Teaching training intelligent application data management system based on internet of things technology

Abstract

The application discloses a teaching training intelligent application data management system based on Internet of Things technology and relates to the technical field of application data, which is used to solve the problem of reducing the coherence and stability of the training process. The trigger response time of a training user after receiving feedback trigger information and training correction data are continuously monitored, a feedback correction trend is generated, and trigger intervention features are calculated in combination with trigger response delays to evaluate the trigger intervention level of the feedback trigger information and determine whether to enter the channel scheduling stage. In the channel scheduling stage, the occupation data of the teaching prompt type under the sensory channel is obtained, the channel adaptation features are evaluated, the training coherence coefficient is calculated in combination with the training interruption duration, the channel replacement features are generated, and when the channel replacement features are lower than the preset threshold, the corresponding teaching prompt type is executed to replace the sensory channel, so that the coherence and stability of the training process are improved without changing the semantic content of the teaching prompt.

Description

Technical Field

[0001] This invention relates to the field of application data technology, and more specifically, to a smart application data management system for teaching and training based on Internet of Things (IoT) technology. Background Technology

[0002] With the deepening application of IoT technology in the fields of educational informatization and intelligent training, teaching and training systems based on multi-terminal perception and real-time interaction are gradually becoming an important means to improve training efficiency and learning experience. Existing teaching and training systems usually collect behavioral data of training users through wearable devices, smart terminals or environmental perception nodes, and push corresponding teaching prompts or feedback information to training users during the training process to guide the correction of training actions or the adjustment of strategies.

[0003] The existing technology has the following shortcomings:

[0004] Currently, existing technologies for teaching feedback management mostly rely on fixed rules or static strategies to trigger teaching prompts. They fail to fully consider the response time characteristics of trainees after receiving feedback and the dynamic evolution trend of training correction behavior. They also lack a comprehensive evaluation mechanism for the frequency of teaching feedback triggers, the degree of trigger intervention, and the occupancy status of sensory channels. As a result, teaching prompts tend to focus on a single sensory channel during training, leading to interruptions in training rhythm or feedback fatigue, and reducing the continuity and stability of the training process. Therefore, a smart application data management system for teaching and training based on Internet of Things (IoT) technology is proposed.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a smart application data management system for teaching and training based on Internet of Things (IoT) technology. This system addresses the problems mentioned in the background by employing a dynamic monitoring mechanism for user feedback response time and training correction data, a feedback-triggered intervention level evaluation mechanism, and a sensory channel evaluation and adaptive allocation mechanism oriented towards teaching prompt types.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a smart application data management system for teaching and training based on Internet of Things (IoT) technology, comprising a feedback monitoring module, a feedback adjustment module, a channel evaluation module, and a channel allocation module, the functions of which are as follows:

[0008] The feedback monitoring module is used to monitor the trigger response time of the training user when the training user receives the feedback trigger information, collect the training correction data of the training user and generate the feedback correction trend, and transmit the trigger response time and feedback correction trend to the feedback adjustment module.

[0009] The feedback adjustment module is used to comprehensively evaluate the trigger intervention level of feedback trigger information by combining the trigger response time and feedback correction trend, count the frequency of feedback generation of feedback trigger information, and determine whether to enter the channel scheduling stage based on the trigger intervention level.

[0010] The channel evaluation module is used to extract the teaching prompt type of feedback trigger information during the channel scheduling phase, access the prompt channel library to obtain the sensory channel occupancy data of the teaching prompt type, evaluate the channel adaptation characteristics based on the sensory channel occupancy data, and pass it to the channel allocation module.

[0011] The channel allocation module is used to sort the teaching prompt types according to channel adaptation characteristics, detect the training interruption duration of training users, and calculate the training duration. practice The coherence coefficient is used to filter and mark the teaching prompt types based on the ranking results, and then sensory channel replacement is performed on the marked teaching prompt types.

[0012] In a preferred embodiment, in the feedback monitoring module, a preset observation period is set. When the training user obtains feedback trigger information, the time point when the training user receives the feedback trigger information is recorded through the interactive interface log. Furthermore, the time point when the training user makes a trigger correction in response to the feedback trigger information is obtained, and the interval between these time points is used as the trigger response time.

