Training analysis method and system for animal cognitive movement

Abstract

The present invention discloses a training analysis method and system for animal cognitive movement, specifically relating to the field of training analysis technology. The method collects original movement behavior data generated by animals during the cognitive task transition process and performs feature segmentation to generate multiple movement behavior subsequences; in combination with the time nodes of changes in cognitive task types, the task labels of the movement behavior subsequences are extracted, the behavioral feature differences between adjacent cognitive task subsequences are analyzed, and a cross-task difference feature matrix is ​​constructed; based on the reverse cognitive transfer interference index, a cognitive transfer interference identification mechanism is established to identify abnormal behavior fragments and key task transition nodes; in combination with historical cognitive training data, a multidimensional interference evaluation model is constructed to evaluate the cognitive transfer interference degree of the animal in the current training stage; the present invention adjusts the training task sequence according to the matching result of the cognitive transfer interference degree and a preset interference threshold, thereby achieving real-time adaptation and interference suppression of the animal's cognitive transfer state.

Description

Technical Field

[0001] The present invention relates to the technical field of training analysis, and more particularly, to a training analysis method and system for animal cognitive movement. Background Art

[0002] Animal cognitive motor training holds significant application value in neuroscience, animal behavior, and medical research. However, during actual training, as animals continuously perform different cognitive tasks, their previously formed cognitive patterns or strategies often fail to adjust effectively and promptly, leading to negative cognitive transfer. This phenomenon, in which animals continue to use old cognitive strategies and fail to adapt to new task requirements, leads to a decrease in the stability and accuracy of animal behavioral data, significantly impacting training effectiveness and the reliability of experimental data. Existing training analysis methods lack effective mechanisms to identify and address this interference effect.

[0003] In order to solve the above problems, a training analysis method and system for animal cognitive movement are provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a training analysis method and system for animal cognitive movement to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The training and analysis method for animal cognitive movement includes the following steps:

[0007] Acquiring the original movement behavior data generated by the animal during the cognitive task transition process, performing feature segmentation processing on the original movement behavior data, and generating multiple movement behavior subsequences;

[0008] Based on the time points when the animal receives changes in the type of cognitive task, the cognitive task label corresponding to each motor behavior subsequence is extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix;

[0009] Establish a reverse cognitive transfer interference index, identify abnormal motor behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determine the key task transition nodes that cause reverse cognitive transfer interference;

[0010] A multidimensional evaluation model for reverse cognitive transfer interference was constructed based on historical cognitive training data. The degree of cognitive transfer interference in the current training phase of the animal was assessed based on key task transition nodes and corresponding abnormal motor behavior segments.

[0011] The degree of cognitive transfer interference in the animal's current training stage is matched with the preset interference threshold, and the sequence arrangement of the cognitive task is adjusted according to the matching result.

[0012] In a preferred embodiment, the original motor behavior data generated by the animal during the cognitive task transition is obtained, and the original motor behavior data is subjected to feature segmentation processing to generate multiple motor behavior subsequences, specifically:

[0013] Perform multi-channel parallel acquisition of the original motor behavior data of animals during different cognitive task execution stages;

[0014] The collected original movement behavior data is segmented according to the cognitive task triggering time nodes and divided into multiple initial behavior segment data sets;

[0015] Based on the initial behavior paragraph data set, the behavior structure feature indicators in the initial behavior paragraph data are extracted to form a structured behavior feature representation;

[0016] According to the change pattern of the behavior structure feature indicators in the structured behavior feature representation, a sliding window method is used to perform fine-grained segmentation to generate a set of motion behavior subsequences that meet the consistency of a single behavior feature.

[0017] In a preferred embodiment, based on the time nodes at which the animal receives a change in cognitive task type, the cognitive task label corresponding to each motor behavior subsequence is extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix, specifically:

[0018] Match the time range corresponding to each motor behavior subsequence with the time node of the cognitive task type change, and determine the cognitive task type label corresponding to each motor behavior subsequence;

[0019] According to the cognitive task type label of each motor behavior subsequence, two motor behavior subsequences arranged consecutively in the time dimension are defined as a pair of adjacent cognitive task subsequences;

[0020] For each pair of adjacent cognitive task subsequences, the behavioral characteristic difference index corresponding to each pair of adjacent cognitive task subsequences is obtained by calculation;

[0021] Based on each pair of adjacent cognitive task subsequences and the corresponding behavioral feature difference indicators, a cross-task difference feature matrix is ​​constructed.

