METHOD FOR PRODUCING, ORGANIZED AND DISTRIBUTING GEOREFERENCED DIGITAL CONTENT ON THE GO, AND RELATED METHOD FOR DEVELOPING CONTEXTUAL MULTIMEDIA GUIDES, THROUGH THE USE OF ARTIFICIAL INTELLIGENCE AND THE USE OF GEOLOCATED DIGITAL AND / OR VIRTUAL MAPS

Description

“Method for producing, organizing and distributing georeferenced digital content on the move, and related method for developing contextual multimedia guides, through the use of artificial intelligence and the use of geolocalized digital and / or virtual maps DESCRIPTION TECHNOLOGICAL BACKGROUND OF THE INVENTION Scope of application. The present invention relates in general to the technical field of the production, organization and distribution of georeferenced digital content on the move, carried out by electronic processing. The present invention also relates to the development of contextual multimedia guides using artificial intelligence and geolocalized digital maps, in particular to the development of contextual multimedia tourist guides, generated by Artificial Intelligence based on parameters such as the user's position, direction, and speed, and the recognition of visual and informative elements present in virtual maps and geolocalized historical or project reconstructions. Description of the known art. The field of digital tourist guides is an application enabled by the spread of mobile devices equipped with GPS or other georeferencing systems, from navigators to smartphones, tablets, and "smart glasses." The sectors with the greatest use are tourism and cultural heritage, but there are also contextual applications linked to the fields of marketing, services, building and construction, transport or others. The state of the art includes solutions that allow content to be delivered to users according to fairly basic logic, linked to points of interest located in the territory or on a map or according to sequential itineraries, without a specific methodology dedicated to the production, organization and distribution of the content. On the other hand, computer vision-based tour guide systems are becoming increasingly popular. While they can recognize monuments, they do not take into account relevant factors such as the user's speed of movement, the scale of importance of the points of interest present, or the availability of reconstructions of the past and future of the surrounding environment. Therefore, these needs remain unmet and the aforementioned technical problems remain unsolved. Among the various technical problems not resolved by existing solutions, one can also mention the issue of paying attention to the ergonomic and safety aspects of a moving user, whether pedestrian, on two or four wheels: the moving user needs to engage their sight in monitoring the environment, without distracting them from driving or the route with written messages, visuals, or interactive touch, graphic, or gestural interfaces. Furthermore, it is critical to develop low-cost, dynamically adaptable content production and management systems dedicated to the production of content specifically intended for mobile distribution. Although generative AI models have recently emerged, potentially capable of producing relevant content, and although immersive geolocalized maps (e.g., Google “Street View®,” virtual tours, or 3D reconstructions) have long been known, such general technical innovations are currently poorly considered in the production, organization, and distribution of georeferenced digital content on the move, and in the development of contextual multimedia guides. In this regard, there is a particularly pressing need to resolve the technical problems outlined above and, more generally, to develop effective, flexible, and reliable methods for producing, organizing, and distributing georeferenced digital content on the move, as well as for developing contextual multimedia guides. These needs, as illustrated above, are not fully satisfied by the known solutions available today. SUMMARY OF THE INVENTION The purpose of the present invention is to provide a method for producing, organizing, and distributing georeferenced digital content on the move, performed through electronic processing, which allows at least partially obviating the drawbacks noted above with reference to the prior art, and meeting the aforementioned needs particularly felt in the technical sector under consideration. This purpose is achieved through a method in accordance with claim 1. Further embodiments of this method are defined in claims 2-16. It is also an object of the present invention to provide a method for developing contextual multimedia guides, using the above method. This object is achieved by a method according to claim 17. It is also an object of the present invention to provide a corresponding electronic processing system capable of carrying out the aforementioned methods. This object is achieved by a system according to claim 18. Further embodiments of such a system are defined in claims 19-25. BRIEF DESCRIPTION OF THE DRAWINGS Further features and advantages of the method and system according to the invention will emerge from the following description of preferred embodiments, given for illustrative and non-limiting purposes, with reference to the attached figures, in which: - Figure 1 is a diagram representing in simplified form the method of the invention, according to one embodiment, illustrating in particular interactions between a user's mobile device and an immersive map; - Figure 2 is a simplified schematic representation of the main components of a platform included in an embodiment of the system according to the invention, capable of carrying out the aforementioned method. DETAILED DESCRIPTION. A method for producing, organizing, and distributing georeferenced digital content on the move is described. The method is implemented using computer processing. The method first involves preparing or accessing at least one geolocalized digital map, capable of providing a three-dimensional visual model, and / or including other multimedia digital content, of each of a plurality of points of interest present in a geographical area covered by the geolocalized digital map. The method further comprises the step of obtaining or determining geolocation data of a user, including at least one location of the user and information relating to the user's movement. The method further comprises the step of determining, based on the aforementioned user geolocation data, a digital point of view of the user, within the geolocalized digital map, representative of a real point of view of the user in real space, dynamically variable depending on the user's movement. This digital viewpoint is associated with at least one of the aforementioned three-dimensional models present in the geolocalized digital map, corresponding to points of interest visible from the user's real point of view. The method then provides for generating, using artificial intelligence, and / or extracting from the geolocalized digital map, digital data of points of interest, including at least one three-dimensional visual model and / or other multimedia digital content relating to at least one of the aforementioned points of interest associated with the user's digital point of view. Such digital point-of-interest data is dynamically variable depending on the user's movement. The method finally includes the