Platform for personalized outdoor fitness training

Abstract

There is provided a method, comprising: accessing a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining fitness resources located in proximity to the geographical location, and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise, feeding into a machine learning model, a combination of resources parameters of each of the fitness resources located in proximity to the geographical location, the terrain map, and personal parameters of the user, and generating by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the personal parameters.

Description

[0001] PLATFORM FOR PERSONALIZED OUTDOOR FITNESS TRAINING

[0002] RELATED APPLICATION

[0003] This application claims the benefit of priority of U.S. Provisional Patent Application No. 63 / 648,183 filed on May 16, 2024, the contents of which are incorporated herein by reference in their entirety.

[0004] BACKGROUND

[0005] The present invention, in some embodiments thereof, relates to platforms for generating personalized fitness training and, more specifically, but not exclusively, to an application running on a mobile device for generating location based personalized fitness training.

[0006] SUMMARY

[0007] According to a first aspect, a computer implemented method of automatic generation of a personalized workout schedule, comprises: accessing a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise, feeding into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user, and generating by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

[0008] According to a second aspect, a system for automatic generation of a personalized workout schedule, comprises: at least one processor executing a code for: accessing a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, , and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise, feeding into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user, and generating by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

[0009] According to a third aspect, a non-transitory medium storing program instructions for automatic generation of a personalized workout schedule, which when executed by at least one processor, cause the at least one processor to: access a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, , and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise, feed into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user, and generate by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

[0010] In a further implementation form of the first, second, and third aspects, the terrain map includes at least one of: indication of stairs, type of path including paved and unpaved, obstacles along the path, and exposure to environment elements along the path.

[0011] In a further implementation form of the first, second, and third aspects, the personalized workout schedule comprises a sequence of exercises to perform at a sequence of different fitness resources located at different geographical locations, the sequence of exercises including the route for performing aerobic exercise, wherein the sequence of exercises is selected according to geographical locations of the fitness resources and the route.

[0012] In a further implementation form of the first, second, and third aspects, the personalized workout schedule includes an active personalized guidance for presentation on a display, for instructing the user in real-time on how to perform each personalized exercise on each fitness resources while complying with the at least one personal parameter. In a further implementation form of the first, second, and third aspects, the active personalized guidance is dynamically adapted in real-time by dynamically adapting the instructions for performing the personalized exercises based on an analysis of measurements of at least one physiological parameter of the user measured by at least one physiological sensor.

[0013] In a further implementation form of the first, second, and third aspects, instructions for performing the personalized exercises to be performed on each fitness resources are dynamically presented on a display of the mobile device according to a real-time geographical location of the location sensor in proximity to a fitness resource for which a personalized exercise to be performed is included in the personalized workout schedule, wherein the instructions for performing a subsequent personalized exercise are dynamically updated as the mobile device is moved in proximity to a subsequent fitness resource according to a sequence of personalized exercises performed on fitness resources defined by the personalized workout schedule.

[0014] In a further implementation form of the first, second, and third aspects, the personalized workout schedule for the user is further generated according to current and future predicted availability of the plurality of fitness resources and / or of the routes, computed according to a schedule generated based on personalized workout schedules generated for other users and / or according to real-time and / or predicted geographical locations of the other users.

[0015] In a further implementation form of the first, second, and third aspects, the schedule is generated by a scheduling process fed the personalized workout schedules generated for other users, trained for optimizing usage of the plurality of fitness resources by users.

[0016] In a further implementation form of the first, second, and third aspects, the machine learning model is trained on a training dataset of a plurality of records, wherein a record includes a combination of at least one resources parameter for each of a plurality of sample fitness resources within a defined region, a terrain map of the defined region, a plurality of personal parameters of a sample user, and a ground truth of a sample personalized workout schedule for the sample user.

[0017] In a further implementation form of the first, second, and third aspects, the at least one resources parameter is selected from: type of possible activity, difficulty level, activated muscle groups.

[0018] In a further implementation form of the first, second, and third aspects, the at least one personal parameter of the user is selected from: fitness level, training goals, physical limitations, personal preferences, and historical training using at least one fitness resources.

[0019] In a further implementation form of the first, second, and third aspects, further comprising: collecting data using the mobile device, including at least one of: feedback from the user, data indicating usage of the plurality of fitness resources, and progress of the user, generating a feedback record using the collected data, and updating the machine learning model using the feedback record for generating personalized workout schedules predicted to at least one of: more likely to be followed by the user, associated with positive feedback by the user, and improve fitness of the user.

[0020] In a further implementation form of the first, second, and third aspects, the at least one resources parameter is automatically generated for a fitness resources by at least one of: feeding an image of the fitness resources into a classifier trained on a training dataset of images of sample fitness resources and a ground truth of sample resources parameters, extracted by a large language model fed a text description of the fitness resources, and based on an analysis of historical usage and / or feedback by users using the fitness resources.

[0021] In a further implementation form of the first, second, and third aspects, further comprising: generating a dataset comprising the plurality of fitness resources, each fitness resources associated with an indication of inclusion in generated personalized workout schedules and / or with an indication of usage by users according to the generated personalized workout schedules, and analyzing the dataset for identifying at least one of: demand exceeding capacity indicating a potential need for additional fitness resources, and trends in usage of the fitness resources.

[0022] In a further implementation form of the first, second, and third aspects, the plurality of fitness resources are of a plurality of different types and / or of a plurality of different manufacturers.

[0023] In a further implementation form of the first, second, and third aspects, the plurality of fitness resources further include strength training equipment.

[0024] In a further implementation form of the first, second, and third aspects, further comprising dynamically generating and / or updating the geo-location dataset, by locating the plurality of fitness resources on an area map.

[0025] In a further implementation form of the first, second, and third aspects, the combination fed into the machine learning model includes the at least one personal parameter of each of a plurality of users, wherein the personalized workout schedule is for a subset of the plurality of users with similar personal parameters for a joint workout.

[0026] In a further implementation form of the first, second, and third aspects, at least one of the following are fed into the machine learning model along with the combination: physiological parameters of the user while following a previously generated personalized workout schedule, the user’s previous performance based on the analysis of the physiological parameters, and the previously generated personalized workout schedule.

[0027] In a further implementation form of the first, second, and third aspects, the personalized workout schedule is generated for meeting a predicted load level for the user and / or predicted to provide an improvement in the user’s performance. Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. Although methods and materials similar or equivalent to those described herein can be used in the practice or testing of embodiments of the invention, exemplary methods and / or materials are described below. In case of conflict, the patent specification, including definitions, will control. In addition, the materials, methods, and examples are illustrative only and are not intended to be necessarily limiting.

[0028] BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0029] Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description taken with the drawings makes apparent to those skilled in the art how embodiments of the invention may be practiced.

[0030] In the drawings:

[0031] FIG. 1 is a block diagram of components of a system for automatic generation of a personalized workout schedule including a combination of fitness resources and a route along a terrain, in accordance with some embodiments of the present invention;

[0032] FIG. 2 is a flowchart of a method of automatic generation of a personalized workout schedule including a combination of fitness resources and a route along a terrain, in accordance with some embodiments of the present invention;

[0033] FIG. 3 is a block diagram of exemplary components of a host system, optionally a client terminal, for generating customized fitness plans, in accordance with some embodiments of the present invention;

[0034] FIG. 4 is a block diagram of components of an ecosystem that includes multiple entities that may interact with a host system for generating of a personalized workout schedule using available fitness equipment, in accordance with some embodiments of the present invention;

[0035] FIG. 5 is a flowchart of a method for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention;

[0036] FIG. 6 is a flowchart of a method of interaction of a user with a system for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention; FIG. 7 is a block diagram of components for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention; and

[0037] FIG. 8 is a block diagram of components for automatic generation of multiple personalized workout schedule for users with similar personal parameters, in accordance with some embodiments of the present invention.

[0038] DETAILED DESCRIPTION

[0039] The present invention, in some embodiments thereof, relates to platforms for generating personalized fitness training and, more specifically, but not exclusively, to an application running on a mobile device for generating location based personalized fitness training.

[0040] As used herein the term fitness equipment, infrastructure for physical activity, resources (fitness resources, public resources), and facilities (physical facilities), are used interchangeably.

