Adaptive behavior recognition method and apparatus, device, medium, and product

Abstract

An adaptive behavior recognition method and apparatus, a device, a medium, and a product. The method comprises: acquiring behavior feature data respectively corresponding to at least two individuals to be recognized (S110), wherein the behavior feature data represents statistical behavior information exhibited by said individuals in response to repetitive threat stimulus signals during repeated threat stimulus experiments; on the basis of at least two pieces of behavior feature data, clustering said at least two individuals to obtain at least two cluster sets (S120); and on the basis of cluster index values respectively corresponding to the at least two cluster sets, determining adaptive behavior results respectively corresponding to said individuals in each cluster set (S130).

Description

Methods, devices, equipment, media, and products for identifying adaptive behaviors

[0001] This application claims priority to Chinese Patent Application No. 202411699991.7, filed with the Chinese Patent Office on November 26, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of data processing technology, such as a method, apparatus, device, medium, and product for identifying adaptive behavior. Background Technology

[0003] Fear is defined as a basic emotion that an organism rapidly experiences when it perceives a threat. In nature, organisms can respond quickly to threats such as predators, harmful stimuli, and danger signals, taking instinctive reactions such as fight, flight, and "freezing" based on environmental cues. Neuroscientists refer to these series of instinctive reactions taken by organisms when facing threats as instinctive defense behaviors.

[0004] While fleeing can reduce harm to an individual, it also leads to the cessation of other survival activities such as foraging and finding habitat, as well as the loss of vital resources. To balance fleeing with other survival behaviors, individuals typically use sensory information and past experiences to assess threats and decide whether to flee. Across different species, individuals repeatedly exposed to threats may exhibit different coping strategies.

[0005] Adaptive coping strategies employed by organisms in response to recurring threats in the environment are crucial for individual survival and species reproduction. Accurate classification of these adaptive behaviors helps in-depth research into their mechanisms, development processes, and influencing factors, thereby providing data support for developing effective intervention strategies.

[0006] Currently, the definition of adaptive behavior in biological individuals relies on the subjective judgment of researchers, making it difficult to accurately distinguish biological individuals on the edge of group boundaries. Summary of the Invention

[0007] This application provides a method, apparatus, device, medium, and product for identifying adaptive behaviors, in order to solve the problem that adaptive behaviors rely on subjective judgment and improve the accuracy and efficiency of adaptive behavior identification.

[0008] According to one embodiment of this application, a method for identifying adaptive behavior is provided, the method comprising:

[0009] Obtain behavioral feature data corresponding to at least two individuals to be identified; wherein, the behavioral feature data represents the statistical behavioral information exhibited by the individuals to be identified in response to repetitive threat stimulus signals in a repetitive threat stimulus experiment;

[0010] Based on at least two behavioral characteristic data, the at least two individuals to be identified are clustered to obtain at least two cluster sets;

[0011] Based on the clustering index values ​​corresponding to at least two cluster sets, determine the adaptive behavior outcome for each individual to be identified in each cluster set.

[0012] According to another embodiment of this application, an adaptive behavior recognition device is provided, the device comprising:

[0013] The behavioral feature data acquisition module is configured to acquire behavioral feature data corresponding to at least two individuals to be identified; wherein, the behavioral feature data represents the statistical behavioral information exhibited by the individuals to be identified in response to repetitive threat stimulus signals in a repetitive threat stimulus experiment;

[0014] The cluster set determination module is configured to cluster the at least two individuals to be identified based on at least two behavioral feature data to obtain at least two cluster sets;

[0015] The adaptive behavior outcome determination module is configured to determine the adaptive behavior outcome for each individual to be identified in each cluster based on the clustering index values ​​corresponding to at least two cluster sets.

[0016] According to another embodiment of this application, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the adaptive behavior recognition method described in any embodiment of this application.

[0020] According to another embodiment of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the adaptive behavior recognition method described in any embodiment of this application.

[0021] According to another embodiment of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the adaptive behavior recognition method described in any embodiment of this application. Attached Figure Description

[0022] The accompanying drawings used in the following description of the embodiments will be introduced. The drawings described below are drawings of some embodiments related to this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 is a flowchart of an adaptive behavior recognition method provided in one embodiment of this application;

[0024] Figure 2 is a flowchart of another adaptive behavior recognition method provided in one embodiment of this application;

[0025] Figure 3 is a schematic diagram of an example of an adaptive behavior recognition method provided in an embodiment of this application;

[0026] Figure 4 is a visualization of the adaptive behavior of a cluster set provided in an embodiment of this application;

[0027] Figure 5 is a schematic diagram of the identification results of adaptive behaviors corresponding to the repeated threat stimulus experiment on days 1-3 in a continuous repeated threat stimulus experiment provided by an embodiment of this application;

[0028] Figure 6 is a schematic diagram of the identification results of adaptive behaviors corresponding to the repeated threat stimulus experiment on the 4th-5th day of a continuous repeated threat stimulus experiment provided in an embodiment of this application;

[0029] Figure 7 is a schematic diagram of the structure of an adaptive behavior recognition device provided in an embodiment of this application;

[0030] Figure 8 is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0031] The embodiments of this application will now be described with reference to the accompanying drawings. These described embodiments are some related to this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort should fall within the scope of protection of this application.