phase of organizing and providing the user, through a digital display interface of a mobile device, the aforementioned digital data of points of interest, dynamically variable, generated and / or obtained, associated with the user's digital point of view. According to one embodiment of the method, the aforementioned step of preparing or accessing a geolocalized digital map comprises preparing or accessing an immersive geolocalized digital map and / or a virtual geolocalized digital map corresponding to a “digital twin” of what is located in a geographic area represented by the “digital twin”. According to one embodiment of the method, the above step of obtaining or determining geolocation data of a user comprises obtaining or determining geolocation data comprising a location of the user, a direction of movement of the user, and a speed of the user. According to one implementation option of such an embodiment, the aforementioned step of determining a digital viewpoint of the user comprises determining the digital viewpoint of the user in a dynamically variable manner, based on the user's position, direction of movement, and speed of the user. According to one embodiment of the method, the aforementioned step of generating and / or deriving digital point of interest data comprises deriving the digital point of interest data from the geolocated digital map. According to one embodiment of the method, the aforementioned step of generating and / or deriving digital point of interest data comprises generating digital data, by means of a trained artificial intelligence model. According to one embodiment of the method, the aforementioned step of organizing and providing the user with digital point-of-interest data comprises generating and / or organizing and / or managing and / or distributing digital content optimized based on the user's movement / mobility, delivering the data based on the dynamically varying digital point of view corresponding to the user's actual point of view. According to an implementation option of this embodiment, the aforementioned phase of generating and / or organizing and / or managing and / or distributing digital content optimized based on the user's movement / mobility is carried out using an algorithm for defining "moving content", which establishes criteria for the production and distribution of content optimized for mobility and personalized to the user. According to one implementation option of this embodiment, the method comprises the further step of producing and disseminating digital content in relation to the position, direction, and speed of the user. Further exemplifying the aforementioned implementation option, text generation is governed by the aforementioned algorithm for defining moving content in relation to the user's speed. If you are driving or cycling through a city or valley, and therefore the presence of a point of interest within the user's sight and attention is relatively brief, the texts can be generated to be much shorter than those produced for a user who is walking along the same route, and therefore travelling more slowly. If the speed is high, the method will appropriately provide only texts relating to the highest scale of importance, for example the general description of the landscape, the city or the valley, with possible brief references to the square. However, if the speed is low, the method appropriately delivers content even for more specific details corresponding to a lower scale of importance, for example the buildings present. If the speed becomes zero, with the user stationary, the method involves proceeding with more in-depth levels and therefore long and detailed texts. According to another implementation option of this embodiment, the method comprises the further step of producing and disseminating digital content based on interests indicated by the user, using a trained artificial intelligence model. According to some possible implementation options of this embodiment, the organization of the AI-generated content is hierarchical, and / or the organization of the AI-generated content takes into account a predefined scale of geographical importance, and / or the organization of the AI-generated content is multilingual, and / or the organization of the AI-generated content is such as to adapt to different narrative registers or presentation registers, dependent on the user. For example, the method provides information in a way that depends on the user's age and / or cultural level and / or cultural tradition. According to an implementation example, the model is trained to describe a church differently if the user is Western and of Christian tradition, compared to a Middle Eastern user of Islamic tradition. In the former case, the functions of the various parts of a church can be taken for granted; in the latter, it is appropriate to distinguish and describe, for example, the function of a bell tower versus a minaret. Similarly, it will not be necessary to detail the meaning of a saint or patron saint—the name given to the church—for Western users, while it is appropriate not to take this for granted for Islamic users. As can easily be imagined, a conceptually similar but dual approach to the previous one is applied to the description of a mosque. According to an implementation example, the model is trained to illustrate a point of interest with a different narrative register if the user is a child than the narrative register used for an adult. With reference to the aforementioned organization of contents depending on a predefined scale of importance, it consists, in an implementation example, in a management of the hierarchy, in terms of "scale of importance" code, of the points of interest detected in the context (for example, according to a hierarchy / scale of geographical importance: city-square-building-portal). In accordance with one embodiment of the method, the aforementioned digital point of interest data comprises data descriptive of the present appearance of one or more points of interest, or of all points of interest visible from the user's point of view. In accordance with one embodiment of the method, the aforementioned digital point-of-interest data comprises descriptive data of the past appearance of one or more points of interest, or of all points of interest visible from the user's point of view, at a given epoch, based on reconstructions of geolocalized computer graphics images referring to the aforementioned epoch. In accordance with one embodiment of the method, the aforementioned digital point-of-interest data comprises descriptive data of the future appearance of one or more points of interest, or of all points of interest visible from the user's point of view, based on renderings or digital reconstructions associated with a project relating to an area surrounding the user's point of view. According to one embodiment, the method provides for a two-way interaction between a user's mobile device and the aforementioned at least one geolocalized digital map. In this case, the method comprises the additional steps of: - transmit to electronic processing means, in which the aforementioned at least one geolocalized digital map is implemented, by the user's mobile device, the aforementioned information relating to the user's position, direction and speed; - obtain in at least one geolocalized digital map a visual