[0013] After obtaining the feedback trigger information, the training correction data of the training user is collected through the training behavior collection interface, including the operation order adjustment ratio and the operation effect adjustment ratio.

[0014] In a preferred embodiment, in the feedback monitoring module, within a preset observation period, the actual operation sequence of the training user is acquired through the training behavior acquisition interface. At the same time, the corresponding benchmark operation sequence is retrieved from the training task library. The actual operation sequence is matched with the benchmark operation sequence, and the operation sequence adjustment ratio is calculated.

[0015] Within a preset observation period, the actual operation result value of the training user is obtained through the training behavior collection interface, the target result threshold of the corresponding training task is obtained by accessing the training task library, and the operation effect adjustment ratio is calculated by combining the actual operation result value and the target result threshold.

[0016] The product of the standardized convergence features of the operation sequence and the convergence features of the operation effect is used as the feedback correction trend.

[0017] In a preferred embodiment, in the feedback adjustment module, the trigger response time of adjacent preset observation periods is selected, and the difference between the trigger response times of adjacent preset observation periods is obtained to obtain the trigger response difference value. When the trigger response difference value is greater than 0, the trigger response difference value is marked; otherwise, the trigger response difference value is not marked.

[0018] The response lag factor is obtained by averaging the response differences of each marker, and the triggering intervention characteristics are calculated by combining the response lag coefficient and the feedback correction trend.

[0019] The triggering intervention characteristics are compared with preset triggering intervention thresholds to evaluate the triggering intervention level of the feedback triggering information:

[0020] If the triggering intervention feature is greater than the preset triggering intervention threshold, the triggering intervention level of the feedback triggering information is determined to be a high intervention level;

[0021] Conversely, if the feedback trigger information is not received, the triggering intervention level is determined to be a low intervention level.

[0022] In a preferred embodiment, in the feedback adjustment module, a preset statistical period is established, and the number of feedback trigger messages issued within the preset statistical period is obtained through the interactive interface log. The ratio of the number of feedback trigger messages to the duration of the preset statistical period is calculated to obtain the feedback generation frequency.

[0023] The frequency of feedback generation is compared with a preset feedback generation threshold, and the trigger intervention level is used to determine whether to enter the channel scheduling stage:

[0024] If the frequency of feedback generation is greater than the preset feedback generation threshold, and the triggering intervention level is a high intervention level, then it is determined to enter the channel scheduling stage and trigger the channel evaluation module.

[0025] Otherwise, it will be determined that the channel scheduling phase will not be entered.

[0026] In a preferred embodiment, in the channel evaluation module, after entering the channel scheduling stage, the feedback trigger information is parsed to extract the corresponding teaching prompt type. The teaching prompt type is a category attribute that represents the feedback trigger information in terms of teaching semantics and interactive purpose.

[0027] Access the pre-built prompt channel library and retrieve the sensory channel occupancy data corresponding to each teaching prompt type, including the sensory channel occupancy degree;

[0028] Sensory channel occupancy is the ratio of the number of times a teaching prompt type is output through the currently bound sensory channel to the total number of times the teaching prompt type is output within the same statistical period;

[0029] For each type of instructional prompt, the channel adaptation feature is defined as the difference between a constant and the sensory channel occupancy.

[0030] In a preferred embodiment, in the channel allocation module, the teaching prompt types are sorted based on channel adaptation features to obtain a sorted list, and the sorting is arranged in ascending order of channel adaptation feature values.

[0031] After sorting, the sorting priority of the teaching prompt type is generated. The sorting priority is the position of the teaching prompt type in the sort list.

[0032] The sorting priority index is calculated based on the sorting priority. The specific calculation method is as follows: ;

[0033] in, This is the sorting priority index. This represents the total number of teaching prompt types. This is the sorting priority.

[0034] In a preferred embodiment, the channel allocation module detects the training interruption duration of the training user, where the training interruption duration is the time interval between two consecutive valid training operations in the training process log.

[0035] The training coherence coefficient is calculated based on the duration of continuous training and the duration of training interruption.

[0036] Continuous training duration refers to the cumulative training time without interruption within the current statistical period. The specific calculation method for the training continuity coefficient is as follows: ;

[0037] in, To train the coherence coefficients, For continuous training duration, This refers to the duration of training interruptions.