[0022] In a preferred embodiment, a reverse cognitive transfer interference index is established to identify abnormal motor behavior segments that deviate from normal cognitive patterns based on a cross-task difference feature matrix, and to determine the key task transition nodes that produce reverse cognitive transfer interference, specifically:

[0023] Based on the cross-task difference feature matrix, the calculation rules of the reverse cognitive transfer interference index are established;

[0024] According to the calculation rules of the reverse cognitive transfer interference index, the behavioral feature difference index in the cross-task difference feature matrix is ​​weighted and calculated to output the reverse cognitive transfer interference index value;

[0025] According to the relationship between the reverse cognitive transfer interference index value and the preset cognitive mode deviation threshold, it is determined whether the movement behavior subsequence belongs to an abnormal movement behavior segment that deviates from the normal cognitive mode;

[0026] According to the adjacent cognitive task subsequences corresponding to the abnormal motor behavior segments, the key task transition nodes that cause reverse cognitive transfer interference are determined.

[0027] In a preferred embodiment, a multidimensional evaluation model of reverse cognitive transfer interference is constructed based on historical cognitive training data. The degree of cognitive transfer interference in the current training stage of the animal is evaluated according to the key task transition nodes and the corresponding abnormal movement behavior segments. Specifically,

[0028] Extract the cognitive task type labels corresponding to the key task transition nodes and the behavioral feature difference indicators corresponding to the abnormal movement behavior segments during the historical cognitive training process;

[0029] Based on the influence weights of cognitive task type labels and behavioral characteristic difference indicators on reverse cognitive transfer interference, a multidimensional evaluation model of reverse cognitive transfer interference is generated.

[0030] The cognitive task type label and behavioral characteristic difference index of the current training stage are input into the multidimensional evaluation model of reverse cognitive transfer interference, and the cognitive transfer interference value of the animal in the current training stage is output.

[0031] In a preferred embodiment, the cognitive transfer interference level of the animal in the current training stage is matched with a preset interference threshold, and the sequence arrangement of the cognitive tasks is adjusted according to the matching result, specifically:

[0032] obtaining a preset interference threshold, and comparing the cognitive transfer interference value of the animal in the current training stage with the preset interference threshold;

[0033] When the cognitive transfer interference value of the animal's current training stage is greater than the preset interference threshold, the cognitive training task sequence is reordered from high to low according to the similarity of cognitive task type labels, and a transition training link is inserted between adjacent cognitive training tasks;

[0034] When the cognitive transfer interference value of the animal's current training stage is less than or equal to the preset interference threshold, the cognitive training task sequence remains unchanged.

[0035] On the other hand, the present invention provides a training and analysis system for animal cognitive movement, comprising a behavior acquisition module, a label extraction module, an interference recognition module, an interference assessment module, and a sequence adjustment module;

[0036] The behavior acquisition module obtains the original movement behavior data generated by the animal during the cognitive task transformation process, performs feature segmentation processing on the original movement behavior data, and generates multiple movement behavior subsequences;

[0037] The label extraction module extracts the cognitive task label corresponding to each motor behavior subsequence based on the time nodes when the animal receives the change of cognitive task type, analyzes the behavioral feature differences between adjacent cognitive task subsequences, and generates a cross-task difference feature matrix;

[0038] The interference identification module establishes a reverse cognitive transfer interference index, identifies abnormal movement behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determines the key task transition nodes that cause reverse cognitive transfer interference;

[0039] The interference assessment module builds a multidimensional evaluation model of reverse cognitive transfer interference based on historical cognitive training data. It evaluates the degree of cognitive transfer interference in the animal's current training stage according to key task transition nodes and corresponding abnormal movement behavior segments.

[0040] The sequence adjustment module matches the cognitive transfer interference level of the animal in the current training stage with the preset interference threshold, and adjusts the sequence arrangement of the cognitive task according to the matching result.

[0041] The technical effects and advantages of the present invention for the training and analysis method and system for animal cognitive movement are as follows:

[0042] By establishing a correspondence between motor behavior subsequences and cognitive task type labels, combined with behavioral structure feature difference indicators, the team accurately identified abnormal behavioral manifestations during cognitive mode switching. By constructing a cross-task difference feature matrix and a reverse cognitive transfer interference indicator, the team precisely located key task transition nodes and established a multidimensional evaluation model based on historical cognitive training data to quantify the degree of interference in the animal's current stage. This approach enabled real-time assessment of cognitive transfer interference and, based on matching results with cognitive thresholds, adjusted the order of subsequent training tasks, improving training continuity and adaptability, effectively enhancing the efficiency and stability of animal cognitive training. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 Schematic diagram of the training and analysis method for animal cognitive movement according to the present invention;