recognition, for example through Computer Vision, of images and points of interest present in the user's digital point of view, by means of electronic processing; - extract from at least one geolocalized digital map information relating to the elements recognized as present in the user's digital point of view; - create descriptive content, based on the aforementioned information obtained, by said electronic processing means using artificial intelligence techniques; - transmit the aforementioned descriptive content created to the user's mobile device, in one or more multimedia formats: audio commentary, text card, images, videos, 3D formats. It should be noted that the aforementioned embodiment allows for the best use of the optional presence of a "computer vision" device available to the user, it being understood that the method of the present invention, in its most general definition and in other embodiments, can be carried out in the absence and regardless of "computer vision" functions (for example, it can also be used by a user who keeps the smartphone in his pocket, without using a camera, and with transmission of information to the user via audio). In the embodiment considered here, in which the user wears, for example, a “smart glass” device or uses a device equipped with a camera and connected to an AI Computer Vision model, information can also be advantageously acquired from the direct recognition of monuments or places. Even in this case, the use of the aforementioned mobile content delivery algorithm remains valid and appropriate, which, for example, manages the length of texts and audio clips in relation to the user's speed, but also in relation to the aforementioned management of the hierarchy of points of interest (for example, city-square-palace-portal) and the generation of the related descriptive texts. Furthermore, even when current monuments are recognized directly by computer vision, the method, according to an implementation option, stands out for its correlation and description with reconstructions of the environment's past or future, which are obviously not visible to the camera framing the present, but only from a parallel virtual environment. In the case of reconstructions of the past and future, the method provides the user with not only textual descriptions but also images of the reconstructions. Therefore, in the aforementioned embodiment, computer vision from a camera in the real environment constitutes an alternative and / or additional source of data relating to the surrounding environment, compared to presence detection from a digital or virtual map, particularly through the recognition of buildings or other present elements. Even in this case, the algorithm for defining moving content retains its role in generating and organizing content with respect to speed, importance scale, and other criteria described. In one embodiment, the method involves delivering content in simulated exercise courses. The algorithm that manages the delivery of moving content, in fact, can be applied not only to the physical movement of people in reality but also to the simulation of movement created with exercise equipment (for example, treadmills, exercise bikes, and rowing machines, synchronized with virtual worlds), as envisaged in this embodiment. In these cases, the direction and sense of travel are normally constrained (one always moves forward along a linear path), but the content can be generated, organized, and delivered taking into account other elements: position, distances, points of view, speed, and pauses, but also the type of locomotion. In virtual simulations, the visual representation (video, 360° video, 3D, virtual tour) is separated and desynchronized from the description (written or vocal) to accommodate changes in speed and pauses. For example, a user can walk or run on a treadmill or pedal an exercise bike at different speeds. Thanks to a monitor or a virtual reality headset and a sensor, their physical movement triggers the visualization of a natural or urban path. A contextual description, such as an audio guide, is also activated, applying the rules of the moving content delivery algorithm. The descriptions therefore concern the position and point of view in the virtual world represented, but they change depending on the speed at which the exercise equipment is operated. Walking, running, and pauses determine the length of the descriptive texts and audio. Pauses, for example, trigger longer in-depth analyses, which are incompatible with the speed of running. Training the AI ​​model to generate motion content will need to take into account the different motor experiences associated with exercise equipment: walking (treadmill), cycling (exercise bike), and canoeing (rowing machine). The descriptive model will also take into account the perspective, which, for example, differs on a bike path versus a navigable body of water. A method for developing contextual multimedia guides, also included in the present invention, is illustrated below. This method first of all provides a method for producing, organizing and distributing georeferenced digital content on the move, according to any of the previously illustrated embodiments, to obtain digital data of a plurality of points of interest, associated with a plurality of digital viewpoints of the user, dynamically variable as a function of the user's movement. The method then involves generating the aforementioned contextual multimedia guides using artificial intelligence, based on the user's position, direction, and speed parameters and the recognition of visual and informative elements present in immersive digital and / or geolocalized virtual maps. A system for producing, organizing and distributing georeferenced digital content on the move, according to the present invention, is described below. This system comprises a user's mobile device equipped with geolocation sensors and electronic processing means, operationally connected to the user's mobile device. The aforementioned electronic processing means include: - at least one virtual reality and / or immersive map software application, associated with at least one geolocalized digital map, configured to provide a visual three-dimensional model, and / or including other multimedia digital content, of each of a plurality of points of interest present in a geographic area covered by the geolocalized digital map; - a software application or program capable of implementing an infomobility algorithm, configured to obtain and / or determine and / or interpret a user's geolocation data, including at least one user position and information relating to the user's movement, and to determine, based on such user geolocation data, a digital viewpoint of the user, within the geolocalized digital map, representative of a real viewpoint of the user in real space, dynamically variable depending on the user's movement; said digital viewpoint is associated with at least one of the three-dimensional models present in the geolocalized digital map, corresponding to points of interest visible from the user's real viewpoint; - a trained artificial intelligence model capable of generating digital point-of-interest data, comprising at least one three-dimensional visual model and / or other multimedia digital content relating to at least one of the points of interest associated with the