[0032] The terms "first," "second," "target," "to be identified," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, for example, including, in addition to the series of steps or units shown in the embodiments of this application, other processes, methods, systems, products, or devices not listed in this series of steps or units, or other steps or units inherent to these processes, methods, systems, products, or devices.

[0033] Figure 1 is a flowchart of an adaptive behavior identification method provided in an embodiment of this application. This embodiment is applicable to the identification of adaptive behaviors in threatening stimulus environments, such as repetitive threatening stimulus environments. The method can be executed by an adaptive behavior identification device, which can be implemented in hardware and / or software and can be configured in a terminal device. As shown in Figure 1, the method includes:

[0034] S110. Obtain behavioral feature data corresponding to at least two individuals to be identified.

[0035] The individual to be identified refers to the biological individual used for adaptive behavior identification. For example, the species of the individual to be identified may include insects, rodents, or primates. When the species of the individual to be identified is a rodent, the individual to be identified may be a mouse. The individual to be identified can be customized according to actual needs.

[0036] In this embodiment, behavioral feature data represents statistical behavioral information of the individual to be identified in response to repetitive threat stimulus signals during a repetitive threat stimulus experiment.

[0037] For example, a repeated threat stimulus experiment refers to an experiment in which the same threat stimulus signal is given to the individual to be identified multiple times within the experimental period in order to collect behavioral response data of the individual to be identified. This is used to simulate the dangerous stimuli that biological individuals face in the natural environment over a long period of time.

[0038] In one optional embodiment, the experimental paradigm of the repeated threat stimulus experiment includes: during the preparation period before the start of the repeated threat stimulus experiment, using a timing device to perform timing operations to allow the individual to be identified to adapt to the experimental chamber; during the repeated threat stimulus experiment, using a timing device to perform timing operations to allow the individual to be identified to adapt to the experimental chamber; and after the timing ends, in response to detecting that the individual to be identified is located in a preset stimulus area in the experimental chamber, controlling the stimulus device to emit a threat stimulus signal.

[0039] In another optional embodiment, the repeated threat stimulus experiment is included in the continuous repeated threat stimulus experiment. The experimental paradigm of the continuous repeated threat stimulus experiment includes: during the preparation period before the start of the continuous repeated threat stimulus experiment, a timing device is used to perform timing operations to allow the individual to be identified to adapt to the experimental chamber; during the continuous repeated threat stimulus experiment, for each repeated threat stimulus experiment, a timing device is used to perform timing operations to allow the individual to be identified to adapt to the experimental chamber, and after the timing ends, in response to detecting that the individual to be identified is located in a preset stimulus area in the experimental chamber, the stimulation device is controlled to emit a threat stimulus signal.

[0040] In this embodiment, the number of repeated threat stimulus experiments in the continuous repeated threat stimulus experiment is 5, and the experimental period of the repeated threat stimulus experiment is 1 day.

[0041] In the above embodiments, the number of threat stimulus signals emitted is greater than 1 but less than a threshold number, the time interval between two adjacent threat stimulus signals is greater than a time interval threshold, and the experiment duration for the individual to be identified is less than an experiment duration threshold. For example, the preparation period is 1 day, the timing operation can be 10 minutes (min) or 15 minutes, the number of emission threshold can be 10 or 15 times, the time interval threshold can be 2 minutes or 3 minutes, and the experiment duration threshold can be 1 hour (h) or 2 hours.

[0042] For example, the types of threatening stimuli signals may include auditory stimuli signals, visual stimuli signals, tactile stimuli signals, or olfactory stimuli signals. For instance, auditory stimuli signals may be sudden high-decibel sound signals or long-lasting sharp sound signals; visual stimuli signals may be gradually enlarging image signals, approaching objects, flashing bright light signals, or terrifying image signals; tactile stimuli signals may be electrical stimulation signals or airflow impact signals; and olfactory stimuli signals may be the predator's scent of the individual to be identified or the scent containing harmful chemicals.

[0043] In one optional embodiment, the threat stimulus signal is a visual looming signal, which represents a signal that starts with a black disk of initial diameter, expands to a target diameter at a preset expansion rate, and is continuously displayed for a preset duration. For example, the initial diameter can be 5 centimeters (cm), the preset expansion rate can be 5 centimeters / second (cm / s), the target diameter can be 30 cm, and the preset duration can be 30 seconds (s) or 1 minute.