[0041] An aspect of some embodiments of the present invention relates to systems, methods, computing devices, and / or code instructions (stored on a data storage device and executable by one or more processors) for automatic generation of a personalized fitness plan for a user. A geolocation dataset is accessed according to a geographical location of a mobile device of a user obtained from a location sensor, for example, a global positioning sensor (GPS) installed within a smartphone of the user. The geo-location dataset is accessed for obtaining multiple fitness resources (e.g., strength training equipment) located in proximity to the geographical location of the user. The fitness resources include a combination of fitness equipment for strength training (e.g., weight lifting, squats, push-ups, sit- ups) and paths for aerobic training (e.g., running, jogging, walking, cycling). The geo-location dataset is further access for obtaining a terrain map in proximity to the geographical location. Each fitness resource is associated with one or more resource parameters, for example, type of possible activity, activated muscle groups, and difficulty level. The terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise. The terrain map may include other features, for example, location of stairs, type of path such as paved or unpaved, obstacles along the path (e.g., fallen tree, river), and exposure to environment elements (e.g., lack of trees indicating exposure to sun, exposure to strong winds, shaded). A combination of the resources parameter(s) of each of the fitness resources located in proximity to the geographical location, the terrain map in proximity to the geographical location, and one or more personal parameters of the user, are fed into a machine learning (ML) model. Examples of personal parameters of the subject include fitness level, training goals, physical limitations, personal preferences, and historical training. The machine learning model generates the personalized workout schedule for the user. The personalized workout schedule includes personalized exercises for performing using a combination of the fitness resources and a route for performing aerobic exercise along the paths of the terrain map, while complying with the personal parameter(s) of the subject. The personalized workout schedule may include a defined sequence of the personalized exercises, including a combination of strength training exercises using strength training equipment and aerobic exercises using the paths. For example, jog 1 kilometer along a paved path along flat ground to a park. At the park, use a first type of strength training equipment to lift 5 kilogram 10 times by using the left arm, then the right arm. Use another fitness equipment to perform 20 sit-ups. Walk for 2 kilometers along a second unpaved path that climbs a hill to return to your original location.

[0042] At least one embodiment described herein addresses the technical problem of automatically generating an improved personalized workout schedule for a user. At least one embodiment described herein improves the technology of platforms for automatically generating a personalized workout schedule for a user. At least one embodiment described herein improves upon existing platforms for automatically generating a personalized workout schedule for a user. At least one embodiment described herein solves the aforementioned technical problem by, and / or improves the aforementioned technology by, and / or improves the aforementioned existing platforms by, and / or provides the practical application of, using a machine learning model for automatically generating the personalized workout schedule for the user. The personalized workout schedule includes personalized exercises for performing using a combination of the fitness resources and a route for performing aerobic exercise along the paths of the terrain map, while complying with the personal parameter(s) of the subject. The machine learning model is fed a combination of the resources parameter(s) of each of the fitness resources located in proximity to a geographical location of the user (i.e., of a mobile device of the user), the terrain map in proximity to the geographical location, and one or more personal parameters of the user.

[0043] At least one embodiment described herein addresses the technical problem of increasing utilization of fitness equipment, optionally public infrastructure for physical activity. Authorities may invest resources in sports and / or fitness infrastructure in public spaces, such as outdoor gym facilities, walking / running / cycling paths, but this investment is not necessarily optimally utilized. In addition, potential users struggle to find, understand, and utilize the infrastructure for physical activity in a way that fits their personal needs, fitness level, and fitness goals. At least one embodiment described herein solves the aforementioned problem by providing approaches that match between the user and the existing infrastructure in the public space by automatically generating personalized workout schedules for users using the public infrastructure for physical activity.

[0044] At least one embodiment described herein provides a system and / or method and / or code for matching users with appropriate public fitness resources based on their personal parameters for example, fitness levels, goals, and / or the specific characteristics of available public resources. The system and / or method and / or code may operate through a mobile application that integrates geographic positioning, user profiling, resource mapping, and / or artificial intelligence to create personalized fitness plans that utilize public fitness infrastructure.

[0045] At least one embodiment described herein provides a system and / or method and / or code for enabling users to photograph public fitness resources (parks, fitness equipment, staircases, etc.) using their smartphones and in real-time receive customized workout plans tailored to these resources. In some embodiments this feature is based on a deep learning model trained to identify different types of fitness equipment and infrastructure from images, characterize their attributes (such as height, angle, distance, type, etc.), and suggest exercises and workouts precisely adapted to the photographed resources. The visual recognition model may improve over time as more users photograph and tag equipment, enabling quick and efficient cataloging of new resources not yet in the central database.

[0046] At least one embodiment described herein provides precise matching between user capabilities and all types of specific infrastructure available in their environment (i.e., not just fitness equipment from a particular manufacturer or running routes), creating a more effective and truly personalized training experience. Unlike some existing approaches, which focus on documentation, or other existing approaches, which focus on equipment by a specific provider, at least one embodiment integrates all public infrastructure into a coherent and comprehensive training program.

[0047] At least one embodiment described herein improves upon existing approaches. Standard fitness applications that offer training programs for use in outdoor spaces, primarily focus on tracking running, cycling, and walking activities and provide a platform for sharing activity data with other users. Users download the application, choose a training program designed for outdoor or park use, and perform the generally suggested workouts. For example, users record their activities, compare performance with others, and follow popular routes. Additionally, companies that offer outdoor fitness equipment may provide accompanying applications that demonstrate how to use their equipment. Users may scan a QR code on the equipment and receive specific guidance for that equipment, but without personalization to their fitness level - as provided by at least one embodiment described herein. In an example, one system recommends exercise routes based on user preferences and location. In contrast, at least one embodiment described herein differs significantly, by considering a comprehensive utilization of all types of public fitness infrastructure (not just routes), incorporating real-time adaptive training programs based on available equipment, and / or including a bidirectional feedback system designed to provide insights for infrastructure planning (e.g., for municipal authorities). Additionally, at least one embodiment described herein may provide computer vision technologies for resource identification and / or exercise form correction.

[0048] In another example, an existing fitness-tracking platform primarily focuses on recording and sharing running and cycling activities. In contrast, at least one embodiment described herein provides Al-driven personalized training programs specifically optimized for public resources, rather than just activity tracking. At least one embodiment described herein may incorporate strength training with public equipment, may offer biomechanical analysis for proper form guidance, and / or may create a comprehensive ecosystem connecting users, resources, and / or municipal authorities.

[0049] Examples of improvements over existing approaches provided by at least one embodiment include:

[0050] • An artificial intelligence based matching engine that combines machine learning technologies.

[0051] • Image processing for equipment identification and mapping.

[0052] • Analysis of user data.

[0053] • While other approaches focus on documenting activities and / or social competitiveness, and applications from manufacturers are limited to their specific equipment, at least one embodiment is designed to create dynamic training programs that integrate all types of public resources and are adjusted in real-time based on the user's location, available infrastructure, personal progress, and / or additional variables.

[0054] • The combination of a user interface and an interface for authorities creates a complete ecosystem that optimizes the utilization of public resources.

[0055] Potential technical advantages provided by at least one embodiment, and / or improvements over existing approaches provided by at least one embodiment, include:

[0056] • Provides alignment between suggested personalized workout schedule and the equipment actually available in the user's environment.

[0057] • Considers the unique characteristics of each public fitness facility in the generation of the personalized workout schedule. • Provides precise mapping of the variety of public resources (i.e., fitness equipment) available in the user's area.

[0058] • Generates personalized workout schedule that are non-generic and / or are tailored to the user's abilities, limitations, and / or personal goals.

[0059] • Provides a feedback mechanism allowing authorities to improve public infrastructure based on actual usage.

[0060] • Provides active guidance rather than simply focusing on documentation and sharing.

[0061] • Provides a comprehensive solution integrating all public resources rather than being limited only to a specific company's equipment.

[0062] Some exemplary examples of use cases based on at least one embodiment described herein are now provided:

[0063] Sarah, a 35-year-old with intermediate fitness level, opens an application running on her smartphone while at her local park. The system identifies her location and presents nearby infrastructure: an outdoor gym with various equipment, a jogging path, and a set of stairs. Based on her profile indicating goals of weight management and improved cardiovascular health, previous workout history, and current fitness level, the system generates a personalized 45-minute circuit-training plan, i.e., fitness plan. The fitness plan intelligently combines the jogging path (for warm-up), specific equipment at the outdoor gym (targeting major muscle groups), and the stairs (for high-intensity intervals). The application guides Sarah through each exercise with proper form instructions and adaptive difficulty levels, making optimal use of all available public resources in an integrated workout experience specifically designed for her needs.

[0064] Another example relates to a city dweller seeking efficient workout options. User A, living in a densely populated urban area, uses an application running on their mobile device to find the nearest park with outdoor fitness equipment suitable for high-intensity interval training. The app suggests a 30-minute jogging route at the geographical vicinity of a fitness park five minutes and tailors a 45-minute workout based on the available equipment in the park. In such case, the platform of the present invention maximizes workout efficiency and reduces travel time, promoting consistent exercise habits.

[0065] Another example relates to a suburban user with limited equipment options. User B, in a suburban area with fewer fitness parks, relies on the app to schedule workouts during times when equipment is available. The app dynamically adjusts the user's workout plan based on equipment status updates from other users, and finds an optimal running route for the user that ends at the fitness park at suitable timing for using the equipment. This ensures access to required equipment and maintains workout quality, enhancing user satisfaction and resource utilization.

[0066] Yet another examples relates to a traveling professional. User C, a business traveler, uses the app in different cities to maintain their fitness regimen. The app identifies available outdoor facilities near hotels and provides customized workouts that adapt to the varying types of equipment found in each new location and to varying terrain for providing optimal jogging routes. This supports consistent training routines despite changes in location and available resources, aiding in maintaining fitness levels while traveling.

[0067] Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of the components and / or methods set forth in the following description and / or illustrated in the drawings and / or the Examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.

[0068] The present invention may be a system, a method, and / or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.

[0069] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0070] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0071] Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.