user's digital point of view; said digital point-of-interest data is dynamically variable depending on the user's movement. The aforementioned trained artificial intelligence model is also capable of organizing and providing the user, through a digital display interface of the user's mobile device, dynamically variable, generated and / or derived digital point-of-interest data associated with the user's digital point of view. According to one embodiment of the system, the aforementioned electronic processing means comprise, or consist of, a cloud software platform. According to one embodiment of the system, the aforementioned at least one virtual reality software application comprises an immersive geolocalized digital map and / or a virtual geolocalized digital map corresponding to a “digital twin” of what is located in a geographic area represented by the “digital twin”. According to an implementation option of the system, the aforementioned at least one virtual reality software application is configured to display current digital reproductions of the one or more points of interest or of the surrounding environment, in the present, and / or descriptive data of the past appearance of the one or more points of interest, at a given time, based on reconstructions of geolocalized computer graphics images referring to that time, and / or descriptive data of the future appearance of the one or more points of interest, based on renderings or digital reconstructions associated with a project referring to an area surrounding the user's point of view. In accordance with one embodiment of the system, the user's mobile device is further equipped with direction and / or speed and / or motion sensors. According to one embodiment of the system, the user's mobile device is further equipped with at least one camera for visual recognition, and is configured to transmit information relating to the user's position, direction and speed to the electronic processing means. In this embodiment, the electronic processing means are further configured to perform the following actions: - perform visual recognition, using Computer Vision, of images and points of interest present in the user's digital point of view; - extract from at least one geolocalized digital map information relating to the elements recognized as present in the user's digital point of view; - create descriptive content, based on the information obtained, through artificial intelligence techniques; - transmit the aforementioned descriptive content created to the user's mobile device. According to one embodiment of the system, the trained AI model is able to generate and disseminate digital content in real time, based on data input by the user or from relevant sources, based on interests indicated by the user, and / or with hierarchical organization, and / or taking into account a predefined scale of geographical relevance, and / or through multilingual organization of content and / or through different narrative registers or presentation registers, dependent on the user. In accordance with several possible embodiments, the system is configured to perform a method according to any of the previously described method embodiments. Further detailed examples of application of the method according to the invention are described below, by way of example and not by way of limitation, with reference to figures 1-2. As already illustrated above, the method involves the introduction of a new cartographic and ergonomic concept, the “Point of View”, which is different from the “Point of Interest” which traditionally corresponds to an element located exactly at the geographical coordinates where a physical entity is located. The “Point of view” instead indicates the geographical position, both punctual and areal, where a specific content is to be broadcast, in reference to what appears in front and is seen by the moving user. For example, while the traditional "point of interest" associated with a cathedral is located precisely at the building's geographic location, the cathedral's "Point of View" is located in the square in front of the building. It is from this location that the user will receive descriptive information about the cathedral itself, such as an audio guide illustrating the architecture, façade, and features of the monument. In most cases, the "Point of View" corresponds to the optimal observation point from which to obtain information related to a "Point of Interest" being observed. The structured insertion of "Points of View" into a dedicated system allows for the creation of digital tourist guides, particularly voice-based but also multimedia, which provide users on the move in an urban, road, or natural environment with contextual information relevant to what they are seeing, be it geographic, touristic, or commercial. The content production and organization process, according to the present invention, presents the following aspects of originality and innovation. Descriptive and multimedia content must be positioned from the perspective of the user in motion and produce contextual content, optimized for viewing precisely from the "Points of View" identified through algorithmic methodologies and computer vision systems applied to virtual maps. The content production method must be optimized for the user's experience as they move through the environment. Text generation, carried out by a suitably trained generative Artificial Intelligence model, according to one embodiment of the method, takes the form of an immersive script, that is, written by placing itself in the user's point of view in a specific position of perception of the surrounding environment, but also in a specific direction and at a specific speed of movement. It should be noted that as the user moves, the points of view change, and therefore it is necessary to receive information dynamically and adaptively with respect to three parameters in the embodiment considered here: position, direction, speed of movement. The multimedia guide experience changes depending on whether you cross a square from one side (facing the cathedral facade) or the other (facing the town hall). The experience of a slow pedestrian stroll or a quick car ride is also different. Furthermore, the perception (point of view) changes depending on your position: whether you're in the center of the square or right next to the cathedral's sculptural portal. It is therefore necessary to develop a method for prioritizing and organizing the distribution and sequencing of content. This goal involves the introduction of an additional aspect, here called “moving content algorithm”. The task of the “moving content algorithm” is to establish the criteria and order for distributing content to the moving user. Corresponding to the "Points of View," thanks to the user's geolocation obtained from GPS or other systems, the "moving content algorithm" manages individual information content, presenting it not only in the appropriate geographic location, but also distributing it based on the direction, speed, criteria, and information priorities established by the system and indicated by the user (topics, expressed interests, weather, traffic, and so on), and also taking into account the direction of travel. The main parameters of the algorithm for moving content are therefore the user's position, the direction and the speed of the user's