[0044] Figure 2 The figure is a schematic diagram of the structure of the training and analysis system for animal cognitive movement according to the present invention. DETAILED DESCRIPTION

[0045] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] Example 1

[0047] Figure 1 The present invention provides a training and analysis method for animal cognitive movement, which includes the following steps:

[0048] Acquiring the original movement behavior data generated by the animal during the cognitive task transition process, performing feature segmentation processing on the original movement behavior data, and generating multiple movement behavior subsequences;

[0049] Based on the time points when the animal receives changes in the type of cognitive task, the cognitive task label corresponding to each motor behavior subsequence is extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix;

[0050] Establish a reverse cognitive transfer interference index, identify abnormal motor behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determine the key task transition nodes that cause reverse cognitive transfer interference;

[0051] A multidimensional evaluation model for reverse cognitive transfer interference was constructed based on historical cognitive training data. The degree of cognitive transfer interference in the current training phase of the animal was assessed based on key task transition nodes and corresponding abnormal motor behavior segments.

[0052] The degree of cognitive transfer interference in the animal's current training stage is matched with the preset interference threshold, and the sequence arrangement of the cognitive task is adjusted according to the matching result.

[0053] Specifically, the original movement behavior data generated by the animal during the cognitive task transition is obtained, and the original movement behavior data is subjected to feature segmentation processing to generate multiple movement behavior subsequences, including:

[0054] Perform multi-channel parallel acquisition of the original motor behavior data of animals during different cognitive task execution stages;

[0055] Specifically, the animal cognitive motion training platform is equipped with a trajectory recording device, a speed sensing device, and a time recording device. The trajectory recording device is used to capture the real-time sequence of changes in the two-dimensional or three-dimensional position coordinate points of the animal in the cognitive task training scenario; the speed sensing device is used to obtain the real-time movement speed value of the animal at each movement sampling moment; and the time recording device is used to record the time point of each set of sampling data for time dimension segmentation.

[0056] All acquisition devices work together through a synchronization control unit to ensure that trajectory, velocity, and time information correspond to each other within the same sampling cycle, generating a unified raw motion behavior data stream. This raw motion behavior data stream provides the foundation for task recognition and behavior segmentation.

[0057] The collected original movement behavior data is segmented according to the cognitive task triggering time nodes and divided into multiple initial behavior segment data sets;

[0058] Specifically, the raw motor behavior data is segmented sequentially along the timeline based on the task triggering time nodes in the cognitive training task settings. The start and end times of each segment correspond to the start and end times of a cognitive task, ensuring that each data segment contains the complete behavioral trajectory of the animal during the execution of a single cognitive task.

[0059] For example, the experimental setting includes three continuous cognitive tasks, namely path recognition task, target discrimination task and spatial jump task. The task triggering times are time point one, time point two and time point three respectively. The original motion behavior data is divided into three initial behavior segment data according to the task triggering time, which correspond to all motion behavior data during the execution of the three cognitive tasks.

[0060] Each initial behavior segment data simultaneously retains the trajectory coordinate sequence, speed sequence and corresponding time series within the corresponding time interval, forming a unified data triple representation structure for structural feature extraction.

[0061] Based on the initial behavior paragraph data set, the behavior structure feature indicators in the initial behavior paragraph data are extracted to form a structured behavior feature representation;

[0062] Specifically, each initial behavior paragraph data is structured and four types of behavior structure characteristic indicators are extracted:

[0063] Trajectory Variation: This measure measures the degree of tortuosity in the animal's trajectory by calculating the average distance between all points in the initial behavioral segment data and the centerline of the fitted trajectory. A more tortuous trajectory, associated with a greater average distance, indicates a greater degree of directional variation during movement.

[0064] Speed ​​Fluctuation: Calculate the standard deviation of the speed data sequence in the initial behavioral segment data to reflect the stability of the animal's movement speed during the cognitive task phase. A larger standard deviation indicates that the animal frequently accelerates or decelerates during the task.

[0065] Behavioral duration: calculated from the difference between the starting and ending time points of the initial behavioral segment data, indicating the length of time it takes the animal to complete the cognitive task.

[0066] Displacement amplitude: It is calculated by calculating the straight-line distance between the starting point and the ending point in the initial behavioral segment data, which is used to represent the overall movement space range covered by the animal during the completion of the current cognitive task.

[0067] The above four types of behavior structure feature indicators are summarized to form the structured behavior feature representation of the initial behavior paragraph data. Each initial behavior paragraph data has a set of structured behavior features.