[0072] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0073] These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0074] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0075] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0076] Reference is now made to FIG. 1, which is a block diagram of components of a system 100 for automatic generation of a personalized workout schedule including a combination of fitness resources and a route along a terrain, in accordance with some embodiments of the present invention. Reference is also made to FIG. 2, which is a flowchart of a method of automatic generation of a personalized workout schedule including a combination of fitness resources and a route along a terrain, in accordance with some embodiments of the present invention. Reference is also made to FIG. 3, which is a block diagram of exemplary components of a host system 302, optionally a client terminal, for generating customized fitness plans, in accordance with some embodiments of the present invention. Reference is also made to FIG. 4, which is a block diagram of components of an ecosystem 402 that includes multiple entities that may interact with a host system 404 for generating of a personalized workout schedule using available fitness equipment, in accordance with some embodiments of the present invention. Reference is also made to FIG. 5, which is a flowchart of a method for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention. Reference is also made to FIG. 6, which is a flowchart of a method of interaction of a user with a system for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention. Reference is also made to FIG. 7, which is a block diagram of components for automatic generation of a personalized workout schedule for a user using fitness equipment and complying with the personal parameters, in accordance with some embodiments of the present invention. Reference is also made to FIG. 8, which is a block diagram of components for automatic generation of multiple personalized workout schedule for users with similar personal parameters, in accordance with some embodiments of the present invention.

[0077] System 100 may implement the acts of the method described with reference to other FIGs. described herein, by processor(s) 102 of a computing environment 104 executing code instructions stored in a memory 106.

[0078] Computing environment 104 may be implemented as, for example one or more and / or combination of: a server, a virtual server, a computing cloud, a group of connected devices, a client terminal, a virtual machine, a desktop computer, a thin client, a network node, and / or a mobile device (e.g., a Smartphone, a Tablet computer, a laptop computer, a wearable computer, glasses computer, and a watch computer (e.g., smartwatch)).

[0079] Multiple architectures of system 100 based on computing environment 104 may be implemented. For example:

[0080] In a centralized architecture, computing environment 104 executing stored code instructions 106A, may be implemented as one or more servers (e.g., network server, web server, a computing cloud, a virtual server) that provides centralized services (e.g., one or more of the acts described with reference to other FIGs. described herein) to one or more client terminals 108 over a network 110. For example, providing software as a service (SaaS) to the client terminal(s) 108, providing software services accessible using a software interface (e.g., application programming interface (API), software development kit (SDK)), providing an application 108A for local download to the client terminal(s) 108, providing an add-on to a web browser running on client terminal(s) 108, and / or providing functions using a remote access session to the client terminals 108, such as through a web browser executed by client terminal 108 accessing a web sited hosted by computing environment 104. For example, data is provided by each respective client terminal 108 of each respective user to computing environment 104. Computing environment centrally feeds the data into the machine learning model 114A, and provides the outcome (e.g., fitness plan), such as for presentation on a display of each respective the client terminal 108 of each respective specific user.

[0081] Application 108 A running on client terminal 108 may implement one or more features described herein with reference to computing environment 104 and / or described with reference to other FIGs. described herein. Application 108A may be implemented as a mobile application platform that interfaces with various hardware and / or software components to deliver personalized fitness guidance.

[0082] In a local architecture, computing environment 104 may be implemented as a standalone device (e.g., kiosk, client terminal, smartphone) that include locally stored code instructions 106A that implement one or more of the acts described with reference to other FIGs. described herein. The locally stored instructions may be obtained from another server, for example, by downloading the code over the network, and / or loading the code from a portable storage device. For example, data is locally entered by a specific user using client terminal 104 and / or collected by sensors 150 connected to the computing environment 104. The computing environment locally feeds the data into the machine learning model 114A, and provides the outcome (e.g., fitness plan), such as for presentation on a display of the client terminal 104 of the specific user.

[0083] Other exemplary implementation architectures include:

[0084] • Cloud-Based Implementation: Primary resources hosted on scalable cloud infrastructure, providing maximum flexibility and computational capacity for AI / ML functions.

[0085] • Edge Computing Enhancement: Certain processing tasks executed on the client terminal to reduce latency and bandwidth usage, particularly for real-time features like workout tracking and guidance.

[0086] • Hybrid Architecture: Critical features distributed between cloud and edge components to optimize for both performance and resource efficiency.

[0087] Hardware processor(s) 102 of computing environment 104 may be implemented, for example, as a central processing unit(s) (CPU), a graphics processing unit(s) (GPU), field programmable gate array(s) (FPGA), digital signal processor(s) (DSP), and application specific integrated circuit(s) (ASIC). Processor(s) 102 may include a single processor, or multiple processors (homogenous or heterogeneous) arranged for parallel processing, as clusters and / or as one or more multi core processing devices. Memory 106 stores code instructions executable by hardware processor(s) 102, for example, a random access memory (RAM), read-only memory (ROM), and / or a storage device, for example, non-volatile memory, magnetic media, semiconductor memory devices, hard drive, removable storage, and optical media (e.g., DVD, CD-ROM). Memory 106 stores code 106A that implements one or more features and / or acts of the method described with reference to other FIGs. described herein when executed by hardware processor(s) 102.

[0088] Computing environment 104 may include a data storage device 114 for storing data, for example, the machine learning model 114A described herein, and / or one or more data repositories 114B. Data storage device 114 may be implemented as, for example, a memory, a local hard-drive, virtual storage, a removable storage unit, an optical disk, a storage device, and / or as a remote server and / or computing cloud (e.g., accessed using a network connection).

[0089] Network 110 may be implemented as, for example, the internet, a local area network, a virtual network, a wireless network, a cellular network, a local bus, a point to point link (e.g., wired), and / or combinations of the aforementioned.

[0090] Different communication technologies may be implemented, for example, for communication between mobile devices of users and the computing environment (e.g., server, computing cloud):

[0091] • Cellular Data Connection (4G / 5G): May be the primary method for most users, enabling real-time access to a complete feature set.

[0092] • Wi-Fi Only Mode: For users with limited data plans, for allowing synchronization of resource data when connected to Wi-Fi networks.

[0093] • Offline Mode: Essential features can function without an active connection using predownloaded resource data for specific geographic areas.

[0094] Computing environment 104 and / or client terminal(s) 108 may be in communication with one or more sensor(s) 150 that perform measurements for collecting parameters, as described herein in additional detail.

[0095] Computing environment 104 may include a network interface 116 for connecting to network 110, for example, one or more of, a network interface card, a wireless interface to connect to a wireless network, a physical interface for connecting to a cable for network connectivity, a virtual interface implemented in software, network communication software providing higher layers of network connectivity, and / or other implementations.

[0096] It is noted that in the standalone implementation, network interface 116 is not necessarily required, as computing environment 104 includes sensors 150 and / or user interface 120 in a single device that may operate without externally communication with other devices, optionally using offline maps, for example, a smartphone, a kiosk, and a dedicated device.

[0097] Computing environment 104 may connect using network 110 (or another communication channel, such as through a direct link (e.g., cable, wireless) and / or indirect link (e.g., via an intermediary computing unit such as a server, and / or via a storage device) with one or more of:

[0098] * Remote server(s) 112 hosting one or more external datasets 112A. For example, for accessing weather forecast data, which may be used to adjust workout recommendations based on environmental conditions, such as suggesting indoor alternatives during inclement weather or modifying outdoor workout intensity during extreme temperatures. In another example, for accessing a social network. Community aspects may be implemented to varying degrees, from basic features like workout sharing to advanced capabilities such as real-time group workouts, challenges, and leaderboards.

[0099] * Client terminal(s) 108, when computing environment 104 is implemented in a central architecture providing centralized services. Examples of client terminals 108 include smartphones, smartwatches, artificial reality (AR) headsets, tablets, and the like.

[0100] Augmented reality may be used, for example, to overlay exercise instructions directly onto real- world fitness equipment, for example, through a device camera. Using augmented reality may enhance user understanding of proper equipment usage.

[0101] * Sensor(s) 150 that perform measurements for collecting parameters, for example, heart rate sensor, body temperature sensor, and the like. Sensors 150 may include smartphone sensors, and / or sensors integrated with wearable fitness devices, which may provide enhanced data collection capabilities, for example, continuous heart rate monitoring, more accurate activity tracking, and advanced sleep analysis for recovery recommendations.

[0102] Computing environment 104 and / or client terminal(s) 108 include and / or are in communication with one or more physical user interfaces 120 that include a mechanism for a user to enter data (e.g., manually enter parameters) and / or view the displayed results (e.g., generated fitness plan), optionally within a GUI. Exemplary user interfaces 120 include, for example, one or more of, a touchscreen, a display, gesture activation devices, a keyboard, a mouse, and voice activated software using speakers and microphone.

[0103] Referring now back to FIG. 2, at 202, a geographical location indicating a location of a user is obtained.

[0104] The geographical location is obtained from a location sensor, for example, a GPS sensor, by triangulation of a location of an antenna of a mobile device, and the like. The measurement made by the location sensor serves as a proxy for the location of the user when the location sensor is installed within the mobile device being used by the user, and / or is otherwise associated with the user, for example, a wearable sensor embedded within clothing, and / or a location sensor attached to clothing (e.g., via a clip).