[0044] In this embodiment, the continuous repeatable threat stimulus experiment that uses visual approach danger signals as threat stimulus signals is defined as the continuous repeatable negative visual experiences (RAVE) experiment. The RAVE experiment has strong stability and is applicable to biological groups of different genders.

[0045] In this embodiment, the behavioral characteristic data includes at least two behavioral characteristic parameters. In an optional embodiment, the behavioral characteristic data includes at least two of the following: number of escape attempts, escape rate, average escape reaction latency, average escape speed, and average escape return time.

[0046] For example, the number of escape attempts represents the cumulative frequency of the individual to be identified making escape actions in response to a threatening stimulus signal within the experimental duration; the escape ratio represents the ratio between the number of escape attempts and the number of times the threatening stimulus signal was emitted within the experimental duration; the average escape response latency represents the ratio between the sum of the response latencies corresponding to at least one escape action and the number of escape attempts; the response latency represents the time interval between the start of the threatening stimulus signal and the moment the individual to be identified made the escape behavior; the average escape speed represents the ratio between the sum of the escape speeds corresponding to at least one escape action and the number of escape attempts; the average escape return time represents the ratio between the sum of the return times corresponding to at least one escape action and the number of escape attempts; and the return time represents the time interval between the start of the threatening stimulus signal and the moment the individual to be identified returned to the nest.

[0047] Based on the above embodiments, optionally, if the individual to be identified does not attempt to escape during the repeated threat stimulus experiment, then each behavioral feature parameter in the behavioral feature data is set to 0. Here, the escape action represents the behavioral action taken when the current moving speed of the individual to be identified exceeds a speed threshold. For example, the speed threshold can be 40 mm / s, and the speed threshold can be customized according to the individual type of the individual to be identified.

[0048] S120. Based on at least two behavioral characteristic data, cluster at least two individuals to be identified to obtain at least two cluster sets.

[0049] For example, clustering algorithms may include K-Means clustering, hierarchical clustering, density-based spatial clustering of applications with noise (DBSCAN), and Gaussian mixture model clustering, etc. The clustering algorithm used in this application can be customized according to actual needs.

[0050] In one optional embodiment, at least two individuals to be identified are clustered based on at least two behavioral feature data to obtain at least two cluster sets, including: for each individual to be identified, performing dimensionality reduction processing on the behavioral feature data corresponding to the individual to be identified to obtain dimensionality-reduced behavioral feature data; and clustering at least two individuals to be identified based on at least two dimensionality-reduced behavioral feature data to obtain at least two cluster sets.

[0051] For example, the dimensionality-reduced behavioral feature data can be represented as [umap1, umap2, umap3]. The dimensionality reduction algorithm used can include Uniform Manifold Approximation and Projection (UMAP), Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (T-SNE), Singular Value Decomposition (SVD), and Locally Linear Embedding (LLE). The dimensionality reduction algorithm used in this application can be customized according to actual needs.

[0052] Dimensionality reduction is used to remove noise and redundant information from behavioral feature data, reducing the computational cost of clustering steps. This makes the distribution structure of behavioral feature data in the low-dimensional space clearer and more separable, thereby improving the quality and interpretability of subsequent clustering results.

[0053] A cluster set represents a set of individuals to be identified that belong to the same adaptive behavior. For example, when there are two cluster sets, the adaptive behavior result is either adaptive or maladaptive; when there are three cluster sets, the adaptive behavior result is either over-adaptive, adaptive, or maladaptive; and when there are four cluster sets, the adaptive behavior result is either over-adaptive, adaptive, maladaptive, or maladaptive. The number of cluster sets and their corresponding adaptive behaviors in this application can be customized according to actual needs.

[0054] S130. Based on the clustering index values ​​corresponding to at least two cluster sets, determine the adaptive behavior results corresponding to each individual to be identified in each cluster set.

[0055] In one optional embodiment, the clustering index value represents the similarity between the clustering features corresponding to the cluster set and the true features corresponding to at least two adaptive behaviors. The clustering features can be statistical characteristics of behavioral feature parameters in the behavioral feature data within the cluster set, or statistical characteristics of other behavioral feature parameters within the cluster set.

[0056] For example, the clustering index value can be a statistical value related to the escape ratio or a statistical value related to the latency of the escape response, such as the average or median. The selection of the clustering index value in this application can be customized according to actual needs.

[0057] In this embodiment, the adaptive behavior result corresponding to each individual to be identified in each cluster is determined based on the clustering index values ​​corresponding to at least two cluster sets, including: for each cluster set, determining the clustering index value of the cluster set based on the clustering characteristics of the cluster set and the true characteristics corresponding to at least two adaptive behavior results; and taking the adaptive behavior result corresponding to the smallest index value among the clustering index values ​​as the adaptive behavior result corresponding to each individual to be identified in the cluster set.

