Method for constructing model for auxiliary determination of abnormal body posture of living body, device, and storage medium

Abstract

The present application relates to the technical field of auxiliary determination, and discloses a method for constructing a model for auxiliary determination of an abnormal body posture of a living body, a device, and a storage medium. The method comprises: performing data analysis on video data of a living body in different emotions or different disease states to obtain a plurality of time-continuous three-dimensional skeletons; performing calculation on three-dimensional information of the three-dimensional skeletons to obtain a plurality of dynamic motion parameters, and labeling the dynamic motion parameters as corresponding emotions or disease states; accordingly establishing a training set of living body behavior features; and by using the dynamic parameters as an input and the corresponding emotions or disease states as an output, using the training set of living body behavior features to train a model for auxiliary determination of an abnormal body posture of a living body to obtain a single model for auxiliary determination of an abnormal body posture of a living body corresponding to a current species. Thus, by means of said analysis process, emotions or disease states can be connected with behavior features, so that the emotions or disease states of a living body can be determined by means of analysis of abnormal body postures.

Description

Method, device and storage medium for constructing a model for assisting in judging abnormal body posture of living subjects Technical Field

[0001] The present application relates to the field of auxiliary judgment technology, and in particular to a method, device and storage medium for constructing an auxiliary judgment model for abnormal body posture of a living person. Background Art

[0002] Humans and animals can involuntarily adopt abnormal postures and body positions due to pain, fear, developmental disorders, and certain diseases. Current assessments of forced and abnormal postures in animal experiments require experienced researchers to describe the animals' responses to noxious stimuli by applying varying degrees of stimulation. This approach is highly empirical and difficult to quantify. Furthermore, objective quantitative evaluation methods are currently lacking for certain forced postures caused by specific factors, such as visceral pain, addiction withdrawal reactions, and abnormal postures due to congenital scoliosis.

[0003] Summary of the Invention

[0004] The purpose of this application is to provide a method, device and storage medium for constructing an auxiliary judgment model for abnormal body posture of a living person.

[0005] In a first aspect, an embodiment of the present application provides a method for constructing a model for assisting in determining abnormal body posture of a living person, the method comprising:

[0006] Step S1: For the same species, obtain video data of a living being in different emotions or different disease states for a first preset time period;

[0007] Step S2: performing data analysis on the video data to obtain a plurality of time-continuous three-dimensional skeletons;

[0008] Step S3: Calculating the three-dimensional information of the three-dimensional skeleton to obtain a plurality of dynamic motion parameters, and marking the dynamic motion parameters as corresponding emotions or disease states;

[0009] Step S4, repeating steps S1-S3 to obtain multiple dynamic motion parameters marked as corresponding to emotions and multiple dynamic motion parameters marked as corresponding to disease states, and using them to establish a living body behavior feature training set;

[0010] Step S5: using the kinetic parameters as input and the corresponding emotions or disease states as output, the abnormal body posture auxiliary judgment model for living beings is trained using the living being behavior feature training set to obtain a single abnormal body posture auxiliary judgment model for living beings corresponding to the current species.

[0011] Optionally, the step of performing data analysis on the video data to obtain a plurality of time-continuous three-dimensional skeletons further comprises:

[0012] Step S21: performing behavioral analysis on the video data to obtain a plurality of living three-dimensional skeletons arranged in chronological order;

[0013] Step S22 : performing posture feature extraction on the plurality of three-dimensional skeletons and performing format adjustment to obtain a plurality of three-dimensional skeletons with uniform size and orientation, wherein the plurality of three-dimensional skeletons are continuous in time.

[0014] Optionally, after the step of training the abnormal body posture auxiliary judgment model for a living body using the dynamic parameters as input and the corresponding emotion or the corresponding disease state as output to obtain a single abnormal body posture auxiliary judgment model for a living body corresponding to the current species, the method further includes:

[0015] Changing the species type of the video data collected, repeating steps S1-S5, and establishing a single living individual abnormal posture auxiliary judgment model corresponding to another species;

[0016] The single living body abnormal posture auxiliary judgment models corresponding to different species are combined to obtain a multi-living body abnormal posture auxiliary judgment model.