[0038] In a preferred embodiment, in the channel allocation module, the ratio of the training coherence coefficient to the ranking priority index is used as the channel replacement feature.

[0039] When the channel replacement feature is less than the channel replacement threshold, the teaching prompt type is filtered and marked; when the channel replacement feature is greater than or equal to the channel replacement threshold, the teaching prompt type is not marked.

[0040] For the selected labeled instructional prompt types, sensory channel replacement is performed. Sensory channel replacement is performed to adjust the currently bound sensory channel while keeping the semantic content and interaction purpose of the instructional prompt type unchanged.

[0041] The technical effects and advantages of this invention are as follows:

[0042] This invention continuously monitors the trigger response time and training correction data of training users after receiving feedback trigger information, generates feedback correction trends, and calculates trigger intervention characteristics based on the trigger response sluggishness. After assessing the trigger intervention level of the feedback trigger information, it determines whether to enter the channel scheduling stage. In the channel scheduling stage, it obtains the occupancy data of the teaching prompt type in the sensory channel, evaluates the channel adaptation characteristics, and calculates the training coherence coefficient based on the training interruption duration, generating channel replacement characteristics. When the channel replacement characteristics are lower than a preset threshold, sensory channel replacement is performed for the corresponding teaching prompt type. Without changing the semantic content of the teaching prompt, it achieves dynamic adjustment of the teaching feedback sensory channel, reduces the repetitive intensity of single sensory stimuli, alleviates feedback fatigue, and improves the coherence and stability of the training process. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating the implementation of the intelligent application data management system for teaching and training based on Internet of Things (IoT) technology according to the present invention.

[0044] Figure 2 This is a module framework diagram of the intelligent application data management system for teaching and training based on Internet of Things technology according to the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] This invention continuously monitors the trigger response time and training correction data of training users after receiving feedback trigger information, generates feedback correction trends, and calculates trigger intervention characteristics based on the trigger response sluggishness. After assessing the trigger intervention level of the feedback trigger information, it determines whether to enter the channel scheduling stage. In the channel scheduling stage, it obtains the occupancy data of the teaching prompt type in the sensory channel, evaluates the channel adaptation characteristics, and calculates the training coherence coefficient based on the training interruption duration, generating channel replacement characteristics. When the channel replacement characteristics are lower than a preset threshold, sensory channel replacement is performed for the corresponding teaching prompt type. Without changing the semantic content of the teaching prompt, it achieves dynamic adjustment of the teaching feedback sensory channel, reduces the repetitive intensity of single sensory stimuli, and alleviates feedback fatigue.

[0047] Example 1, such as Figures 1 to 2As shown, the teaching and training smart application data management system based on Internet of Things technology includes a feedback monitoring module, a feedback adjustment module, a channel evaluation module, and a channel allocation module. The modules interact with each other through signal connections.

[0048] The functions of each module are as follows:

[0049] The feedback monitoring module is used to monitor the trigger response time of the training user when the training user receives the feedback trigger information, collect the training correction data of the training user and generate the feedback correction trend, and transmit the trigger response time and feedback correction trend to the feedback adjustment module.

[0050] The feedback adjustment module is used to comprehensively evaluate the trigger intervention level of feedback trigger information by combining the trigger response time and feedback correction trend, count the frequency of feedback generation of feedback trigger information, and determine whether to enter the channel scheduling stage based on the trigger intervention level.

[0051] The channel evaluation module is used to extract the teaching prompt type of feedback trigger information during the channel scheduling phase, access the prompt channel library to obtain the sensory channel occupancy data of the teaching prompt type, evaluate the channel adaptation characteristics based on the sensory channel occupancy data, and pass it to the channel allocation module.

[0052] The channel allocation module is used to sort the teaching prompt types according to channel adaptation characteristics, detect the training interruption duration of training users, and calculate the training duration. practice The coherence coefficient is used to filter and mark the teaching prompt types based on the ranking results, and then sensory channel replacement is performed on the marked teaching prompt types.