[0068] According to the change pattern of the behavior structure characteristic index in the structured behavior feature representation, a sliding window method is used to perform fine-grained segmentation to generate a set of motion behavior subsequences that meet the consistency of a single behavior feature;

[0069] Specifically, after constructing the structured behavior feature representation, a sliding window approach is used to perform fine-grained analysis on each initial behavior segment. Each sliding window covers a set of continuous trajectory point sequences, velocity data sequences, and time series within the initial behavior segment data, and the four types of behavior structure feature indicators mentioned above are extracted using the sliding window as a unit.

[0070] The stability of behavioral features is determined by analyzing the change patterns of characteristic indicators between consecutive sliding windows. When the trajectory variation, velocity fluctuation characteristics, behavior duration, and displacement amplitude changes of two adjacent sliding windows remain within the set feature consistency threshold, the initial behavior segment data is considered to have consistent behavioral features.

[0071] Within the initial behavioral segment data, all sliding window regions that meet feature consistency are merged to form multiple subsequences of movement behaviors that meet single-behavior feature consistency. Each subsequence of movement behaviors exhibits continuous and stable trajectory morphology and velocity characteristics within a corresponding timeframe, serving as the fundamental unit for cognitive task label matching and interference index calculation.

[0072] Specifically, based on the time nodes at which the animal receives changes in cognitive task type, the cognitive task labels corresponding to each motor behavior subsequence are extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix, including:

[0073] Match the time range corresponding to each motor behavior subsequence with the time node of the cognitive task type change, and determine the cognitive task type label corresponding to each motor behavior subsequence;

[0074] Specifically, based on the cognitive task execution plan configured during the experimental setup phase, the actual triggering time nodes of each cognitive task are known, forming a cognitive task time node sequence. Each movement behavior subsequence in the movement behavior subsequence set has a clear start and end time, determined by the collected time information.

[0075] The start and end time ranges of the motor behavior subsequences are matched against the cognitive task time node sequence one by one to determine whether the time interval of each motor behavior subsequence completely falls within the start and end time range of the cognitive task. If the time interval of each motor behavior subsequence completely falls within the start and end time range of the cognitive task, it can be determined that the motor behavior subsequence and the cognitive task form a corresponding relationship.

[0076] For example, the sequence of cognitive tasks configured in the training process is path recognition task, target discrimination task and spatial jump task, and the task triggering times are the first time point, the second time point and the third time point respectively. If the time starting point of the movement behavior subsequence is greater than or equal to the first time point and the time ending point is less than the second time point, then the movement behavior subsequence is determined to correspond to the path recognition task.

[0077] The binding between the motor behavior subsequence and the cognitive task type label is completed in the above manner, and a unique cognitive task type label is added to each motor behavior subsequence to form a set of labeled motor behavior subsequences.

[0078] According to the cognitive task type label of each motor behavior subsequence, two motor behavior subsequences arranged consecutively in the time dimension are defined as a pair of adjacent cognitive task subsequences;

[0079] Specifically, in the set of labeled movement behavior subsequences, each movement behavior subsequence is arranged in chronological order, and every two consecutive movement behavior subsequences with different labels are defined as a pair of adjacent cognitive task subsequences.

[0080] For example, if the subsequence labels arranged in chronological order are path recognition task, target discrimination task and space jump task, then the path recognition task and target discrimination task constitute the first pair of adjacent cognitive task subsequences, and the target discrimination task and space jump task constitute the second pair of adjacent cognitive task subsequences.

[0081] Each pair of adjacent cognitive task subsequences constitutes a difference analysis unit, which is used for processing feature difference indicators.

[0082] For each pair of adjacent cognitive task subsequences, the behavioral characteristic difference index corresponding to each pair of adjacent cognitive task subsequences is obtained by calculation;

[0083] Specifically, for each pair of adjacent cognitive task subsequences, the behavioral structure characteristic indicators are extracted in turn. The behavioral structure characteristic indicators include trajectory variability, speed fluctuation characteristics, behavior duration, and displacement amplitude.

[0084] The difference between the values ​​of the same type of behavioral structure characteristic indicators for the two motor behavior subsequences within each pair of adjacent cognitive task subsequences is calculated to obtain the difference value of the behavioral structure characteristic indicator, namely the behavioral characteristic difference index. For example, if the trajectory variation degree of the first motor behavior subsequence is a first value, and the trajectory variation degree of the second motor behavior subsequence is a second value, then the difference in trajectory variation between adjacent cognitive task subsequences is the absolute value of the first value minus the second value. Similarly, the calculations for velocity fluctuation characteristic differences, behavior duration differences, and displacement amplitude differences are completed in sequence to obtain a set of behavioral characteristic difference indicators corresponding to adjacent cognitive task subsequences.