[0017] Optionally, after the step of using the dynamic parameters as input and the corresponding emotions or the corresponding disease states as output, and training the abnormal body posture auxiliary judgment model for the living body using the living body behavior feature training set to obtain a single abnormal body posture auxiliary judgment model for the living body corresponding to the current species, the step further includes:

[0018] Step S6, repeating steps S1-S3 to obtain a plurality of dynamic motion parameters labeled as corresponding to emotions and a plurality of dynamic motion parameters labeled as corresponding to disease states, and using these to establish a live behavior feature verification set, wherein each set of dynamic motion parameters in the live behavior feature verification set is different from each set of dynamic motion parameters in the live behavior feature training set;

[0019] Step S7: verify the trained single living body abnormal posture auxiliary judgment model based on the living body behavior feature verification set until the loss function meets a preset threshold.

[0020] Optionally, the dynamic parameters include posture, the time interval since the last appearance of the same posture in the current video data, the cumulative number of appearances of the posture, the duration of the posture, and the order and frequency of switching between different postures.

[0021] Optionally, the parameters of the posture include body length, body height, body bending degree, body shaking amplitude and body curling degree.

[0022] Optionally, the multi-living abnormal posture auxiliary judgment model includes:

[0023] A data preprocessing layer is used to obtain video data of the living body to be analyzed and obtain real-time dynamic parameters based on the video data, and to call a single living body abnormal posture auxiliary judgment model corresponding to the species of the living body to be analyzed; and

[0024] The single living body abnormal posture auxiliary judgment model;

[0025] The single living body abnormal posture auxiliary judgment model includes:

[0026] The input layer is used to obtain the species of living organisms to be analyzed and real-time dynamic parameters;

[0027] A hidden layer, configured to input the dynamic parameters into the called single living body abnormal posture auxiliary judgment model;

[0028] The output layer is used to output the corresponding emotion or disease state according to the single living body abnormal posture auxiliary judgment model.

[0029] Optionally, the emotion includes any one of fear and tension, and the disease state includes any one of mechanical pain, hot and cold pain, chemical pain, visceral pain, migraine, neuropathic pain, addiction withdrawal reaction, congenital scoliosis, and bone disease or muscle development disease.

[0030] In a second aspect, an embodiment of the present application further provides a device for constructing a model for assisting in determining abnormal body posture of a living person, comprising:

[0031] A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0032] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the method for constructing the auxiliary judgment model of abnormal body posture of a living person as described above.

[0033] In a third aspect, an embodiment of the present application further provides a storage medium storing at least one executable instruction. When the executable instruction is executed on a device / apparatus for constructing a model for auxiliary judgment of abnormal body posture of a living person, the device / apparatus for constructing a model for auxiliary judgment of abnormal body posture of a living person enables the device / apparatus for constructing a model for auxiliary judgment of abnormal body posture of a living person to perform the operation of the method for constructing a model for auxiliary judgment of abnormal body posture of a living person as described above.

[0034] This solution constructs a new way of corresponding video data to a three-dimensional skeleton, analyzes dynamic motion parameters with data characteristics based on the three-dimensional skeleton, and corresponds the dynamic motion parameters to the emotions or disease states of the living body, thereby forming a living body behavior feature training set with the dynamic parameters as input and the corresponding emotions or disease states as output, and trains a living body abnormal body posture auxiliary judgment model based on the above-mentioned living body behavior feature training set to obtain a single living body abnormal body posture auxiliary judgment model corresponding to the current species, so that the emotions or disease states can be connected with the behavioral characteristics through the above-mentioned data analysis and model training process, so as to obtain a single living body abnormal body posture auxiliary judgment model that determines the emotions or disease states of the living body through abnormal body posture analysis, thereby solving the technical problem of the lack of effective quantitative evaluation means for abnormal body postures of living bodies in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0036] FIG1 is a flow chart showing a first embodiment of a method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0037] FIG2 is a schematic diagram showing a three-dimensional skeleton reconstruction process in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0038] FIG2-a is a schematic diagram showing video data collected from multiple angles in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0039] FIG2-b is a schematic diagram showing the determination of two-dimensional spatial coordinates based on video data in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0040] FIG2-c is a schematic diagram showing two-dimensional spatial coordinates extracted in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0041] FIG2-d shows a schematic diagram of a reconstructed three-dimensional skeleton in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0042] FIG2-e shows a schematic perspective view of a three-dimensional skeleton in the method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0043] FIG2-f is a schematic diagram showing various posture transitions of a living body in the method for constructing an auxiliary judgment model for abnormal body posture of a living body provided by the present invention;