[0053] The specific implementation is as follows:

[0054] In the feedback monitoring module, during IoT-based teaching and training, the training system typically guides and corrects user behavior by generating feedback triggers. However, as the training cycle lengthens and feedback frequency increases, user response to feedback may gradually decline, leading to reduced feedback absorption efficiency and affecting the stability of the training rhythm. Therefore, before adjusting the feedback presentation method, the actual user response and corrective effects after receiving feedback triggers are quantitatively monitored to determine whether the feedback is still being effectively received.

[0055] With a preset observation period, when the training user receives feedback trigger information, the time point when the training user receives the feedback trigger information is recorded through the interaction interface log, and the time point when the training user makes trigger corrections in response to the feedback trigger information is further obtained. The interval between these time points is used as the trigger response time to reflect the training user's immediate response to the feedback trigger information.

[0056] After obtaining the feedback trigger information, the training correction data of the training user is collected through the training behavior collection interface. The training correction data refers to the adjustment results of the operation behavior performed by the training user on the training task relative to the baseline operation state within the preset observation period after receiving the feedback trigger information, including the operation order adjustment ratio and the operation effect adjustment ratio.

[0057] Specifically, within a preset observation period, the actual operation sequence of the training user is obtained through the training behavior acquisition interface, and at the same time, the corresponding baseline operation sequence is retrieved from the training task library; the actual operation sequence and the baseline operation sequence are matched in position, the number of trajectory nodes that have been adjusted is counted, and the ratio of the actual operation sequence to the total number of nodes in the baseline operation sequence is calculated to obtain the operation sequence adjustment ratio.

[0058] Within a preset observation period, the actual operation result values ​​of the training users are obtained through the training behavior acquisition interface, and the target result threshold of the corresponding training task is obtained by accessing the training task library. The difference between the actual operation result value and the target result threshold is calculated to obtain the operation result deviation value, and then the ratio is calculated with the operation result deviation value before receiving the feedback trigger information to obtain the operation effect adjustment ratio. This ratio reflects the degree of improvement of the training effect before and after the feedback guidance. The smaller the operation effect adjustment ratio, the closer the operation result is to the target result threshold, and the higher the degree of improvement of the training effect.

[0059] Within multiple consecutive preset observation periods, the operation sequence adjustment ratio and operation effect adjustment ratio corresponding to each preset observation period are obtained respectively.

[0060] The operation order adjustment ratios are arranged in chronological order, and the difference between adjacent operation order adjustment ratios is calculated and the absolute value is taken to obtain the operation order adjustment change. Furthermore, the average value of each operation order adjustment change is calculated to generate operation order convergence features, which are used to reflect the degree to which the operation order of the training user gradually stabilizes under the guidance of feedback trigger information.

[0061] Similarly, the operation effect adjustment ratios are arranged in chronological order, and the difference between adjacent operation effect adjustment ratios is calculated and the absolute value is taken to obtain the operation effect adjustment change. Furthermore, the average value of each operation effect adjustment change is calculated to generate operation effect adjustment convergence features, which are used to reflect the continuity and stability of the training effect improvement of the training user under the guidance of feedback trigger information.

[0062] The product of the standardized convergence features of the operation sequence and the convergence features of the operation effect is used as the feedback correction trend, reflecting the stability of the training user's operation behavior and the stability of the training effect improvement.

[0063] The trigger response time and feedback correction trend are passed to the feedback adjustment module.

[0064] It should be explained that the interaction interface log refers to the event record data generated by the human-computer interaction interface of the training system; the training behavior acquisition interface refers to the system interface used to collect the operation behavior data generated by the training user during the execution of the training task; the preset observation period can be set according to the operation complexity or training rhythm of the training task; the training task library refers to the data storage unit used to store the benchmark operation sequence, target result threshold and related task configuration parameters corresponding to the training task; the standardization processing method includes, but is not limited to, standard linear transformation based on interval scaling, Z-Score standardization method based on statistics or normalization method based on nonlinear mapping function. The application methods of standardization processing will not be elaborated here.

[0065] In the feedback adjustment module, the trigger response time of adjacent preset observation periods is selected, and the difference between the trigger response times of adjacent preset observation periods is obtained to obtain the trigger response difference value. When the trigger response difference value is greater than 0, the trigger response difference value is marked; otherwise, the trigger response difference value is not marked.