[0085] The above set of behavioral characteristic difference indicators serves as a behavioral difference representation of adjacent cognitive task subsequences, providing basic variables for interference identification and modeling.

[0086] Based on each pair of adjacent cognitive task subsequences and the corresponding behavioral feature difference indicators, a cross-task difference feature matrix is ​​constructed;

[0087] Specifically, a cross-task difference feature matrix was constructed, with all pairs of adjacent cognitive task subsequences as rows and the types of behavioral characteristic difference indicators as columns. Each row in the cross-task difference feature matrix corresponds to a pair of adjacent cognitive task subsequences, and each column corresponds to the differences in trajectory variability, velocity fluctuation characteristics, behavioral duration, and displacement amplitude, respectively. Each cell in the cross-task difference feature matrix represents the difference in the calculated behavioral structure characteristic indicators.

[0088] Specifically, we established a reverse cognitive transfer interference index, identified abnormal motor behavior segments that deviated from normal cognitive patterns based on the cross-task difference feature matrix, and determined the key task transition nodes that caused reverse cognitive transfer interference, including:

[0089] Based on the cross-task difference feature matrix, the calculation rules of the reverse cognitive transfer interference index are established;

[0090] Specifically, a standard definition is made for the behavioral characteristic difference indicators included in the cross-task difference feature matrix. For each type of behavioral structure characteristic difference indicator, a behavioral deviation degree weight is set. The behavioral deviation degree weight is determined based on the stable range of historical behavioral differences obtained from statistics in the early stages of the experiment. The higher the behavioral deviation degree weight, the greater the sensitivity of the characteristic difference to cognitive transfer interference. For example, in most experimental animals, the change in speed fluctuation characteristics has a greater impact on task cognitive switching than the change in displacement amplitude. Therefore, the weight value corresponding to the speed fluctuation characteristic difference indicator is greater than the weight value corresponding to the displacement amplitude difference indicator.

[0091] The reverse cognitive transfer interference index is calculated by multiplying the absolute value of each behavioral characteristic difference index by the corresponding behavioral deviation weight, and then summing all the product results. The resulting sum is the interference index value of adjacent cognitive task subsequences in the behavioral structure characteristic dimension, which is used to measure behavioral stability and consistency during cognitive task switching.

[0092] According to the calculation rules of the reverse cognitive transfer interference index, the behavioral feature difference index in the cross-task difference feature matrix is ​​weighted and calculated to output the reverse cognitive transfer interference index value;

[0093] Specifically, for each row in the cross-task difference feature matrix, that is, each pair of adjacent cognitive task subsequences, the reverse cognitive transfer interference index value is output according to the calculation rules of the reverse cognitive transfer interference index. The specific processing includes:

[0094] The absolute values ​​of the differences in the degree of trajectory variability, the absolute values ​​of the differences in the characteristics of speed fluctuations, the absolute values ​​of the differences in the duration of the behavior, and the absolute values ​​of the differences in the displacement amplitude were read.

[0095] The absolute values ​​of the differences in trajectory variation, speed fluctuation characteristics, behavior duration, and displacement amplitude are multiplied by their corresponding weight values, and the resulting products are recorded as four intermediate values.

[0096] The four intermediate values ​​are added together as the reverse cognitive transfer interference index value corresponding to the adjacent cognitive task subsequences.

[0097] According to the relationship between the reverse cognitive transfer interference index value and the preset cognitive mode deviation threshold, it is determined whether the movement behavior subsequence belongs to an abnormal movement behavior segment that deviates from the normal cognitive mode;

[0098] Specifically, a cognitive mode deviation threshold is set to determine whether the animal's behavioral deviation during cognitive task switching meets the interference standard. The cognitive mode deviation threshold is set based on the average behavioral fluctuation range of the experimental subjects and the limit value that represents the upper limit of normal cognitive behavior fluctuation is determined based on the statistical results of previous experiments.

[0099] The reverse cognitive transfer interference index value for each pair of adjacent cognitive task subsequences is compared with the cognitive mode deviation threshold. If the reverse cognitive transfer interference index value is greater than the cognitive mode deviation threshold, it is considered that structural behavioral drift has occurred during the task switching process of the adjacent cognitive task subsequences, indicating cognitive transfer impairment. The corresponding subsequent motor behavior subsequence is then marked as a motor behavior abnormality segment.

