whether the symbol values ​​are the same.

[0150] Combined with expert scoring, the hierarchical analysis method is used to set the weight of each attribute value in the similarity calculation, and the weighted sum is calculated to calculate the similarity of the exercise scene. Finally, combined with multiple factor information, suitable exercise scenes are recommended to the exercise personnel.

[0151] Furthermore, the existing technology can only repeatedly practice in the scene to improve the overall practice level, but it is impossible to learn one's own strengths and weaknesses from the practice results, and it is impossible to conduct targeted practice on skills that are not well mastered. At the same time, different practice scenes have different emphases, and the drillers cannot quickly select the practice scene with the best practice effect from the practice scene library. The underwater robot dam inspection virtual drill assessment and drill scene recommendation method provided in this example can analyze the current mastery of various skills by the drillers through the drill results of the drillers.

[0152] In an optional example, the marginal judgment rate (MMR) and the pattern judgment rate (PMR) are used to evaluate the performance of the underwater robot dam inspection virtual drill assessment and drill scenario recommendation method provided above in the underwater robot dam inspection virtual drill.

[0153] Specifically, the marginal accuracy rate is used to calculate the average accuracy of a single attribute judgment. The calculation formula is shown in the following relationship:

[0154]

[0155] Where: K represents the total number of attributes; N represents the number of people participating in the test; n k Indicates the number of people whose attributes are judged correctly.

[0156] Furthermore, the pattern accuracy rate is used to calculate the ratio of the number of individuals with correct attribute judgments to the total number of tested individuals. The calculation formula is shown in the following relationship:

[0157]

[0158] Where: N p Indicates the number of people whose assessment attributes were correctly judged.

[0159] Furthermore, this example generates 3,000 subjects in each simulation, assuming that all subjects taking the test adopt the ideal response mode as their observed response mode. The generation process of simulation data is as follows:

[0160] 1) According to the knowledge status that the subjects may have, the ideal response patterns are sorted according to the total score, and the number of people for the ideal response pattern of each score is allocated according to the probability of the standard normal distribution. For situations where the knowledge status is different but the ideal total score is the same, the strategy of evenly allocating the number of people is adopted.

[0161] 2) Use a probability of 0.3 for sliding, and execute the loop 15 times. The size of the sliding probability to different scores is distributed in proportion to the inverse of the score difference, ensuring that the probability of the ideal score sliding to its surrounding values ​​is high. As the difference between the observed score and the ideal score increases, the sliding probability decreases accordingly. Each item generates a sliding probability matrix.

[0162] 3) Determine the value of the observed reaction pattern by generating a random number U and comparing it with the sliding probability matrix probability value.

[0163] Further, the test results are shown in Table 4 below:

[0164] Table 4. Test results

[0165] frequency MMR PMR 1 0.953 0.948 2 0.958 0.992 3 0.956 0.971 4 0.961 0.956 5 0.969 0.968 6 0.976 0.954 7 0.963 0.942 8 0.943 0.962 9 0.977 0.994 10 0.973 0.985 11 0.977 0.993 12 0.959 0.992 13 0.977 0.950 14 0.990 0.969 15 0.967 0.989 average value 0.967 0.971 variance 0.000133 0.000324

[0166] Therefore, Table 4 shows that the above-mentioned underwater robot dam body inspection virtual drill assessment and evaluation and drill scenario recommendation method is applicable to the underwater robot dam body inspection virtual drill system.

[0167] The embodiment of the present invention also provides a computer device for executing the above Figures 2 to 4 The recommended method for the virtual rehearsal scenario of underwater robot dam inspection is shown.

[0168] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0169] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0170] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0171] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0173] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0174] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0175] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0176] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for recommending virtual drill scenarios for underwater robot dam inspection, characterized in that: Used in a virtual training system for an underwater robot; the method comprises: Acquire a real case attribute data set, an assessment attribute set, and a plurality of drill scenario data sets of the to-be-drilled scenarios, wherein the real case attribute data set and the drill scenario data set are stored in a scenario attribute database in a structured storage manner and are associated with corresponding scenarios; Based on the assessment attribute set, using the exercise scenario data set, the underwater robot dam body inspection virtual exercise skill assessment and evaluation is performed in the multiple to-be-exercised scenarios to obtain multiple skill assessment and evaluation results; Based on the multiple skill assessment results, the assessment and evaluation of the underwater robot dam body inspection virtual drill skills in multiple initial un-drilled scenarios are predicted to obtain multiple skill assessment prediction results; Based on the real case attribute data set, the multiple skill assessment results and the multiple skill assessment prediction results, a target recommendation scenario for the virtual exercise of underwater robot dam inspection is determined.