[0058] The clustering index value includes at least two index values. The index value represents the feature distance between the clustering features corresponding to the cluster set and the true features corresponding to the adaptive behavior results. For example, the algorithm for determining the clustering index value may include a distance algorithm or a neural network algorithm.

[0059] This embodiment clusters at least two individuals based on their behavioral feature data, resulting in at least two cluster sets. Then, based on the clustering index values ​​corresponding to each of the at least two cluster sets, it determines the adaptive behavior outcome for each individual in each cluster set. The behavioral feature data represents the statistical behavioral information exhibited by the individuals in response to repetitive threat stimuli in a repetitive threat stimulus experiment. This solves the problem of adaptive behavior relying on subjective judgment and improves the accuracy and efficiency of identifying the adaptive behavior of biological individuals in repetitive threat stimulus scenarios.

[0060] Figure 2 is a flowchart of another adaptive behavior identification method provided in an embodiment of this application. This embodiment adjusts the above embodiment's "determining the adaptive behavior result corresponding to each individual to be identified in each cluster based on the clustering index values ​​corresponding to at least two cluster sets." In this embodiment, determining the adaptive behavior result corresponding to each individual to be identified in each cluster based on the clustering index values ​​corresponding to at least two cluster sets includes: comparing the clustering index values ​​corresponding to at least two cluster sets to obtain a comparison result; and determining the adaptive behavior result corresponding to each individual to be identified in each cluster based on the comparison result. As shown in Figure 2, the method includes:

[0061] S210. Obtain behavioral feature data corresponding to at least two individuals to be identified.

[0062] In one optional embodiment, S210 corresponds to or is similar to S110 shown in Figure 1 of the above embodiment, and will not be described again in this embodiment.

[0063] In another optional embodiment, when the individual to be identified is a rodent, the behavioral characteristic data includes a motion transition frequency and a motion percentage dataset. The motion percentage dataset represents the ratio between the duration of the individual's behavioral motion and the duration of its escape. The escape duration represents the length of time from the start of the threatening stimulus signal to the end of the individual's escape within a single stimulus cycle. The motion percentage dataset includes at least one of the following: flight motion percentage, running motion percentage, trotting motion percentage, walking motion percentage, left turn motion percentage, right turn motion percentage, stepping motion percentage, climbing motion percentage, sniffing motion percentage, grooming motion percentage, pausing motion percentage, freezing behavior percentage, and jumping behavior percentage.

[0064] For example, the action transition frequency represents the number of times the individual to be identified transitions from one behavioral action to another in a repeated threat stimulus experiment; the single stimulus period represents the time interval between the start time of the current threat stimulus signal and the start time of the next threat stimulus signal; the single stimulus periods corresponding to two adjacent threat stimulus signals may be the same or different; and the escape end time represents the moment when the escape speed of the individual to be identified changes from greater than or equal to the speed threshold to less than the speed threshold within a single stimulus period.

[0065] The duration of a behavior or action represents a statistical value of the duration of the behavior or action. For example, the statistical value can be a sum, a maximum value, or an average value.

[0066] The percentage of running actions corresponds to running actions that meet the criteria of a movement speed reaching a first speed threshold and / or a stride length reaching a first stride length threshold. The percentage of jogging actions corresponds to jogging actions that meet the criteria of a movement speed greater than a second speed threshold and less than a first speed threshold and / or a stride length greater than a second stride length threshold and less than a first stride length threshold. The percentage of walking actions corresponds to walking actions that meet the criteria of a movement speed greater than a third speed threshold and less than a second speed threshold and / or a stride length greater than a third stride length threshold and less than a second stride length threshold. The percentage of stepping actions corresponds to stepping actions that include at least two of the following actions: running, jogging, and walking.

[0067] S220. Based on at least two behavioral characteristic data, cluster at least two individuals to be identified to obtain at least two cluster sets.

[0068] In this embodiment, S220 corresponds to or is similar to S120 shown in Figure 1 of the above embodiment, and will not be described again in this embodiment.

[0069] S230. Compare the cluster index values ​​corresponding to at least two cluster sets to obtain the comparison results.

[0070] For example, the clustering index value represents the statistical value of the clustering feature corresponding to the cluster set under the cluster set. The clustering feature can be the statistical feature of the behavioral feature parameter in the behavioral feature data under the cluster set, or it can be the statistical feature of other behavioral feature parameters under the cluster set.

[0071] In one alternative embodiment, the clustering index value is a statistical value corresponding to the escape ratio; for example, the statistical value can be the average or the median.