movement. Depending on the embodiment of the method, aspects of hierarchy and sequence are considered: scale of geographical and informational importance. In audio information, time sequence is a relevant factor. The use of an importance code (or other specific code) allows you to produce content according to a hierarchy corresponding to the geographical scale, and to establish a temporal sequence in the message, which influences the editorial setting, for example making it possible to manage: - Welcome and introductory instructions from the guide upon departure; in general, beyond the specific descriptions of a single point of interest, it is helpful to provide the user with a general overview of the tourist area, or of the historical and artistic period and style of the monuments in the area. If you are also presenting reconstructions of the past or future, it is essential to begin with an overview of the historical era or future project being reconstructed. - general messages on large areas (which, depending on their level of importance, may precede or follow other messages relating to more restricted areas); - incremental in-depth sequences, even overlapping in the same area, that interact with the user's speed. If the user stops, they hear, in the sequence established by the editorial staff, all the messages related to the area they are in. If they move quickly, they hear only the primary information and then move on to the information in the adjacent areas they have just moved through. Defining the importance scale of content is important in order to train an Artificial Intelligence model to produce texts with different levels of scale, to be distributed in relation to the user's position, speed, and distance from points of interest. The training of the artificial intelligence model therefore responds, in one embodiment of the method, to the following objectives: writing descriptive texts relating to a user's tourist itinerary that include general introductions to the area traversed, quick descriptions in the case of crossing by fast transport, in-depth descriptions for slow passages or stops, and narrations of details in the case of close-up points of view. Artificial Intelligence, in one embodiment, also manages the timing of content delivery, estimating the speed of travel in real time, and thus generating text (audio) clips of the correct duration for the individual relevant section traveled. Content generated by Artificial Intelligence can be multilingual and adapt to various narrative genres and users with different cultural levels (as illustrated in figure 2: PLATFORM COMPONENTS). In some embodiments of the method, it adapts and integrates with several available mapping options. The extended reality guide, thanks to dedicated algorithms, generates and delivers different types of information depending on the different types of digital cartography available. Here we mention, distinguishing between, two types of digital cartography that can be currently available as reference digital twins for the creation of extended reality guides: - 2D digital cartography, consisting of geo-positioned two-dimensional vector maps, and - 3D digital maps consisting of 360 photos and three-dimensional models of the environment, both geopositioned. 2D digital maps allow content to be delivered anywhere, as they now cover practically the entire planet, and thanks to GPS they can always define the position of the point of view with respect to the point of interest. However, 2D maps do not provide the system with information about the elevations of buildings, such as the façade of a church. Therefore, the information generated by AI will not describe the details of vertical surfaces. Thanks to a dedicated algorithm, AI can therefore generate information about the building's history, its builders, its owners, the events that occurred, its overall shape, its style, and so on. If, in addition to 2D cartography, a cartography with 360° photos, or 3D models, such as street view, or three-dimensional photogrammetry, is available, the platform, thanks to artificial intelligence, can recognize the vertical parts of the building and can therefore describe, for example, the facade and its components, such as the portal and the rose window, thus generating a guide more closely correlated to the real point of view. The availability of geopositioned photogrammetry also makes it possible to precisely position 3D models in the environment, for example virtual archaeological reconstructions over the remains of an ancient building, or a 3D model of a home renovation project on the house itself. Some embodiments of the method allow for several possible customization options. One of the tasks of the “moving content algorithm” is to manage the rotation of information in a personalized way for the individual user. Personalization is achieved through additional system components, particularly content typology classification, time-based synchronization, and a customizable settings interface. Content is classified according to a taxonomy geared toward meeting user interests. For example, for tourism users, content can be organized by artistic, historical, and natural attractions, accommodations, tourist services, events, and promotional offers. Users must be able to explicitly indicate, through a personal settings interface, what type of content they intend to consume. When visiting a city of art, for example, users can select the artistic attractions, and the moving content algorithm organizes the corresponding "Viewpoints." But even when the user hasn't explicitly customized the content types, the moving content algorithm can automatically organize moving content into personalized formats. Clock and calendar synchronization also allows the motion content algorithm to prioritize content personalized to the user's location and situation. For example, if a user is walking along a coastal road on a summer morning, the proximity algorithm can prioritize information about beaches, while a user walking along the same road in the evening can be served content about restaurants. The customization of the algorithm for moving content, applied to a travel guide to be enjoyed on the go, also allows a tourist passing by the same spot to avoid repeatedly hearing the same information. Another feature present in one embodiment of the method is information rotation. Information rotation allows, for example, to offer different information for the outward and return journeys, even on the same stretch of highway. The speed of movement is also a factor managed by the "moving content algorithm": if the user moves quickly from one local cell to another, the information should not be interrupted. Conversely, if the user is stationary, for example in a traffic jam on the highway or in front of a museum, the information units should not be repeated. According to one embodiment, the aspect of the audio channel and the text to speech (push mode) and translations are considered. The basic ergonomic assumption is the use of the “moving content algorithm” during movement, when the user is engaged in driving a car, riding a motorbike or walking. The user on the move cannot actively interact, read texts or look at images, so the emphasis is on the audio channel: the information is read aloud (products with “Text to Speech” voice synthesis). Also to avoid