[0044] FIG3 is a flow chart showing a second embodiment of a method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0045] FIG4 is a flow chart showing a third embodiment of a method for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention;

[0046] FIG5 shows a schematic structural diagram of a living body abnormal body posture auxiliary judgment model in a method for constructing a living body abnormal body posture auxiliary judgment model provided by the present invention;

[0047] FIG6 shows a schematic structural diagram of an embodiment of a device for constructing a model for assisting in determining abnormal body posture of a living person provided by the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe 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 them. 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.

[0049] The following describes the method for determining abnormal body posture in the prior art:

[0050] Humans and animals may adopt forced or abnormal postures and postures in response to fear, pain, or certain developmental disorders. These include forced postures during withdrawal from addiction, abnormal postures due to muscular dysplasia, and pain-induced abnormal postures and postures. For example, pain is an unpleasant sensory and emotional experience that can be broadly categorized as acute or chronic pain. Acute pain is typically associated with actual or potential tissue damage and can be further categorized as mechanical pain (crush injuries), hot and cold pain (scalds), and chemical pain (chemical burns). Chronic pain, on the other hand, typically persists beyond normal healing time, is persistent pain caused by non-healing, or recurs after relief. Regardless of the type of pain, humans and animals will adopt some degree of abnormal posture or posture to alleviate pain, depending on the location, nature, and severity of the pain. Accurate and objective quantification of posture and posture characteristics is crucial for pain management following injury, illness, or surgery, particularly for nonverbal patients, including animals.

[0051] However, due to the technical limitations of video information extraction, the current analysis of animal posture is still very rough, and there is basically no mature method to quantitatively analyze abnormal animal postures.

[0052] The present application provides a method, device and storage medium for constructing a model for auxiliary determination of abnormal body posture of a living subject. By analyzing and processing image data and using the analyzed and processed data for model training, emotions or disease states can be connected with behavioral characteristics, thereby obtaining a single auxiliary model for abnormal body posture determination of a living subject that determines the emotions or disease states of a living subject through abnormal body posture analysis, thereby solving the technical problem of the lack of effective quantitative evaluation methods for abnormal body postures of living subjects in the prior art.

[0053] In one implementation scenario, this solution is implemented based on a camera component and a computer component.

[0054] The camera component is used to obtain video data, and the computer component is used to execute the method for constructing a model for auxiliary judgment of abnormal body posture of living beings.

[0055] FIG1 shows a flowchart of a first embodiment of a method for constructing a model for assisting in determining abnormal body postures of a living person according to the present invention. The method is executed by a device for constructing a model for assisting in determining abnormal body postures of a living person. As shown in FIG1 , the method includes the following steps:

[0056] The method for constructing the single living body abnormal posture auxiliary judgment model includes:

[0057] Step S1: For the same species, obtain video data of a living being in different emotions or different disease states for a first preset time period;

[0058] The above process can be achieved by using multiple high-resolution cameras to capture the spontaneous behavior of the same species from multiple angles. In this case, different living organisms have different emotions or different disease states. By changing the acquisition object, different emotions or different disease states can be captured. The duration of the video data collected can be set as needed. For example, the data collection time for a single living organism is between 15 minutes and 60 minutes. Multiple angles can be collected, as shown in the four perspectives shown in Figure 2-a.

[0059] Morphological analysis reveals that different species, when faced with different emotions or disease states, perceive subtle differences in the external environment due to differences in physiological structure. This can lead to distinct species-specific behavioral tendencies. For example, when in pain, mice tend to curl up, while humans tend to cover the painful area. These two behaviors, as well as the video data, differ significantly. Therefore, we only capture video data of the same species in different emotions or disease states to ensure data consistency.

[0060] In addition, when the species is an animal, the above steps can be carried out under the premise of complying with animal ethics to construct animal experimental models in different states, including fear, using visual, olfactory or pain stimuli that animals instinctively fear, taking mice as an example, such as vision, shadow stimulation that keeps approaching in the upper field of vision, smell: the smell of cat or fox urine, pain: electric shock to the sole of the foot; pain, limb injury: animal fracture model, visceral pain: inflammation model, through injection of pro-inflammatory factors or physical injury surgery of viscera, addiction withdrawal: giving animals a certain dose of addictive drugs, developmental bone and muscle diseases: constructing related gene-deficient animals through gene editing technology, etc. The above schemes can be used to construct experimental animals in different emotions or different disease states, and collect relevant video data from them.