[0066] The response lag factor is obtained by averaging the difference in the trigger response of each marker. The response lag factor is then standardized to obtain the response lag coefficient, which reflects whether the trigger response time is frequently prolonged.

[0067] Triggering intervention characteristics are calculated by combining the comprehensive response lag coefficient and feedback correction trend. ,in, To provide feedback and correct the trend, For response lag coefficient, and These are the preset adjustment weights corresponding to the response sluggishness coefficient and the feedback correction trend, respectively. To trigger intervention features;

[0068] The triggering intervention characteristics are compared with preset triggering intervention thresholds to evaluate the triggering intervention level of the feedback triggering information:

[0069] If the triggering intervention feature is greater than the preset triggering intervention threshold, the triggering intervention level of the feedback triggering information is determined to be a high intervention level;

[0070] Conversely, if the feedback triggering information is not received, the triggering intervention level is determined to be a low intervention level.

[0071] When the trigger intervention level is high, it indicates that the training user is fatigued by the current feedback trigger information, and the feedback absorption efficiency decreases; when the trigger intervention level is low, it indicates that the training user has not yet developed significant fatigue from the current feedback trigger information, and the feedback absorption effect is acceptable.

[0072] The system sets a preset statistical period and obtains the number of feedback trigger messages issued within the preset statistical period through the interaction interface log. The ratio of the number of feedback trigger messages to the duration of the preset statistical period is calculated to obtain the feedback generation frequency.

[0073] The frequency of feedback generation is compared with a preset feedback generation threshold, and the trigger intervention level is used to determine whether to enter the channel scheduling stage:

[0074] If the frequency of feedback generation is greater than the preset feedback generation threshold, and the triggering intervention level is a high intervention level, then it is determined to enter the channel scheduling stage and trigger the channel evaluation module.

[0075] Otherwise, it will be determined that the channel scheduling phase will not be entered.

[0076] It should be explained that the preset adjustment weights can be set according to the emphasis of the training task on the sensitivity of immediate response and the stability of long-term training effect; the preset trigger intervention threshold can be set according to the distribution of trigger intervention features in historical training samples; the preset statistical period can be set according to the feedback trigger density or the stage characteristics of the training process; and the preset feedback generation threshold can be set according to the statistical results of the feedback dense intervals in historical training.

[0077] In the channel evaluation module, after entering the channel scheduling stage, the channel evaluation module first parses the feedback trigger information and extracts the corresponding teaching prompt type. The teaching prompt type is used to characterize the category attribute of the feedback trigger information in terms of teaching semantics and interaction purpose, and serves as the index basis for subsequent sensory channel evaluation.

[0078] Based on the extracted teaching prompt types, the channel evaluation module accesses the pre-built prompt channel library and retrieves the historical presentation records of each teaching prompt type under the sensory channel to obtain the corresponding sensory channel occupancy data.

[0079] It should be noted that the prompt channel library is a pre-built data storage unit for teaching, training, and feedback management, used to structurally record and manage the teaching prompt types and their corresponding sensory channel presentation history.

[0080] Sensory channel occupancy data includes sensory channel occupancy rate, which is derived from the prompt output logs in the prompt channel library within a preset statistical period. The calculation method is the ratio of the number of times the teaching prompt type is output through the currently bound sensory channel to the total number of times the teaching prompt type is output within the same statistical period.

[0081] Sensory channel occupancy reflects the degree to which the type of instructional cue relies on the currently bound sensory channel during the current training phase. The higher the value, the more concentrated the use of the instructional cue type on the currently bound sensory channel, the higher the repetition of sensory stimulation, and the greater the risk of sensory fatigue.

[0082] It should be noted that the prompt output log is the basic data unit in the prompt channel library used to record the actual presentation behavior of teaching prompts. It is used to record the output process of teaching prompt types during the training process. The prompt output log takes a single teaching prompt output event as the smallest recording granularity, and each prompt output log corresponds to one actual prompt output behavior.

[0083] After obtaining the sensory channel occupancy rate corresponding to the teaching prompt type, the channel evaluation module evaluates the channel adaptation feature based on the sensory channel occupancy rate. Specifically, for each teaching prompt type, the channel adaptation feature is defined as the difference between a constant and the sensory channel occupancy rate, which is used to characterize the degree of adaptation between the teaching prompt type and its currently bound sensory channel.