interfering with driving, the platform delivers content in PUSH format, i.e. through automatic mechanisms defined by the "proximity algorithm". Another parameter for content distribution is temporal: nighttime, daytime, projection into the past or future of the location, lunch or dinner time, opening hours of functional buildings, even weather conditions. Content production takes advantage of the potential offered by Artificial Intelligence, in particular machine translation and text-to-speech with synthetic pronunciation in multiple languages. There are also more interactive and less passive usage situations, for example, by passengers rather than the driver on board a means of transport, or for the use of content before or after the journey, or if the user stops and wants to enjoy additional content. In the more interactive consultation modes, the system also allows texts to be read, and provides for the transmission of images, both 2D and 3D, which can be synchronized with the audio. Spatio-temporal variants of the point of view: elevator and “time machine. In several situations, it may be useful to develop spatial or temporal variations of the Point of View. In particular, where the eye-level view is obstructed by visual disturbances, such as trees, low walls, or other obstacles, the system can use an aerial view, raising the point of view above the obstacles and describing what lies beyond. A further variation of the Point of View is temporal in nature: if the current appearance of the environment is of little importance, the description can move on to illustrate reconstructions of the past or plans for the future. This may, for example, concern archaeological sites without elevations, which are difficult for non-experts to interpret, or ongoing construction sites. In these cases, the description does not concern the context as it appears today, but how it was in the past or how it will be in the future. Data Ingestion and processing of geolocalized information. Training the AI ​​model, and feeding it with data, even in real time, can occur in different ways. The simplest is the use of online databases of geolocalized information (texts, images or other content). For example, the acquisition of open-source data such as Wikipedia entries is relevant, particularly those related to geolocated points of interest. Wikipedia offers numerous entries not only for locations, but also for individual monuments and attractions. These entries include latitude and longitude, textual descriptions, and even images. The textual descriptions, in the form of encyclopedic entries, will be processed by the Artificial Intelligence model to take on the narrative form relevant to the guide and the "moving content algorithm." Images help visually identify what appears before the user. The system also includes a "Data Ingestion" tool that allows you to manually enter geolocalized information (text, images, coordinates) relating to any point of interest, whether present in the present, past, or future environment. For example, it will be possible to insert descriptive cards for points of interest at an archaeological site or construction site, as well as computer-generated reconstructions of the site's past appearance (virtual archaeology) or future projects (CAD design). Computer vision: applied to an immersive map or via camera. When using a camera and visually recognizing monuments, the method still generates and delivers moving content, depending on the user's speed and the other criteria described. When using reconstructions of the past or future, the camera is unable to provide any information from images of the present, and therefore the method allows for the integration of descriptions and images of the reconstructions themselves, consistent with the aforementioned features. Another feature of the method for producing, organizing, and distributing georeferenced digital content on the move is the ability to deliver content to the user on the move not only based on their geographic location, detected via GPS, but also based on visual recognition of the surrounding environment. In this case the reference technologies are “visual recognition” and “visual search”, activated in two distinct modes: a) Access to a geolocalised immersive map that replicates the environment in which the user is located (for example, Google Street View, a virtual tour or a reconstruction (3D environmental data). Dynamic geolocation data (position, direction, speed) detected by the device's sensor is transmitted to the immersive map, which displays virtual images corresponding to the "real" point of view. Thanks to visual recognition of virtual images and the presence of a database of points of interest, the system generates content according to the criteria dictated by the "algorithm for moving content." For example, if I am walking along the streets of a historic center, my mobile device detects my position, direction, and speed and passes them to the virtual map, which frames the same street I am on and allows the recognition of images and points of interest (e.g., buildings, churches, historical information, etc.) inserted into the virtual map. b) a camera that frames objects in the external environment. In this case, visual recognition is applied in a classic way: the system recognizes the elements in front of the user and passes the data to the artificial intelligence model responsible for generating the content, always according to the criteria dictated by the "algorithm for moving content" (position, speed, direction), even when the description concerns reconstructions of the past and present, not visible in the camera footage. The scope of application concerns, in the two cases mentioned, the following devices: A. All mobile devices connected to the network and equipped with motion sensors and microphone B. all networked mobile devices equipped with a digital camera, from smartphones to tablets, from car cameras to smart glasses. As can be seen, the aims of the present invention, as previously indicated, are fully achieved by the method and system described above, by virtue of the characteristics illustrated in detail above. In fact, the method and system described above respond to the need to solve the technical problems outlined at the beginning of this description and to have effective, flexible and reliable solutions for the production, organisation and distribution of georeferenced digital content on the move, and for the development of contextual multimedia guides. In particular, the method and system described above offer a technical solution for producing, organizing, and distributing georeferenced digital content, specifically intended for mobile distribution, at a low cost and dynamically adaptable, i.e., capable of being delivered in ways that are appropriately adapted to variables such as the user's movement conditions and speed, or the scale of importance of the points of interest present, or others. To meet contingent needs, a person skilled in the art may make modifications, adaptations, and replacements of elements with functionally equivalent ones to the embodiments of the method, device, and system described above, without departing from the scope of the following claims. Each of the features described as belonging to a possible embodiment may be implemented independently of the other embodiments described.