[0061] When the species is human, with the consent of the subject, the different emotions or disease states of the subject can be defined by collecting personal statements and doctor-assisted judgments, and relevant video data can be collected.

[0062] Optionally, the emotion includes any one of fear and tension, and the disease state includes any one of mechanical pain, hot and cold pain, chemical pain, visceral pain, migraine, neuropathic pain, addiction withdrawal reaction, congenital scoliosis, and bone disease or muscle development disease.

[0063] Step S2: performing data analysis on the video data to obtain a plurality of time-continuous three-dimensional skeletons;

[0064] Because living things are typically in continuous motion within a video, their 3D skeletons also change over time. This means that each frame of an image yields a single 3D skeleton. After analyzing a video, the resulting 3D skeletons are sequentially linked.

[0065] Furthermore, referring to FIG3 , the step of performing data analysis on the video data to obtain a plurality of time-continuous three-dimensional skeletons further includes:

[0066] Step S21: performing behavioral analysis on the video data to obtain a plurality of living three-dimensional skeletons arranged in chronological order;

[0067] In the above process, multiple key body parts of the animal can be automatically tracked through fine behavioral analysis programs such as BehaviorAtlas (a new intelligent animal behavior precision analysis system), Moseq (action sequencing algorithm / behavioral analysis algorithm that can recognize three-dimensional mouse body language (called "syllables")), LEAP (behavioral analysis model), Deeplabcut (posture learning tool for posture estimation and motion analysis), EthoVision (animal motion trajectory tracking system) and other animal body multi-site tracking methods. The specific process of the above fine behavioral analysis program is as follows: Referring to Figure 2-b, first, based on the position information calibrated by the camera, the two-dimensional spatial coordinate information of the key parts of the animal's body is calculated. Referring to Figure 2-c and Figure 2-d, the spatial coordinate information of the key parts of the body of multiple images is then integrated to calculate the coordinate information of the key points in three-dimensional space and reconstruct the three-dimensional skeleton of the animal.

[0068] Step S22 : performing posture feature extraction on the plurality of three-dimensional skeletons and performing format adjustment to obtain a plurality of three-dimensional skeletons with uniform size and orientation, wherein the plurality of three-dimensional skeletons are continuous in time.

[0069] Among them, the process of posture feature extraction is to extract the information of the reconstructed three-dimensional skeleton of each frame, such as extracting the three-dimensional spatial coordinates of the 16 body key points of the animal in each frame. More body key points can also be set, and the three-dimensional skeleton of the animal is aligned with the back point as the center; the three-dimensional skeleton spatial coordinate information is rotated to unify the three-dimensional skeleton orientation; according to the size ratio of the animal in the real three-dimensional space, the skeleton is scaled, and the mouse skeleton is scaled to the same scale size, thereby obtaining the three-dimensional stereo image shown in Figure 2-e.

[0070] Step S3: Calculate the three-dimensional information of the three-dimensional skeleton to obtain a plurality of dynamic motion parameters, and mark the dynamic motion parameters as corresponding emotions or disease states.

[0071] The calculation of the 3D skeleton's 3D information to obtain multiple dynamic motion parameters applies to each frame of the reconstructed 3D skeleton. Therefore, the labeling of corresponding emotions or disease states also applies to each frame of the video image. The labeling process is performed frame by frame by the experimenter or user based on the acquired process of constructing experimental animals in different emotions or disease states, or based on the collected individual's self-report and doctor-assisted judgment, and the labels are associated with dynamic motion parameters.

[0072] Optionally, the dynamic parameters include posture, the time interval since the last appearance of the same posture in the current video data, the cumulative number of appearances of the posture, the duration of the posture, and the order and frequency of switching between different postures.

[0073] Here, gestures also refer to actions. When counting, the number of occurrences of action A is 0 / 1, meaning each occurrence count is incremented, regardless of duration. After the action ends, the next action, action B, appears. However, the next occurrence of action A increases the cumulative number of occurrences by 1. The previous statistics require a fixed observation time window, such as an hour between 8:00 AM and 12:00 AM.