[0105] The geographical location may be automatically obtained in response to a trigger, optionally the opening of an application (for automatic generation of the personalized workout schedule) running on the mobile device of the user. In another example, the trigger may be the user pressing an icon (for automatic generation of the personalized workout schedule) presented in a graphical user interface (GUI) displayed on a display of a mobile device.

[0106] The geographical location may represent the current (i.e., real-time) location of the user. Alternatively, the geographical location may represent a future desired location of the user. The user may provide the future geographical location, for example, by entering an address, and / or pressing a location on a map presented within the GUI. For example, the user may plan to stay in a hotel in a different city tomorrow, and would like to obtain to generate the personalized workout schedule in proximity to the hotel.

[0107] At 204, a geo-location dataset is accessed according to a geographical location.

[0108] The geo-location dataset stores locations of fitness resources mapped to a geographical area map.

[0109] Fitness resources may include fitness equipment designed for strength training. The fitness resources may be manufactured equipment that is not available naturally.

[0110] The fitness resources may be publicly accessible, for example, located in public areas such as parks and / or streets. The fitness resources may be accessed without requiring special permission, for example, do not necessarily requiring advanced reservations, no fees are required, and not limitations are placed on the people accessing the fitness resources. The fitness resources may be available 24 / 7, or access may be limited in certain times, such as when the park is closed, or during time when excessive noise is prohibited (e.g., night).

[0111] Examples of fitness resources include:

[0112] • Pull-up bars - Simple metal bars for pull-ups, chin-ups, and hanging exercises.

[0113] • Parallel bars - For dips, L-sits, and bodyweight exercises.

[0114] • Push-up stations - Low bars or platforms designed to assist in doing push-ups.

[0115] • Sit-up benches - Inclined or flat benches for abdominal exercises.

[0116] • Balance beams - Narrow beams to improve balance and coordination.

[0117] • Monkey bars / climbing frames - Great for grip strength and agility.

[0118] • Step platforms - Raised steps for cardio step-ups and jumping drills.

[0119] • Resistance wheels or gears - Often part of low-resistance shoulder or flexibility exercises. • Leg press machines - Outdoor versions for seated leg pressing using bodyweight.

[0120] • Rowing bars - For simulating a rowing motion for upper body strength.

[0121] • Elliptical machines - Pedal-powered outdoor cardio machines.

[0122] • Outdoor exercise bikes - Stationary bikes meant for general cardio, sometimes solar- powered.

[0123] • Cross-trainers - Like ellipticals, allowing full-body cardio workouts.

[0124] • Climbing walls - Short climbing walls designed for public use (not full rock walls).

[0125] The geographical location of the user may be used to automatically select a set of fitness resources from the geo-location dataset located in proximity to the user. For example, within a radius of a defined size centered at the geographical location of the user. The radius may be, for example, predefined, selected by a user, and / or automatically selected by an automated process. Examples of radii include about 100 meters, or about 500 meters, or about 1 kilometer (km), or about 2 km, or about 5 km, or other values. It is noted that shapes other than circles may be defined, for example, a box of size 500 meters x 500 meters centered at the geographical location, or nonlinear boundaries defined by the terrain (e.g., excluding bodies of water, streets, fenced off property) and the like.

[0126] The geo-location dataset may include a terrain map. The terrain map may indicate elevation and / or terrain features, for example, type of terrain such as bodies of water, streets, parks, buildings, mountains, and the like. The terrain may including paths suitable for aerobic exercise, for example, for walking, jogging, running, and / or cycling. The terrain may include one or more path parameters associated with each path. The path parameters may be extracted from the terrain map, based on physical features of the path according to the terrain map. Examples of path parameters include, for example, indication of stairs, type of path such as paved and unpaved, obstacles along the path, width of the path (e.g., wide enough for a group of people, or narrow requiring passing single file, and exposure to environment elements along the path such as wind and sun.

[0127] A portion of the terrain map in proximity to the geographical location of the user is identified. The portion of the terrain may corresponding to the region used to select the set of fitness resources, for example, the radius of the circle used to select the set of fitness resources is used to define the portion of the terrain map. Paths within the portion are identified.

[0128] The geo-location dataset may be automatically generated and / or automatically updated, for example, by one or more of:

[0129] Automatic searching of data (e.g., on the internet and / or defined datasets) to identify new fitness resources. • In response to manual user input, for example, a user adding a location of new fitness resources and / or new paths.

[0130] • In response to receive updates from a defined source, for example, code and / or script indicating new fitness equipment installed in a new park from the municipality.

[0131] • Other examples are described herein.

[0132] The resolution of the geo-location dataset may be set to be relatively high, for providing the user with specific location and / or enabling separating between two fitness equipment structures located in proximity to each other in the same part. For example, about 1-3 meters, or about 3-5 meters. In another example, resolution may be within about 5 meters or about 10 meters or about 15 meters, such as to enable accurate locations of paths. This precision may provide for effective navigation and resource identification in densely equipped areas.

[0133] At 206, one or more resources parameters may be accessed for each of fitness resources located in proximity to the geographical location.

[0134] The resource parameters may be stored in association with the location of the fitness resources on the geo-location dataset, for example, as metadata. Alternatively or additionally, the resource parameters may be stored in a different external dataset (e.g., database) that is mapped to the geo-location dataset. For example, coordinates (e.g., longitude and / or latitude) of the location of the fitness resource may be used as a key for looking up a record of the resource parameters of the fitness resource in the database. Other keys may be used, for example, a code and the like.

[0135] Other examples of resource parameters include: type of possible activity (e.g., sit-up, pushup, chin-lift), difficulty level (e.g., beginner, intermediate, expert, or easy, medium, difficult), and activated muscle groups (e.g., abdomen, biceps, legs).

[0136] The fitness resources may be of different types and / or of different manufacturers. One or more resource parameters may be defined across the different types and / or different manufacturers, which enables generation of the personalized workout schedule using the fitness resources of different types and / or of different manufacturers.

[0137] The resource parameter(s) for the fitness resource may obtained, for example, by:

[0138] • Automatic classification of each fitness resource into one or more resource parameters. The classification may be perform by a trained classifier. The hierarchical classification system for fitness resources may be designed to be sufficiently granular to capture meaningful differences in equipment capabilities while remaining broad enough to group functionally similar resources. For example, using a three-level taxonomy categories (e.g., cardio equipment, strength training), types (e.g., running tracks, bars), and subtypes (e.g., synthetic surface track, chin-ups). • Analyzing an image of the fitness resource. The image of the fitness resource may be fed into a classifier or other machine learning model, which outputs the resource parameter(s).

[0139] The classifier and / or other machine learning model may be trained on a training dataset of images of sample fitness resources and a ground truth of sample resources parameters. The image may be captured by a user using their smartphone and / or uploaded by a manufacture of the fitness resource.

[0140] • Extracted by a large language model (LLM) fed a text description of the fitness resources. The text description may be provided, for example, manually by a user and / or extracted from a website of the manufacturer of the fitness resource.

[0141] • Based on an analysis of historical usage and / or feedback by users using the fitness resources. For example, the resource parameter indicating difficulty of using the fitness resource may be based on user feedback after using the equipment, such as asking the users to rate the equipment as easy, medium, or difficult.

[0142] At 208, one or more personal parameter of the users may be accessed.

[0143] The personal parameters may represent a set of constraints to be met by the personalized workout schedule. The generated personalized workout schedule is to comply with the constraints.

[0144] The personal parameters may be included in a personal profile of the user.

[0145] Examples of personal parameters of the user include: fitness level, training goals, physical limitations, personal preferences, and historical training using at least one fitness resources.

[0146] The personal parameters of the user may be accessed, for example, from a central dataset (e.g., database) storing personal parameters of different users which were pre-provided which may be hosted on a computing cloud and / or server, dynamically entered by a user via the GUI, and / or locally stored on the mobile device of the user.

[0147] At 210, a combination of resources parameter(s) of each the fitness resources located in proximity to the geographical location, the terrain map in proximity to the geographical location, and the personal parameter(s) of the user, are fed into a machine learning model.

[0148] Exemplary architectures of one or more machine learning models described herein include: neural networks of various architectures (e.g., convolutional, fully connected, deep, encoderdecoder, recurrent, transformer, graph), support vector machines (SVM), logistic regression, k- nearest neighbor, decision trees, boosting, random forest, a regressor, and / or any other commercial or open source package allowing regression, classification, dimensional reduction, supervised, unsupervised, semi-supervised, and / or reinforcement learning. Machine learning models may be trained using supervised approaches and / or unsupervised approaches Other data may be fed into the machine learning model, for example, environmental data which may be obtained, for example, from a weather server. The environmental data may represent a set of constraints to be met by the personalized workout schedule. For example, if the environmental data indicates very hot weather, the personalized workout schedule may include less intense exercises, and / or a time to perform the exercises when the weather has cooled down and the sun is not as strong, such as late afternoon or early morning.

[0149] The machine learning model may be trained on a training dataset of records, where a record may include a combination of at least one resources parameter for each of multiple sample fitness resources within a defined region, a terrain map of the defined region, personal parameters of a sample user, and a ground truth of a sample personalized workout schedule for the sample user. The sample personalized workout schedule may be obtained, for example, manually designed by a domain expert (e.g., personal fitness trainer), and / or selected by the sample themselves.

