Methods and user body data analysis systems for analysing user body data

Abstract

A method performed by a user body data analysis system, the method comprises obtaining (200), by the headset (110), movement related information for a user (190); representing (202), by the headset (110), the movement related information to the user (190) so the user (190) can follow; collecting (204) user body data, by at least a subset of the at least one sensor (130, 140, 150); determining (205), by the headset (110), updated movement related information for the user (190) based on the collected (204) user body data; representing (206), by the headset (110), the updated movement related information to the user (190); transmitting (208), by the headset (110), the collected user body data to the network entity (160); analysing (210), by the network entity (160), the user body data based on a Machine Learning, ML model (170).

Description

METHODS AND USER BODY DATA ANALYSIS SYSTEMS FOR ANALYSING USER BODY DATATECHNICAL FIELD

[0001] The present disclosure relates generally to methods and user body data analysis systems for analysing user body data.BACKGROUND

[0002] In rehabilitation area, a patient might suffer from dizziness, whiplash injury, bad balance, sensitivity for light or sound, brain fatigue, difficulties concentrating or exhaustion.

[0003] In order to obtain accurate body data of the patient, certain device measures patient movements of the patient and gathers user body / movement information from multiple sources, combines the information and provides the healthcare provider with unparalleled information regarding the status / condition of the patient. The information is analyzed and processed and then presented to both the practitioner and the patient.

[0004] Existing technical solutions are often analogue tools for examining a patient. For example, the medical practitioner stands in front of the patient with a bucket on his head with a straight diametric line inside, moving it in various directions until the patient says the line is truly vertical. The medical practitioner measures, how much the angle differs from vertical in order to assess the patient’s condition.

[0005] There are also some technologies using measuring devices to measure specific patient data, e.g., a position of the patient, a single motion of the patient, an acceleration of a movement of the patient, etc. For example, several cameras can be used to measure movement of the patient. The cameras are positioned in different spots in the room where the patient is situated. Another example is a diagnostic tool used in ophthalmology, otolaryngology and audiovestibular medicine for the medical evaluation of involuntary eye movement (nystagmus).There are also more expensive devices like pupillometers which are used to obtain the situation of the patient.

[0006] A problem with the existing technology is that the medical practitioner may need to do a lot of examinations using different measuring devices and gather data from all the different sources, sometimes manually. Normally the different kinds of equipment are not situated in the same room, nor the competence to evaluate the data or perform the measurements. It is also difficult to instruct the patient to do another or alternative movement for further evaluations, since no instant feedback from all the measuring devices is possible and no data is objectively collected. Furthermore, the medical practitioner must rely on intuition and experience when giving patient instruction, and decision making of diagnoses is often slow.

[0007] When the measuring devices, e.g., pupillometers are used, the cost is high. Furthermore, such measuring device does not have competence to make a diagnosis. A medical practitioner is still needed.

[0008] Another problem is that the patient user body data cannot be collected at a distance, i.e. , the patient has to visit a specific location to collect the body data and meet the medical practitioner.

[0009] Therefore, there is a need for a system which can collect different types of patient body data in a high-efficient way and can analyze the patient body data automatically. Furthermore, the patient does not need to leave their home and visit the medical practitioner.SUMMARY

[0010] It is an object of the invention to address at least some of the problems and issues outlined above. It is an object of embodiments of the invention to collect different types of patient body data in a high-efficient way and analyze the patient body data automatically. It is another object of embodiments of the invention to provide an online solution to the patient. It is possible to achieve oneor more of these objects and possibly others by using methods and user body data analysis systems as defined in the attached independent claims.