Claims

1. A method for producing, organizing, and distributing georeferenced digital content on the move, performed using computer processing, comprising: - preparing or accessing at least one geolocalized digital map, capable of providing a three-dimensional visual model and / or including other multimedia digital content, of each of a plurality of points of interest present in a geographic area covered by the geolocalized digital map; - obtaining or determining a user's geolocation data, including at least one user position and information relating to the user's movement;- determining, based on said user geolocation data, a digital viewpoint of the user within the geolocalized digital map, representative of a real-world viewpoint of the user, dynamically variable based on the user's movement, wherein said digital viewpoint is associated with at least one of said three-dimensional models present in the geolocalized digital map, corresponding to points of interest visible from the user's real-world viewpoint; - generating, using artificial intelligence, and / or extracting from the geolocalized digital map, digital point-of-interest data, including at least one three-dimensional visual model and / or other digital multimedia content relating to at least one of said points of interest associated with the user's digital viewpoint, said digital point-of-interest data being dynamically variable based on the user's movement;- organize and provide to the user, through a digital display interface of a user's mobile device, such dynamically variable, generated and / or derived digital point-of-interest data associated with the user's digital point of view.; 2. A method according to claim 1, wherein said step of preparing or accessing a geolocalized digital map comprises preparing or accessing an immersive geolocalized digital map and / or a virtual geolocalized digital map corresponding to a “digital twin” of what is located in a geographic area represented by the “digital twin”.

3. A method according to claim 1 or claim 2, wherein said step of obtaining or determining geolocation data of a user comprises obtaining or determining geolocation data comprising a location of the user, a direction of movement of the user, and a speed of the user.

4. The method of claim 3, wherein said step of determining a digital viewpoint of the user comprises determining said digital viewpoint of the user in a dynamically variable manner, based on said user position, direction of movement and speed of the user.

5. A method according to any preceding claim, wherein said step of generating and / or deriving digital point of interest data comprises deriving the digital point of interest data from the geolocated digital map.

6. A method according to any preceding claim, wherein said step of generating and / or deriving digital point-of-interest data comprises generating digital data, by means of a trained artificial intelligence model.

7. A method according to any preceding claim, wherein said step of organizing and providing the user with digital point-of-interest data comprises generating and / or organizing and / or managing and / or distributing digital content optimized based on the user's movement / mobility, delivering the data based on the dynamically varying digital point of view corresponding to the user's actual point of view.

8. Method according to claim 7, wherein said step of generating and / or organizing and / or managing and / or distributing digital content optimized based on the user's movement / mobility is carried out by means of an algorithm for defining “moving content”, which establishes criteria for the production and distribution of content optimized for mobility and personalized to the user.

9. A method according to claim 7 or claim 8, comprising the further step of producing and disseminating digital content in relation to the position, direction, speed of the user.

10. A method according to any of claims 7-9, comprising the further step of producing and disseminating digital content based on interests indicated by the user, by means of a trained artificial intelligence model.

11. A method according to claim 9 or claim 10, wherein the organization of the content generated by the Artificial Intelligence is hierarchical, and / or wherein the organization of the content generated by the Artificial Intelligence takes into account a predefined scale of geographical importance and / or wherein the organization of the content generated by the Artificial Intelligence is multilingual and / or wherein the organization of the content generated by the Artificial Intelligence is such as to adapt to different narrative registers or presentation registers, dependent on the user.

12. A method according to any preceding claim, wherein said digital point-of-interest data comprises data descriptive of the present appearance of one or more points of interest, or of all points of interest visible from the user's point of view.

13. A method according to any of the preceding claims, wherein said digital data of points of interest comprise descriptive data of the past appearance of one or more points of interest, or of all points of interest visible from the user's point of view, at a given time, based on reconstructions of geolocalised computer graphics images referring to said time.