[0074] Optionally, the parameters of the posture include body length, body height, body bending degree, body shaking amplitude and body curling degree.

[0075] As shown in Figure 2-f, the postures include running, walking, rising, right turning, hunching, climbing up, grooming, jumping, rearing, pausing, sniffing, left turning, and stepping.

[0076] Among the various parameters of the above posture, the specific posture is defined as:

[0077] Body length: The straight-line distance from the nose to the tail of a mouse in three-dimensional space.

[0078] Body height: the height of the mouse's nose, neck, and back from the ground.

[0079] Body curvature: Calculate the angles formed by the three points: nose, neck, and back, and neck, back, and tail base. The smaller the angle, the greater the curvature of the mouse's body.

[0080] Body vibration amplitude: The mouse's back point is fixed in the same position, and the displacement of the rest of the mouse's body in three-dimensional space is calculated. This is then used to calculate the number and frequency of movement cycles.

[0081] Degree of body curling: Calculate the distance from each body part to the body center of gravity.

[0082] The time and number of times the last posture appeared, the duration of the posture, and the frequency of switching between different postures.

[0083] Step S4, repeating steps S1-S3 to obtain multiple dynamic motion parameters marked as corresponding to emotions and multiple dynamic motion parameters marked as corresponding to disease states, and using them to establish a living body behavior feature training set;

[0084] Step S5: using the kinetic parameters as input and the corresponding emotions or disease states as output, the abnormal body posture auxiliary judgment model for living beings is trained using the living being behavior feature training set to obtain a single abnormal body posture auxiliary judgment model for living beings corresponding to the current species.

[0085] In the above scheme, by constructing a new way of corresponding video data to three-dimensional skeleton, dynamic motion parameters with data characteristics are analyzed based on the three-dimensional skeleton, and the dynamic motion parameters are corresponded to the emotions or disease states of the living body, thereby forming a living body behavior feature training set with the dynamic parameters as input and the corresponding emotions or the disease states as output, and the living body abnormal posture auxiliary judgment model is trained based on the above living body behavior feature training set to obtain a single living body abnormal posture auxiliary judgment model corresponding to the current species, so that the emotions or disease states can be connected with the behavioral characteristics through the above data analysis and model training process, so as to obtain a single living body abnormal posture auxiliary judgment model that determines the emotions or disease states of the living body through abnormal posture analysis, thereby solving the technical problem of the lack of effective quantitative evaluation means for the abnormal postures of living bodies in the existing technology.

[0086] Based on the above scheme, the above-mentioned single living abnormal posture auxiliary judgment model is not only used in scientific research and drug development, nor is it only used for mouse experimental animals. Any animal protection scene that can use video recording, including: hospitals, pet hospitals, zoos, wildlife protection, etc., can use the algorithm of the present invention to monitor the health status of animals or humans.

[0087] It can be used to help identify the approximate range of potential abnormal emotions or disease states in animals, providing a data foundation for doctors and experimenters to more quickly judge the state of humans or animals. This includes different pain templates such as mechanical pain, hot and cold pain, chemical pain, visceral pain, migraine, and neuropathic pain, as well as spontaneous abnormal postures in animal models of addiction withdrawal reactions, congenital scoliosis, and some skeletal or muscular developmental diseases.

[0088] It is also possible to identify an animal's emotional or medical condition simply by observing its spontaneous behavioral and postural characteristics, without the need for external stimuli. This allows for observing the abnormal postures exhibited by animals in their natural state when experiencing specific emotions and illnesses, without external stimuli causing emotional changes. This allows for a more realistic and spontaneous reflection of the animal's experiences of fear, addiction withdrawal, pain, and other such conditions. By digitizing the various postural characteristics of an animal, this allows for a more precise description of these characteristics, providing quantifiable comparative indicators for assessing levels of fear, pain, and the distress of addiction withdrawal.

[0089] In an optional embodiment, after the step of training the abnormal body posture auxiliary judgment model for a living body using the dynamic parameters as input and the corresponding emotion or the corresponding disease state as output to obtain a single abnormal body posture auxiliary judgment model for a living body corresponding to the current species, the method further includes:

[0090] Changing the species type of the video data collected, repeating steps S1-S5, and establishing a single living individual abnormal posture auxiliary judgment model corresponding to another species;

[0091] The single living body abnormal posture auxiliary judgment models corresponding to different species are combined to obtain a multi-living body abnormal posture auxiliary judgment model.