[0011] According to an embodiment, a method performed by a user body data analysis system for analysing user body data is disclosed. The user body data analysis system comprises a user headset and a network entity, the user headset and the network entity are communicatively connected, the user headset comprises at least one sensor, the method comprises: obtaining, by the headset , movement related information for a user; representing, by the headset, the movement related information to the user so the user can follow; collecting user body data, by at least a subset of the at least one sensor; representing, by the headset, updated movement related information to the user based on the collected user body data; transmitting, by the headset, the collected user body data to the network entity; analysing, by the network entity, the user body data based on a Machine Learning, ML model.

[0012] According to another embodiment, a user body data analysis system for analysing user body data is disclosed. The user body data analysis system comprises a user headset and a network entity, the user headset and the network entity are communicatively connected, the user headset comprises at least one sensor, the headset comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the network entity comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the user body data analysis system is operative for: obtaining, by the headset, movement related information for a user; representing, by the headset, the movement related information to the user so the user can follow; collecting user body data, by at least a subset of the at least one sensor; representing, by the headset , updated movement related information to the user based on the collected user body data; transmitting, by the headset, the collected user body data to the network entity; analysing, by the network entity , the user body data based on a Machine Learning, ML model.

[0013] Further possible features and benefits of this solution will become apparent from the detailed description below.BRIEF DESCRIPTION OF DRAWINGS

[0014] The solution will now be described in more detail by means of exemplary embodiments and with reference to the accompanying drawings, in which:

[0015] Fig. 1 is a schematic block diagram of a user body data analysis system, according to possible embodiments.

[0016] Fig. 2 is a flow chart illustrating a method performed by the user body data analysis system, according to possible embodiments.DETAILED DESCRIPTION

[0017] Fig. 1 shows a user body data analysis system according to an embodiment. A user body data analysis system 100 is provided in this invention. The user body data analysis system 100 comprises at least a user headset 110 and a network entity 160, the user headset 110 and the network entity 160 are communicatively connected. The user headset 110 comprises at least one sensor 130, 140 and 150.

[0018] When the user 190 experiences impaired balance, dizziness, sensitivity to light and sound, brain fatigue, difficulty concentrating or exhaustion, a thorough examination and assessment of all sensory organs is important as part of the clinical examination to make the correct diagnosis and prescribe appropriate rehabilitation for the individual.

[0019] By wearing the headset 110, the user 190 is presented with easy-to- follow instructions for each exercise and screening test (e.g. range of motion, joint position error, cervical movements sense test, subjective visual vertical test, postural sway, smooth pursuit, gaze stability, eye and head coordination, follow the figure, catching the disc, balance exercises and memory), valuable sensor motoric data is collected, analyzed and presented for a medical practitioner.

[0020] To be specific, a basic idea of this invention is that the user headset 110 instructs the patient, i.e. , the user 190 to perform training / movement according to its instruction. When the user 190 performs the training / movement, at least one part of the sensors 130, 140, 150 collects user body data. Based on the collecteduser body data, the user headset 110 can update its instruction and represent the updated instruction to the user 190. The headset 110 can also analyze the collected user body data and represent the analysis result to the user 190. Meanwhile, the user headset 110 transmits the collected user body data to a network entity 160. The network entity 160 comprises a Machine Leaning (ML) model 160, so that the ML model 160 analyses the collected user body data, e.g., performing disease diagnosis, determine treatment, determining training for the user 190, etc.

[0021] The network entity 160 may be a network side device of any kind of wireless communication network. Example of such wireless communication networks are Global System for Mobile communication (GSM), Enhanced Data Rates for GSM Evolution (EDGE), Universal Mobile Telecommunications System (UMTS), Code Division Multiple Access 2000 (CDMA 2000), Long Term Evolution (LTE) Frequency Division Duplex (FDD) and Time Division Duplex (TDD), LTE Advanced, Wireless Local Area Networks (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), WiMAX Advanced, as well as 5G wireless communication networks based on technology such as New Radio (NR), or even 6G. The network entity 160 may also be a network side device of any kind of wired communication network. Therefore, the communication between the network entity 160 and the user headset 110 can be utilize any one of the communication networks discussed above.