[0100] Abnormal motor behavior fragments indicate that animals cannot effectively adapt to the new task scenario after cognitive switching.

[0101] According to the adjacent cognitive task subsequences corresponding to the abnormal motor behavior segments, the key task transition nodes that cause reverse cognitive transfer interference are determined;

[0102] Specifically, each abnormal motor behavior segment originates from the transition phase from the previous cognitive task to the next. The cognitive task switching time point during this transition phase constitutes the critical task transition node. Based on the task switching time point of the subsequent subsequence corresponding to the abnormal motor behavior segment in the original cognitive task plan, the task transition boundary to which it belongs is determined, which is the critical time point for the occurrence of reverse cognitive transfer interference.

[0103] All identified key task transition nodes will be aggregated to form a set of key time points for interference degree modeling, cognitive task sequence optimization and individual adaptability assessment.

[0104] Specifically, a multidimensional evaluation model of reverse cognitive transfer interference was constructed based on historical cognitive training data. The degree of cognitive transfer interference in the animal's current training stage was evaluated based on key task transition nodes and corresponding abnormal movement behavior segments, including:

[0105] Extract the cognitive task type labels corresponding to the key task transition nodes and the behavioral feature difference indicators corresponding to the abnormal movement behavior segments during the historical cognitive training process;

[0106] Specifically, historical cognitive training data is retrieved from the animal cognitive movement training platform. The historical cognitive training data includes key task transition nodes and corresponding abnormal movement behavior segments recorded in multiple training cycles.

[0107] For each key task transition node, we extract the cognitive task type label at the time of its occurrence. This label represents the specific type combination of the previous and subsequent cognitive tasks represented by the key task transition node, such as switching from a path recognition task to a spatial jump task. We then uniformly encode the cognitive task type labels and use them as one of the modeling input dimensions.

[0108] For the abnormal motion behavior segments corresponding to each key task transition node, behavioral feature difference indicators of the abnormal motion behavior segments are extracted.

[0109] The cognitive task type labels and behavioral feature difference indicators are combined into complete feature entries, which are summarized to form a historical reverse cognitive transfer interference basic dataset for training multidimensional evaluation models.

[0110] Based on the influence weights of cognitive task type labels and behavioral characteristic difference indicators on reverse cognitive transfer interference, a multidimensional evaluation model of reverse cognitive transfer interference is generated.

[0111] Specifically, a multidimensional evaluation model was constructed using a weighted feature fusion strategy based on cognitive task type labels and behavioral feature difference indicators. This multidimensional evaluation uses task switching type as a categorical variable and behavioral structure feature difference indicators as input variables to comprehensively assess the degree of reverse cognitive transfer interference.

[0112] The mean and range of the behavioral structure characteristic difference indicators corresponding to each type of task switching in all historical samples are counted to analyze the sensitivity of different task switching types to interference risk.

[0113] Based on the statistical results, specific weighting factors for differences in trajectory variability, speed fluctuation characteristics, behavior duration, and displacement amplitude were determined respectively.

[0114] Input the cognitive task type label and behavioral characteristic difference index of the current training stage into the multidimensional evaluation model of reverse cognitive transfer interference, and output the cognitive transfer interference value of the animal's current training stage;

[0115] Specifically, the key task transition nodes and corresponding abnormal motor behavior segments identified in the current training stage are imported into the multidimensional evaluation model to assess the degree of cognitive transfer interference in the current training stage of the animal.

[0116] Read the cognitive task type label corresponding to the key task conversion node in the current training stage, and match the cognitive task type label with the task switching type classification variable encoding position in the multidimensional evaluation model.

[0117] Behavioral feature difference indicators are extracted from abnormal movement behavior fragments associated with key task transition nodes.

[0118] The current task switching type and behavioral characteristic difference index are input into the multidimensional evaluation model, and the cognitive transfer interference value of the animal in the current training stage is output according to the preset weighted calculation rules.

[0119] Specifically, the cognitive transfer interference level of the animal in the current training stage is matched with the preset interference threshold, and the sequence arrangement of the cognitive tasks is adjusted according to the matching result, including:

[0120] obtaining a preset interference threshold, and comparing the cognitive transfer interference value of the animal in the current training stage with the preset interference threshold;

[0121] Specifically, through statistical analysis of multiple animal cognitive training experiments, a critical interference value representing the upper limit of the normal fluctuation of the animal's cognitive transfer is obtained. This value is defined as the preset interference threshold and is used to determine whether the degree of cognitive transfer interference in the animal's current training stage requires adjustment of the training task sequence.