[0150] The relative importance, defined by weights, assigned to different resource and / or personal parameters fed to the machine learning model may impact recommendation quality. The weights may be adaptable, for example, automatically associated with each parameters. The weights may be automatically adjusted by the ML model during learning and / or in response to updates. The weights may be self-adjusted based on user feedback. For example, if several users indicate a personal user parameter is very important and other user parameters are less important, the weights may be adjusted accordingly, increased for the important personal user parameters and decreased for the less important user parameters. Initial weights may prioritize safety (for example, avoiding excessive difficulty) followed by goal alignment and user preferences.

[0151] At 212, the machine learning model generates the personalized workout schedule for the user.

[0152] The personalized workout schedule includes personalized exercises for performing using a combination of the fitness resources within the geographical region in proximity to the user, and a route for performing aerobic exercise along the paths defined by the terrain map within the geographical region in proximity to the user. The personalized workout schedule is generated to comply with the personal parameter(s) fed into the machine learning model.

[0153] The personalized workout schedule includes a sequence of exercises to perform at a sequence of different fitness resources located at different geographical locations, including when to perform aerobic exercise along the route. The sequence of exercises is selected according to geographical locations of the fitness resources and the route. For example, running or walking along different paths along which are located different exercise machines. The sequence of exercises may follow the locations of the exercise machines along the paths. The sequence may be selected to comply with the persona parameters. For example, if a user selects to start with a walk, followed by abdominal exercises, then with arm strengthening, leg strengthening and finally a run, the sequence may be selected according to the personal preference, even if the user needs to backtrack, such as pass by the arm strengthening machine to reach the abdominal exercise machine, then return to the arm strengthening machine.

[0154] Optionally, the personalized workout schedule for the user is further generated according to current and / or future predicted availability of the fitness resources and / or according to current and / or future predicted availability of the routes. For example, if a certain park has fitness machines has a history of many people using its equipment during certain hours, the personalized workout schedule may be selected for the off-peak hours. In another example, the personalized workout schedules of different users may be synchronized by scheduling the different users to use the same fitness equipment at different scheduled times. For example, a first user may be scheduled to use a crunch machine at 16:30, a second user schedule for 16:35, and a third user for 16:40.

[0155] The current and / or future predicted availability of the fitness resources and / or routes may be computed according to a schedule generated based on personalized workout schedules generated for other users and / or according to real-time and / or predicted geographical locations of the other users based on a historical analysis. The schedule may be generated by a scheduling process fed the personalized workout schedules generated for other users. The scheduling process may be trained for optimizing usage of the fitness resources by users, for example, based on heuristic scheduling approaches.

[0156] Alternatively or additionally, the personalized workout schedule for the user may be generated by the ML model, taking into account the future predicted availability of the fitness resources and / or the routes. The ML model may be fed a history of use of the fitness resources and / or the routes by the user and / or other users, for predicting future availability. The prediction may be performed by the ML model and / or another prediction model. In the case another prediction model, the prediction generated by the other prediction model may be fed into the ML model for generating the personalized workout schedule for using fitness resources and / or routes according to predicted availability.

[0157] The personalized workout schedule may be generated for a group of users, for providing a group workout experience. Each user in the group may perform the same exercise at the same time, for example, a joint run along a path, or chin-ups using multiple bars. In another example, each user in the group may perform the same exercise at approximately the same time, such as sequentially. For example, all the users in the group are instructed to use the rowing machine. Users may sequentially use the rowing machine, and then proceed together to the next exercise, or follow the same sequence of exercises using the same set of equipment. The group personalized workout schedule may be generated by feeding the combination of personal parameters of each user of the group, a common set of resource parameters of fitness resources located in proximity to the geographical location of the group, and the terrain map common to the group. The same geographical location may be used for all members of the group. The ML model may generated the personalized workout schedule for complying with overlapping personal parameters of the different users of the group, for attempting to generate a common personalized workout schedule that will be most suitable for the greatest number of users of the group. For example, if most users in the group are beginners and prefer aerobic exercises, the personalized workout schedule may include a walk along a wide paved path, followed by simple low resistance strength training exercises at a set of equipment.

[0158] At 214, one or more features may be implemented while the user is performing the personalized exercises according to the generated personalized workout schedule.

[0159] The personalized workout schedule may include an active personalized guidance for presentation on a display, for instructing the user in real-time on how to perform each personalized exercise on each fitness resources while complying with the personal parameter. For example, how to use a rowing machine for low intensity exercises, or how to use a fitness structures to perform high intensity chin-ups.

[0160] The location of the mobile device may be dynamically monitored in real-time, and optionally compared to the personalized workout schedule. The GUI presented on a display of the mobile device may be updated in real-time according to the real-time location of the user (e.g., using a location sensor installed in the mobile device as a proxy), for guiding the user to the next fitness resource and / or path. The user may be provided with specific instructions, for example, turn to the left, and walk 20 meters to the sip-up bench. Or turn around, and walk 150 meters to the paved jogging path which starts next to a sign. The real-time location of the user (i.e., of the location sensor) in close proximity to the fitness resource included in the personalized workout schedule may be detected, for example, less than about 15 meters, or 10 meters, or 5 meters, and the like. The real-time location of the user in close proximity to the fitness resource may trigger a real-time presentation within the GUI presented on the mobile device, instructing the user on which personalized exercise to perform and / or how to perform the personalized exercise. The GUI may be dynamically updated in real-time according to the real-time location of the location sensor as the user moves to the subsequent fitness resource, for presenting instructions for performing the subsequent personalized exercise on the subsequent fitness resource according to the sequence of personalized exercises defined by the personalized workout schedule. Optionally, the active personalized guidance instructs the user in real-time based on an analysis of measurements of one or more physiological parameters of the user measured by one or more physiological sensors. Examples of physical parameters and physiological sensors include a heart rate sensed by a heart rate sensor, and a body temperature sensed by a temperature sensor. The active personalized guidance may be dynamically adapted in real-time, by dynamically adapting the instructions for performing the personalized exercise in real-time based on the realtime physiological measurements. For example, when the user has performed several exercise and is about to start a jog, and the heart rate is higher than a threshold, the personalized exercise may be dynamically adapted to a walk, in order to lower the heart rate. In another example, when the user is performing chin-ups and is exposed to the sun on a hot day, the number of chin-ups may be reduced when the body temperature is exceeding a threshold.

[0161] Optionally, users may record themselves (or others) performing the personalized exercises on the fitness equipment, by capturing a video or image, optionally using a camera integrated into their mobile device. The video or image may be analyzed locally by the application running on the mobile device, and / or may be centrally analyzed by a server or computing cloud after being uploaded. A real-time or post-workout feedback on the movement may be generated and presented on a display. For example, machine learning models designed for biomechanical analysis of human movement may be used to analyze the video and / or image, for identifying joint and / or muscle positions and optionally comparing the user's exercise execution to optimal performance. A visual feedback on incorrect execution may be generated, which may suggest specific posture and / or movement corrections. Improvement in performance over time may be tracked. The aforementioned features may allow users to exercise safely even without the presence of a personal trainer, may reduce risk of injury, and / or may improve the effectiveness of workouts on public equipment.

[0162] Optionally, one or more physiological parameters of the user are monitored while the user is following the personalized workout schedule. The physiological parameters are sensed by one or more physiological sensors, for example, heart rate by a heart rate sensor installed within a smartwatch, as described herein. The physiological parameters may be monitored while the user is performing the personalized exercises using the different fitness resources and / or performing aerobic exercise along the path. The physiological parameters may be analyzed to determine the user’s performance, for example, effort level exerted while performing the exercises, and / or recovery such as time taken to recover from the personalized exercises.

[0163] The history of physiological parameters of the user while following the personalized workout schedule and / or the user’s previous performance based on the analysis of the physiological parameters may be used for generation of the personalized workout schedule. For example, the history of physiological parameters and / or the user’s previous performance may be fed into the machine learning model, optionally with the previously generated personalized workout schedule, in combination with the other data, for example, as described with reference to 210 of FIG. 2. The ML model may be trained accordingly and / or designed with a suitable architecture. The feeding may trigger the ML model to adjust future personalized workout scheduled by taking into consideration the user’s physical abilities and / or physical limitations, and / or to help the user improve their physical abilities. Alternatively or additionally, other data may be fed into the ML model in combination with the other data (e.g., as described with reference to 210), which may provide for a holistic integration, for example:

[0164] • Sleep data, for example, perceived quality of sleep, amount of hours of sleep, number of times waking up during the night, snoring during sleep, diagnosis of sleep apnea, and the like. The sleep data may be collected by one or more sensors (in the smartwatch) while the user is sleeping and / or manually entered by the user such as via the GUI.

[0165] • Stress data, for example, perceived stress, diagnosis of anxiety disorder, body temperature, resting heart rate (expected to be higher during stress), perspiration indication, and the like. The stress data may be collected by one or more sensors during the day sleeping and / or manually entered by the user such as via the GUI.