[0022] Fig. 2, in conjunction with fig. 1 , describes a method performed by a user body data analysis system 100 for analysing user body data. The user body data analysis system 100 comprises a user headset 110 and a network entity 160, the user headset 110 and the network entity 160 are communicatively connected, the user headset 110 comprises at least one sensor 130, 140, 150, the method comprises: obtaining 200 , by the headset 110, movement related information for a user 190; representing 202, by the headset 110, the movement related information to the user 190 so the user 190 can follow; collecting 204 user body data, by at least a subset of the at least one sensor 130, 140, 150; representing 206, by the headset 110, updated movement related information to the user 190 based on thecollected 204 user body data; transmitting 208, by the headset 110, the collected user body data to the network entity 160; analysing 210, by the network entity 160, the user body data based on a Machine Learning, ML model 170.

[0023] The user headset 110 comprises software or application, so that the method is performed when the headset 110 software or application is running on the headset 110 hardware.

[0024] In the step 200, the headset 110 obtains movement related information for the user 190. The movement related information can comprise e.g., training instruction to the user 190, diagnose related instruction to the user 190, or other information related to the movement of the user body. The headset 110 can obtain the movement related information from the network entity 160, or generate the movement related information by itself. This will be discussed further in the text below.

[0025] In the step 202, the headset 110 represents the movement related information to the user 190, so that the user 190 can follow. The representation by the headset 110 can be visual or audible or both, i.e. , representing the movement related information on a screen of the headset 110, or voice play the movement related information so that the user 190 can hear, or both. Other way of representing is also possible. For example, the represented movement related information can be a text shown on the screen, or an audio being played, or both, instructing the user 190 ’’turn your head to your left side”. The user 190 follows the movement related information.

[0026] In the step 204, the headset 110 collects the user body data by at least a subset of the sensors 130, 140, 150, when the user 190 performs the movement according to the represented movement related information. The sensors 130, 140, 150 can be different types of cameras, sense vibration controllers, eye tracking cameras and sensors, face tracking cameras and sensors, inertial measurement unit (IMU), accelerometer, gyroscope, magnetometer, altimeter, etc., as long as these sensors detect and collect user movement related to the head, e.g., position, rotation, orientation, velocity, eye movement, visioninformation, etc. The headset 110 can also process the data format for the collected user body data, so that the user body data is adapted for subsequent processing. For example, the headset 110 can align the formats of the user body data from difference sources.

[0027] In the step 205, based on the collected user body data, the headset 110 determines updated movement related information. The updated movement related information can be updated movement instruction to the user 190, or analysis result of the collected user body data, etc. For example, the headset 110 makes an initial analysis of the collected user body data. For another example, when the collected user body data shows that the user 190 has already turned his / her head to the left, the headset 110 determines that the updated movement related information can be “turn your head to your right side”, which is an updated movement instruction. The headset 110 can also determine that new exercises and / or exercises with different difficulty levels. In another example, when it is determined based on the collected user body data that the user 190 difficulty in turning his / her head, the headset 110 determines that the updated movement related information can be “gaze your eyes to your left side”.

[0028] In the step 206, the updated movement related information is represented to the user 190, so that the user 190 can follow or be aware of. For an example, the headset 110 directly represents the result of the initial analysis, i.e., represents to the user 190: “It seems you have difficulty in turning your head”. For another example, the updated movement related information “turn your head to your right side” or “gaze your eyes to your left side” is represented by the headset 110 to the user 190. For another example, the represented updated movement related information can be information of new exercises and / or exercises with different difficulty levels.

[0029] In the step 208, the headset 110 sends the collected user body data to the network entity 160. The headset 110 can send all the collected user body data, or part of the collected user body data. When the communication between the headset 110 and the network entity 160 is temporarily disabled, the headset 110can save the collected user body data, then transmits the saved user body data to the network entity 160 when the communication is recovered.