[0092] Through the above scheme, a corresponding single-body abnormal posture auxiliary judgment model can be trained for each species, so that detailed behavioral analysis can be performed for each species. This is to further extract posture features from the unsupervised clustering discrimination action, which can not only provide dynamic posture dynamics data, but also more objectively divide the action more meaningfully based on posture features, and realize objective and digital quantitative analysis indicators for each species. As a result, not only the pain state of each species, bone and muscle development diseases, but also any disease state that exhibits abnormal spontaneous behavioral characteristics can be extracted and calculated through the scheme constructed by this application. Moreover, by training a single-body abnormal posture auxiliary judgment model for each species for supervision, such as cats, dogs, pigs, cattle, sheep, monkeys, other wild animals and humans, and thus by constructing a single-body abnormal posture auxiliary judgment model corresponding to the disease model of each species, it has important reference value for many fields such as basic scientific research, drug development, and animal health status detection.

[0093] In an optional embodiment, referring to FIG4 , after the step of using the dynamic parameters as input and the corresponding emotions or the corresponding disease states as output, and training the abnormal body posture auxiliary judgment model for the living body using the living body behavior feature training set to obtain a single abnormal body posture auxiliary judgment model for the current species, the step further includes:

[0094] Step S6, repeating steps S1-S3 to obtain a plurality of dynamic motion parameters labeled as corresponding to emotions and a plurality of dynamic motion parameters labeled as corresponding to disease states, and using these to establish a live behavior feature verification set, wherein each set of dynamic motion parameters in the live behavior feature verification set is different from each set of dynamic motion parameters in the live behavior feature training set;

[0095] Each set of dynamic motion parameters of the living body behavior feature verification set and the living body behavior feature training set are different. By replacing the collected living objects, the living bodies collected in the living body behavior feature verification set and the living body behavior feature training set can be different, thereby achieving the purpose of different dynamic motion parameters.

[0096] Step S7: verify the trained single living body abnormal posture auxiliary judgment model based on the living body behavior feature verification set until the loss function meets a preset threshold.

[0097] Through the above solution, the verification of the single living body abnormal posture auxiliary judgment model can be achieved, ensuring the accuracy of the auxiliary judgment of the single living body abnormal posture auxiliary judgment model in subsequent use.

[0098] Optionally, the multi-living abnormal posture auxiliary judgment model includes:

[0099] A data preprocessing layer is used to obtain video data of the living body to be analyzed and obtain real-time dynamic parameters based on the video data, and to call a single living body abnormal posture auxiliary judgment model corresponding to the species of the living body to be analyzed; and

[0100] The single living body abnormal posture auxiliary judgment model;

[0101] As shown in FIG5 , the single living person abnormal posture auxiliary judgment model includes:

[0102] The input layer is used to obtain the species of living organisms to be analyzed and real-time dynamic parameters;

[0103] A hidden layer, configured to input the dynamic parameters into the called single living body abnormal posture auxiliary judgment model;

[0104] The output layer is used to output the corresponding emotion or disease state according to the single living body abnormal posture auxiliary judgment model.

[0105] The steps of acquiring video data of the living subject to be analyzed and obtaining real-time kinetic parameters based on the video data are implemented with reference to steps S1-S3. The single living subject abnormal body position auxiliary judgment model corresponding to the species of the living subject to be analyzed is called based on the species of the living subject to be analyzed. The single living subject abnormal body position auxiliary judgment model called is constructed in the construction method and verified using the living subject behavior feature verification set.

[0106] In the above embodiment, as shown in reference figure 5, the input layer has two dimensions, x_axis and y_axis respectively, the hidden layer has 50 dimensions, and the output layer is a 1*4 matrix, thereby constructing a one-to-one corresponding fully connected neural network model with input as dynamic parameters and output as emotions or disease states, thereby providing an effective auxiliary judgment model for further analyzing the precise high-dimensional correspondence between animal states and abnormal behavioral phenotypes and postures. It should be noted that at this time, the matrices of the input layer and the output layer can be transformed as needed, and the number of layers and dimensions of the hidden layer can also be transformed according to the actual number of action combinations, so as to obtain a single living body behavioral logic abnormality auxiliary judgment model suitable for each species.