[0166] Optionally, the personalized workout schedule is dynamically adjusted in real-time, such as while the user is performing the personalized exercises. The personalized workout schedule may be adjusted based on the sensed physiological parameters of the user (e.g., by sensors installed within the smartwatch). For example, intensity, duration, and / or nature of the personalized exercises may be dynamically adapted during the workout based on readings from the smartwatch. For example, if the user’s heart rate is above a threshold for longer than a time interval while jogging, the user may be instructed in real-time to switch to walking in order to reduce the heart rate.

[0167] The effectiveness of the personalized exercises of the personalized workout schedule on the user may be monitored and / or analyzed, for example, using the physiological parameters and / or other data such as videos of the user performing the personalized exercise. The personalized exercise and / or personalized workout schedule that yields the best result for individual users may be determined. The personalized workout schedule may be dynamically adapted in real-time accordingly. Alternatively or additionally, instructions based on the effectiveness and / or the identified personalized exercise and / or personalized workout schedule that yields the best result may be fed into the ML model. For example, the ML model may be associated with a large language model (LLM) which is designed to process instructions. The ML model may be fed a prompt indicating which exercises were effective and / or which were not effective, for generation of the personalized workout schedule with personalized exercises predicted to be more effective. The ML model may generate the personalized workout schedule that include a predicted ideal load level for the user and / or a gradual progression, based on physiological metrics and / or other data collected while monitoring the user performing the personalized workout schedule.

[0168] Optionally, during the monitoring of the user performing the personalized workout schedule, the app running on the mobile device and / or the GUI presented on the mobile device may automatically generate psychological interaction and / or personalized encouragement to continue the workout. For example, when the processor detects that the user is jogging on the path and slowing down, and around the comer there is only half a kilometer left, the following message may be played over speakers of the mobile device “Just a little bit around the corner and you are done, don’t slow down now!”. The user responses may be analyzed. Communication style and / or motivation may be dynamically adjusted according to the personality profile and / or previous responses of the user. For example, it may be determined that yelling at the user such “GO GO GO! Don’t slow down now! !” is discouraging for the user and makes the user slow down, while the user may respond better to more persuasive language such as “You can do it.”

[0169] At 216, feedback regarding the personalized workout schedule may be provided by the user. The feedback may be provided via the mobile device, optionally via the GUI and / or application. The feedback may include, for example, ratings on whether the personalized workout schedule was suitable for the user, and / or whether the personalized workout schedule complied with the personal parameter(s) of the user. Feedback may be provided for individual personalized exercises, such as whether each respective personal exercise was suitable for the user and / or complied with the personal parameter(s). Feedback may be provided, for example, by selection of a category from a group of categories (e.g., yes, no, was somewhat suitable), a numerical rating (e.g., on a scale of 1- 10), and / or via free text (e.g., analyzed by a large language model). For example, a user may indicate that they could not perform the full number of sit-ups that were scheduled for them, that the walk was too easy, and / or that they enjoyed using the selected fitness equipment.

[0170] At 218, the ML model may be updated, optionally dynamically, based on real-time and / or current data.

[0171] One or more of the following may be collected, optionally using the mobile device, such as via the GUI and / or application:

[0172] • Feedback from the user, for example, as described with reference to 216 of FIG. 2. • Data indicating usage of the fitness resources, for example, from an analysis of location data collected by location sensors associated with other users. The location data may be associated with personalized workout scheduled generated for other users, to determine the usability. In another example, from videos captured by users indicating themselves or others using the equipment. In another example, from feedback provided by users, for example, complaints that there were long line ups to use the fitness resources, that the users had to wait a long time to user the fitness resources, and the like.

[0173] • Progress of the user, for example, indicating whether the user is improving following the generated personalized workout schedule. Progress may be determined, for example, by analyzing physiological data of the users captured by physiological sensors (e.g., whether the heart rate is improving over time), by feedback from the user (e.g., whether the user feels they are improving or not), and / or by analyzing sequences of generated personalized workout schedules (e.g., to detect if they are changing such as increasing in difficulty), and / or by analyzing location data (e.g., to determine if the user is moving faster).

[0174] A feedback record may be generated using the collected data. The record may include, for example, the generated personalized workout schedule, and ground truth based on one or more of: the feedback provided by the user, the data indicating usage, and / or the progress.

[0175] The machine learning model may be updated using the feedback record, for example, using reinforcement learning and / or transfer learning approaches. The machine learning model may be centrally updated using feedback records provided by different users. Alternatively or additionally, personalized machine learning models may be generated for individual users, by using a baseline machine learning model which is adapted according to personal feedback records of specific users. Each user may be provided with their own customized machine learning model.

[0176] The updated machine learning model may be trained for generating personalized workout schedules predicted to be more likely to be followed by the user, and / or more likely to be associated with positive feedback by the user, and / or to improve fitness of the user.

[0177] At 220, data based on the generated personalized workout scheduled may be provided, for example, for analysis, such as by local authorities that manage the fitness resources. The data may be analyzed for determining usage of the fitness resource, for example, for identifying demand exceeding capacity indicating a potential need for additional fitness resources, and / or trends in usage of the fitness resources. The analysis may guide decision making, such as a need to install additional fitness resources where demand exceeds capacity of the existing fitness resources, a recommendation to move an existing fitness resource from a location where it is rarely used to a different location where it is predicted to be used more frequently, and for planning new installations of fitness resources such as along jogging / walking routes with high traffic.

[0178] A dataset (e.g., database) including indications of the fitness resources may be generated and / or updated. The fitness resources are mapped to geographical locations, optionally on an area map, for example, as described herein. The geo-location dataset may be used as the dataset and / or to populate the database, with additional associated data. Each fitness resource may be associated with an indication of usage, for example, whether it was included in generated personalized workout schedules. In another example, each fitness resource may be associated with an indication of usage by users according to the generated personalized workout schedules, for example, based on feedback received from the users (where the provided feedback serves as a proxy that the user used the fitness resource) and / or based on an analysis of location data of the user (where the presence of the user at the geographical location of the fitness resource serves as a proxy that the user used the fitness resource). The dataset may be analyzed for determining usage of the fitness resources for guiding decision making, as described herein.

[0179] The dataset and / or other data may be made accessible, for example, by a virtual interface, such as an API, which may be provided to local authorities according to the geographical areas they are responding for.

[0180] At 222, one or more features described with reference to 202-220 may be iterated.

[0181] Iterations may be performed, for example, for the same user for generating different personalized workout schedules, such as at different points in time (e.g., a different workout every day, or every 3 days), and / or at different places. In another example, iterations may be performed for different users, and / or for groups of users.

[0182] Different features may be updated dynamically, such as in the background, continuously, in response to triggering events, and / or during iterations. For example, the ML model and / or the geo-locations location may be updated as described herein.

[0183] Resource database (e.g., the geo-location dataset) update frequency may help maintain system reliability. High-traffic facilities may be validated, for example, at least monthly. Less-used resources may be updated less frequency, for example, quarterly. User-reported changes may trigger verification workflows within 48 hours to maintain data integrity.

[0184] Referring now back to FIG. 3, features and / or components described with reference to FIG. 3 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIG. 1.

[0185] Host system 302 may be implemented as a client terminal. Host system 302 includes a mobile application 3O8A. Host system 302 may include a frontend UI / UX 320, optionally a GUI, presented on a user interface such as a touch screen. Host system 302 may include a backend API 372 for communicating with the computing environment, optionally cloud services 304. Host system 302 may include local storage 360, for example, for hosting application 3O8A, offline maps, generated fitness plans, and / or other data as described herein.

[0186] Cloud services 304 may include a user dataset 304A, a resource dataset 304B, and / or an AI / ML engine 314A.

[0187] Host system 302 may be in communication with one or more device components 350, which may be installed thereon and / or may be external components. Device components 350 may include a GPS module 350A, a sensor interface 350B, and / or a notification system 350C.

[0188] Additional exemplary details of one or more components are now provided:

[0189] Frontend UI / UX 320: Designed to provide the user interface (e.g., user interface 120 of FIG. 1) through which users interact with the system. May include a GUI designed, for example, for user profile creation, workout planning, resource discovery, progress tracking, and / or social interaction. The presentation presented within the GUI may adapt based on user preferences and / or fitness level, showing appropriate difficulty options and / or relevant resources.

[0190] Backend API 372: designed to serve as the communication layer between the frontend and various backend services. May handles authentication, data validation, request routing, and / or response formatting. The API may be designed with RESTful principles for seamless integration with mobile clients and / or third-party services.

[0191] Local storage 360: caches frequently accessed data on the device, for example, user preferences, recent workouts, and / or nearby resource information. This may enable offline functionality and / or may reduce server load while improving response times.

[0192] User database 304 A: may be set for storing comprehensive user profiles, for example, demographic information, fitness assessments, workout history, goals, preferences, and / or social connections. The data stored in the user database may be securely stored and / or accessed using industry-standard encryption and / or authentication protocols.

[0193] Resource dataset 304B: may host detailed information about public fitness resources, for example, geographic coordinates, equipment types, specifications, attributes (e.g., difficulty level, muscle groups targeted), availability patterns, and / or user-generated metadata such as ratings and / or comments. Different approaches may be implemented for populating and / or updating the resource database, for example:

[0194] Professional Surveying: System administrators may physically document and catalog public resources. • Crowdsourced Data: Users may contribute information about undocumented resources or updates to existing records.