[0072] S240. Based on the comparison results, determine the adaptive behavior outcome corresponding to each individual to be identified in each cluster.

[0073] In an optional embodiment, based on the comparison results, the adaptive behavior result corresponding to each individual to be identified in each cluster is determined, including: when the cluster index value is a statistical value corresponding to the escape ratio, and the number of clusters is two, the adaptive behavior result of at least one individual to be identified in the cluster with the larger cluster index value in the comparison results is regarded as adaptive; the adaptive behavior result of at least one individual to be identified in the cluster with the smaller cluster index value in the comparison results is regarded as maladaptive.

[0074] In another optional embodiment, based on the comparison results, the adaptive behavior result corresponding to each individual to be identified in each cluster is determined, including: when the cluster index value is a statistical value corresponding to the escape ratio, and the number of clusters is three, the adaptive behavior results of at least one individual to be identified in the cluster with the largest cluster index value in the comparison results are all considered overfitting; the adaptive behavior results of at least one individual to be identified in the cluster with the second largest cluster index value in the comparison results are all considered adaptive; and the adaptive behavior results of at least one individual to be identified in the cluster with the smallest cluster index value in the comparison results are all considered maladaptive.

[0075] This embodiment compares the clustering index values ​​corresponding to at least two cluster sets to obtain the comparison results. Based on the comparison results, the adaptive behavior results corresponding to each individual to be identified in each cluster set are determined. This achieves the effect of unsupervised identification of adaptive behavior of biological individuals, saves manpower, material resources and time costs, improves the versatility of the adaptive behavior identification method, and helps to explore the previously unknown distribution patterns of cluster sets.

[0076] Based on the above embodiments, optionally, the method further includes: when the number of clusters is two, determining an escape ratio threshold based on the escape ratio and adaptive behavior results of at least two individuals to be identified; if the escape ratio of the target individual is greater than or equal to the escape ratio threshold, then setting the adaptive behavior result of the target individual to adaptive; if the escape ratio of the target individual is less than the escape ratio threshold, then setting the adaptive behavior result of the target individual to maladaptive; wherein, the target individual is a biological individual participating in the repeated threat stimulus experiment other than at least two individuals to be identified.

[0077] For example, determining an escape ratio threshold based on the escape ratios and adaptive behavior results of at least two individuals to be identified includes: averaging the escape ratios of at least one individual to be identified corresponding to an adaptive type to obtain a first average escape ratio; averaging the escape ratios of at least one individual to be identified corresponding to an maladaptive type to obtain a second average escape ratio; and determining the escape ratio threshold based on the first average escape ratio and the second average escape ratio. For example, the escape ratio threshold satisfies [p2, p1], where p1 represents the first average escape ratio and p2 represents the second average escape ratio.

[0078] In one alternative embodiment, the escape ratio threshold is the average of the first average escape ratio and the second average escape ratio.

[0079] For example, the adaptive recognition condition is expressed as: M / N≥P, where M represents the number of times the biological individual flees in the repeated threat stimulus experiment, N represents the number of times the biological individual emits the threat stimulus signal triggered in the repeated threat stimulus experiment, and P represents the escape ratio threshold.

[0080] This setup, while ensuring the accuracy of adaptive behavior results, overcomes the dependence of adaptive behavior identification methods on the biological population, achieving the effect of quickly identifying the adaptive behavior of individual organisms.

[0081] Figure 3 is a schematic diagram of an example of an adaptive behavior identification method provided in an embodiment of this application. Exemplarily, continuous repeated threat stimulus experiments are conducted on multiple individuals to be identified, and the behavioral feature data of each individual to be identified in each repeated threat stimulus experiment are statistically analyzed. For each repeated threat stimulus experiment, the behavioral feature data corresponding to each individual to be identified and the repeated threat stimulus experiment are dimensionality-reduced to obtain 3D behavioral feature data. Hierarchical clustering is performed on the 3D behavioral feature data of all individuals to be identified to obtain two cluster sets, namely cluster set A and cluster set B. Determine whether the average escape rate corresponding to cluster A is greater than that corresponding to cluster B. If so, set the adaptive behavior results of the individuals to be identified in cluster A in the repeated threat stimulus experiment as adaptive, and set the adaptive behavior results of the individuals to be identified in cluster B in the repeated threat stimulus experiment as maladaptive. If not, set the adaptive behavior results of the individuals to be identified in cluster B in the repeated threat stimulus experiment as adaptive, and set the adaptive behavior results of the individuals to be identified in cluster A in the repeated threat stimulus experiment as maladaptive.

[0082] Figure 4 is a visualization of the adaptive behavior results of a cluster set provided in an embodiment of this application. Figure 4 uses two cluster sets as an example, with the dimensionality-reduced behavioral feature data as three-dimensional data. For example, the three coordinate axes in Figure 4 represent the three dimensions of the dimensionality-reduced behavioral feature data, the clusters formed by solid triangles represent the clusters of adaptive individuals to be identified, and the clusters formed by solid circles represent the clusters of non-adaptive individuals to be identified.