[0107] FIG6 is a schematic structural diagram of an embodiment of a device for constructing a model for assisting in determining abnormal body posture of a living person according to the present invention. The specific embodiment of the present invention does not limit the specific implementation of the device for constructing a model for assisting in determining abnormal body posture of a living person.

[0108] As shown in FIG6 , the device for constructing the abnormal body posture auxiliary judgment model for a living body may include: a processor 402 , a communications interface 404 , a memory 406 , and a communication bus 408 .

[0109] Processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other devices, such as client devices or other server network elements. Processor 402 is used to execute program 410, which may specifically perform the steps described in the aforementioned embodiment of the method for constructing a model for assisting in determining abnormal body posture in a living person.

[0110] Specifically, the program 410 may include program code including computer-executable instructions.

[0111] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the apparatus for constructing a model for assisting in determining abnormal body posture in a living person may be of the same type, such as one or more CPUs, or may be of different types, such as one or more CPUs and one or more ASICs.

[0112] The memory 406 is used to store the program 410. The memory 406 may be a high-speed RAM memory, or may also include a non-volatile memory, such as at least one disk memory.

[0113] The program 410 can be specifically called by the processor 402 to enable the device for constructing a model for auxiliary determination of abnormal body posture of a living person to perform the operations of the method for constructing a model for auxiliary determination of abnormal body posture of a living person as described above.

[0114] It should be noted that, since the device for constructing a model for assisting in determining abnormal body postures of living persons of the present application can implement all embodiments of the method for constructing a model for assisting in determining abnormal body postures of living persons, the device for constructing a model for assisting in determining abnormal body postures of living persons of the present application has all the beneficial effects of the method for constructing a model for assisting in determining abnormal body postures of living persons, and will not be repeated here.

[0115] An embodiment of the present invention provides a storage medium storing at least one executable instruction. When the executable instruction is executed on a device / apparatus for constructing a model for auxiliary determination of abnormal body posture of a living body, the device / apparatus for constructing a model for auxiliary determination of abnormal body posture of a single living body executes the method for constructing a model for auxiliary determination of abnormal body posture of a living body in any of the above-mentioned method embodiments.

[0116] It should be noted that, since the storage medium of the present application can implement all embodiments of the method for constructing a model for auxiliary determination of abnormal body posture of a living person, the storage medium of the present application has all the beneficial effects of the method for constructing a model for auxiliary determination of abnormal body posture of a living person, and will not be repeated here.

[0117] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system or other device. In addition, the embodiments of the present invention are not directed to any particular programming language.

[0118] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present invention may be practiced without these specific details. Similarly, in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. The claims that follow the detailed description are hereby expressly incorporated into that detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0119] Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively changed and installed in one or more devices different from the embodiments. The modules, units, or components in the embodiments can be combined into one module, unit, or component, and furthermore, they can be divided into multiple submodules, subunits, or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0120] It should be noted that the above embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by a person skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments should not be understood as limiting the order of execution unless otherwise specified.

Claims

1. A method for constructing an auxiliary judgment model for abnormal body positions of living bodies, characterized in that, The method includes: Step S1: For the same species, obtain video data of a living body in different emotional states or different disease states for a first preset duration; Step S2: Perform data analysis on the video data to obtain a plurality of temporally continuous three-dimensional skeletons; Step S3: Calculate the three-dimensional information of the three-dimensional skeletons to obtain a plurality of kinetic motion parameters, and label the kinetic motion parameters with the corresponding emotional states or disease states; Step S4: Repeat steps S1 - S3 to obtain a plurality of kinetic motion parameters labeled with the corresponding emotions and a plurality of kinetic motion parameters labeled with the corresponding disease states, and establish a training set of living body behavior characteristics based on this; Step S5: Use the kinetic parameters as input and the corresponding emotional state or disease state as output, and train an auxiliary judgment model for abnormal body positions of a living body through the training set of living body behavior characteristics to obtain an auxiliary judgment model for abnormal body positions of a single living body corresponding to the current species.