[0195] • Municipal Data Integration: Direct data feeds from city planning and parks departments.

[0196] • Computer Vision Analysis: Automated identification of potential fitness resources from satellite imagery and street view data.

[0197] • User Image Recognition: Users can photograph public resources through the application, and the system may use computer vision processes to automatically identify, classify, and characterize the photographed equipment and resources. Users can verify or correct the automatic identification, thereby contributing to improving the model's accuracy.

[0198] AI / ML engine 314A: may be the core intelligence component that processes user and / or resource data to generate personalized recommendations. Various machine learning models may be used, for example, for user classification, resource matching, difficulty assessment, and / or progress prediction. The engine may continuously improves its recommendations based on user feedback and outcomes.

[0199] GPS module 350A: may interface with the device's location services to determine the user's position accurately. May enables discovery of nearby resources, workout tracking, and / or route planning for activities like running and / or cycling.

[0200] Sensors interface 350B: may connect with various device sensors (e.g., accelerometer, gyroscope, heart rate monitor) and / or external wearable devices to gather physical activity data. The physical activity data may enrich the user profile and / or may enable more accurate workout guidance and / or progress tracking.

[0201] Notification system 350C: may manage user engagement through, for example, timely alerts, reminders, and / or motivational messages. May incorporate behavioral science principles to encourage consistent workout habits and / or may utilize geo-fencing to provide context-aware notifications when users are near relevant resources.

[0202] Referring now back to FIG. 4, features and / or components described with reference to FIG. 4 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIG. 1 and / or FIG. 3. For example, core system (host system) 404 may refer to computing environment 104 of FIG. 1.

[0203] Users 408 use core system 404 as described herein. Users include individual users 482 and / or groups 484. Individual users 482 may be the primary consumers of system 404. Users 482 may range from fitness beginners to advanced athletes, each with unique fitness levels, goals, preferences, and constraints. System 404 provides personalized guidance to these users 482 based on their profiles and / or available fitness resources, as described herein. User groups 484 represent collections of individual users who share fitness interests, goals, and / or social connections. System 404 may facilitate group activities by identifying suitable public resources for collective workouts and / or coordinating scheduling among group members.

[0204] Physical facilities 486 may include all public fitness resources 480 such as outdoor gyms, walking / running / cycling paths, staircases, and / or other infrastructure that can be utilized for physical activity. Each facility may be characterized by its location, available equipment, specifications, and / or suitability for various fitness activities.

[0205] Municipal authorities 488 may be governmental entities responsible for public spaces and / or facilities. Municipal authorities 488 may provide and / or maintain the physical facilities 486 that system 404 leverages. System 404 may offers municipal authorities 488 valuable data insights about resource utilization, helping inform future infrastructure investments and improvements.

[0206] Third-party services 412, including health and fitness platforms 490 may integrate with system 404 through APIs to exchange data, for enhancing the user experience. For example, platforms like wearable device ecosystems, nutrition tracking applications, and comprehensive health management systems.

[0207] Data analytics services 492 may process aggregated, anonymized data from system 404 to generate insights about public resource utilization, fitness trends, and / or user behavior patterns. These insights may benefit municipal authorities 488 for infrastructure planning and / or system 404 for feature enhancement.

[0208] Referring now back to FIG. 5, features described with reference to FIG. 5 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIGs. 1-2 and / or other FIGs described herein. For example, the system may refer to computing environment 104 of FIG. 1, and / or to the application running on the mobile device of the user.

[0209] FIG. 5 may depict system operations including technical processes that enable the core functionality of matching users with appropriate public fitness resources.

[0210] At 502, the method starts.

[0211] At 504, when a user first joins the system, a personal profile may be created through a combination of explicit user input (e.g., age, fitness goals, experience level, preferences) and / or initial fitness assessment tests. The system may suggest simple exercises that the user can perform to establish baseline metrics for strength, endurance, flexibility, and / or cardiovascular fitness.

[0212] At 506, the resource database may be continuously updated through multiple channels, for example,: (a) systematic surveys conducted by system administrators, (b) municipal authority data feeds, (c) user-generated content including photos, descriptions, and ratings, and (d) automated analysis of satellite imagery and map data to identify potential fitness resources not yet cataloged.

[0213] At 508, when a user opens the application, the system may use GPS (or other location) data to identify their location and query the resource database for nearby fitness facilities. This discovery process may apply spatial filtering processes that consider not only proximity but also accessibility factors such as elevation changes, traffic patterns, and operating hours.

[0214] At 510, the core matching engine may evaluate the suitability of each discovered resource for the specific user by analyzing multiple dimensions, for example: (a) alignment with user's fitness goals, (b) appropriate difficulty level based on user's current capabilities, (c) compatibility with user preferences, and (d) historical engagement patterns with similar resources.

[0215] At 512, based on the matched resources, the system generates a personalized training plan that optimally utilizes available public facilities. The plan may incorporates exercise science principles such as progressive overload, periodization, and / or balanced muscle group targeting while considering practical constraints like weather conditions, time availability, and facility crowding patterns.

[0216] At 514, during workout execution, the system may track user activity through device sensors and / or manual logging. This monitoring may capture performance metrics, completion rates, and perceived exertion levels. For certain activities like running or cycling, the system may record detailed GPS tracks and / or performance data.

[0217] In addition to standard metrics, the system may monitor the quality of exercise execution through video analysis. Users may record themselves performing exercises, and the system may analyze the movement, identify technical errors, and / or suggest corrections specifically tailored to the user. The biomechanical analysis may improve exercise efficiency and / or may reduce the risk of injuries when using public facilities that lack professional guidance.

[0218] At 516, after each workout, the system may collect explicit feedback (e.g., user ratings, comments) and / or implicit feedback (e.g., performance data, engagement patterns). This feedback may be used to update the user profile and / or refine the matching processes through machine learning techniques, including reinforcement learning and / or collaborative filtering.

[0219] At 518, the adapted system is provided for the next user and / or for the next personalized workout schedule.

[0220] Referring now back to FIG. 6, features described with reference to FIG. 6 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIGs. 1-2 and / or other FIGs described herein. For example, the system may refer to computing environment 104 of FIG. 1, and / or to the application running on the mobile device of the user.

[0221] FIG. 6 may depict user interaction flow indicating how users engage with the system to achieve their fitness goals using public resources.

[0222] At 602, the user initiates the application, which automatically determines their location and may automatically retrieves their profile information. The system checks for any scheduled workouts, previously saved routes, and / or recommendations based on the user's routine and current location.

[0223] At 604, the user is presented with a map or list view of nearby public fitness resources, which may be categorized by type (e.g., outdoor gyms, running paths, staircases, etc.) and / or may be highlighted based on relevance to the personalized profile of the user. The interface may provide filtering options, for example, based on distance, type of equipment, difficulty level, and other parameters.

[0224] At 606, when selecting a specific resource, the user may access detailed information including: equipment specifications, suitable exercises, difficulty ratings, user reviews, typical usage patterns (crowding times), photos, and workout suggestions specific to that resource. For path-based resources like running trails, elevation profiles and surface conditions may be provided.

[0225] At 608, the system generates and presents a personalized workout plan that leverages available resources based on the user's profile, goals, and current location. This plan includes a structured sequence of exercises, suggested repetitions / durations, rest periods, and / or navigation guidance between different resources when the workout incorporates multiple locations.

[0226] At 610, the user may make a decision to accept and follow the recommended plan 612 or customize the plan 614 according to their preferences. Customization options include, for example, adjusting difficulty levels, focusing on specific muscle groups, changing the duration, and / or selecting alternative resources from those available nearby.

[0227] At 616, during workout execution, the application may provide step-by-step guidance, including instructions on how to properly use each piece of equipment, form guidance, timing functions, and motivational prompts. For running or cycling activities, real-time navigation and performance metrics may be displayed.

[0228] At 618, upon workout completion, the user confirms the activities performed and / or may provide feedback on the experience. This includes, for example, rating the workout overall, specific resources used, and / or reporting any issues with facilities. The system may also automatically capture performance metrics from device sensors and / or connected wearables. At 620, the user may access their fitness journey visualization, showing progress toward goals, performance improvements over time, and comparative analytics. The system may provide insights based on the collected data and / or may suggest adjustments to future workouts to optimize results.

[0229] Referring now back to FIG. 7, features described with reference to FIG. 7 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIGs. 1-2 and / or other FIGs described herein.

[0230] Referring now back to FIG. 7, exemplary components, optionally implemented as code stored on a data storage device executable by a processor, include one or more of:

[0231] * A user profiling component 704 designed to generated and / or access a user profile of a user including one or more personal parameters of the user.

[0232] * A resource matching component 706 designed to identify the fitness equipment most suitable for the user based on the personal parameters.

[0233] * A training plan generation component 708 designed to generate a personalized workout schedule for the user.

[0234] * A user interface 710 designed to enable the user to provide input and / or view output.

[0235] * A resource mapping component 712 designed to locate fitness equipment on a geographical area map.

[0236] * A progress tracking component 714 designed to track progress of the user following the generated training plans.