14. A method according to any preceding claim, wherein said digital point-of-interest data comprises data descriptive of the future appearance of one or more points of interest, or of all points of interest visible from the user's point of view, based on renderings or digital reconstructions associated with a project relating to an area surrounding the user's point of view.

15. A method according to any preceding claim, comprising a two-way interaction between a user's mobile device and said at least one geolocalized digital map, further comprising the steps of: - transmitting said information relating to the user's position, direction, and speed to electronic processing means implementing said at least one geolocalized digital map, by the user's mobile device; - obtaining in the at least one geolocalized digital map a visual recognition, for example by computer vision, of images and points of interest present in the user's digital viewpoint, by said electronic processing means; - obtaining from the at least one geolocalized digital map information relating to the elements recognized as present in the user's digital viewpoint;- create descriptive content based on the information obtained using electronic processing tools using artificial intelligence techniques; - transmit the created descriptive content to the user's mobile device in one or more multimedia formats: audio commentary, text file, images, videos, 3D formats; 16. A method for developing contextual multimedia guides, comprising: - performing a method for producing, organizing, and distributing georeferenced digital content on the move, according to any of the preceding claims, to obtain digital data of a plurality of points of interest, associated with a plurality of digital viewpoints of the user, dynamically variable as a function of the user's movement; generating said contextual multimedia guides using artificial intelligence, based on the user's position, direction, and speed parameters and the recognition of visual and informative elements present in immersive and / or virtual geolocalized digital maps.

17. A method according to any of the preceding claims, comprising the provision of content in simulations of courses with gymnastic equipment, wherein the provision of moving content is applied not with respect to the physical movement of people in reality but with respect to a simulation of movement carried out with gymnastic equipment.

18. A system for producing, organizing, and distributing georeferenced digital content on the move, comprising a user's mobile device equipped with geolocation sensors and electronic processing equipment, operationally connected to the user's mobile device, comprising: - at least one virtual reality and / or immersive map software application, associated with at least one geolocalized digital map, configured to provide a visual three-dimensional model, and / or including other multimedia digital content, of each of a plurality of points of interest present in a geographic area covered by the geolocalized digital map;- a software application or program capable of implementing an infomobility algorithm, configured to obtain and / or determine and / or interpret a user's geolocation data, including at least one user position and information relating to the user's movement, and to determine, based on said user geolocation data, a digital viewpoint of the user, within the geolocalized digital map, representative of a real viewpoint of the user in real space, dynamically variable depending on the user's movement, wherein said digital viewpoint is associated with at least one of said three-dimensional models present in the geolocalized digital map, corresponding to points of interest visible from the user's real viewpoint;- a trained artificial intelligence model, capable of generating digital point-of-interest data, comprising at least one three-dimensional visual model and / or other multimedia digital content relating to at least one of said points of interest associated with the user's digital point of view, said digital point-of-interest data being dynamically variable depending on the user's movement, said trained artificial intelligence model further capable of organizing and providing to the user, through a digital display interface of said user's mobile device, said dynamically variable digital point-of-interest data generated and / or derived, associated with the user's digital point of view.; 19. System according to claim 18, wherein said electronic processing means comprise, or consist of, a cloud software platform.

20. System according to one of claims 18 or 19, wherein said at least one virtual reality software application comprises an immersive geolocalized digital map and / or a virtual geolocalized digital map corresponding to a “digital twin” of what is located in a geographic area represented by the “digital twin”.

21. System according to claim 20, wherein said at least one virtual reality software application is configured to display current digital reproductions of the one or more points of interest or of the surrounding environment, in the present, and / or descriptive data of the past appearance of the one or more points of interest, in a given era, based on reconstructions of geolocalized computer graphics images referred to said era, and / or descriptive data of the future appearance of the one or more points of interest, based on renderings or digital reconstructions associated with a project referred to an area surrounding the user's point of view.

22. System according to any of claims 18-21 wherein the user's mobile device is further equipped with direction and / or speed and / or motion sensors.

23. A system according to any of claims 18-22, wherein the user's mobile device is further equipped with at least one camera for visual recognition, and is configured to transmit to said electronic processing means information relating to the user's position, direction, and speed; wherein the electronic processing means are further configured to: - perform visual recognition, using computer vision, of images and points of interest present in the user's digital viewpoint; - extract information from the geolocalized digital map relating to the elements recognized as present in the user's digital viewpoint; - create descriptive content, based on said information obtained, using artificial intelligence techniques; - transmit said created descriptive content to the user's mobile device.

24. A system according to any of claims 18-23, wherein the trained artificial intelligence model is capable of generating and disseminating digital content in real time, based on data input by the user or from relevant sources, based on interests indicated by the user, and / or with hierarchical organization, and / or taking into account a predefined scale of geographical importance, and / or through multilingual organization of the content and / or through different narrative registers or presentation registers, dependent on the user.

25. A system according to any of claims 18-24, configured to perform a method according to any of claims 1-17.