[0083] Figures 5 and 6 show the identification results of adaptive behaviors corresponding to the repeated threat stimulus experiment from day 1 to day 5 in the continuous repeated threat stimulus experiment. For example, day 1 to day 5 represent five consecutive days. In Figures 5 and 6, solid triangles indicate adaptive behaviors of the individuals to be identified, solid circles indicate maladaptive behaviors, "F" indicates that the sex of the individual to be identified is female, "M" indicates that the sex of the individual to be identified is male, the number after "F" or "M" indicates the individual's identification number, "A" indicates the identification result of adaptive behavior based on five behavioral characteristic parameters: number of escape attempts, escape ratio, average escape response latency, average escape speed, and average escape return time, etc., and "B" indicates the identification result of adaptive behavior based on 14 behavioral characteristic parameters, including action transition frequency and action percentage datasets. The action percentage dataset contains the percentage of 13 different behavioral actions.

[0084] Figure 5 shows the identification results of adaptive behaviors in 26 individuals for the repeated threat stimulus experiment on Day 1, including 14 females and 12 males. Figure 5 also shows the identification results of adaptive behaviors in 30 individuals for the repeated threat stimulus experiment on Day 2, including 14 females and 16 males. Finally, Figure 5 shows the identification results of adaptive behaviors in 31 individuals for the repeated threat stimulus experiment on Day 3, including 15 females and 16 males.

[0085] Figure 6 shows the identification results of adaptive behaviors of 32 individuals for the repeated threat stimulus experiment on day 4, including 16 females and 16 males. Figure 6 also shows the identification results of adaptive behaviors of 28 individuals for the repeated threat stimulus experiment on day 5, including 14 females and 14 males.

[0086] As shown in Figures 5 and 6, the identification results demonstrate that in the continuous repeated threat stimulus experiment, the proportion of adaptive individuals in the biological population increases with the repeated execution of the experiment. Furthermore, the consistency of the identification results of adaptive behaviors based on the two different behavioral characteristic data reached over 95%, proving the feasibility of the two behavioral characteristic data.

[0087] In some embodiments, the escape ratio threshold for distinguishing between adaptive and maladaptive behaviors is 50%, obtained by performing regular statistical analysis on the identification results of adaptive behaviors shown in Figures 5 and 6.

[0088] The following are embodiments of the adaptive behavior recognition device provided in this application. For content not described in the embodiments of the adaptive behavior recognition device, please refer to the content of the adaptive behavior recognition method in the above embodiments.

[0089] Figure 7 is a schematic diagram of an adaptive behavior recognition device provided in one embodiment of this application. As shown in Figure 7, the device includes: a behavior feature data acquisition module 310, a cluster set determination module 320, and an adaptive behavior result determination module 330.

[0090] The behavioral feature data acquisition module 310 is configured to acquire behavioral feature data corresponding to at least two individuals to be identified; wherein, the behavioral feature data represents the statistical behavioral information exhibited by the individuals to be identified in response to repetitive threat stimulus signals in a repetitive threat stimulus experiment;

[0091] The cluster set determination module 320 is configured to cluster at least two individuals to be identified based on at least two behavioral feature data to obtain at least two cluster sets;

[0092] The adaptive behavior outcome determination module 330 is configured to determine the adaptive behavior outcome corresponding to each individual to be identified in each cluster based on the cluster index values ​​corresponding to at least two cluster sets.

[0093] This embodiment clusters at least two individuals based on their behavioral feature data, resulting in at least two cluster sets. Then, based on the clustering index values ​​corresponding to each of the at least two cluster sets, it determines the adaptive behavior outcome for each individual in each cluster set. The behavioral feature data represents the statistical behavioral information exhibited by the individuals in response to repetitive threat stimuli in a repetitive threat stimulus experiment. This solves the problem of adaptive behavior relying on subjective judgment and improves the accuracy and efficiency of identifying the adaptive behavior of biological individuals in repetitive threat stimulus scenarios.

[0094] In an optional embodiment, the adaptive behavior outcome determination module 330 includes:

[0095] The comparison result determination unit is configured to compare the cluster index values ​​corresponding to at least two cluster sets to obtain the comparison result;

[0096] The adaptive behavior outcome determination unit is configured to determine the adaptive behavior outcome corresponding to each individual to be identified in each cluster based on the comparison results.

[0097] In an optional embodiment, the adaptive behavior result determination unit is configured as follows:

[0098] In response to the cluster index value being a statistical value corresponding to the escape ratio, and the number of clusters being two, the adaptive behavior results of at least one individual to be identified in the cluster with the larger cluster index value in the comparison results are all taken as the adaptive type.