[0030] In the step 210, the network entity 160 analyses the user body data based on a ML model 170. The analysis can be making diagnosis, determining movement related information, determining treatment, etc. Furthermore, the analysis result of the network entity 160 can also be gamified information about skins, result, rating, scoring based on the collected user body data.

[0031] By such an embodiment, the system collects different types of patient body data in a high-efficient way and analyses the patient body data automatically. The system provides a solution for medical supporting without medical practitioners by utilizing an online ML model. It also enables patients perform physical therapy on a distance and in a digital way.

[0032] According to another embodiment, the method further comprises: representing 212, by the network entity 160, the analysis 210 result and / or collected user body data to a supervisor 300.

[0033] In this embodiment, a medical practitioner, i.e. , the supervisor 300 is involved. The network entity 160 represents the analysis result and / or the collected user body data, i.e., “raw” user body data, to the supervisor 300. The supervisor 300 can review the analysis result made by the network entity 160, or check the user body data if necessary. Therefore, the system also provides possibility to involve a supervisor 300, so as to provide professional decision.When using the embodiment, containing all necessary measuring techniques, the supervisor 300 can base his / her decisions on facts, using the data from the different sources. The medical decisions are objective and high-efficient. The supervisor 300 could get all information in real time or follow it up later.

[0034] According to another embodiment, the method further comprises: transmitting 214, by the network entity 160, the analysis 210 result and / or information from the supervisor 300 to the headset 110, wherein the updatedmovement related information is further determined 205 based on the analysis 210 result and / or the information from the supervisor 300.

[0035] By such an embodiment, the analysis result of the network entity 160 and / or information from the supervisor 300 can be used to update the movement related information. For example, the analysis result from the network entity 160 can give recommendation to next step movement for the user 190. Furthermore, the supervisor 300 can give real-time instruction to the user 190 based on current user body data and / or analysis result from the network entity 160. Furthermore, when the analysis result of the network entity 160 is gamified information, the gamified information is transmitted to headset 110 for representing to the user 190. The updated movement related information determined is further based on the transmitted analysis result from the network entity 160 and / or the information supervisor, so that the exercise is more attractive to the user 190 if the updated movement related information is e.g., based on the gamified information.

[0036] According to another embodiment, the user body data analysis system 100 further comprises a handheld controller 180, the handheld controller 180 and the headset 110 are communicatively connected.

[0037] By this embodiment, the user 190 can interact with the headset 110 by using a handheld controller 180. The user 190 can e.g., change settings of the headset 110, send instructions to the headset 110 by the handheld controller 180.

[0038] According to another embodiment, the handheld controller 180 comprises at least one sensor 182, 184, the method further comprises: collecting 216 user body data, by at least a subset of the at least one sensor 182, 184 on the handheld controller 180; transmitting 218, by the handheld controller 180, the collected user body data to the headset 110, wherein the determination 205 of the updated movement related information for the user 190 is further based on the transmitted 218 user body data from the headheld controller 180.

[0039] By this embodiment, the handheld controller 180 also comprises at least one sensor 182, 184. The type of the sensors 182, 184 can be similar to thesensors 130, 140, 150, and the sensors 182, 184 are operative for detect and collect user body data on the hand of the user 190. Therefore, the user body data relates to hand movement is also transmitted to the headset 110. Similar to the user body data collected by the headset 110 sensor 130, 140, 150, the headset 110 can determine the updated movement related information for the user 190 based on the user body data collected by the sensor 182, 184 of the handheld controller 180, and can further transmit the user body data collected by the sensor 182, 184 on the handheld controller 180 to the network entity 160 for further analyzing.