[0122] When the cognitive transfer interference value of the animal's current training stage is greater than the preset interference threshold, the cognitive training task sequence is reordered from high to low according to the similarity of cognitive task type labels, and a transition training link is inserted between adjacent cognitive training tasks;

[0123] Specifically, the cognitive tasks to be performed are reordered based on the cognitive task type labels. The reordering rule is to prioritize placing training tasks that are more similar to the current task type that causes significant cognitive transfer interference at the beginning of the cognitive training task sequence, and placing tasks that are less similar to the current task type at the end of the cognitive training task sequence.

[0124] For example, if the current task causing interference is a path recognition task, recognition tasks similar to the path recognition task will be prioritized in the cognitive training task sequence so that the animals can gradually adapt to similar cognitive patterns; other tasks with large differences in categories, such as spatial jumping tasks, will be placed at the end of the cognitive training task sequence to reduce the frequent and drastic switching of the animals' cognitive patterns.

[0125] Between the reordered tasks, a transition training session was inserted. This was a simplified training task with a cognitive difficulty between the two previous tasks. This was used to help the animals gradually adapt to the cognitive mode switch and reduce the risk of reverse cognitive transfer interference.

[0126] For example, a simple path tracking task is inserted between the path recognition task and the space jumping task. Through training in this path tracking task, animals gradually adapt to the cognitive transformation from pure visual recognition tasks to action-oriented tasks, reducing the drastic changes in cognitive behavioral patterns.

[0127] When the cognitive transfer interference value of the animal's current training stage is less than or equal to the preset interference threshold, the cognitive training task sequence remains unchanged.

[0128] Example 2

[0129] The difference between Example 2 of the present invention and Example 1 is that this example introduces a training and analysis system for animal cognitive movement.

[0130] Figure 2 The present invention provides a structural diagram of a training and analysis system for animal cognitive movement, which includes a behavior acquisition module, a label extraction module, an interference recognition module, an interference evaluation module, and a sequence adjustment module.

[0131] The behavior acquisition module obtains the original movement behavior data generated by the animal during the cognitive task transformation process, performs feature segmentation processing on the original movement behavior data, and generates multiple movement behavior subsequences;

[0132] The label extraction module extracts the cognitive task label corresponding to each motor behavior subsequence based on the time nodes when the animal receives the change of cognitive task type, analyzes the behavioral feature differences between adjacent cognitive task subsequences, and generates a cross-task difference feature matrix;

[0133] The interference identification module establishes a reverse cognitive transfer interference index, identifies abnormal movement behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determines the key task transition nodes that cause reverse cognitive transfer interference;

[0134] The interference assessment module builds a multidimensional evaluation model of reverse cognitive transfer interference based on historical cognitive training data. It evaluates the degree of cognitive transfer interference in the animal's current training stage according to key task transition nodes and corresponding abnormal movement behavior segments.

[0135] The sequence adjustment module matches the cognitive transfer interference level of the animal in the current training stage with the preset interference threshold, and adjusts the sequence arrangement of the cognitive task according to the matching result.

[0136] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0137] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0138] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0139] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0141] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0142] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0143] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0144] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0145] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A training and analysis method for animal cognitive movement, characterized in that: The steps include: Acquiring the original movement behavior data generated by the animal during the cognitive task transition process, performing feature segmentation processing on the original movement behavior data, and generating multiple movement behavior subsequences; Based on the time points when the animal receives changes in the type of cognitive task, the cognitive task label corresponding to each motor behavior subsequence is extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix; Establish a reverse cognitive transfer interference index, identify abnormal motor behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determine the key task transition nodes that cause reverse cognitive transfer interference; Based on the cross-task difference feature matrix, the calculation rules of the reverse cognitive transfer interference index are established; According to the calculation rules of the reverse cognitive transfer interference index, the behavioral feature difference index in the cross-task difference feature matrix is ​​weighted and calculated to output the reverse cognitive transfer interference index value; According to the relationship between the reverse cognitive transfer interference index value and the preset cognitive mode deviation threshold, it is determined whether the movement behavior subsequence belongs to an abnormal movement behavior segment that deviates from the normal cognitive mode; According to the adjacent cognitive task subsequences corresponding to the abnormal motor behavior segments, the key task transition nodes that cause reverse cognitive transfer interference are determined; A multidimensional evaluation model for reverse cognitive transfer interference was constructed based on historical cognitive training data. The degree of cognitive transfer interference in the current training phase of the animal was assessed based on key task transition nodes and corresponding abnormal motor behavior segments. Extract the cognitive task type labels corresponding to the key task transition nodes and the behavioral feature difference indicators corresponding to the abnormal movement behavior segments during the historical cognitive training process; Based on the influence weights of cognitive task type labels and behavioral characteristic difference indicators on reverse cognitive transfer interference, a multidimensional evaluation model of reverse cognitive transfer interference is generated. Input the cognitive task type label and behavioral characteristic difference index of the current training stage into the multidimensional evaluation model of reverse cognitive transfer interference, and output the cognitive transfer interference value of the animal's current training stage; The degree of cognitive transfer interference in the animal's current training stage is matched with the preset interference threshold, and the sequence arrangement of the cognitive task is adjusted according to the matching result.