[0099] The adaptive behavior of at least one individual in the cluster with the smaller cluster index value in the comparison results is considered maladaptive.

[0100] In an optional embodiment, the cluster set determination module 320 is configured as follows:

[0101] For each individual to be identified, the behavioral feature data corresponding to the individual to be identified is subjected to dimensionality reduction processing to obtain the dimensionality-reduced behavioral feature data.

[0102] Based on at least two behavioral feature data after dimensionality reduction, at least two cluster sets are obtained by clustering at least two individuals to be identified.

[0103] In one alternative embodiment, the behavioral characteristic data includes at least two of the following: number of escapes, escape ratio, average escape response latency, average escape speed, and average escape return time.

[0104] In an optional embodiment, when the individual to be identified is a rodent, the behavioral characteristic data includes a motion transition frequency and a motion percentage dataset. The motion percentage dataset represents the ratio between the duration of the individual's behavioral motion and the duration of its escape. The escape duration represents the length of time from the start of the threatening stimulus signal to the end of the individual's escape within a single stimulus cycle. The motion percentage dataset includes at least one of the following: flight motion percentage, running motion percentage, trotting motion percentage, walking motion percentage, left turn motion percentage, right turn motion percentage, stepping motion percentage, climbing motion percentage, sniffing motion percentage, grooming motion percentage, pausing motion percentage, freezing behavior percentage, and jumping behavior percentage.

[0105] In an optional embodiment, the repeated threat stimulus experiment is included in the continuous repeated threat stimulus experiment, and the apparatus further includes:

[0106] The continuous repeated threat stimulus experiment paradigm module is set up to use a timing device to perform timing operations during the preparation period before the continuous repeated threat stimulus experiment begins, so that the individual to be identified can adapt to the experimental chamber.

[0107] During the continuous repetitive threat stimulus experiment, a timing device is used to perform timing operation for each repetitive threat stimulus experiment to allow the individual to be identified to adapt to the experimental chamber. After the timing ends, in response to the detection that the individual to be identified is located in the preset stimulus area in the experimental chamber, the stimulation device is controlled to emit a threat stimulus signal.

[0108] Among them, the number of repeated threat stimulus experiments in the continuous repeated threat stimulus experiment is 5, the experimental period of the repeated threat stimulus experiment is 1 day, the number of threat stimulus signals issued is greater than 1 and less than the number threshold, the time interval between two adjacent threat stimulus signals is greater than the time interval threshold, and the experimental duration of the repeated threat stimulus experiment is less than the experimental duration threshold.

[0109] In an optional embodiment, the device further includes:

[0110] The escape ratio threshold determination module is configured to determine the escape ratio threshold based on the escape ratio and adaptive behavior results of at least two individuals to be identified when the number of clusters is two.

[0111] In response to the target individual's escape rate being greater than or equal to the escape rate threshold, the target individual's adaptive behavior outcome is set to adaptive.

[0112] If the escape rate of the target individual is less than the escape rate threshold, the adaptive behavior outcome of the target individual is set to maladaptive.

[0113] The target individuals are biological individuals who participate in repeated threat-stimuli experiments, excluding at least two individuals to be identified.

[0114] The adaptive behavior recognition device provided in this application embodiment can execute the adaptive behavior recognition method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

[0115] Figure 8 is a schematic diagram of an electronic device provided in one embodiment of this application. The electronic device 10 represents various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples.

[0116] As shown in Figure 8, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information or data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0118] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 may include a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the adaptive behavior recognition method provided in the above embodiments.

[0119] In some embodiments, the adaptive behavior identification method provided in the above embodiments can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, at least one step of the adaptive behavior identification method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the adaptive behavior identification method by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the systems and techniques described above herein can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs used to implement the adaptive behavior identification method of this application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable storage medium. Examples of machine-readable storage media may include a portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on a terminal device having: a display device for displaying information to the user (e.g., a cathode-ray tube (CRT) or liquid crystal display (LCD) or monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the terminal device. Other types of devices can also provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0124] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0125] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0126] The various processes shown above can be used to reorder, add, or delete steps. For example, the multiple steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of this application can be achieved.

Claims

1. A method for identifying adaptive behavior, comprising: Obtain behavioral feature data corresponding to at least two individuals to be identified; wherein, the behavioral feature data represents the statistical behavioral information exhibited by the individuals to be identified in response to repetitive threat stimulus signals in a repetitive threat stimulus experiment; Based on at least two behavioral characteristic data, the at least two individuals to be identified are clustered to obtain at least two cluster sets; Based on the clustering index values ​​corresponding to at least two cluster sets, determine the adaptive behavior outcome for each individual to be identified in each cluster set.