[0040] According to another embodiment, the user body data analysis system 100 further comprises at least one sensor 194, 196 arranged on body of the user 190, the at least one sensor 194, 196 arranged on the body of the user 190 being communicatively connected to the headset 110, the method further comprises: collecting 220 user body data, by at least a subset of the at least one sensor 192, 194 arranged on body of the user 190; transmitting 222, by the at least a subset of the at least one sensor 192, 194 arranged on body of the user 190, the collected user body data to the headset 110, wherein the determination 205 of the updated movement related information for the user 190 is further based on the transmitted 222 user body data by the at least subset of the at least one sensor 192, 194 arranged on body of the user 190.

[0041] In this embodiment, the system 100 further comprises at least one sensor 192, 194 arranged on other parts of the user body, e.g., legs, knees, waist, etc. The type of the sensors 192, 194 can be similar to the sensors 130, 140, 150, and the sensors 192, 194 are operative for detect and collect user body data on corresponding position of the user body. The user body data collected by at least a subset of the sensors 192, 194 is also transmitted to the headset 110. The headset 110 can determine the updated movement related information for the user 190 based on the transmitted user body data collected by the sensor 192, 194 arranged on user body. The user body data collected by the sensor 192, 194 arranged on user body can be transmitted by the headset 110 to the network entity 160 for further analyzing.

[0042] According to another embodiment, the obtaining 200 of the movement related information for the user 190 comprises receiving the movement related information from the network entity 160 and / or generating the movement related information.

[0043] In this embodiment, the headset 110 can receive the movement related information from the network entity 160. For example, the network entity 160 suggests: let the user move his / her head to the left side. The headset 110 receives this movement related information and represents the movement related information accordingly. The network entity 160 can also generates its own movement related information: let the user nod. The generation of the movement related information can also be based on the movement related information sent from the network entity 160, i.e. , the network entity 160 sends suggestion of the movement related information to the headset 110, and the headset 110 generates its own movement related information based on the suggestion.

[0044] According to another embodiment, the method further comprises: selecting 222, by the headset 110, the at least a subset of the at least one sensor 130, 140, 150 prior to collecting 204, based on injury, harm, disease, symptom and / or the movement related information.

[0045] In this embodiment, the headset 110 selects proper sensor 130 for collecting user body data based on injury, harm, disease, symptom of the user 190, and / or the movement related information. In short, the headset 110 selects the most applicable sensors for in-depth analysis and precise calculations according to user situation. For example, the user 190 has injury on neck, so only one sensor 130 which relates to neck movement is selected by the headset 110 to collect user body data. For another example, the movement related information instructs the user 190 to gaze at different places, so that an eye tracking sensor 140 is selected to collect user body data.

[0046] According to another embodiment, the analysing 210 comprises analysing success rate of different treatments to the user 190, recovery rate of the user 190, and / or severity of disease / symptom of the user 190.

[0047] By this embodiment, the ML model 170 is used to analyze certain issues based on the collected body data. The success rate of different treatments can be provided to the supervisor 300 for reference. The recovery rate and / or the seventy of disease / symptom can be provided to the supervisor 300 and / or the user 190.

[0048] According to another embodiment, ML model 170 is based on injury, harm, disease, symptom and / or the movement related information when analysing 210 the user body data. The collected user body data is gathered within specific contexts of injury, harm, disease, symptom and / or the movement related information using the ML model 170.

[0049] By this embodiment, the ML model 170 takes into injury, harm, disease, symptom and / or the movement related information account when making analysis, so that the analysis is more tailored to the real situation of the user 190.

[0050] According to another embodiment, a user body data analysis system 100 for analysing user body data, wherein the user body data analysis system 100 comprises a user headset 110 and a network entity 160, the user headset 110 and the network entity 160 are communicatively connected, the user headset 110 comprises at least one sensor 130, 140, 150, the headset 110 comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the network entity 160 comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the user body data analysis system 100 is operative for: obtaining, by the headset 110, movement related information for a user 190; representing, by the headset 110, the movement related information to the user 190 so the user 190 can follow; collecting user body data, by at least a subset of the at least one sensor 130, 140, 150; determining, by the headset 110, updated movement related information for the user 190 based on the collected user body data; representing, by the headset 110, the updated movement related information to the user 190; transmitting, by the headset 110, the collected user body data to the network entity 160; analysing, by the network entity 160, the user body data based on a Machine Learning, ML model 170.