2. The method according to claim 1, characterized in that Based on the assessment attribute set, the underwater robot dam body inspection virtual exercise skill assessment and evaluation is performed in the multiple to-be-exercised scenes using the exercise scenario data set, and multiple skill assessment and evaluation results are obtained, including: Determining a test matrix based on the assessment attribute set; Obtaining a first assessment association matrix and a first scoring matrix for the scenario to be drilled, wherein the first assessment association matrix is ​​used to associate drill assessment items with drill skill assessment attributes, and the first scoring matrix is ​​used to record the score of each assessment item; Based on the assessment attribute set, the test matrix, the first assessment association matrix and the first score matrix, the underwater robot dam body inspection virtual exercise skill assessment and evaluation is carried out in the multiple to-be-exercised scenarios using the exercise scenario data set to obtain the multiple skill assessment and evaluation results.

3. The method according to claim 2, characterized in that Determining a test matrix based on the assessment attribute set includes: Obtaining direct correlations between the assessment attributes in the assessment attribute set and determining an adjacency matrix, wherein the assessment attributes are divided into primary attributes and secondary attributes; Obtaining a comprehensive relationship between each assessment attribute in the assessment attribute set and determining a reachable matrix; Obtaining the qualified status of each secondary attribute in the assessment attribute set and determining the cognitive structure; The test matrix is ​​determined based on the adjacency matrix, the reachability matrix and the cognitive structure.

4. The method according to claim 1, characterized in that: Based on the multiple skill assessment results, the assessment and evaluation of the underwater robot dam body inspection virtual drill skills in multiple initial un-drilled scenarios are predicted to obtain multiple skill assessment prediction results, including: Obtain a second assessment association matrix and a second score matrix for the plurality of initial unexercised scenarios; Based on the multiple skill assessment results, the second assessment association matrix and the second scoring matrix, the assessment and evaluation conditions of the underwater robot dam inspection virtual practice skills in the multiple initial un-practiced scenarios are predicted to obtain the multiple skill assessment prediction results.

5. The method according to claim 1, characterized in that Based on the real case attribute data set, the multiple skill assessment results and the multiple skill assessment prediction results, a target recommendation scenario for a virtual exercise of underwater robot dam inspection is determined, including: Based on the multiple skill assessment prediction results, determining multiple target unrehearsed scenarios from the multiple initial unrehearsed scenarios; Based on the real case attribute data set, respectively calculating a plurality of scene importance values ​​and a plurality of scene similarity values ​​of the plurality of target unexercised scenes; Based on the multiple skill assessment prediction results, the multiple scene importance values ​​and the multiple scene similarity values, the target recommended scene for the underwater robot dam inspection virtual drill is determined.

6. The method according to claim 5, characterized in that Based on the real case attribute data set, a plurality of scene importance values ​​and a plurality of scene similarity values ​​of the plurality of target unexercised scenes are calculated respectively, including: Calculating multiple attribute frequency weight values ​​and multiple attribute similarity values ​​of the real case attribute data set; Calculating the plurality of scene importance values ​​based on the plurality of attribute frequency weight values; Based on expert experience and analytic hierarchy process, the multiple scene similarity values ​​are calculated using the multiple attribute similarity values.

7. An underwater robot virtual training system, characterized in that: Used to execute the underwater robot dam inspection virtual drill scene recommendation method as described in any one of claims 1 to 6; the system includes: an underwater robot virtual drill assessment module and a virtual drill scene recommendation module.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the underwater robot dam inspection virtual rehearsal scene recommendation method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the underwater robot dam inspection virtual exercise scene recommendation method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for recommending a virtual exercise scenario for underwater robot dam inspection according to any one of claims 1 to 6.

Images