2. The training and analysis method for animal cognitive movement according to claim 1, characterized in that: The original motor behavior data generated by the animal during the cognitive task transition is obtained, and the original motor behavior data is subjected to feature segmentation processing to generate multiple motor behavior subsequences, specifically: Perform multi-channel parallel acquisition of the original motor behavior data of animals during different cognitive task execution stages; The collected original movement behavior data is segmented according to the cognitive task triggering time nodes and divided into multiple initial behavior segment data sets; Based on the initial behavior paragraph data set, the behavior structure feature indicators in the initial behavior paragraph data are extracted to form a structured behavior feature representation; According to the change pattern of the behavior structure feature indicators in the structured behavior feature representation, a sliding window method is used to perform fine-grained segmentation to generate a set of motion behavior subsequences that meet the consistency of a single behavior feature.

3. The training and analysis method for animal cognitive movement according to claim 2, characterized in that: Based on the time points when the animal receives changes in the type of cognitive task, the cognitive task labels corresponding to each motor behavior subsequence are extracted, and the behavioral feature differences between adjacent cognitive task subsequences are analyzed to generate a cross-task difference feature matrix, specifically: Match the time range corresponding to each motor behavior subsequence with the time node of the cognitive task type change, and determine the cognitive task type label corresponding to each motor behavior subsequence; According to the cognitive task type label of each motor behavior subsequence, two motor behavior subsequences arranged consecutively in the time dimension are defined as a pair of adjacent cognitive task subsequences; For each pair of adjacent cognitive task subsequences, the behavioral characteristic difference index corresponding to each pair of adjacent cognitive task subsequences is obtained by calculation; Based on each pair of adjacent cognitive task subsequences and the corresponding behavioral feature difference indicators, a cross-task difference feature matrix is ​​constructed.

4. The training and analysis method for animal cognitive movement according to claim 3, characterized in that: Match the cognitive transfer interference level of the animal in the current training stage with the preset interference threshold, and adjust the sequence arrangement of cognitive tasks according to the matching result, specifically: obtaining a preset interference threshold, and comparing the cognitive transfer interference value of the animal in the current training stage with the preset interference threshold; When the cognitive transfer interference value of the animal's current training stage is greater than the preset interference threshold, the cognitive training task sequence is reordered from high to low according to the similarity of cognitive task type labels, and a transition training link is inserted between adjacent cognitive training tasks; When the cognitive transfer interference value of the animal's current training stage is less than or equal to the preset interference threshold, the cognitive training task sequence remains unchanged.

5. A training and analysis system for animal cognitive movement, used to implement the training and analysis method for animal cognitive movement according to any one of claims 1 to 4, characterized in that: It includes behavior acquisition module, label extraction module, interference identification module, interference assessment module and sequence adjustment module; The behavior acquisition module obtains the original movement behavior data generated by the animal during the cognitive task transformation process, performs feature segmentation processing on the original movement behavior data, and generates multiple movement behavior subsequences; The label extraction module extracts the cognitive task label corresponding to each motor behavior subsequence based on the time nodes when the animal receives the change of cognitive task type, analyzes the behavioral feature differences between adjacent cognitive task subsequences, and generates a cross-task difference feature matrix; The interference identification module establishes a reverse cognitive transfer interference index, identifies abnormal movement behavior segments that deviate from normal cognitive patterns based on the cross-task difference feature matrix, and determines the key task transition nodes that cause reverse cognitive transfer interference; The interference assessment module builds a multidimensional evaluation model of reverse cognitive transfer interference based on historical cognitive training data. It evaluates the degree of cognitive transfer interference in the animal's current training stage according to key task transition nodes and corresponding abnormal movement behavior segments. The sequence adjustment module matches the cognitive transfer interference level of the animal in the current training stage with the preset interference threshold, and adjusts the sequence arrangement of the cognitive task according to the matching result.

Images