[0084] Channel adaptation features reflect the remaining capacity of the currently bound sensory channel when carrying instructional prompts. The larger the value, the lower the degree of occupation of the instructional prompt type on the currently bound sensory channel in the current training cycle, the lower the repetition of sensory stimulation, and the more novel and perceptible the currently bound sensory channel can still carry the corresponding instructional prompt type with high novelty and perceptibility.

[0085] The smaller the value, the more concentrated the presentation of teaching prompts on the currently bound sensory channel is, the higher the sensory load, and the more likely it is to cause sensory fatigue if the current bound sensory channel continues to output teaching prompts. The adaptability of the current bound sensory channel to teaching prompts decreases.

[0086] After calculating the channel adaptation features, the channel evaluation module transmits the channel adaptation features corresponding to the teaching prompt type to the channel allocation module, providing a quantitative and comparable decision basis for the channel allocation module to subsequently execute the teaching prompt type sorting and sensory channel replacement decisions.

[0087] In the channel allocation module, after obtaining the channel adaptation features passed from the channel evaluation module, the channel allocation module takes the teaching prompt type as the processing object and compares and analyzes the channel adaptation features corresponding to each teaching prompt type under its current bound sensory channel.

[0088] It should be noted that at any given time, each teaching prompt type corresponds to only one sensory channel. The channel adaptation feature is used to characterize the degree of adaptation between the teaching prompt type and its currently bound sensory channel.

[0089] The channel allocation module sorts the teaching prompt types based on channel adaptation features to obtain a sorted list. The sorting is based on the channel adaptation features, arranged from smallest to largest. The smaller the channel adaptation feature value, the lower the remaining carrying capacity of the teaching prompt type under its current bound sensory channel, the worse the adaptation of the teaching prompt type, and the higher its sorting priority. Conversely, the larger the channel adaptation feature value, the more suitable the currently bound sensory channel is for carrying the teaching prompt type, and the lower its sorting priority.

[0090] After sorting, the sorting priority of the teaching prompt type is generated. The sorting priority is the position of the teaching prompt type in the sort list.

[0091] Specifically, if the total number of teaching prompt types participating in the sorting in the current scheduling cycle is N, and the sorting position increases sequentially from 1 to N, then the teaching prompt type with sorting position 1 corresponds to the channel with the smallest adaptation feature and the highest adaptation risk.

[0092] The sorting priority index is calculated based on the sorting priority. The specific calculation method is as follows:

[0093] ;

[0094] in, This is the sorting priority index. This represents the total number of teaching prompt types. This is the sorting priority.

[0095] The ranking priority index ranges from 0 to 1. The larger the value, the higher the adaptation risk of the teaching prompt type among all teaching prompt types, and the higher the priority it is as the target of sensory channel adjustment; the smaller the value, the more stable the current sensory channel adaptation status of the teaching prompt type.

[0096] After completing the sorting process based on channel adaptation features, the channel allocation module synchronously detects the training interruption duration of training users to characterize the actual impact of feedback prompts on the training rhythm during the training process.

[0097] Training interruption duration is the time interval between two consecutive valid training operations in the training process log. It reflects the duration during which the training user's operation is halted or the process is interrupted after receiving feedback prompts. The larger the value, the greater the degree of interference of the feedback prompts on the training process.

[0098] Based on the continuous training duration and the training interruption duration, the channel allocation module further calculates the training coherence coefficient, where the continuous training duration represents the cumulative training duration without interruption within the current statistical period. The specific calculation method for the training coherence coefficient is as follows:

[0099] ;

[0100] in, To train the coherence coefficients, For continuous training duration, This refers to the duration of training interruptions.

[0101] The training coherence coefficient is used to quantify the overall coherence of the training process. Its value ranges from 0 to 1. The larger the value, the more continuous and stable the training process is; the smaller the value, the higher the proportion of training interruptions, that is, the current sensory channel configuration of the teaching prompt type has an adverse effect on training coherence.

[0102] The ratio of the training coherence coefficient to the ranking priority index is used as the channel substitution feature. The smaller the training coherence coefficient and the larger the ranking priority index, the smaller the value of the channel substitution feature.