[0237] Referring now back to FIG. 8, features described with reference to FIG. 8 may correspond to, and / or be implemented by, and / or may be combined with, features and / or components described with reference to FIGs. 1-2 and / or other FIGs described herein.

[0238] Exemplary components described with reference to FIG. 8, optionally implemented as code stored on a data storage device executable by a processor, include one or more of:

[0239] * A user profiling component 804 designed to generated and / or access a user profile of a user including one or more personal parameters of the user. The user profile component 804 is operated for each user of a group of users.

[0240] * A group matching component 806 designed to identify the fitness equipment most suitable for the group of users as a whole, based on the personal parameters that are common to the group of users.

[0241] * A community activity scheduler component 808 designed to generate a personalized workout schedule for the group. The schedule may include workouts that can be performed as a group, for example, a group run along a jogging trail. The schedule may include a schedule for the members of the group to perform certain workouts that need to be performed individually, for example, using a certain piece of equipment. The members of the group may be scheduled sequentially. Members that are not currently using the piece of equipment may be recommended other exercises and / or other equipment.

[0242] * A user interface 810 designed to enable the users to provide input and / or view output.

[0243] * A resource mapping component 812 designed to locate fitness equipment on a geographical area map.

[0244] * A social networking component 814 designed to link the personalized workout schedule for the group to a social network, for example, to automatically post the personalized workout schedule on a social network page of the group, enable users to post videos and / or images captured during the workout session to the social network page, and the like.

[0245] The descriptions of the various embodiments of the present invention have been presented for purposes of illustration, but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

[0246] It is expected that during the life of a patent maturing from this application many relevant machine learning models will be developed and the scope of the term machine learning model is intended to include all such new technologies a priori.

[0247] As used herein the term “about” refers to ± 10 %.

[0248] The terms "comprises", "comprising", "includes", "including", “having” and their conjugates mean "including but not limited to". This term encompasses the terms "consisting of" and "consisting essentially of".

[0249] The phrase "consisting essentially of" means that the composition or method may include additional ingredients and / or steps, but only if the additional ingredients and / or steps do not materially alter the basic and novel characteristics of the claimed composition or method.

[0250] As used herein, the singular form "a", "an" and "the" include plural references unless the context clearly dictates otherwise. For example, the term "a compound" or "at least one compound" may include a plurality of compounds, including mixtures thereof.

[0251] The word “exemplary” is used herein to mean “serving as an example, instance or illustration”. Any embodiment described as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments and / or to exclude the incorporation of features from other embodiments.

[0252] The word “optionally” is used herein to mean “is provided in some embodiments and not provided in other embodiments”. Any particular embodiment of the invention may include a plurality of “optional” features unless such features conflict.

[0253] Throughout this application, various embodiments of this invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0254] Whenever a numerical range is indicated herein, it is meant to include any cited numeral (fractional or integral) within the indicated range. The phrases “ranging / ranges between” a first indicate number and a second indicate number and “ranging / ranges from” a first indicate number “to” a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numerals therebetween.

[0255] It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination or as suitable in any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements.

[0256] Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims.

[0257] It is the intent of the applicant(s) that all publications, patents and patent applications referred to in this specification are to be incorporated in their entirety by reference into the specification, as if each individual publication, patent or patent application was specifically and individually noted when referenced that it is to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting. In addition, any priority document(s) of this application is / are hereby incorporated herein by reference in its / their entirety.

Claims

WHAT IS CLAIMED IS:

1. A computer implemented method of automatic generation of a personalized workout schedule, comprising: accessing a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise; feeding into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user; and generating by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

2. The computer implemented method of claim 1, wherein the terrain map includes at least one of: indication of stairs, type of path including paved and unpaved, obstacles along the path, and exposure to environment elements along the path.

3. The computer implemented method of claim 1, wherein the personalized workout schedule comprises a sequence of exercises to perform at a sequence of different fitness resources located at different geographical locations, the sequence of exercises including the route for performing aerobic exercise, wherein the sequence of exercises is selected according to geographical locations of the fitness resources and the route.

4. The computer implemented method of claim 1, wherein the personalized workout schedule includes an active personalized guidance for presentation on a display, for instructing the user in real-time on how to perform each personalized exercise on each fitness resources while complying with the at least one personal parameter.

5. The computer implemented method of claim 4, wherein the active personalized guidance is dynamically adapted in real-time by dynamically adapting the instructions for performing thepersonalized exercises based on an analysis of measurements of at least one physiological parameter of the user measured by at least one physiological sensor.

6. The computer implemented method of claim 1, wherein instructions for performing the personalized exercises to be performed on each fitness resources are dynamically presented on a display of the mobile device according to a real-time geographical location of the location sensor in proximity to a fitness resource for which a personalized exercise to be performed is included in the personalized workout schedule, wherein the instructions for performing a subsequent personalized exercise are dynamically updated as the mobile device is moved in proximity to a subsequent fitness resource according to a sequence of personalized exercises performed on fitness resources defined by the personalized workout schedule.

7. The computer implemented method of claim 1, wherein the personalized workout schedule for the user is further generated according to current and future predicted availability of the plurality of fitness resources and / or of the routes, computed according to a schedule generated based on personalized workout schedules generated for other users and / or according to real-time and / or predicted geographical locations of the other users.

8. The computer implemented method of claim 6, wherein the schedule is generated by a scheduling process fed the personalized workout schedules generated for other users, trained for optimizing usage of the plurality of fitness resources by users.

9. The computer implemented method of claim 1, wherein the machine learning model is trained on a training dataset of a plurality of records, wherein a record includes a combination of at least one resources parameter for each of a plurality of sample fitness resources within a defined region, a terrain map of the defined region, a plurality of personal parameters of a sample user, and a ground truth of a sample personalized workout schedule for the sample user.

10. The computer implemented method of claim 1, wherein the at least one resources parameter is selected from: type of possible activity, difficulty level, activated muscle groups.

11. The computer implemented method of claim 1 , wherein the at least one personal parameter of the user is selected from: fitness level, training goals, physical limitations, personal preferences, and historical training using at least one fitness resources.

12. The computer implemented method of claim 1, further comprising: collecting data using the mobile device, including at least one of: feedback from the user, data indicating usage of the plurality of fitness resources, and progress of the user; generating a feedback record using the collected data; and updating the machine learning model using the feedback record for generating personalized workout schedules predicted to at least one of: more likely to be followed by the user, associated with positive feedback by the user, and improve fitness of the user.

13. The computer implemented method of claim 1, wherein the at least one resources parameter is automatically generated for a fitness resources by at least one of: feeding an image of the fitness resources into a classifier trained on a training dataset of images of sample fitness resources and a ground truth of sample resources parameters, extracted by a large language model fed a text description of the fitness resources, and based on an analysis of historical usage and / or feedback by users using the fitness resources.

14. The computer implemented method of claim 1, further comprising: generating a dataset comprising the plurality of fitness resources, each fitness resources associated with an indication of inclusion in generated personalized workout schedules and / or with an indication of usage by users according to the generated personalized workout schedules; and analyzing the dataset for identifying at least one of: demand exceeding capacity indicating a potential need for additional fitness resources, and trends in usage of the fitness resources.

15. The computer implemented method of claim 1, wherein the plurality of fitness resources are of a plurality of different types and / or of a plurality of different manufacturers.

16. The computer implemented method of claim 1, wherein the plurality of fitness resources further include strength training equipment.

17. The computer implemented method of claim 1, further comprising dynamically generating and / or updating the geo-location dataset, by locating the plurality of fitness resources on an area map.

18. The computer implemented method of claim 1, wherein the combination fed into the machine learning model includes the at least one personal parameter of each of a plurality of users, wherein the personalized workout schedule is for a subset of the plurality of users with similar personal parameters for a joint workout.

19. The computer implemented method of claim 1, wherein at least one of the following are fed into the machine learning model along with the combination: physiological parameters of the user while following a previously generated personalized workout schedule, the user’s previous performance based on the analysis of the physiological parameters, and the previously generated personalized workout schedule.

20. The computer implemented method of claim 19, wherein the personalized workout schedule is generated for meeting a predicted load level for the user and / or predicted to provide an improvement in the user’s performance.

21. A system for automatic generation of a personalized workout schedule, comprising: at least one processor executing a code for: accessing a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, , and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise; feeding into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user; and generating by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

22. A non-transitory medium storing program instructions for automatic generation of a personalized workout schedule, which when executed by at least one processor, cause the at least one processor to:access a geo-location dataset according to a geographical location of a mobile device of a user obtained from a location sensor, for obtaining a plurality of fitness resources located in proximity to the geographical location, , and for obtaining a terrain map in proximity to the geographical location, the terrain map indicating elevation and / or terrain features including paths suitable for aerobic exercise; feed into a machine learning model, a combination of at least one resources parameter of each of the plurality of fitness resources located in proximity to the geographical location, the terrain map, and at least one personal parameter of the user; and generate by the machine learning model, the personalized workout schedule for the user comprising personalized exercises for performing using a combination of the plurality of fitness resources and a route for performing aerobic exercise along the paths of the terrain map, the personalized workout schedule complying with the at least one personal parameter.

Images