2. The method according to claim 1, wherein, The step of determining the adaptive behavior outcome for each individual to be identified in each cluster based on the clustering index values ​​corresponding to at least two cluster sets includes: The cluster index values ​​corresponding to at least two cluster sets are compared to obtain the comparison results; Based on the comparison results, the adaptive behavior outcome corresponding to each individual to be identified in each cluster is determined.

3. The method according to claim 2, wherein, The step of determining the adaptive behavior outcome corresponding to each individual to be identified in each cluster based on the comparison results includes: In response to the cluster index value being a statistical value corresponding to the escape ratio, and the number of cluster sets being two, the adaptive behavior results of at least one individual to be identified in the cluster set showing a larger cluster index value in the comparison results are all taken as adaptive types. The adaptive behavior results of at least one individual in the cluster with a smaller cluster index value in the comparison results are all classified as maladaptive.

4. The method according to any one of claims 1-3, wherein, The step of clustering the at least two individuals to be identified based on at least two behavioral feature data to obtain at least two cluster sets includes: For each individual to be identified, the behavioral feature data corresponding to the individual to be identified is subjected to dimensionality reduction processing to obtain dimensionality-reduced behavioral feature data. Based on at least two behavioral feature data after dimensionality reduction, at least two cluster sets are obtained by clustering the at least two individuals to be identified.

5. The method according to claim 1, wherein, The behavioral characteristic data includes at least two of the following: number of escapes, escape ratio, average escape reaction latency, average escape speed, and average escape return time.

6. The method according to claim 1, wherein, When the individual to be identified is a rodent, the behavioral characteristic data includes a frequency of action transitions and a percentage of actions dataset. The percentage of actions dataset represents the ratio between the duration of the individual's actions and the duration of its escape. The duration of escape represents the time from the start of the threat stimulus signal to the end of the individual's escape within a single stimulus cycle. The percentage of actions dataset includes at least one of the following: percentage of flight actions, percentage of running actions, percentage of trotting actions, percentage of walking actions, percentage of left-turning actions, percentage of right-turning actions, percentage of stepping actions, percentage of climbing actions, percentage of snoring actions, percentage of grooming actions, percentage of pausing actions, percentage of freezing behavior, and percentage of jumping behavior.

7. The method according to claim 1, wherein, The repeated threat stimulus experiment is included in the continuous repeated threat stimulus experiment, and the experimental paradigm of the continuous repeated threat stimulus experiment includes: During the preparation period before the start of the continuous repetitive threat stimulus experiment, a timing device is used to perform timing operations so that the individual to be identified can adapt to the experimental chamber. During the continuous repetitive threat stimulus experiment, a timing device is used to perform timing operation for each repetitive threat stimulus experiment so that the individual to be identified can adapt to the experimental chamber. After the timing ends, in response to detecting that the individual to be identified is located in the preset stimulus area in the experimental chamber, the stimulation device is controlled to emit a threat stimulus signal. The continuous repeated threat stimulus experiment consists of 5 repeated threat stimulus experiments, the experimental period of the repeated threat stimulus experiment is 1 day, the number of threat stimulus signals emitted is greater than 1 and less than the number threshold, the time interval between two adjacent threat stimulus signals is greater than the time interval threshold, and the experimental duration of the repeated threat stimulus experiment is less than the experimental duration threshold.

8. The method according to claim 1, further comprising: When the number of clusters is two, the escape ratio threshold is determined based on the escape ratio and adaptive behavior results of at least two individuals to be identified. In response to the target individual's escape rate being greater than or equal to the escape rate threshold, the target individual's adaptive behavior outcome is set to adaptive. In response to the target individual's escape rate being less than the escape rate threshold, the target individual's adaptive behavior outcome is set to maladaptive. The target individual is a biological individual participating in the repeated threat stimulus experiment, other than the at least two individuals to be identified.

9. A device for recognizing adaptive behavior, comprising: The behavioral feature data acquisition module is configured to acquire behavioral feature data corresponding to at least two individuals to be identified; wherein, the behavioral feature data represents the statistical behavioral information exhibited by the individuals to be identified in response to repetitive threat stimulus signals in a repetitive threat stimulus experiment; The cluster set determination module is configured to cluster the at least two individuals to be identified based on at least two behavioral feature data to obtain at least two cluster sets; The adaptive behavior outcome determination module is configured to determine the adaptive behavior outcome for each individual to be identified in each cluster based on the clustering index values ​​corresponding to at least two cluster sets.

10. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the adaptive behavior recognition method according to any one of claims 1-8.

11. A computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for recognizing adaptive behavior according to any one of claims 1-8.

12. A computer program product comprising a computer program that, when executed by a processor, implements a method for recognizing adaptive behavior according to any one of claims 1-8.

Images