[0103] The channel replacement feature reflects the acceptability of the teaching prompt type under the current sensory channel configuration. The smaller the value, the lower the rationality of the current sensory channel configuration of the teaching prompt type in terms of training effect or channel capacity, and the higher the necessity of channel replacement.

[0104] The channel allocation module compares the channel replacement feature with the preset channel replacement threshold. When the channel replacement feature is less than the channel replacement threshold, the teaching prompt type is filtered and marked; when the channel replacement feature is greater than or equal to the channel replacement threshold, the teaching prompt type is not marked.

[0105] It should be noted that the preset channel replacement threshold is a quantitative decision parameter used to determine whether sensory channel replacement needs to be performed on the teaching prompt type. Specifically, it is set based on statistical analysis of historical training data. During the offline analysis phase, a correlation analysis is performed between the channel replacement characteristics of each teaching prompt type and the corresponding training effect indicators across multiple training cycles. These training effect indicators include average training interruption duration, effective operation count per unit time, or training task completion rate. By statistically analyzing the distribution relationship between channel replacement characteristics and training effect degradation intervals, it is determined that when the channel replacement characteristics fall below a certain critical value, training continuity decreases. This critical value is then set as the preset channel replacement threshold.

[0106] For the selected labeled instructional cue types, sensory channel replacement is performed. In practice, the semantic content and interaction purpose of the instructional cue type remain unchanged, while the currently bound sensory channel is adjusted. That is, the original sensory channel is unbound, and a new sensory channel is selected and rebound. For example, when an instructional cue type is presented in visual form for a long time and signs of user sensory fatigue are detected, its corresponding sensory channel is switched to an auditory cue or a multi-sensory combination cue to reduce the repetitive intensity of a single sensory stimulus.

[0107] By replacing sensory channels as described above, the user's perceptual load can be dynamically adjusted without changing the teaching feedback information itself, thereby alleviating feedback fatigue and improving the continuity and comfort of the training process.

[0108] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0109] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] In this document, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that terms such as “comprising / including” or “having” specify the presence of the stated features, integrals, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, integrals, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0111] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0112] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart application data management system for teaching and training based on Internet of Things (IoT) technology, characterized in that: It includes a feedback monitoring module, a feedback adjustment module, a channel evaluation module, and a channel allocation module. The functions of each module are as follows: The feedback monitoring module is used to monitor the trigger response time of the training user when the training user receives the feedback trigger information, collect the training correction data of the training user and generate the feedback correction trend, and transmit the trigger response time and feedback correction trend to the feedback adjustment module. The feedback adjustment module is used to comprehensively evaluate the trigger intervention level of feedback trigger information by combining the trigger response time and feedback correction trend, count the frequency of feedback generation of feedback trigger information, and determine whether to enter the channel scheduling stage based on the trigger intervention level. The channel evaluation module is used to extract the teaching prompt type of feedback trigger information during the channel scheduling phase, access the prompt channel library to obtain the sensory channel occupancy data of the teaching prompt type, evaluate the channel adaptation characteristics based on the sensory channel occupancy data, and pass it to the channel allocation module. The channel allocation module is used to sort the teaching prompt types according to channel adaptation characteristics, detect the training interruption duration of training users, and calculate the training duration. practice The coherence coefficient is used to filter and mark the teaching prompt types based on the ranking results, and then sensory channel replacement is performed on the marked teaching prompt types.

2. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 1, characterized in that: In the feedback monitoring module, an observation period is preset. When the training user receives feedback trigger information, the time point when the training user receives the feedback trigger information is recorded through the interaction interface log. Furthermore, the time point when the training user makes a trigger correction in response to the feedback trigger information is obtained, and the interval between these time points is used as the trigger response time. After obtaining the feedback trigger information, the training correction data of the training user is collected through the training behavior collection interface, including the operation order adjustment ratio and the operation effect adjustment ratio.

3. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 2, characterized in that: In the feedback monitoring module, within a preset observation period, the actual operation sequence of the training user is obtained through the training behavior acquisition interface. At the same time, the corresponding benchmark operation sequence is retrieved from the training task library. The actual operation sequence is matched with the benchmark operation sequence, and the operation sequence adjustment ratio is calculated. Within a preset observation period, the actual operation result value of the training user is obtained through the training behavior collection interface, the target result threshold of the corresponding training task is obtained by accessing the training task library, and the operation effect adjustment ratio is calculated by combining the actual operation result value and the target result threshold. The product of the standardized convergence features of the operation sequence and the convergence features of the operation effect is used as the feedback correction trend.

4. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 2, characterized in that: In the feedback adjustment module, the trigger response time of adjacent preset observation periods is selected, and the difference between the trigger response times of adjacent preset observation periods is obtained to obtain the trigger response difference value. When the trigger response difference value is greater than 0, the trigger response difference value is marked; otherwise, the trigger response difference value is not marked. The response lag factor is obtained by averaging the response differences of each marker, and the triggering intervention characteristics are calculated by combining the response lag coefficient and the feedback correction trend. The triggering intervention characteristics are compared with preset triggering intervention thresholds to evaluate the triggering intervention level of the feedback triggering information: If the triggering intervention feature is greater than the preset triggering intervention threshold, the triggering intervention level of the feedback triggering information is determined to be a high intervention level; Conversely, if the feedback trigger information is not received, the triggering intervention level is determined to be a low intervention level.

5. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 4, characterized in that: In the feedback adjustment module, a preset statistical period is set, and the number of feedback trigger messages issued within the preset statistical period is obtained through the interactive interface log. The ratio of the number of feedback trigger messages to the duration of the preset statistical period is calculated to obtain the feedback generation frequency. The frequency of feedback generation is compared with a preset feedback generation threshold, and the trigger intervention level is used to determine whether to enter the channel scheduling stage: If the frequency of feedback generation is greater than the preset feedback generation threshold, and the triggering intervention level is a high intervention level, then it is determined to enter the channel scheduling stage and trigger the channel evaluation module. Otherwise, it will be determined that the channel scheduling phase will not be entered.

6. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 1, characterized in that: In the channel evaluation module, after entering the channel scheduling stage, the feedback trigger information is parsed to extract the corresponding teaching prompt type. The teaching prompt type is a category attribute that represents the feedback trigger information in terms of teaching semantics and interactive purpose. Access the pre-built prompt channel library and retrieve the sensory channel occupancy data corresponding to each teaching prompt type, including the sensory channel occupancy degree; Sensory channel occupancy is the ratio of the number of times a teaching prompt type is output through the currently bound sensory channel to the total number of times the teaching prompt type is output within the same statistical period; For each type of instructional prompt, the channel adaptation feature is defined as the difference between a constant and the sensory channel occupancy.

7. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 6, characterized in that: In the channel allocation module, the teaching prompt types are sorted based on channel adaptation features to obtain a sorted list. The sorting process is arranged in ascending order of channel adaptation feature values. After sorting, the sorting priority of the teaching prompt type is generated. The sorting priority is the position of the teaching prompt type in the sort list. The sorting priority index is calculated based on the sorting priority. The specific calculation method is as follows: ; in, This is the sorting priority index. This represents the total number of teaching prompt types. This is the sorting priority.

8. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 1, characterized in that: In the channel allocation module, the training interruption duration of the training user is detected. The training interruption duration is the time interval between two consecutive valid training operations in the training process log. The training coherence coefficient is calculated based on the duration of continuous training and the duration of training interruption. Continuous training duration refers to the cumulative training time without interruption within the current statistical period. The specific calculation method for the training continuity coefficient is as follows: ; in, To train the coherence coefficients, For continuous training duration, This refers to the duration of training interruptions.

9. The intelligent application data management system for teaching and training based on Internet of Things technology according to claim 8, characterized in that: In the channel allocation module, the ratio of the training coherence coefficient to the ranking priority index is used as the channel replacement feature; When the channel replacement feature is less than the channel replacement threshold, the teaching prompt types are filtered and marked; When the channel replacement feature is greater than or equal to the channel replacement threshold, the teaching prompt type is not marked. For the selected labeled instructional prompt types, sensory channel replacement is performed. Sensory channel replacement is performed to adjust the currently bound sensory channel while keeping the semantic content and interaction purpose of the instructional prompt type unchanged.

Images