[0051] According to other embodiments, the user body data analysis system is further operative for performing the methods mentioned above.

[0052] In conclusion, the user body data analysis system comprises sophisticated models that engage various sensors to perform calculations, conduct analyses, and derive meaningful insights. The utilization of sensors varies, with some being more frequently used than others. Certain sensors serve as constants, continuously providing essential data, while others are dynamically utilized based on ML model driven insights. This dynamic adaptation involves utilizing new sensors to validate, scrutinize, and refine the calculated outcomes.

[0053] In the user body data analysis system, the collected user body data is gathered within specific contexts of injury, harm or symptoms using Machine Learning techniques and models, enabling the system to make informed decisions about which sensors to be utilized or activate based on the intended purpose.

[0054] In situations involving specific injury, harm or symptoms, the system's configuration is adapted for selecting the most applicable sensors for in-depth analysis and precise calculations. This capability not only enhances the decisionmaking process but also forms the foundation for selecting appropriate treatments through ML model informed decision support.

[0055] The user body data system also verifies results, further attesting to the accuracy of its adaptive sensor approach. In essence, this mobile system represents a paradigm shift in data collection and analysis, capitalizing on ML- driven strategies to optimize sensor utilization, support treatment decisions, and dynamically refine its sensor selection for result validation.

[0056] The invention combines the various data sources of information together with the new calculations and creation of new data types and data in the software client application which makes it possible to provide information to a server with combined and extended information of sensory information for e.g., a human body's eye and vision, proprioception, vestibular and tactile information for physiotherapeutic needs. The network entity itself also processes and addsmethods and algorithms based on the data supplied by the VR application and the software client.

[0057] By measuring cervical range of motion in all directions, cervical follow-up movements, cervical position sense (JPE), neuromuscular control through coordination and speed measurements, subjective visual vertical - vestibular function, symptom assessment, cervical proprioception, cervical mobility, cervical motor control, cervical endurance, gaze stability, eye reflex, pupils, smooth pursuit, eye-head-coordination, balance, simultaneous capacity, and focus and planning, before, during and after rehabilitation, treatment can be tailored to obtain optimal results and reduce the risk of recurring problems. All these movements can be measured at the same time with the invention.

[0058] The amount of data information can be used as base for ML models for probabilities, recommendations, and diagnoses where the processed output data can be used to make / suggest diagnoses to the doctor or other roles with medical, healthcare.

[0059] Although the description above contains a plurality of specificities, these should not be construed as limiting the scope of the concept described herein but as merely providing illustrations of some exemplifying embodiments of the described concept. It will be appreciated that the scope of the presently described concept fully encompasses other embodiments which may become obvious to those skilled in the art, and that the scope of the presently described concept is accordingly not to be limited. Reference to an element in the singular is not intended to mean "one and only one" unless explicitly so stated, but rather "one or more." Further, the term “a number of”, such as in “a number of wireless devices” signifies one or more devices. All structural and functional equivalents to the elements of the above-described embodiments that are known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed hereby. Moreover, it is not necessary for an apparatus or method to address each and every problem sought to be solved by the presently described concept, for it to be encompassed hereby. In the exemplary figures, a broken line generally signifies that the feature within the broken line is optional.