2. The method for constructing an abnormal body position assistance judgment model for a living body according to claim 1, wherein The step of performing data analysis on the video data to obtain a plurality of temporally continuous three-dimensional skeletons further includes: Step S21: Perform ethological analysis on the video data to obtain a plurality of three-dimensional skeletons of the living body arranged in chronological order; Step S22: Extract the pose features of the plurality of three-dimensional skeletons and adjust the format to obtain a plurality of three-dimensional skeletons with unified size and orientation, and the plurality of three-dimensional skeletons are temporally continuous.

3. The method for constructing a living body abnormal body position auxiliary judgment model according to claim 1 or 2, characterized in that, After the step of using the kinetic parameters as input and the corresponding emotional state or corresponding disease state as output, and training an auxiliary judgment model for abnormal body positions of a living body through the training set of living body behavior characteristics to obtain an auxiliary judgment model for abnormal body positions of a single living body corresponding to the current species, it further includes: Change the species type for collecting the video data, repeat steps S1 - S5, and establish an auxiliary judgment model for abnormal body positions of a single living body corresponding to another species; Combine the auxiliary judgment models for abnormal body positions of a single living body corresponding to different species to obtain an auxiliary judgment model for abnormal body positions of multiple living bodies.

4. The method for constructing an in-vivo abnormal body position auxiliary judgment model according to claim 1 or 2, characterized in that, After the step of using the kinetic parameters as input and the corresponding emotional state or corresponding disease state as output, and training an auxiliary judgment model for abnormal body positions of a living body through the training set of living body behavior characteristics to obtain an auxiliary judgment model for abnormal body positions of a single living body corresponding to the current species, it further includes: Step S6: Repeat steps S1 - S3 to obtain a plurality of kinetic motion parameters labeled with the corresponding emotions and a plurality of kinetic motion parameters labeled with the corresponding disease states, and establish a verification set of living body behavior characteristics based on this. Each set of kinetic motion parameters in the verification set of living body behavior characteristics is different from that in the training set of living body behavior characteristics; Step S7: Verify the trained auxiliary judgment model for abnormal body positions of a single living body according to the verification set of living body behavior characteristics until the loss function meets a preset threshold.

5. The method for constructing an in-vivo abnormal body position auxiliary judgment model according to claim 1, wherein, The kinetic parameters include pose, the time interval between the last occurrence of the same pose in the current video data, the cumulative occurrence times of the pose, the duration of the pose, the order and frequency of switching between different poses.

6. The method for constructing an in-vivo abnormal body position auxiliary judgment model according to claim 5, wherein The parameters of the posture include body length, body height, body bending degree, body jitter amplitude, and body curling degree.

7. The method for constructing an in-vivo abnormal body position auxiliary judgment model according to claim 2, wherein The multi-living body abnormal posture auxiliary judgment model includes: A data preprocessing layer, configured to obtain video data of a living body to be analyzed, obtain real-time kinetic parameters according to the video data, and call the single-living body abnormal posture auxiliary judgment model corresponding to the species according to the species of the living body to be analyzed; and The single-living body abnormal posture auxiliary judgment model; The single-living body abnormal posture auxiliary judgment model includes: An input layer, configured to obtain the species of the living body to be analyzed and real-time kinetic parameters; A hidden layer, configured to input the kinetic parameters into the called single-living body abnormal posture auxiliary judgment model; An output layer, configured to output corresponding emotions or disease states according to the single-living body abnormal posture auxiliary judgment model.

8. The method for constructing an in-vivo abnormal body position auxiliary judgment model according to claim 2, wherein The emotions include any one of fear and tension, and the disease states include any one of mechanical pain, cold and heat pain, chemical pain, visceral pain, migraine, neuralgia, addiction withdrawal reaction, congenital scoliosis, and bone disease or muscle development disease.

9. An apparatus for constructing an auxiliary judgment model for abnormal body positions of a living body, characterized in that, It includes: A processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations of the method for constructing the abnormal posture auxiliary judgment model of a living body according to any one of claims 1-6.

10. A storage medium, characterized in that, At least one executable instruction is stored in the storage medium. When the executable instruction runs on the device for constructing the abnormal posture auxiliary judgment model of a living body, the device for constructing the abnormal posture auxiliary judgment model of a living body executes the operations of the method for constructing the abnormal posture auxiliary judgment model of a living body according to any one of claims 1-6.

Images