Claims

CLAIMS1 . A method performed by a user body data analysis system (100) for analysing user body data, wherein the user body data analysis system (100) comprises a user headset (110) and a network entity (160), the user headset (110) and the network entity (160) are communicatively connected, the user headset (110) comprises at least one sensor (130, 140, 150), the method comprises: obtaining (200), by the headset (110), movement related information for a user (190); representing (202), by the headset (110), the movement related information to the user (190) so the user (190) can follow; collecting (204) user body data, by at least a subset of the at least one sensor (130, 140, 150); determining (205), by the headset (110), updated movement related information for the user (190) based on the collected (204) user body data; representing (206), by the headset (110), the updated movement related information to the user (190); transmitting (208), by the headset (110), the collected user body data to the network entity (160); analysing (210), by the network entity (160), the user body data based on a Machine Learning, ML model (170).

2. The method according to claim 1 , the method further comprises: representing (212), by the network entity (160), the analysis (210) result and / or collected user body data to a supervisor (300).

3. The method according to claim 1 or 2, the method further comprises: transmitting (214), by the network entity (160), the analysis (210) result and / or information from the supervisor (300) to the headset (110), wherein the updated movement related information is further determined (205) based on the analysis (210) result and / or the information from the supervisor (300).

4. The method according any one preceding claims, the user body data analysis system (100) further comprises a handheld controller (180), the handheld controller (180) and the headset (110) are communicatively connected.

5. The method according to claim 4, wherein the handheld controller (180) comprises at least one sensor (182, 184), the method further comprises: collecting (216) user body data, by at least a subset of the at least one sensor (182, 184) on the handheld controller (180); transmitting (218), by the handheld controller (180), the collected user body data to the headset (110), wherein the determination (205) of the updated movement related information for the user (190) is further based on the transmitted (218) user body data from the handheld controller (180).

6. The method according to any one of preceding claims, wherein the user body data analysis system (100) further comprises at least one sensor (194, 196) arranged on body of the user (190), the at least one sensor (194, 196) arranged on the body of the user (190) being communicatively connected to the headset (110), the method further comprises: collecting (220) user body data, by at least a subset of the at least one sensor (192, 194) arranged on body of the user (190); transmitting (222), by the at least a subset of the at least one sensor (192, 194) arranged on body of the user (190), the collected user body data to the headset (110), wherein the determination (205) of the updated movement related information for the user (190) is further based on the transmitted (222) user body data by the at least subset of the at least one sensor (192, 194) arranged on body of the user (190).

7. The method according to any one of the preceding claims, wherein the obtaining (200) of the movement related information for the user (190) comprises receiving the movement related information from the network entity (160) and / or generating the movement related information.

8. The method according to any one of the preceding claims, the method further comprises: selecting (222), by the headset (110), the at least a subset of the at least one sensor (130, 140, 150) prior to collecting (204), based on injury, harm, disease, symptom and / or the movement related information.

9. The method as claimed in any one of preceding claims, the analysing (210) comprises analysing success rate of different treatments to the user (190), recovery rate of the user (190), and / or seventy of disease / symptom of the user (190).

10. The method as claimed in any one of the preceding claims, wherein ML model (170) is based on injury, harm, disease, symptom and / or the movement related information when analysing (210) the user body data.

11. A user body data analysis system (100) for analysing user body data, wherein the user body data analysis system (100) comprises a user headset (110) and a network entity (160), the user headset (110) and the network entity (160) are communicatively connected, the user headset (110) comprises at least one sensor (130, 140, 150), the headset (110) comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the network entity (160) comprises a processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, the user body data analysis system (100) is operative for: obtaining, by the headset (110), movement related information for a user (190); representing, by the headset (110), the movement related information to the user (190) so the user (190) can follow; collecting user body data, by at least a subset of the at least one sensor (130, 140, 150); determining, by the headset (110), updated movement related information for the user (190) based on the collected (204) user body data; representing, by the headset (110), the updated movement related information to the user (190); transmitting, by the headset (110), the collected user body data to the network entity (160); analysing, by the network entity (160), the user body data based on a Machine Learning, ML model (170).

12. The user body data analysis system (100) according to claim 11 , wherein the user body data analysis system (100) is operative for performing the methods according to claims 2-10.

Images